diff --git a/checkpoint-10000/config.json b/checkpoint-10000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-10000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-10000/experiment_cfg/metadata.json b/checkpoint-10000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-10000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-10000/model-00001-of-00002.safetensors b/checkpoint-10000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-10000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-10000/model-00002-of-00002.safetensors b/checkpoint-10000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5638d6605794948913af78767d4111f090178848 --- /dev/null +++ b/checkpoint-10000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595f7bca8c51123b14908af4b1eac93a96d52a59a6b0fe7d8bae323aa957c147 +size 2586705312 diff --git a/checkpoint-10000/model.safetensors.index.json b/checkpoint-10000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-10000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-10000/optimizer.pt b/checkpoint-10000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..65a8c0abd674f0d5a0fa567c96c3a4c743e94817 --- /dev/null +++ b/checkpoint-10000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da86f5adf2d73c513c74e0a03ac6ef1580f785e88602acbe8e24e4c6d9e311d3 +size 4147424698 diff --git a/checkpoint-10000/rng_state.pth b/checkpoint-10000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..826a3ba5c96417aac7de0f3f286ba7d7ebbc5d7e --- /dev/null +++ b/checkpoint-10000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19496a2c7f714f9d36473c01b7fd34ce69b238124e9968608454712b8e5755ba +size 14244 diff --git a/checkpoint-10000/scheduler.pt b/checkpoint-10000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6fe32e541103d98cffffc5aa51a3354887597fa --- /dev/null +++ b/checkpoint-10000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07356cb668b8efc440ddb2f7f81f7da3152060e81d0229922fa3b30df3313f82 +size 1064 diff --git a/checkpoint-10000/trainer_state.json b/checkpoint-10000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..6e54c1c2ccbc59223afca6339df4ddf013f96a86 --- /dev/null +++ b/checkpoint-10000/trainer_state.json @@ -0,0 +1,7034 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.982477100756671, + "eval_steps": 500, + "global_step": 10000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + }, + { + "epoch": 2.393468737554759, + "grad_norm": 0.33681097626686096, + "learning_rate": 3.758152155160255e-05, + "loss": 0.0167, + "step": 6010 + }, + { + "epoch": 2.397451214655516, + "grad_norm": 0.4447823166847229, + "learning_rate": 3.742142385506999e-05, + "loss": 0.0187, + "step": 6020 + }, + { + "epoch": 2.4014336917562726, + "grad_norm": 0.32111281156539917, + "learning_rate": 3.72614637158309e-05, + "loss": 0.0167, + "step": 6030 + }, + { + "epoch": 2.405416168857029, + "grad_norm": 0.3327321708202362, + "learning_rate": 3.710164288318371e-05, + "loss": 0.021, + "step": 6040 + }, + { + "epoch": 2.409398645957786, + "grad_norm": 0.3221536874771118, + "learning_rate": 3.694196310490345e-05, + "loss": 0.0172, + "step": 6050 + }, + { + "epoch": 2.4133811230585422, + "grad_norm": 0.2384720742702484, + "learning_rate": 3.678242612722259e-05, + "loss": 0.0172, + "step": 6060 + }, + { + "epoch": 2.417363600159299, + "grad_norm": 0.4310377240180969, + "learning_rate": 3.6623033694811953e-05, + "loss": 0.0207, + "step": 6070 + }, + { + "epoch": 2.421346077260056, + "grad_norm": 0.2742801904678345, + "learning_rate": 3.6463787550761665e-05, + "loss": 0.0204, + "step": 6080 + }, + { + "epoch": 2.4253285543608123, + "grad_norm": 0.30959945917129517, + "learning_rate": 3.630468943656202e-05, + "loss": 0.0171, + "step": 6090 + }, + { + "epoch": 2.429311031461569, + "grad_norm": 0.23991258442401886, + "learning_rate": 3.6145741092084523e-05, + "loss": 0.0158, + "step": 6100 + }, + { + "epoch": 2.433293508562326, + "grad_norm": 0.3445211350917816, + "learning_rate": 3.598694425556278e-05, + "loss": 0.0171, + "step": 6110 + }, + { + "epoch": 2.4372759856630823, + "grad_norm": 0.23148199915885925, + "learning_rate": 3.58283006635736e-05, + "loss": 0.0168, + "step": 6120 + }, + { + "epoch": 2.441258462763839, + "grad_norm": 0.34516337513923645, + "learning_rate": 3.566981205101781e-05, + "loss": 0.0214, + "step": 6130 + }, + { + "epoch": 2.445240939864596, + "grad_norm": 0.2975906729698181, + "learning_rate": 3.5511480151101556e-05, + "loss": 0.0182, + "step": 6140 + }, + { + "epoch": 2.4492234169653524, + "grad_norm": 0.3364192545413971, + "learning_rate": 3.5353306695317104e-05, + "loss": 0.0149, + "step": 6150 + }, + { + "epoch": 2.4532058940661092, + "grad_norm": 0.32481926679611206, + "learning_rate": 3.519529341342402e-05, + "loss": 0.0205, + "step": 6160 + }, + { + "epoch": 2.4571883711668656, + "grad_norm": 0.35478660464286804, + "learning_rate": 3.503744203343026e-05, + "loss": 0.0184, + "step": 6170 + }, + { + "epoch": 2.4611708482676224, + "grad_norm": 0.40364179015159607, + "learning_rate": 3.487975428157318e-05, + "loss": 0.0213, + "step": 6180 + }, + { + "epoch": 2.4651533253683793, + "grad_norm": 0.2646041512489319, + "learning_rate": 3.472223188230083e-05, + "loss": 0.0182, + "step": 6190 + }, + { + "epoch": 2.4691358024691357, + "grad_norm": 0.21933303773403168, + "learning_rate": 3.4564876558252866e-05, + "loss": 0.02, + "step": 6200 + }, + { + "epoch": 2.4731182795698925, + "grad_norm": 0.41874152421951294, + "learning_rate": 3.440769003024195e-05, + "loss": 0.0192, + "step": 6210 + }, + { + "epoch": 2.4771007566706493, + "grad_norm": 0.40349701046943665, + "learning_rate": 3.425067401723477e-05, + "loss": 0.0195, + "step": 6220 + }, + { + "epoch": 2.4810832337714057, + "grad_norm": 0.36892589926719666, + "learning_rate": 3.409383023633325e-05, + "loss": 0.0214, + "step": 6230 + }, + { + "epoch": 2.4850657108721625, + "grad_norm": 0.3317766785621643, + "learning_rate": 3.3937160402755894e-05, + "loss": 0.0179, + "step": 6240 + }, + { + "epoch": 2.4890481879729194, + "grad_norm": 0.28070494532585144, + "learning_rate": 3.378066622981885e-05, + "loss": 0.0227, + "step": 6250 + }, + { + "epoch": 2.4930306650736758, + "grad_norm": 0.23878398537635803, + "learning_rate": 3.362434942891738e-05, + "loss": 0.0203, + "step": 6260 + }, + { + "epoch": 2.4970131421744326, + "grad_norm": 0.29855674505233765, + "learning_rate": 3.346821170950693e-05, + "loss": 0.0188, + "step": 6270 + }, + { + "epoch": 2.500995619275189, + "grad_norm": 0.35947370529174805, + "learning_rate": 3.3312254779084585e-05, + "loss": 0.0203, + "step": 6280 + }, + { + "epoch": 2.504978096375946, + "grad_norm": 0.38355863094329834, + "learning_rate": 3.315648034317039e-05, + "loss": 0.0229, + "step": 6290 + }, + { + "epoch": 2.5089605734767026, + "grad_norm": 0.20965726673603058, + "learning_rate": 3.3000890105288564e-05, + "loss": 0.0156, + "step": 6300 + }, + { + "epoch": 2.512943050577459, + "grad_norm": 0.21126852929592133, + "learning_rate": 3.284548576694908e-05, + "loss": 0.0221, + "step": 6310 + }, + { + "epoch": 2.516925527678216, + "grad_norm": 0.29997190833091736, + "learning_rate": 3.2690269027628815e-05, + "loss": 0.0163, + "step": 6320 + }, + { + "epoch": 2.5209080047789723, + "grad_norm": 0.2688118815422058, + "learning_rate": 3.253524158475324e-05, + "loss": 0.018, + "step": 6330 + }, + { + "epoch": 2.524890481879729, + "grad_norm": 0.3369862139225006, + "learning_rate": 3.238040513367757e-05, + "loss": 0.0182, + "step": 6340 + }, + { + "epoch": 2.528872958980486, + "grad_norm": 0.17766013741493225, + "learning_rate": 3.222576136766843e-05, + "loss": 0.0159, + "step": 6350 + }, + { + "epoch": 2.5328554360812428, + "grad_norm": 0.2567964494228363, + "learning_rate": 3.2071311977885324e-05, + "loss": 0.0183, + "step": 6360 + }, + { + "epoch": 2.536837913181999, + "grad_norm": 0.2693711519241333, + "learning_rate": 3.191705865336197e-05, + "loss": 0.0195, + "step": 6370 + }, + { + "epoch": 2.540820390282756, + "grad_norm": 0.2565217912197113, + "learning_rate": 3.1763003080988075e-05, + "loss": 0.0175, + "step": 6380 + }, + { + "epoch": 2.5448028673835124, + "grad_norm": 0.44722431898117065, + "learning_rate": 3.160914694549063e-05, + "loss": 0.0198, + "step": 6390 + }, + { + "epoch": 2.548785344484269, + "grad_norm": 0.3705827593803406, + "learning_rate": 3.145549192941573e-05, + "loss": 0.019, + "step": 6400 + }, + { + "epoch": 2.552767821585026, + "grad_norm": 0.3155789077281952, + "learning_rate": 3.130203971310999e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 2.5567502986857824, + "grad_norm": 0.29949137568473816, + "learning_rate": 3.114879197470225e-05, + "loss": 0.0188, + "step": 6420 + }, + { + "epoch": 2.5607327757865392, + "grad_norm": 0.3367830216884613, + "learning_rate": 3.0995750390085285e-05, + "loss": 0.0175, + "step": 6430 + }, + { + "epoch": 2.5647152528872956, + "grad_norm": 0.2421615719795227, + "learning_rate": 3.084291663289728e-05, + "loss": 0.0192, + "step": 6440 + }, + { + "epoch": 2.5686977299880525, + "grad_norm": 0.17980587482452393, + "learning_rate": 3.069029237450375e-05, + "loss": 0.0155, + "step": 6450 + }, + { + "epoch": 2.5726802070888093, + "grad_norm": 0.42298945784568787, + "learning_rate": 3.053787928397911e-05, + "loss": 0.0169, + "step": 6460 + }, + { + "epoch": 2.576662684189566, + "grad_norm": 0.2914910316467285, + "learning_rate": 3.0385679028088526e-05, + "loss": 0.0195, + "step": 6470 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 0.40466681122779846, + "learning_rate": 3.023369327126959e-05, + "loss": 0.0191, + "step": 6480 + }, + { + "epoch": 2.5846276383910793, + "grad_norm": 0.260161429643631, + "learning_rate": 3.0081923675614198e-05, + "loss": 0.0164, + "step": 6490 + }, + { + "epoch": 2.5886101154918357, + "grad_norm": 0.348817378282547, + "learning_rate": 2.993037190085034e-05, + "loss": 0.0155, + "step": 6500 + }, + { + "epoch": 2.5925925925925926, + "grad_norm": 0.22140339016914368, + "learning_rate": 2.977903960432392e-05, + "loss": 0.0192, + "step": 6510 + }, + { + "epoch": 2.5965750696933494, + "grad_norm": 0.3535783886909485, + "learning_rate": 2.9627928440980722e-05, + "loss": 0.0196, + "step": 6520 + }, + { + "epoch": 2.600557546794106, + "grad_norm": 0.229234978556633, + "learning_rate": 2.9477040063348183e-05, + "loss": 0.0206, + "step": 6530 + }, + { + "epoch": 2.6045400238948626, + "grad_norm": 0.30883148312568665, + "learning_rate": 2.9326376121517456e-05, + "loss": 0.0195, + "step": 6540 + }, + { + "epoch": 2.608522500995619, + "grad_norm": 0.4454684257507324, + "learning_rate": 2.9175938263125236e-05, + "loss": 0.024, + "step": 6550 + }, + { + "epoch": 2.612504978096376, + "grad_norm": 0.34252026677131653, + "learning_rate": 2.9025728133335873e-05, + "loss": 0.0206, + "step": 6560 + }, + { + "epoch": 2.6164874551971327, + "grad_norm": 0.410495400428772, + "learning_rate": 2.8875747374823288e-05, + "loss": 0.0201, + "step": 6570 + }, + { + "epoch": 2.6204699322978895, + "grad_norm": 0.2930971384048462, + "learning_rate": 2.872599762775298e-05, + "loss": 0.0242, + "step": 6580 + }, + { + "epoch": 2.624452409398646, + "grad_norm": 0.1941741406917572, + "learning_rate": 2.857648052976425e-05, + "loss": 0.0168, + "step": 6590 + }, + { + "epoch": 2.6284348864994027, + "grad_norm": 0.4398362338542938, + "learning_rate": 2.8427197715952047e-05, + "loss": 0.019, + "step": 6600 + }, + { + "epoch": 2.632417363600159, + "grad_norm": 0.434218168258667, + "learning_rate": 2.8278150818849393e-05, + "loss": 0.0188, + "step": 6610 + }, + { + "epoch": 2.636399840700916, + "grad_norm": 0.29979050159454346, + "learning_rate": 2.812934146840922e-05, + "loss": 0.0175, + "step": 6620 + }, + { + "epoch": 2.6403823178016728, + "grad_norm": 0.27494296431541443, + "learning_rate": 2.7980771291986764e-05, + "loss": 0.0175, + "step": 6630 + }, + { + "epoch": 2.644364794902429, + "grad_norm": 0.3515009582042694, + "learning_rate": 2.783244191432167e-05, + "loss": 0.0185, + "step": 6640 + }, + { + "epoch": 2.648347272003186, + "grad_norm": 0.3444755971431732, + "learning_rate": 2.768435495752022e-05, + "loss": 0.0171, + "step": 6650 + }, + { + "epoch": 2.652329749103943, + "grad_norm": 0.2616831362247467, + "learning_rate": 2.753651204103771e-05, + "loss": 0.02, + "step": 6660 + }, + { + "epoch": 2.656312226204699, + "grad_norm": 0.2663615643978119, + "learning_rate": 2.7388914781660523e-05, + "loss": 0.0149, + "step": 6670 + }, + { + "epoch": 2.660294703305456, + "grad_norm": 0.21043306589126587, + "learning_rate": 2.7241564793488693e-05, + "loss": 0.0202, + "step": 6680 + }, + { + "epoch": 2.664277180406213, + "grad_norm": 0.45657920837402344, + "learning_rate": 2.7094463687918037e-05, + "loss": 0.0151, + "step": 6690 + }, + { + "epoch": 2.6682596575069693, + "grad_norm": 0.37648776173591614, + "learning_rate": 2.694761307362268e-05, + "loss": 0.0192, + "step": 6700 + }, + { + "epoch": 2.672242134607726, + "grad_norm": 0.26603221893310547, + "learning_rate": 2.6801014556537467e-05, + "loss": 0.0169, + "step": 6710 + }, + { + "epoch": 2.6762246117084825, + "grad_norm": 0.3080855906009674, + "learning_rate": 2.6654669739840243e-05, + "loss": 0.0169, + "step": 6720 + }, + { + "epoch": 2.6802070888092393, + "grad_norm": 0.3766150176525116, + "learning_rate": 2.650858022393451e-05, + "loss": 0.0183, + "step": 6730 + }, + { + "epoch": 2.684189565909996, + "grad_norm": 0.2229013293981552, + "learning_rate": 2.6362747606431747e-05, + "loss": 0.0205, + "step": 6740 + }, + { + "epoch": 2.688172043010753, + "grad_norm": 0.24441877007484436, + "learning_rate": 2.6217173482134172e-05, + "loss": 0.0182, + "step": 6750 + }, + { + "epoch": 2.6921545201115094, + "grad_norm": 0.25608956813812256, + "learning_rate": 2.6071859443017044e-05, + "loss": 0.013, + "step": 6760 + }, + { + "epoch": 2.696136997212266, + "grad_norm": 0.3526802957057953, + "learning_rate": 2.5926807078211414e-05, + "loss": 0.0153, + "step": 6770 + }, + { + "epoch": 2.7001194743130226, + "grad_norm": 0.46395474672317505, + "learning_rate": 2.5782017973986728e-05, + "loss": 0.0181, + "step": 6780 + }, + { + "epoch": 2.7041019514137794, + "grad_norm": 0.23045793175697327, + "learning_rate": 2.5637493713733374e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 2.7080844285145362, + "grad_norm": 0.32080161571502686, + "learning_rate": 2.549323587794559e-05, + "loss": 0.0196, + "step": 6800 + }, + { + "epoch": 2.7120669056152926, + "grad_norm": 0.23438672721385956, + "learning_rate": 2.5349246044203895e-05, + "loss": 0.0143, + "step": 6810 + }, + { + "epoch": 2.7160493827160495, + "grad_norm": 0.33166348934173584, + "learning_rate": 2.520552578715808e-05, + "loss": 0.0144, + "step": 6820 + }, + { + "epoch": 2.720031859816806, + "grad_norm": 0.2601594626903534, + "learning_rate": 2.506207667850981e-05, + "loss": 0.0159, + "step": 6830 + }, + { + "epoch": 2.7240143369175627, + "grad_norm": 0.3093375265598297, + "learning_rate": 2.4918900286995555e-05, + "loss": 0.0141, + "step": 6840 + }, + { + "epoch": 2.7279968140183195, + "grad_norm": 0.15893106162548065, + "learning_rate": 2.4775998178369458e-05, + "loss": 0.0161, + "step": 6850 + }, + { + "epoch": 2.7319792911190763, + "grad_norm": 0.3865691125392914, + "learning_rate": 2.4633371915386017e-05, + "loss": 0.0188, + "step": 6860 + }, + { + "epoch": 2.7359617682198327, + "grad_norm": 0.2376730591058731, + "learning_rate": 2.4491023057783235e-05, + "loss": 0.0192, + "step": 6870 + }, + { + "epoch": 2.7399442453205896, + "grad_norm": 0.38163626194000244, + "learning_rate": 2.4348953162265375e-05, + "loss": 0.0182, + "step": 6880 + }, + { + "epoch": 2.743926722421346, + "grad_norm": 0.22240246832370758, + "learning_rate": 2.420716378248607e-05, + "loss": 0.0217, + "step": 6890 + }, + { + "epoch": 2.7479091995221028, + "grad_norm": 0.4573044180870056, + "learning_rate": 2.4065656469031266e-05, + "loss": 0.0165, + "step": 6900 + }, + { + "epoch": 2.7518916766228596, + "grad_norm": 0.22964206337928772, + "learning_rate": 2.3924432769402268e-05, + "loss": 0.0186, + "step": 6910 + }, + { + "epoch": 2.755874153723616, + "grad_norm": 0.30862241983413696, + "learning_rate": 2.3783494227998844e-05, + "loss": 0.0224, + "step": 6920 + }, + { + "epoch": 2.759856630824373, + "grad_norm": 0.22101591527462006, + "learning_rate": 2.3642842386102264e-05, + "loss": 0.0163, + "step": 6930 + }, + { + "epoch": 2.763839107925129, + "grad_norm": 0.2185278832912445, + "learning_rate": 2.3502478781858567e-05, + "loss": 0.0145, + "step": 6940 + }, + { + "epoch": 2.767821585025886, + "grad_norm": 0.24134941399097443, + "learning_rate": 2.3362404950261628e-05, + "loss": 0.019, + "step": 6950 + }, + { + "epoch": 2.771804062126643, + "grad_norm": 0.2902449071407318, + "learning_rate": 2.3222622423136458e-05, + "loss": 0.0165, + "step": 6960 + }, + { + "epoch": 2.7757865392273997, + "grad_norm": 0.3769952058792114, + "learning_rate": 2.3083132729122332e-05, + "loss": 0.0135, + "step": 6970 + }, + { + "epoch": 2.779769016328156, + "grad_norm": 0.22340670228004456, + "learning_rate": 2.294393739365621e-05, + "loss": 0.019, + "step": 6980 + }, + { + "epoch": 2.783751493428913, + "grad_norm": 0.33232781291007996, + "learning_rate": 2.2805037938956e-05, + "loss": 0.0162, + "step": 6990 + }, + { + "epoch": 2.7877339705296693, + "grad_norm": 0.33404746651649475, + "learning_rate": 2.266643588400386e-05, + "loss": 0.0162, + "step": 7000 + }, + { + "epoch": 2.791716447630426, + "grad_norm": 0.2362033873796463, + "learning_rate": 2.252813274452969e-05, + "loss": 0.0166, + "step": 7010 + }, + { + "epoch": 2.795698924731183, + "grad_norm": 0.15253150463104248, + "learning_rate": 2.2390130032994427e-05, + "loss": 0.0153, + "step": 7020 + }, + { + "epoch": 2.7996814018319394, + "grad_norm": 0.36513105034828186, + "learning_rate": 2.2252429258573633e-05, + "loss": 0.0172, + "step": 7030 + }, + { + "epoch": 2.803663878932696, + "grad_norm": 0.22622640430927277, + "learning_rate": 2.2115031927140904e-05, + "loss": 0.0158, + "step": 7040 + }, + { + "epoch": 2.8076463560334526, + "grad_norm": 0.3483319580554962, + "learning_rate": 2.1977939541251463e-05, + "loss": 0.0218, + "step": 7050 + }, + { + "epoch": 2.8116288331342094, + "grad_norm": 0.3104790449142456, + "learning_rate": 2.1841153600125684e-05, + "loss": 0.0165, + "step": 7060 + }, + { + "epoch": 2.8156113102349662, + "grad_norm": 0.2423543781042099, + "learning_rate": 2.170467559963267e-05, + "loss": 0.0167, + "step": 7070 + }, + { + "epoch": 2.819593787335723, + "grad_norm": 0.3841968774795532, + "learning_rate": 2.1568507032273982e-05, + "loss": 0.0135, + "step": 7080 + }, + { + "epoch": 2.8235762644364795, + "grad_norm": 0.2059573382139206, + "learning_rate": 2.1432649387167264e-05, + "loss": 0.015, + "step": 7090 + }, + { + "epoch": 2.8275587415372363, + "grad_norm": 0.22446751594543457, + "learning_rate": 2.1297104150029973e-05, + "loss": 0.0162, + "step": 7100 + }, + { + "epoch": 2.8315412186379927, + "grad_norm": 0.36766108870506287, + "learning_rate": 2.116187280316307e-05, + "loss": 0.0172, + "step": 7110 + }, + { + "epoch": 2.8355236957387495, + "grad_norm": 0.3884134292602539, + "learning_rate": 2.1026956825434908e-05, + "loss": 0.0182, + "step": 7120 + }, + { + "epoch": 2.8395061728395063, + "grad_norm": 0.3192227780818939, + "learning_rate": 2.0892357692265017e-05, + "loss": 0.0145, + "step": 7130 + }, + { + "epoch": 2.8434886499402627, + "grad_norm": 0.2538623511791229, + "learning_rate": 2.0758076875607947e-05, + "loss": 0.0191, + "step": 7140 + }, + { + "epoch": 2.8474711270410196, + "grad_norm": 0.2836097478866577, + "learning_rate": 2.0624115843937207e-05, + "loss": 0.0201, + "step": 7150 + }, + { + "epoch": 2.851453604141776, + "grad_norm": 0.2728939652442932, + "learning_rate": 2.0490476062229157e-05, + "loss": 0.0176, + "step": 7160 + }, + { + "epoch": 2.855436081242533, + "grad_norm": 0.3548661172389984, + "learning_rate": 2.035715899194704e-05, + "loss": 0.0161, + "step": 7170 + }, + { + "epoch": 2.8594185583432896, + "grad_norm": 0.3930123448371887, + "learning_rate": 2.022416609102499e-05, + "loss": 0.0177, + "step": 7180 + }, + { + "epoch": 2.8634010354440464, + "grad_norm": 0.510944664478302, + "learning_rate": 2.009149881385205e-05, + "loss": 0.0222, + "step": 7190 + }, + { + "epoch": 2.867383512544803, + "grad_norm": 0.3476032018661499, + "learning_rate": 1.995915861125634e-05, + "loss": 0.0176, + "step": 7200 + }, + { + "epoch": 2.8713659896455597, + "grad_norm": 0.2559760510921478, + "learning_rate": 1.9827146930489065e-05, + "loss": 0.0149, + "step": 7210 + }, + { + "epoch": 2.875348466746316, + "grad_norm": 0.20961345732212067, + "learning_rate": 1.9695465215208848e-05, + "loss": 0.018, + "step": 7220 + }, + { + "epoch": 2.879330943847073, + "grad_norm": 0.29862138628959656, + "learning_rate": 1.9564114905465813e-05, + "loss": 0.0156, + "step": 7230 + }, + { + "epoch": 2.8833134209478297, + "grad_norm": 0.3706551492214203, + "learning_rate": 1.9433097437685936e-05, + "loss": 0.0166, + "step": 7240 + }, + { + "epoch": 2.887295898048586, + "grad_norm": 0.4077451825141907, + "learning_rate": 1.930241424465521e-05, + "loss": 0.0139, + "step": 7250 + }, + { + "epoch": 2.891278375149343, + "grad_norm": 0.3151760399341583, + "learning_rate": 1.9172066755504115e-05, + "loss": 0.0164, + "step": 7260 + }, + { + "epoch": 2.8952608522500993, + "grad_norm": 0.29641613364219666, + "learning_rate": 1.9042056395691914e-05, + "loss": 0.0168, + "step": 7270 + }, + { + "epoch": 2.899243329350856, + "grad_norm": 0.3831641376018524, + "learning_rate": 1.8912384586991066e-05, + "loss": 0.0147, + "step": 7280 + }, + { + "epoch": 2.903225806451613, + "grad_norm": 0.3114636540412903, + "learning_rate": 1.8783052747471717e-05, + "loss": 0.0144, + "step": 7290 + }, + { + "epoch": 2.90720828355237, + "grad_norm": 0.26268333196640015, + "learning_rate": 1.865406229148611e-05, + "loss": 0.0185, + "step": 7300 + }, + { + "epoch": 2.911190760653126, + "grad_norm": 0.22112445533275604, + "learning_rate": 1.8525414629653233e-05, + "loss": 0.0203, + "step": 7310 + }, + { + "epoch": 2.915173237753883, + "grad_norm": 0.2656763195991516, + "learning_rate": 1.8397111168843255e-05, + "loss": 0.0158, + "step": 7320 + }, + { + "epoch": 2.9191557148546394, + "grad_norm": 0.341366171836853, + "learning_rate": 1.8269153312162323e-05, + "loss": 0.0176, + "step": 7330 + }, + { + "epoch": 2.9231381919553963, + "grad_norm": 0.27272844314575195, + "learning_rate": 1.8141542458937054e-05, + "loss": 0.0155, + "step": 7340 + }, + { + "epoch": 2.927120669056153, + "grad_norm": 0.4220792353153229, + "learning_rate": 1.8014280004699268e-05, + "loss": 0.0173, + "step": 7350 + }, + { + "epoch": 2.9311031461569095, + "grad_norm": 0.2644200325012207, + "learning_rate": 1.788736734117078e-05, + "loss": 0.0111, + "step": 7360 + }, + { + "epoch": 2.9350856232576663, + "grad_norm": 0.27255773544311523, + "learning_rate": 1.7760805856248152e-05, + "loss": 0.0166, + "step": 7370 + }, + { + "epoch": 2.9390681003584227, + "grad_norm": 0.17350824177265167, + "learning_rate": 1.7634596933987518e-05, + "loss": 0.016, + "step": 7380 + }, + { + "epoch": 2.9430505774591795, + "grad_norm": 0.23067346215248108, + "learning_rate": 1.7508741954589404e-05, + "loss": 0.0164, + "step": 7390 + }, + { + "epoch": 2.9470330545599364, + "grad_norm": 0.3143824636936188, + "learning_rate": 1.7383242294383717e-05, + "loss": 0.0166, + "step": 7400 + }, + { + "epoch": 2.951015531660693, + "grad_norm": 0.2438683658838272, + "learning_rate": 1.7258099325814632e-05, + "loss": 0.0129, + "step": 7410 + }, + { + "epoch": 2.9549980087614496, + "grad_norm": 0.31693488359451294, + "learning_rate": 1.7133314417425594e-05, + "loss": 0.02, + "step": 7420 + }, + { + "epoch": 2.9589804858622064, + "grad_norm": 0.26909369230270386, + "learning_rate": 1.7008888933844408e-05, + "loss": 0.0155, + "step": 7430 + }, + { + "epoch": 2.962962962962963, + "grad_norm": 0.29988786578178406, + "learning_rate": 1.6884824235768172e-05, + "loss": 0.0173, + "step": 7440 + }, + { + "epoch": 2.9669454400637196, + "grad_norm": 0.2735227048397064, + "learning_rate": 1.6761121679948592e-05, + "loss": 0.0148, + "step": 7450 + }, + { + "epoch": 2.9709279171644765, + "grad_norm": 0.23975975811481476, + "learning_rate": 1.663778261917695e-05, + "loss": 0.0177, + "step": 7460 + }, + { + "epoch": 2.974910394265233, + "grad_norm": 0.3303283452987671, + "learning_rate": 1.651480840226952e-05, + "loss": 0.0154, + "step": 7470 + }, + { + "epoch": 2.9788928713659897, + "grad_norm": 0.3179773688316345, + "learning_rate": 1.639220037405258e-05, + "loss": 0.017, + "step": 7480 + }, + { + "epoch": 2.982875348466746, + "grad_norm": 0.26732003688812256, + "learning_rate": 1.6269959875347906e-05, + "loss": 0.0162, + "step": 7490 + }, + { + "epoch": 2.986857825567503, + "grad_norm": 0.35051149129867554, + "learning_rate": 1.614808824295802e-05, + "loss": 0.0161, + "step": 7500 + }, + { + "epoch": 2.9908403026682597, + "grad_norm": 0.24838776886463165, + "learning_rate": 1.602658680965152e-05, + "loss": 0.0115, + "step": 7510 + }, + { + "epoch": 2.9948227797690166, + "grad_norm": 0.3378634452819824, + "learning_rate": 1.5905456904148686e-05, + "loss": 0.0183, + "step": 7520 + }, + { + "epoch": 2.998805256869773, + "grad_norm": 0.28400248289108276, + "learning_rate": 1.57846998511067e-05, + "loss": 0.0165, + "step": 7530 + }, + { + "epoch": 3.00278773397053, + "grad_norm": 0.2319607138633728, + "learning_rate": 1.566431697110538e-05, + "loss": 0.0137, + "step": 7540 + }, + { + "epoch": 3.006770211071286, + "grad_norm": 0.326729953289032, + "learning_rate": 1.554430958063259e-05, + "loss": 0.0135, + "step": 7550 + }, + { + "epoch": 3.010752688172043, + "grad_norm": 0.2378934919834137, + "learning_rate": 1.5424678992069912e-05, + "loss": 0.0152, + "step": 7560 + }, + { + "epoch": 3.0147351652728, + "grad_norm": 0.24295467138290405, + "learning_rate": 1.5305426513678362e-05, + "loss": 0.0142, + "step": 7570 + }, + { + "epoch": 3.018717642373556, + "grad_norm": 0.2576531767845154, + "learning_rate": 1.518655344958388e-05, + "loss": 0.0181, + "step": 7580 + }, + { + "epoch": 3.022700119474313, + "grad_norm": 0.18377450108528137, + "learning_rate": 1.5068061099763275e-05, + "loss": 0.0166, + "step": 7590 + }, + { + "epoch": 3.02668259657507, + "grad_norm": 0.27830517292022705, + "learning_rate": 1.494995076002988e-05, + "loss": 0.0154, + "step": 7600 + }, + { + "epoch": 3.0306650736758263, + "grad_norm": 0.21844340860843658, + "learning_rate": 1.4832223722019456e-05, + "loss": 0.012, + "step": 7610 + }, + { + "epoch": 3.034647550776583, + "grad_norm": 0.2617688775062561, + "learning_rate": 1.4714881273176035e-05, + "loss": 0.0174, + "step": 7620 + }, + { + "epoch": 3.0386300278773395, + "grad_norm": 0.32421252131462097, + "learning_rate": 1.4597924696737835e-05, + "loss": 0.0145, + "step": 7630 + }, + { + "epoch": 3.0426125049780963, + "grad_norm": 0.29088929295539856, + "learning_rate": 1.4481355271723252e-05, + "loss": 0.0159, + "step": 7640 + }, + { + "epoch": 3.046594982078853, + "grad_norm": 0.33224666118621826, + "learning_rate": 1.4365174272916809e-05, + "loss": 0.0172, + "step": 7650 + }, + { + "epoch": 3.0505774591796095, + "grad_norm": 0.28133267164230347, + "learning_rate": 1.4249382970855319e-05, + "loss": 0.0164, + "step": 7660 + }, + { + "epoch": 3.0545599362803664, + "grad_norm": 0.2961582839488983, + "learning_rate": 1.4133982631813903e-05, + "loss": 0.0174, + "step": 7670 + }, + { + "epoch": 3.058542413381123, + "grad_norm": 0.19143448770046234, + "learning_rate": 1.4018974517792194e-05, + "loss": 0.0148, + "step": 7680 + }, + { + "epoch": 3.0625248904818796, + "grad_norm": 0.26252588629722595, + "learning_rate": 1.390435988650048e-05, + "loss": 0.0143, + "step": 7690 + }, + { + "epoch": 3.0665073675826364, + "grad_norm": 0.19971930980682373, + "learning_rate": 1.3790139991346006e-05, + "loss": 0.0125, + "step": 7700 + }, + { + "epoch": 3.0704898446833933, + "grad_norm": 0.2495674192905426, + "learning_rate": 1.367631608141926e-05, + "loss": 0.0155, + "step": 7710 + }, + { + "epoch": 3.0744723217841496, + "grad_norm": 0.22202928364276886, + "learning_rate": 1.3562889401480278e-05, + "loss": 0.0148, + "step": 7720 + }, + { + "epoch": 3.0784547988849065, + "grad_norm": 0.4576508402824402, + "learning_rate": 1.3449861191945074e-05, + "loss": 0.0165, + "step": 7730 + }, + { + "epoch": 3.0824372759856633, + "grad_norm": 0.3544761836528778, + "learning_rate": 1.3337232688872009e-05, + "loss": 0.0139, + "step": 7740 + }, + { + "epoch": 3.0864197530864197, + "grad_norm": 0.3484187722206116, + "learning_rate": 1.3225005123948364e-05, + "loss": 0.0147, + "step": 7750 + }, + { + "epoch": 3.0904022301871765, + "grad_norm": 0.19573178887367249, + "learning_rate": 1.311317972447681e-05, + "loss": 0.0127, + "step": 7760 + }, + { + "epoch": 3.094384707287933, + "grad_norm": 0.19815529882907867, + "learning_rate": 1.3001757713361996e-05, + "loss": 0.0109, + "step": 7770 + }, + { + "epoch": 3.0983671843886897, + "grad_norm": 0.35429829359054565, + "learning_rate": 1.2890740309097204e-05, + "loss": 0.0161, + "step": 7780 + }, + { + "epoch": 3.1023496614894466, + "grad_norm": 0.2911655008792877, + "learning_rate": 1.2780128725750944e-05, + "loss": 0.0138, + "step": 7790 + }, + { + "epoch": 3.106332138590203, + "grad_norm": 0.270168662071228, + "learning_rate": 1.266992417295379e-05, + "loss": 0.015, + "step": 7800 + }, + { + "epoch": 3.11031461569096, + "grad_norm": 0.32108160853385925, + "learning_rate": 1.2560127855885073e-05, + "loss": 0.0163, + "step": 7810 + }, + { + "epoch": 3.1142970927917166, + "grad_norm": 0.24168479442596436, + "learning_rate": 1.2450740975259745e-05, + "loss": 0.0167, + "step": 7820 + }, + { + "epoch": 3.118279569892473, + "grad_norm": 0.30409395694732666, + "learning_rate": 1.234176472731517e-05, + "loss": 0.0221, + "step": 7830 + }, + { + "epoch": 3.12226204699323, + "grad_norm": 0.3229791522026062, + "learning_rate": 1.2233200303798158e-05, + "loss": 0.0147, + "step": 7840 + }, + { + "epoch": 3.1262445240939867, + "grad_norm": 0.26919838786125183, + "learning_rate": 1.2125048891951846e-05, + "loss": 0.0158, + "step": 7850 + }, + { + "epoch": 3.130227001194743, + "grad_norm": 0.23068082332611084, + "learning_rate": 1.2017311674502745e-05, + "loss": 0.013, + "step": 7860 + }, + { + "epoch": 3.1342094782955, + "grad_norm": 0.17686747014522552, + "learning_rate": 1.1909989829647822e-05, + "loss": 0.0144, + "step": 7870 + }, + { + "epoch": 3.1381919553962563, + "grad_norm": 0.45290425419807434, + "learning_rate": 1.1803084531041553e-05, + "loss": 0.0173, + "step": 7880 + }, + { + "epoch": 3.142174432497013, + "grad_norm": 0.2763400673866272, + "learning_rate": 1.1696596947783162e-05, + "loss": 0.0144, + "step": 7890 + }, + { + "epoch": 3.14615690959777, + "grad_norm": 0.2585810422897339, + "learning_rate": 1.1590528244403803e-05, + "loss": 0.0175, + "step": 7900 + }, + { + "epoch": 3.1501393866985263, + "grad_norm": 0.22105610370635986, + "learning_rate": 1.148487958085382e-05, + "loss": 0.0151, + "step": 7910 + }, + { + "epoch": 3.154121863799283, + "grad_norm": 0.21400152146816254, + "learning_rate": 1.1379652112490086e-05, + "loss": 0.0177, + "step": 7920 + }, + { + "epoch": 3.15810434090004, + "grad_norm": 0.1969025582075119, + "learning_rate": 1.1274846990063315e-05, + "loss": 0.0136, + "step": 7930 + }, + { + "epoch": 3.1620868180007964, + "grad_norm": 0.2094409465789795, + "learning_rate": 1.117046535970554e-05, + "loss": 0.0151, + "step": 7940 + }, + { + "epoch": 3.166069295101553, + "grad_norm": 0.29152101278305054, + "learning_rate": 1.106650836291755e-05, + "loss": 0.0195, + "step": 7950 + }, + { + "epoch": 3.17005177220231, + "grad_norm": 0.28160348534584045, + "learning_rate": 1.0962977136556418e-05, + "loss": 0.0184, + "step": 7960 + }, + { + "epoch": 3.1740342493030664, + "grad_norm": 0.3710784614086151, + "learning_rate": 1.0859872812823024e-05, + "loss": 0.0144, + "step": 7970 + }, + { + "epoch": 3.1780167264038233, + "grad_norm": 0.23486924171447754, + "learning_rate": 1.0757196519249747e-05, + "loss": 0.0189, + "step": 7980 + }, + { + "epoch": 3.1819992035045797, + "grad_norm": 0.31155335903167725, + "learning_rate": 1.0654949378688077e-05, + "loss": 0.0156, + "step": 7990 + }, + { + "epoch": 3.1859816806053365, + "grad_norm": 0.21536493301391602, + "learning_rate": 1.0553132509296376e-05, + "loss": 0.0146, + "step": 8000 + }, + { + "epoch": 3.1899641577060933, + "grad_norm": 0.25504568219184875, + "learning_rate": 1.0451747024527613e-05, + "loss": 0.0139, + "step": 8010 + }, + { + "epoch": 3.1939466348068497, + "grad_norm": 0.43125614523887634, + "learning_rate": 1.0350794033117189e-05, + "loss": 0.017, + "step": 8020 + }, + { + "epoch": 3.1979291119076065, + "grad_norm": 0.3463977873325348, + "learning_rate": 1.0250274639070856e-05, + "loss": 0.0153, + "step": 8030 + }, + { + "epoch": 3.2019115890083634, + "grad_norm": 0.33657532930374146, + "learning_rate": 1.0150189941652599e-05, + "loss": 0.0136, + "step": 8040 + }, + { + "epoch": 3.2058940661091198, + "grad_norm": 0.27286818623542786, + "learning_rate": 1.0050541035372635e-05, + "loss": 0.0123, + "step": 8050 + }, + { + "epoch": 3.2098765432098766, + "grad_norm": 0.3115975260734558, + "learning_rate": 9.951329009975458e-06, + "loss": 0.0149, + "step": 8060 + }, + { + "epoch": 3.2138590203106334, + "grad_norm": 0.2783370018005371, + "learning_rate": 9.852554950427845e-06, + "loss": 0.015, + "step": 8070 + }, + { + "epoch": 3.21784149741139, + "grad_norm": 0.2135641872882843, + "learning_rate": 9.754219936907105e-06, + "loss": 0.0145, + "step": 8080 + }, + { + "epoch": 3.2218239745121466, + "grad_norm": 0.2889596223831177, + "learning_rate": 9.656325044789194e-06, + "loss": 0.0125, + "step": 8090 + }, + { + "epoch": 3.225806451612903, + "grad_norm": 0.16843768954277039, + "learning_rate": 9.55887134463697e-06, + "loss": 0.0116, + "step": 8100 + }, + { + "epoch": 3.22978892871366, + "grad_norm": 0.22345881164073944, + "learning_rate": 9.461859902188475e-06, + "loss": 0.0133, + "step": 8110 + }, + { + "epoch": 3.2337714058144167, + "grad_norm": 0.4386395812034607, + "learning_rate": 9.365291778345303e-06, + "loss": 0.0166, + "step": 8120 + }, + { + "epoch": 3.237753882915173, + "grad_norm": 0.15999703109264374, + "learning_rate": 9.269168029160991e-06, + "loss": 0.0103, + "step": 8130 + }, + { + "epoch": 3.24173636001593, + "grad_norm": 0.33131685853004456, + "learning_rate": 9.173489705829447e-06, + "loss": 0.0152, + "step": 8140 + }, + { + "epoch": 3.2457188371166867, + "grad_norm": 0.18595287203788757, + "learning_rate": 9.078257854673516e-06, + "loss": 0.0136, + "step": 8150 + }, + { + "epoch": 3.249701314217443, + "grad_norm": 0.18805378675460815, + "learning_rate": 8.983473517133429e-06, + "loss": 0.0141, + "step": 8160 + }, + { + "epoch": 3.2536837913182, + "grad_norm": 0.15438763797283173, + "learning_rate": 8.889137729755537e-06, + "loss": 0.013, + "step": 8170 + }, + { + "epoch": 3.257666268418957, + "grad_norm": 0.27492639422416687, + "learning_rate": 8.79525152418087e-06, + "loss": 0.0169, + "step": 8180 + }, + { + "epoch": 3.261648745519713, + "grad_norm": 0.28761956095695496, + "learning_rate": 8.701815927133961e-06, + "loss": 0.014, + "step": 8190 + }, + { + "epoch": 3.26563122262047, + "grad_norm": 0.17063534259796143, + "learning_rate": 8.608831960411534e-06, + "loss": 0.0139, + "step": 8200 + }, + { + "epoch": 3.2696136997212264, + "grad_norm": 0.22604522109031677, + "learning_rate": 8.516300640871321e-06, + "loss": 0.0164, + "step": 8210 + }, + { + "epoch": 3.2735961768219832, + "grad_norm": 0.27093005180358887, + "learning_rate": 8.424222980421038e-06, + "loss": 0.0165, + "step": 8220 + }, + { + "epoch": 3.27757865392274, + "grad_norm": 0.2355274260044098, + "learning_rate": 8.332599986007184e-06, + "loss": 0.0151, + "step": 8230 + }, + { + "epoch": 3.2815611310234964, + "grad_norm": 0.23121079802513123, + "learning_rate": 8.241432659604203e-06, + "loss": 0.0144, + "step": 8240 + }, + { + "epoch": 3.2855436081242533, + "grad_norm": 0.1323615461587906, + "learning_rate": 8.150721998203331e-06, + "loss": 0.0128, + "step": 8250 + }, + { + "epoch": 3.28952608522501, + "grad_norm": 0.24003800749778748, + "learning_rate": 8.06046899380184e-06, + "loss": 0.0123, + "step": 8260 + }, + { + "epoch": 3.2935085623257665, + "grad_norm": 0.24698399007320404, + "learning_rate": 7.970674633392133e-06, + "loss": 0.0166, + "step": 8270 + }, + { + "epoch": 3.2974910394265233, + "grad_norm": 0.38070154190063477, + "learning_rate": 7.881339898950924e-06, + "loss": 0.018, + "step": 8280 + }, + { + "epoch": 3.30147351652728, + "grad_norm": 0.1986345499753952, + "learning_rate": 7.792465767428597e-06, + "loss": 0.0136, + "step": 8290 + }, + { + "epoch": 3.3054559936280365, + "grad_norm": 0.21766434609889984, + "learning_rate": 7.704053210738376e-06, + "loss": 0.0132, + "step": 8300 + }, + { + "epoch": 3.3094384707287934, + "grad_norm": 0.20243440568447113, + "learning_rate": 7.6161031957458494e-06, + "loss": 0.0152, + "step": 8310 + }, + { + "epoch": 3.3134209478295498, + "grad_norm": 0.2816754877567291, + "learning_rate": 7.5286166842582605e-06, + "loss": 0.0148, + "step": 8320 + }, + { + "epoch": 3.3174034249303066, + "grad_norm": 0.2514406442642212, + "learning_rate": 7.4415946330140814e-06, + "loss": 0.0145, + "step": 8330 + }, + { + "epoch": 3.3213859020310634, + "grad_norm": 0.2709660530090332, + "learning_rate": 7.3550379936725644e-06, + "loss": 0.0141, + "step": 8340 + }, + { + "epoch": 3.32536837913182, + "grad_norm": 0.2837410569190979, + "learning_rate": 7.2689477128032035e-06, + "loss": 0.018, + "step": 8350 + }, + { + "epoch": 3.3293508562325766, + "grad_norm": 0.131383016705513, + "learning_rate": 7.183324731875551e-06, + "loss": 0.0105, + "step": 8360 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.31221866607666016, + "learning_rate": 7.098169987248782e-06, + "loss": 0.012, + "step": 8370 + }, + { + "epoch": 3.33731581043409, + "grad_norm": 0.2039610892534256, + "learning_rate": 7.013484410161553e-06, + "loss": 0.0135, + "step": 8380 + }, + { + "epoch": 3.3412982875348467, + "grad_norm": 0.22186747193336487, + "learning_rate": 6.92926892672176e-06, + "loss": 0.0131, + "step": 8390 + }, + { + "epoch": 3.3452807646356035, + "grad_norm": 0.1861848533153534, + "learning_rate": 6.845524457896446e-06, + "loss": 0.0124, + "step": 8400 + }, + { + "epoch": 3.34926324173636, + "grad_norm": 0.23007585108280182, + "learning_rate": 6.7622519195017165e-06, + "loss": 0.0126, + "step": 8410 + }, + { + "epoch": 3.3532457188371168, + "grad_norm": 0.26495233178138733, + "learning_rate": 6.679452222192684e-06, + "loss": 0.0136, + "step": 8420 + }, + { + "epoch": 3.357228195937873, + "grad_norm": 0.2193382978439331, + "learning_rate": 6.597126271453579e-06, + "loss": 0.011, + "step": 8430 + }, + { + "epoch": 3.36121067303863, + "grad_norm": 0.10426363348960876, + "learning_rate": 6.51527496758782e-06, + "loss": 0.0114, + "step": 8440 + }, + { + "epoch": 3.365193150139387, + "grad_norm": 0.16592855751514435, + "learning_rate": 6.433899205708155e-06, + "loss": 0.0131, + "step": 8450 + }, + { + "epoch": 3.369175627240143, + "grad_norm": 0.1602918803691864, + "learning_rate": 6.352999875726856e-06, + "loss": 0.0121, + "step": 8460 + }, + { + "epoch": 3.3731581043409, + "grad_norm": 0.16960707306861877, + "learning_rate": 6.272577862346052e-06, + "loss": 0.0115, + "step": 8470 + }, + { + "epoch": 3.377140581441657, + "grad_norm": 0.29499271512031555, + "learning_rate": 6.192634045047996e-06, + "loss": 0.0129, + "step": 8480 + }, + { + "epoch": 3.3811230585424132, + "grad_norm": 0.23193804919719696, + "learning_rate": 6.113169298085458e-06, + "loss": 0.0194, + "step": 8490 + }, + { + "epoch": 3.38510553564317, + "grad_norm": 0.3416202962398529, + "learning_rate": 6.034184490472195e-06, + "loss": 0.0114, + "step": 8500 + }, + { + "epoch": 3.389088012743927, + "grad_norm": 0.22498588263988495, + "learning_rate": 5.955680485973386e-06, + "loss": 0.0156, + "step": 8510 + }, + { + "epoch": 3.3930704898446833, + "grad_norm": 0.3182886838912964, + "learning_rate": 5.877658143096265e-06, + "loss": 0.0132, + "step": 8520 + }, + { + "epoch": 3.39705296694544, + "grad_norm": 0.1463838666677475, + "learning_rate": 5.800118315080661e-06, + "loss": 0.0129, + "step": 8530 + }, + { + "epoch": 3.4010354440461965, + "grad_norm": 0.23471392691135406, + "learning_rate": 5.723061849889716e-06, + "loss": 0.0126, + "step": 8540 + }, + { + "epoch": 3.4050179211469533, + "grad_norm": 0.1969936192035675, + "learning_rate": 5.646489590200604e-06, + "loss": 0.0161, + "step": 8550 + }, + { + "epoch": 3.40900039824771, + "grad_norm": 0.15309295058250427, + "learning_rate": 5.570402373395256e-06, + "loss": 0.0125, + "step": 8560 + }, + { + "epoch": 3.4129828753484666, + "grad_norm": 0.4474526643753052, + "learning_rate": 5.494801031551305e-06, + "loss": 0.0163, + "step": 8570 + }, + { + "epoch": 3.4169653524492234, + "grad_norm": 0.18500779569149017, + "learning_rate": 5.41968639143291e-06, + "loss": 0.0139, + "step": 8580 + }, + { + "epoch": 3.4209478295499802, + "grad_norm": 0.19193483889102936, + "learning_rate": 5.345059274481751e-06, + "loss": 0.0127, + "step": 8590 + }, + { + "epoch": 3.4249303066507366, + "grad_norm": 0.15665030479431152, + "learning_rate": 5.270920496808002e-06, + "loss": 0.0159, + "step": 8600 + }, + { + "epoch": 3.4289127837514934, + "grad_norm": 0.16787682473659515, + "learning_rate": 5.1972708691814695e-06, + "loss": 0.0116, + "step": 8610 + }, + { + "epoch": 3.4328952608522503, + "grad_norm": 0.29282400012016296, + "learning_rate": 5.124111197022674e-06, + "loss": 0.0145, + "step": 8620 + }, + { + "epoch": 3.4368777379530067, + "grad_norm": 0.1538035124540329, + "learning_rate": 5.051442280394081e-06, + "loss": 0.0118, + "step": 8630 + }, + { + "epoch": 3.4408602150537635, + "grad_norm": 0.16790461540222168, + "learning_rate": 4.979264913991322e-06, + "loss": 0.0132, + "step": 8640 + }, + { + "epoch": 3.44484269215452, + "grad_norm": 0.1722331941127777, + "learning_rate": 4.907579887134489e-06, + "loss": 0.0134, + "step": 8650 + }, + { + "epoch": 3.4488251692552767, + "grad_norm": 0.21935425698757172, + "learning_rate": 4.836387983759572e-06, + "loss": 0.0137, + "step": 8660 + }, + { + "epoch": 3.4528076463560335, + "grad_norm": 0.2668359875679016, + "learning_rate": 4.765689982409816e-06, + "loss": 0.0121, + "step": 8670 + }, + { + "epoch": 3.45679012345679, + "grad_norm": 0.34474870562553406, + "learning_rate": 4.695486656227233e-06, + "loss": 0.0178, + "step": 8680 + }, + { + "epoch": 3.4607726005575468, + "grad_norm": 0.3360903859138489, + "learning_rate": 4.625778772944156e-06, + "loss": 0.013, + "step": 8690 + }, + { + "epoch": 3.4647550776583036, + "grad_norm": 0.1198967769742012, + "learning_rate": 4.556567094874825e-06, + "loss": 0.0139, + "step": 8700 + }, + { + "epoch": 3.46873755475906, + "grad_norm": 0.12995925545692444, + "learning_rate": 4.487852378907059e-06, + "loss": 0.0099, + "step": 8710 + }, + { + "epoch": 3.472720031859817, + "grad_norm": 0.14079661667346954, + "learning_rate": 4.419635376493986e-06, + "loss": 0.0133, + "step": 8720 + }, + { + "epoch": 3.4767025089605736, + "grad_norm": 0.23179714381694794, + "learning_rate": 4.351916833645825e-06, + "loss": 0.0145, + "step": 8730 + }, + { + "epoch": 3.48068498606133, + "grad_norm": 0.19353191554546356, + "learning_rate": 4.284697490921691e-06, + "loss": 0.013, + "step": 8740 + }, + { + "epoch": 3.484667463162087, + "grad_norm": 0.2545132040977478, + "learning_rate": 4.2179780834215585e-06, + "loss": 0.0161, + "step": 8750 + }, + { + "epoch": 3.4886499402628433, + "grad_norm": 0.22561277449131012, + "learning_rate": 4.151759340778178e-06, + "loss": 0.0142, + "step": 8760 + }, + { + "epoch": 3.4926324173636, + "grad_norm": 0.25932180881500244, + "learning_rate": 4.086041987149109e-06, + "loss": 0.0131, + "step": 8770 + }, + { + "epoch": 3.496614894464357, + "grad_norm": 0.23832671344280243, + "learning_rate": 4.020826741208811e-06, + "loss": 0.016, + "step": 8780 + }, + { + "epoch": 3.5005973715651137, + "grad_norm": 0.1888727992773056, + "learning_rate": 3.956114316140746e-06, + "loss": 0.0165, + "step": 8790 + }, + { + "epoch": 3.50457984866587, + "grad_norm": 0.2623044550418854, + "learning_rate": 3.891905419629643e-06, + "loss": 0.0125, + "step": 8800 + }, + { + "epoch": 3.508562325766627, + "grad_norm": 0.25887444615364075, + "learning_rate": 3.8282007538536946e-06, + "loss": 0.0164, + "step": 8810 + }, + { + "epoch": 3.5125448028673834, + "grad_norm": 0.21378953754901886, + "learning_rate": 3.7650010154769265e-06, + "loss": 0.0126, + "step": 8820 + }, + { + "epoch": 3.51652727996814, + "grad_norm": 0.2530067563056946, + "learning_rate": 3.7023068956415608e-06, + "loss": 0.0168, + "step": 8830 + }, + { + "epoch": 3.520509757068897, + "grad_norm": 0.27777713537216187, + "learning_rate": 3.6401190799604303e-06, + "loss": 0.0132, + "step": 8840 + }, + { + "epoch": 3.5244922341696534, + "grad_norm": 0.16841277480125427, + "learning_rate": 3.578438248509536e-06, + "loss": 0.015, + "step": 8850 + }, + { + "epoch": 3.5284747112704102, + "grad_norm": 0.22934165596961975, + "learning_rate": 3.5172650758205583e-06, + "loss": 0.0158, + "step": 8860 + }, + { + "epoch": 3.5324571883711666, + "grad_norm": 0.2117910385131836, + "learning_rate": 3.45660023087353e-06, + "loss": 0.0138, + "step": 8870 + }, + { + "epoch": 3.5364396654719235, + "grad_norm": 0.12349478155374527, + "learning_rate": 3.3964443770894528e-06, + "loss": 0.0115, + "step": 8880 + }, + { + "epoch": 3.5404221425726803, + "grad_norm": 0.25816065073013306, + "learning_rate": 3.3367981723231245e-06, + "loss": 0.013, + "step": 8890 + }, + { + "epoch": 3.544404619673437, + "grad_norm": 0.24896445870399475, + "learning_rate": 3.2776622688558746e-06, + "loss": 0.0134, + "step": 8900 + }, + { + "epoch": 3.5483870967741935, + "grad_norm": 0.20246760547161102, + "learning_rate": 3.2190373133884677e-06, + "loss": 0.0141, + "step": 8910 + }, + { + "epoch": 3.5523695738749503, + "grad_norm": 0.17225037515163422, + "learning_rate": 3.1609239470340446e-06, + "loss": 0.0125, + "step": 8920 + }, + { + "epoch": 3.5563520509757067, + "grad_norm": 0.16104808449745178, + "learning_rate": 3.1033228053110373e-06, + "loss": 0.0127, + "step": 8930 + }, + { + "epoch": 3.5603345280764636, + "grad_norm": 0.25064268708229065, + "learning_rate": 3.0462345181363314e-06, + "loss": 0.0121, + "step": 8940 + }, + { + "epoch": 3.5643170051772204, + "grad_norm": 0.177175834774971, + "learning_rate": 2.9896597098182654e-06, + "loss": 0.0145, + "step": 8950 + }, + { + "epoch": 3.5682994822779768, + "grad_norm": 0.23675449192523956, + "learning_rate": 2.933598999049891e-06, + "loss": 0.0133, + "step": 8960 + }, + { + "epoch": 3.5722819593787336, + "grad_norm": 0.19365286827087402, + "learning_rate": 2.8780529989021697e-06, + "loss": 0.0126, + "step": 8970 + }, + { + "epoch": 3.57626443647949, + "grad_norm": 0.3542676270008087, + "learning_rate": 2.823022316817242e-06, + "loss": 0.0162, + "step": 8980 + }, + { + "epoch": 3.580246913580247, + "grad_norm": 0.2057904750108719, + "learning_rate": 2.7685075546018456e-06, + "loss": 0.0134, + "step": 8990 + }, + { + "epoch": 3.5842293906810037, + "grad_norm": 0.19681024551391602, + "learning_rate": 2.7145093084206598e-06, + "loss": 0.0158, + "step": 9000 + }, + { + "epoch": 3.5882118677817605, + "grad_norm": 0.11298860609531403, + "learning_rate": 2.661028168789892e-06, + "loss": 0.0114, + "step": 9010 + }, + { + "epoch": 3.592194344882517, + "grad_norm": 0.20377224683761597, + "learning_rate": 2.6080647205706855e-06, + "loss": 0.0115, + "step": 9020 + }, + { + "epoch": 3.5961768219832737, + "grad_norm": 0.20502862334251404, + "learning_rate": 2.555619542962834e-06, + "loss": 0.0141, + "step": 9030 + }, + { + "epoch": 3.60015929908403, + "grad_norm": 0.2239837795495987, + "learning_rate": 2.503693209498409e-06, + "loss": 0.0108, + "step": 9040 + }, + { + "epoch": 3.604141776184787, + "grad_norm": 0.21607056260108948, + "learning_rate": 2.452286288035449e-06, + "loss": 0.0138, + "step": 9050 + }, + { + "epoch": 3.6081242532855438, + "grad_norm": 0.23609691858291626, + "learning_rate": 2.4013993407518363e-06, + "loss": 0.0129, + "step": 9060 + }, + { + "epoch": 3.6121067303863, + "grad_norm": 0.20945118367671967, + "learning_rate": 2.351032924139063e-06, + "loss": 0.0117, + "step": 9070 + }, + { + "epoch": 3.616089207487057, + "grad_norm": 0.180077463388443, + "learning_rate": 2.30118758899619e-06, + "loss": 0.0146, + "step": 9080 + }, + { + "epoch": 3.6200716845878134, + "grad_norm": 0.25069552659988403, + "learning_rate": 2.2518638804238157e-06, + "loss": 0.0135, + "step": 9090 + }, + { + "epoch": 3.62405416168857, + "grad_norm": 0.14733609557151794, + "learning_rate": 2.203062337818118e-06, + "loss": 0.0135, + "step": 9100 + }, + { + "epoch": 3.628036638789327, + "grad_norm": 0.27784958481788635, + "learning_rate": 2.1547834948649483e-06, + "loss": 0.014, + "step": 9110 + }, + { + "epoch": 3.632019115890084, + "grad_norm": 0.18988502025604248, + "learning_rate": 2.1070278795340017e-06, + "loss": 0.0148, + "step": 9120 + }, + { + "epoch": 3.6360015929908402, + "grad_norm": 0.15056854486465454, + "learning_rate": 2.059796014073029e-06, + "loss": 0.0098, + "step": 9130 + }, + { + "epoch": 3.639984070091597, + "grad_norm": 0.25632742047309875, + "learning_rate": 2.01308841500214e-06, + "loss": 0.0121, + "step": 9140 + }, + { + "epoch": 3.6439665471923535, + "grad_norm": 0.33377549052238464, + "learning_rate": 1.9669055931081704e-06, + "loss": 0.0153, + "step": 9150 + }, + { + "epoch": 3.6479490242931103, + "grad_norm": 0.24696041643619537, + "learning_rate": 1.9212480534390507e-06, + "loss": 0.0153, + "step": 9160 + }, + { + "epoch": 3.651931501393867, + "grad_norm": 0.1778692901134491, + "learning_rate": 1.8761162952983246e-06, + "loss": 0.0139, + "step": 9170 + }, + { + "epoch": 3.6559139784946235, + "grad_norm": 0.31593841314315796, + "learning_rate": 1.8315108122396618e-06, + "loss": 0.0148, + "step": 9180 + }, + { + "epoch": 3.6598964555953803, + "grad_norm": 0.2725008726119995, + "learning_rate": 1.787432092061475e-06, + "loss": 0.0126, + "step": 9190 + }, + { + "epoch": 3.6638789326961367, + "grad_norm": 0.2079121172428131, + "learning_rate": 1.743880616801602e-06, + "loss": 0.0168, + "step": 9200 + }, + { + "epoch": 3.6678614097968936, + "grad_norm": 0.1617252379655838, + "learning_rate": 1.7008568627319865e-06, + "loss": 0.0125, + "step": 9210 + }, + { + "epoch": 3.6718438868976504, + "grad_norm": 0.23413202166557312, + "learning_rate": 1.6583613003535226e-06, + "loss": 0.0139, + "step": 9220 + }, + { + "epoch": 3.6758263639984072, + "grad_norm": 0.20422157645225525, + "learning_rate": 1.6163943943908522e-06, + "loss": 0.0129, + "step": 9230 + }, + { + "epoch": 3.6798088410991636, + "grad_norm": 0.3413521349430084, + "learning_rate": 1.5749566037873476e-06, + "loss": 0.0133, + "step": 9240 + }, + { + "epoch": 3.6837913181999205, + "grad_norm": 0.1363775134086609, + "learning_rate": 1.5340483817000428e-06, + "loss": 0.012, + "step": 9250 + }, + { + "epoch": 3.687773795300677, + "grad_norm": 0.11363986134529114, + "learning_rate": 1.4936701754947101e-06, + "loss": 0.0116, + "step": 9260 + }, + { + "epoch": 3.6917562724014337, + "grad_norm": 0.27134454250335693, + "learning_rate": 1.4538224267409361e-06, + "loss": 0.0147, + "step": 9270 + }, + { + "epoch": 3.6957387495021905, + "grad_norm": 0.16270877420902252, + "learning_rate": 1.414505571207314e-06, + "loss": 0.0111, + "step": 9280 + }, + { + "epoch": 3.699721226602947, + "grad_norm": 0.23508696258068085, + "learning_rate": 1.3757200388566816e-06, + "loss": 0.0122, + "step": 9290 + }, + { + "epoch": 3.7037037037037037, + "grad_norm": 0.18475975096225739, + "learning_rate": 1.3374662538414074e-06, + "loss": 0.0147, + "step": 9300 + }, + { + "epoch": 3.70768618080446, + "grad_norm": 0.23747357726097107, + "learning_rate": 1.2997446344987617e-06, + "loss": 0.0127, + "step": 9310 + }, + { + "epoch": 3.711668657905217, + "grad_norm": 0.25293728709220886, + "learning_rate": 1.262555593346315e-06, + "loss": 0.0124, + "step": 9320 + }, + { + "epoch": 3.7156511350059738, + "grad_norm": 0.3373745381832123, + "learning_rate": 1.2258995370774685e-06, + "loss": 0.0153, + "step": 9330 + }, + { + "epoch": 3.7196336121067306, + "grad_norm": 0.21809877455234528, + "learning_rate": 1.1897768665569798e-06, + "loss": 0.0164, + "step": 9340 + }, + { + "epoch": 3.723616089207487, + "grad_norm": 0.21654918789863586, + "learning_rate": 1.1541879768165954e-06, + "loss": 0.0111, + "step": 9350 + }, + { + "epoch": 3.727598566308244, + "grad_norm": 0.19067105650901794, + "learning_rate": 1.1191332570507085e-06, + "loss": 0.0143, + "step": 9360 + }, + { + "epoch": 3.731581043409, + "grad_norm": 0.20294006168842316, + "learning_rate": 1.0846130906121132e-06, + "loss": 0.0172, + "step": 9370 + }, + { + "epoch": 3.735563520509757, + "grad_norm": 0.2206583172082901, + "learning_rate": 1.0506278550078131e-06, + "loss": 0.0137, + "step": 9380 + }, + { + "epoch": 3.739545997610514, + "grad_norm": 0.18981283903121948, + "learning_rate": 1.0171779218949185e-06, + "loss": 0.0158, + "step": 9390 + }, + { + "epoch": 3.7435284747112703, + "grad_norm": 0.21733026206493378, + "learning_rate": 9.842636570765174e-07, + "loss": 0.0133, + "step": 9400 + }, + { + "epoch": 3.747510951812027, + "grad_norm": 0.2571982741355896, + "learning_rate": 9.518854204977612e-07, + "loss": 0.013, + "step": 9410 + }, + { + "epoch": 3.7514934289127835, + "grad_norm": 0.2336360365152359, + "learning_rate": 9.200435662418349e-07, + "loss": 0.0144, + "step": 9420 + }, + { + "epoch": 3.7554759060135403, + "grad_norm": 0.25008511543273926, + "learning_rate": 8.887384425261658e-07, + "loss": 0.0111, + "step": 9430 + }, + { + "epoch": 3.759458383114297, + "grad_norm": 0.23758894205093384, + "learning_rate": 8.579703916985648e-07, + "loss": 0.0137, + "step": 9440 + }, + { + "epoch": 3.763440860215054, + "grad_norm": 0.27957940101623535, + "learning_rate": 8.277397502335194e-07, + "loss": 0.0143, + "step": 9450 + }, + { + "epoch": 3.7674233373158104, + "grad_norm": 0.2032625526189804, + "learning_rate": 7.980468487284675e-07, + "loss": 0.0153, + "step": 9460 + }, + { + "epoch": 3.771405814416567, + "grad_norm": 0.2791658341884613, + "learning_rate": 7.688920119002297e-07, + "loss": 0.0126, + "step": 9470 + }, + { + "epoch": 3.7753882915173236, + "grad_norm": 0.14666704833507538, + "learning_rate": 7.402755585814269e-07, + "loss": 0.0126, + "step": 9480 + }, + { + "epoch": 3.7793707686180804, + "grad_norm": 0.2378731667995453, + "learning_rate": 7.121978017170073e-07, + "loss": 0.0145, + "step": 9490 + }, + { + "epoch": 3.7833532457188372, + "grad_norm": 0.3094591796398163, + "learning_rate": 6.846590483608306e-07, + "loss": 0.0122, + "step": 9500 + }, + { + "epoch": 3.7873357228195936, + "grad_norm": 0.14007677137851715, + "learning_rate": 6.576595996722834e-07, + "loss": 0.016, + "step": 9510 + }, + { + "epoch": 3.7913181999203505, + "grad_norm": 0.24854406714439392, + "learning_rate": 6.311997509130141e-07, + "loss": 0.013, + "step": 9520 + }, + { + "epoch": 3.7953006770211073, + "grad_norm": 0.22404152154922485, + "learning_rate": 6.052797914436803e-07, + "loss": 0.0152, + "step": 9530 + }, + { + "epoch": 3.7992831541218637, + "grad_norm": 0.2653384804725647, + "learning_rate": 5.799000047208181e-07, + "loss": 0.0149, + "step": 9540 + }, + { + "epoch": 3.8032656312226205, + "grad_norm": 0.1700735241174698, + "learning_rate": 5.550606682937054e-07, + "loss": 0.0148, + "step": 9550 + }, + { + "epoch": 3.8072481083233773, + "grad_norm": 0.3729400336742401, + "learning_rate": 5.307620538013481e-07, + "loss": 0.0163, + "step": 9560 + }, + { + "epoch": 3.8112305854241337, + "grad_norm": 0.28273651003837585, + "learning_rate": 5.070044269694874e-07, + "loss": 0.0148, + "step": 9570 + }, + { + "epoch": 3.8152130625248906, + "grad_norm": 0.25636887550354004, + "learning_rate": 4.837880476077417e-07, + "loss": 0.0149, + "step": 9580 + }, + { + "epoch": 3.819195539625647, + "grad_norm": 0.11277643591165543, + "learning_rate": 4.6111316960670835e-07, + "loss": 0.0132, + "step": 9590 + }, + { + "epoch": 3.823178016726404, + "grad_norm": 0.31709930300712585, + "learning_rate": 4.389800409352218e-07, + "loss": 0.0141, + "step": 9600 + }, + { + "epoch": 3.8271604938271606, + "grad_norm": 0.1908944696187973, + "learning_rate": 4.173889036376277e-07, + "loss": 0.015, + "step": 9610 + }, + { + "epoch": 3.831142970927917, + "grad_norm": 0.2939547300338745, + "learning_rate": 3.963399938311463e-07, + "loss": 0.0177, + "step": 9620 + }, + { + "epoch": 3.835125448028674, + "grad_norm": 0.20435106754302979, + "learning_rate": 3.7583354170328545e-07, + "loss": 0.0137, + "step": 9630 + }, + { + "epoch": 3.8391079251294307, + "grad_norm": 0.177963525056839, + "learning_rate": 3.558697715093207e-07, + "loss": 0.0117, + "step": 9640 + }, + { + "epoch": 3.843090402230187, + "grad_norm": 0.23722724616527557, + "learning_rate": 3.3644890156983576e-07, + "loss": 0.0142, + "step": 9650 + }, + { + "epoch": 3.847072879330944, + "grad_norm": 0.24979689717292786, + "learning_rate": 3.175711442683638e-07, + "loss": 0.0139, + "step": 9660 + }, + { + "epoch": 3.8510553564317007, + "grad_norm": 0.13695870339870453, + "learning_rate": 2.9923670604902197e-07, + "loss": 0.0127, + "step": 9670 + }, + { + "epoch": 3.855037833532457, + "grad_norm": 0.2963074743747711, + "learning_rate": 2.814457874143028e-07, + "loss": 0.0165, + "step": 9680 + }, + { + "epoch": 3.859020310633214, + "grad_norm": 0.2667098641395569, + "learning_rate": 2.641985829228366e-07, + "loss": 0.0134, + "step": 9690 + }, + { + "epoch": 3.8630027877339703, + "grad_norm": 0.21023236215114594, + "learning_rate": 2.474952811872877e-07, + "loss": 0.0131, + "step": 9700 + }, + { + "epoch": 3.866985264834727, + "grad_norm": 0.21310463547706604, + "learning_rate": 2.3133606487228397e-07, + "loss": 0.0135, + "step": 9710 + }, + { + "epoch": 3.870967741935484, + "grad_norm": 0.2762566804885864, + "learning_rate": 2.157211106924295e-07, + "loss": 0.0148, + "step": 9720 + }, + { + "epoch": 3.874950219036241, + "grad_norm": 0.2990756928920746, + "learning_rate": 2.006505894103672e-07, + "loss": 0.0147, + "step": 9730 + }, + { + "epoch": 3.878932696136997, + "grad_norm": 0.17009320855140686, + "learning_rate": 1.8612466583489696e-07, + "loss": 0.0143, + "step": 9740 + }, + { + "epoch": 3.882915173237754, + "grad_norm": 0.1569436490535736, + "learning_rate": 1.7214349881918834e-07, + "loss": 0.0132, + "step": 9750 + }, + { + "epoch": 3.8868976503385104, + "grad_norm": 0.12430369853973389, + "learning_rate": 1.5870724125904845e-07, + "loss": 0.0106, + "step": 9760 + }, + { + "epoch": 3.8908801274392673, + "grad_norm": 0.2661726176738739, + "learning_rate": 1.4581604009124006e-07, + "loss": 0.0132, + "step": 9770 + }, + { + "epoch": 3.894862604540024, + "grad_norm": 0.10029175132513046, + "learning_rate": 1.334700362918717e-07, + "loss": 0.0113, + "step": 9780 + }, + { + "epoch": 3.8988450816407805, + "grad_norm": 0.24978956580162048, + "learning_rate": 1.2166936487486015e-07, + "loss": 0.0125, + "step": 9790 + }, + { + "epoch": 3.9028275587415373, + "grad_norm": 0.4270276725292206, + "learning_rate": 1.1041415489045914e-07, + "loss": 0.0131, + "step": 9800 + }, + { + "epoch": 3.9068100358422937, + "grad_norm": 0.22719305753707886, + "learning_rate": 9.970452942384412e-08, + "loss": 0.0126, + "step": 9810 + }, + { + "epoch": 3.9107925129430505, + "grad_norm": 0.20977602899074554, + "learning_rate": 8.954060559375754e-08, + "loss": 0.0114, + "step": 9820 + }, + { + "epoch": 3.9147749900438074, + "grad_norm": 0.1370612531900406, + "learning_rate": 7.99224945512489e-08, + "loss": 0.018, + "step": 9830 + }, + { + "epoch": 3.918757467144564, + "grad_norm": 0.17637065052986145, + "learning_rate": 7.085030147843675e-08, + "loss": 0.0149, + "step": 9840 + }, + { + "epoch": 3.9227399442453206, + "grad_norm": 0.22800922393798828, + "learning_rate": 6.232412558736523e-08, + "loss": 0.0166, + "step": 9850 + }, + { + "epoch": 3.9267224213460774, + "grad_norm": 0.23249153792858124, + "learning_rate": 5.434406011893822e-08, + "loss": 0.0172, + "step": 9860 + }, + { + "epoch": 3.930704898446834, + "grad_norm": 0.17791615426540375, + "learning_rate": 4.6910192341864664e-08, + "loss": 0.0113, + "step": 9870 + }, + { + "epoch": 3.9346873755475906, + "grad_norm": 0.21019835770130157, + "learning_rate": 4.0022603551737035e-08, + "loss": 0.0146, + "step": 9880 + }, + { + "epoch": 3.9386698526483475, + "grad_norm": 0.1602124720811844, + "learning_rate": 3.3681369070120985e-08, + "loss": 0.0127, + "step": 9890 + }, + { + "epoch": 3.942652329749104, + "grad_norm": 0.17522773146629333, + "learning_rate": 2.7886558243744866e-08, + "loss": 0.0145, + "step": 9900 + }, + { + "epoch": 3.9466348068498607, + "grad_norm": 0.2072092741727829, + "learning_rate": 2.2638234443722596e-08, + "loss": 0.0123, + "step": 9910 + }, + { + "epoch": 3.950617283950617, + "grad_norm": 0.1036510095000267, + "learning_rate": 1.7936455064887504e-08, + "loss": 0.016, + "step": 9920 + }, + { + "epoch": 3.954599761051374, + "grad_norm": 0.08399386703968048, + "learning_rate": 1.378127152514841e-08, + "loss": 0.0114, + "step": 9930 + }, + { + "epoch": 3.9585822381521307, + "grad_norm": 0.27939972281455994, + "learning_rate": 1.0172729264917857e-08, + "loss": 0.0167, + "step": 9940 + }, + { + "epoch": 3.9625647152528876, + "grad_norm": 0.17596809566020966, + "learning_rate": 7.1108677466458215e-09, + "loss": 0.0142, + "step": 9950 + }, + { + "epoch": 3.966547192353644, + "grad_norm": 0.1545400619506836, + "learning_rate": 4.595720454353414e-09, + "loss": 0.0145, + "step": 9960 + }, + { + "epoch": 3.970529669454401, + "grad_norm": 0.24510076642036438, + "learning_rate": 2.627314893294264e-09, + "loss": 0.0124, + "step": 9970 + }, + { + "epoch": 3.974512146555157, + "grad_norm": 0.2673027217388153, + "learning_rate": 1.2056725896270048e-09, + "loss": 0.0118, + "step": 9980 + }, + { + "epoch": 3.978494623655914, + "grad_norm": 0.2962305545806885, + "learning_rate": 3.308090902098826e-10, + "loss": 0.0156, + "step": 9990 + }, + { + "epoch": 3.982477100756671, + "grad_norm": 0.3653580844402313, + "learning_rate": 2.7339624120159555e-12, + "loss": 0.0137, + "step": 10000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-4000/config.json b/checkpoint-4000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-4000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-4000/experiment_cfg/metadata.json b/checkpoint-4000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-4000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-4000/model-00001-of-00002.safetensors b/checkpoint-4000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-4000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-4000/model-00002-of-00002.safetensors b/checkpoint-4000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe4419ab442c8c509a34dc858a14b8997b7a5ad5 --- /dev/null +++ b/checkpoint-4000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9bf9ecec75543ce10ef434c434df87246ed1520853803dbde888a1e053e80b +size 2586705312 diff --git a/checkpoint-4000/model.safetensors.index.json b/checkpoint-4000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-4000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-4000/optimizer.pt b/checkpoint-4000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..3544740f5ef90a5484ee2e3f737e710ed8b7c43a --- /dev/null +++ b/checkpoint-4000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39008997be56844954a656172d474c0ac07a1aff1983543078e43e76e3c07cea +size 4147424698 diff --git a/checkpoint-4000/rng_state.pth b/checkpoint-4000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..aad73c5b928a1daa6d18d6ba9d8049c4f83ea92d --- /dev/null +++ b/checkpoint-4000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b853fa74473f32e44be47a34bdeaf5dc696917c249e44f780bcd71368abd20c +size 14244 diff --git a/checkpoint-4000/scheduler.pt b/checkpoint-4000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a577fafd92ca57c7e3213b00663853a5847ecb3 --- /dev/null +++ b/checkpoint-4000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7211b192985f3cf213c0fe5d877c55ab1774647baa7fcf0d4d0c00aad611b2fd +size 1064 diff --git a/checkpoint-4000/trainer_state.json b/checkpoint-4000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..9913dec53d8d3cacd3b846cb49b689be82ae5708 --- /dev/null +++ b/checkpoint-4000/trainer_state.json @@ -0,0 +1,2834 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.5929908403026682, + "eval_steps": 500, + "global_step": 4000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-5000/config.json b/checkpoint-5000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-5000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-5000/experiment_cfg/metadata.json b/checkpoint-5000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-5000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-5000/model-00001-of-00002.safetensors b/checkpoint-5000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-5000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-5000/model-00002-of-00002.safetensors b/checkpoint-5000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb6b7195227ac2403d2ae4d6611d7284c9e57dd8 --- /dev/null +++ b/checkpoint-5000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942142544a489d10a803779874cba9a1ec18d2cc3ccabfe9f5c2879f5eedfe04 +size 2586705312 diff --git a/checkpoint-5000/model.safetensors.index.json b/checkpoint-5000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-5000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-5000/optimizer.pt b/checkpoint-5000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..02aea15eb3e9ce55fca6b99f1df8afac898c9d5d --- /dev/null +++ b/checkpoint-5000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135deb8770b61632d6a636310cc1589a33722ffdda34d98861c3ee95512da7ac +size 4147424698 diff --git a/checkpoint-5000/rng_state.pth b/checkpoint-5000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..2507ecec046e9c4ef3ac2f542f1cb6e4202bb021 --- /dev/null +++ b/checkpoint-5000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89704cf03f557538e476cee66579fbaadf78bed5388d837bfa424566e8e0755 +size 14244 diff --git a/checkpoint-5000/scheduler.pt b/checkpoint-5000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..73ca436d0ae58f483363fbc870cab286c99ffded --- /dev/null +++ b/checkpoint-5000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3860515cdc95c999d5fee0e8633bc5123ccc0bc4f65d625f0a33425450fa0f7 +size 1064 diff --git a/checkpoint-5000/trainer_state.json b/checkpoint-5000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dd1441f2e4e1609738f2305f10264f5e9df051c2 --- /dev/null +++ b/checkpoint-5000/trainer_state.json @@ -0,0 +1,3534 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.9912385503783354, + "eval_steps": 500, + "global_step": 5000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-6000/config.json b/checkpoint-6000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-6000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-6000/experiment_cfg/metadata.json b/checkpoint-6000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-6000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-6000/model-00001-of-00002.safetensors b/checkpoint-6000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-6000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-6000/model-00002-of-00002.safetensors b/checkpoint-6000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1aea45d2997fed2f518eb471a27fe56d48bec10 --- /dev/null +++ b/checkpoint-6000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:185c359b4bba0fb8e8f070cc9219b2dc7ef2b9222aa348ef4d29659957794091 +size 2586705312 diff --git a/checkpoint-6000/model.safetensors.index.json b/checkpoint-6000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-6000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-6000/optimizer.pt b/checkpoint-6000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..09a24cd9b32c416e1f0a38acdc68ff1dec77013c --- /dev/null +++ b/checkpoint-6000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145c4fbd2b48ae7a568038fa1ecc19b796c1fce35b0883b3c0ce72c3a956a2a6 +size 4147424698 diff --git a/checkpoint-6000/rng_state.pth b/checkpoint-6000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a002b7fd3bad4be61b08a06cf154915b9dd4334 --- /dev/null +++ b/checkpoint-6000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13bd3aee67d899586785f110c683415e1f00044b0294c797f6849a5b51cc801a +size 14244 diff --git a/checkpoint-6000/scheduler.pt b/checkpoint-6000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a64e7adced2f5cd594b7b17b94285128331d8bb --- /dev/null +++ b/checkpoint-6000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6c0bf646ac78d188a2258804081d2e369772e8091e5395d9073771ec310aca +size 1064 diff --git a/checkpoint-6000/trainer_state.json b/checkpoint-6000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..48ca80dc51ea30a7652be3eb506fa2d76a25778f --- /dev/null +++ b/checkpoint-6000/trainer_state.json @@ -0,0 +1,4234 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.389486260454002, + "eval_steps": 500, + "global_step": 6000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-7000/config.json b/checkpoint-7000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-7000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-7000/experiment_cfg/metadata.json b/checkpoint-7000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-7000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-7000/model-00001-of-00002.safetensors b/checkpoint-7000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-7000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-7000/model-00002-of-00002.safetensors b/checkpoint-7000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50f95cbc6119e12337a7683260f53240f5401fa6 --- /dev/null +++ b/checkpoint-7000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e7230b2f52e65b83629e430d28e02bffb786970b756c13cd4a21211b800f5a +size 2586705312 diff --git a/checkpoint-7000/model.safetensors.index.json b/checkpoint-7000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-7000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-7000/optimizer.pt b/checkpoint-7000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b6916d9c621a6297eb903988d6bf35cb7d60d6b --- /dev/null +++ b/checkpoint-7000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bc9ed5dcc9ab13c182c3a8d5c25bc5f9d6e9cf1efae67134d2e683a75c39e1 +size 4147424698 diff --git a/checkpoint-7000/rng_state.pth b/checkpoint-7000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..32ba739910d0dc616265ec7e746555874b18c89c --- /dev/null +++ b/checkpoint-7000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebdbf47e1b77224d159715275bc578926a4cd08f83b15b47e0225eb3eab56e59 +size 14244 diff --git a/checkpoint-7000/scheduler.pt b/checkpoint-7000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb08f265e8ede954499926b60eac135516e78b1b --- /dev/null +++ b/checkpoint-7000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45049460c0fa55fae34b1884c511d0c5cb5241d0d636fad92c82b0e0a657580e +size 1064 diff --git a/checkpoint-7000/trainer_state.json b/checkpoint-7000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dc541adbf2942e62bb1535cfd88c181fc0c7c689 --- /dev/null +++ b/checkpoint-7000/trainer_state.json @@ -0,0 +1,4934 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.7877339705296693, + "eval_steps": 500, + "global_step": 7000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + }, + { + "epoch": 2.393468737554759, + "grad_norm": 0.33681097626686096, + "learning_rate": 3.758152155160255e-05, + "loss": 0.0167, + "step": 6010 + }, + { + "epoch": 2.397451214655516, + "grad_norm": 0.4447823166847229, + "learning_rate": 3.742142385506999e-05, + "loss": 0.0187, + "step": 6020 + }, + { + "epoch": 2.4014336917562726, + "grad_norm": 0.32111281156539917, + "learning_rate": 3.72614637158309e-05, + "loss": 0.0167, + "step": 6030 + }, + { + "epoch": 2.405416168857029, + "grad_norm": 0.3327321708202362, + "learning_rate": 3.710164288318371e-05, + "loss": 0.021, + "step": 6040 + }, + { + "epoch": 2.409398645957786, + "grad_norm": 0.3221536874771118, + "learning_rate": 3.694196310490345e-05, + "loss": 0.0172, + "step": 6050 + }, + { + "epoch": 2.4133811230585422, + "grad_norm": 0.2384720742702484, + "learning_rate": 3.678242612722259e-05, + "loss": 0.0172, + "step": 6060 + }, + { + "epoch": 2.417363600159299, + "grad_norm": 0.4310377240180969, + "learning_rate": 3.6623033694811953e-05, + "loss": 0.0207, + "step": 6070 + }, + { + "epoch": 2.421346077260056, + "grad_norm": 0.2742801904678345, + "learning_rate": 3.6463787550761665e-05, + "loss": 0.0204, + "step": 6080 + }, + { + "epoch": 2.4253285543608123, + "grad_norm": 0.30959945917129517, + "learning_rate": 3.630468943656202e-05, + "loss": 0.0171, + "step": 6090 + }, + { + "epoch": 2.429311031461569, + "grad_norm": 0.23991258442401886, + "learning_rate": 3.6145741092084523e-05, + "loss": 0.0158, + "step": 6100 + }, + { + "epoch": 2.433293508562326, + "grad_norm": 0.3445211350917816, + "learning_rate": 3.598694425556278e-05, + "loss": 0.0171, + "step": 6110 + }, + { + "epoch": 2.4372759856630823, + "grad_norm": 0.23148199915885925, + "learning_rate": 3.58283006635736e-05, + "loss": 0.0168, + "step": 6120 + }, + { + "epoch": 2.441258462763839, + "grad_norm": 0.34516337513923645, + "learning_rate": 3.566981205101781e-05, + "loss": 0.0214, + "step": 6130 + }, + { + "epoch": 2.445240939864596, + "grad_norm": 0.2975906729698181, + "learning_rate": 3.5511480151101556e-05, + "loss": 0.0182, + "step": 6140 + }, + { + "epoch": 2.4492234169653524, + "grad_norm": 0.3364192545413971, + "learning_rate": 3.5353306695317104e-05, + "loss": 0.0149, + "step": 6150 + }, + { + "epoch": 2.4532058940661092, + "grad_norm": 0.32481926679611206, + "learning_rate": 3.519529341342402e-05, + "loss": 0.0205, + "step": 6160 + }, + { + "epoch": 2.4571883711668656, + "grad_norm": 0.35478660464286804, + "learning_rate": 3.503744203343026e-05, + "loss": 0.0184, + "step": 6170 + }, + { + "epoch": 2.4611708482676224, + "grad_norm": 0.40364179015159607, + "learning_rate": 3.487975428157318e-05, + "loss": 0.0213, + "step": 6180 + }, + { + "epoch": 2.4651533253683793, + "grad_norm": 0.2646041512489319, + "learning_rate": 3.472223188230083e-05, + "loss": 0.0182, + "step": 6190 + }, + { + "epoch": 2.4691358024691357, + "grad_norm": 0.21933303773403168, + "learning_rate": 3.4564876558252866e-05, + "loss": 0.02, + "step": 6200 + }, + { + "epoch": 2.4731182795698925, + "grad_norm": 0.41874152421951294, + "learning_rate": 3.440769003024195e-05, + "loss": 0.0192, + "step": 6210 + }, + { + "epoch": 2.4771007566706493, + "grad_norm": 0.40349701046943665, + "learning_rate": 3.425067401723477e-05, + "loss": 0.0195, + "step": 6220 + }, + { + "epoch": 2.4810832337714057, + "grad_norm": 0.36892589926719666, + "learning_rate": 3.409383023633325e-05, + "loss": 0.0214, + "step": 6230 + }, + { + "epoch": 2.4850657108721625, + "grad_norm": 0.3317766785621643, + "learning_rate": 3.3937160402755894e-05, + "loss": 0.0179, + "step": 6240 + }, + { + "epoch": 2.4890481879729194, + "grad_norm": 0.28070494532585144, + "learning_rate": 3.378066622981885e-05, + "loss": 0.0227, + "step": 6250 + }, + { + "epoch": 2.4930306650736758, + "grad_norm": 0.23878398537635803, + "learning_rate": 3.362434942891738e-05, + "loss": 0.0203, + "step": 6260 + }, + { + "epoch": 2.4970131421744326, + "grad_norm": 0.29855674505233765, + "learning_rate": 3.346821170950693e-05, + "loss": 0.0188, + "step": 6270 + }, + { + "epoch": 2.500995619275189, + "grad_norm": 0.35947370529174805, + "learning_rate": 3.3312254779084585e-05, + "loss": 0.0203, + "step": 6280 + }, + { + "epoch": 2.504978096375946, + "grad_norm": 0.38355863094329834, + "learning_rate": 3.315648034317039e-05, + "loss": 0.0229, + "step": 6290 + }, + { + "epoch": 2.5089605734767026, + "grad_norm": 0.20965726673603058, + "learning_rate": 3.3000890105288564e-05, + "loss": 0.0156, + "step": 6300 + }, + { + "epoch": 2.512943050577459, + "grad_norm": 0.21126852929592133, + "learning_rate": 3.284548576694908e-05, + "loss": 0.0221, + "step": 6310 + }, + { + "epoch": 2.516925527678216, + "grad_norm": 0.29997190833091736, + "learning_rate": 3.2690269027628815e-05, + "loss": 0.0163, + "step": 6320 + }, + { + "epoch": 2.5209080047789723, + "grad_norm": 0.2688118815422058, + "learning_rate": 3.253524158475324e-05, + "loss": 0.018, + "step": 6330 + }, + { + "epoch": 2.524890481879729, + "grad_norm": 0.3369862139225006, + "learning_rate": 3.238040513367757e-05, + "loss": 0.0182, + "step": 6340 + }, + { + "epoch": 2.528872958980486, + "grad_norm": 0.17766013741493225, + "learning_rate": 3.222576136766843e-05, + "loss": 0.0159, + "step": 6350 + }, + { + "epoch": 2.5328554360812428, + "grad_norm": 0.2567964494228363, + "learning_rate": 3.2071311977885324e-05, + "loss": 0.0183, + "step": 6360 + }, + { + "epoch": 2.536837913181999, + "grad_norm": 0.2693711519241333, + "learning_rate": 3.191705865336197e-05, + "loss": 0.0195, + "step": 6370 + }, + { + "epoch": 2.540820390282756, + "grad_norm": 0.2565217912197113, + "learning_rate": 3.1763003080988075e-05, + "loss": 0.0175, + "step": 6380 + }, + { + "epoch": 2.5448028673835124, + "grad_norm": 0.44722431898117065, + "learning_rate": 3.160914694549063e-05, + "loss": 0.0198, + "step": 6390 + }, + { + "epoch": 2.548785344484269, + "grad_norm": 0.3705827593803406, + "learning_rate": 3.145549192941573e-05, + "loss": 0.019, + "step": 6400 + }, + { + "epoch": 2.552767821585026, + "grad_norm": 0.3155789077281952, + "learning_rate": 3.130203971310999e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 2.5567502986857824, + "grad_norm": 0.29949137568473816, + "learning_rate": 3.114879197470225e-05, + "loss": 0.0188, + "step": 6420 + }, + { + "epoch": 2.5607327757865392, + "grad_norm": 0.3367830216884613, + "learning_rate": 3.0995750390085285e-05, + "loss": 0.0175, + "step": 6430 + }, + { + "epoch": 2.5647152528872956, + "grad_norm": 0.2421615719795227, + "learning_rate": 3.084291663289728e-05, + "loss": 0.0192, + "step": 6440 + }, + { + "epoch": 2.5686977299880525, + "grad_norm": 0.17980587482452393, + "learning_rate": 3.069029237450375e-05, + "loss": 0.0155, + "step": 6450 + }, + { + "epoch": 2.5726802070888093, + "grad_norm": 0.42298945784568787, + "learning_rate": 3.053787928397911e-05, + "loss": 0.0169, + "step": 6460 + }, + { + "epoch": 2.576662684189566, + "grad_norm": 0.2914910316467285, + "learning_rate": 3.0385679028088526e-05, + "loss": 0.0195, + "step": 6470 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 0.40466681122779846, + "learning_rate": 3.023369327126959e-05, + "loss": 0.0191, + "step": 6480 + }, + { + "epoch": 2.5846276383910793, + "grad_norm": 0.260161429643631, + "learning_rate": 3.0081923675614198e-05, + "loss": 0.0164, + "step": 6490 + }, + { + "epoch": 2.5886101154918357, + "grad_norm": 0.348817378282547, + "learning_rate": 2.993037190085034e-05, + "loss": 0.0155, + "step": 6500 + }, + { + "epoch": 2.5925925925925926, + "grad_norm": 0.22140339016914368, + "learning_rate": 2.977903960432392e-05, + "loss": 0.0192, + "step": 6510 + }, + { + "epoch": 2.5965750696933494, + "grad_norm": 0.3535783886909485, + "learning_rate": 2.9627928440980722e-05, + "loss": 0.0196, + "step": 6520 + }, + { + "epoch": 2.600557546794106, + "grad_norm": 0.229234978556633, + "learning_rate": 2.9477040063348183e-05, + "loss": 0.0206, + "step": 6530 + }, + { + "epoch": 2.6045400238948626, + "grad_norm": 0.30883148312568665, + "learning_rate": 2.9326376121517456e-05, + "loss": 0.0195, + "step": 6540 + }, + { + "epoch": 2.608522500995619, + "grad_norm": 0.4454684257507324, + "learning_rate": 2.9175938263125236e-05, + "loss": 0.024, + "step": 6550 + }, + { + "epoch": 2.612504978096376, + "grad_norm": 0.34252026677131653, + "learning_rate": 2.9025728133335873e-05, + "loss": 0.0206, + "step": 6560 + }, + { + "epoch": 2.6164874551971327, + "grad_norm": 0.410495400428772, + "learning_rate": 2.8875747374823288e-05, + "loss": 0.0201, + "step": 6570 + }, + { + "epoch": 2.6204699322978895, + "grad_norm": 0.2930971384048462, + "learning_rate": 2.872599762775298e-05, + "loss": 0.0242, + "step": 6580 + }, + { + "epoch": 2.624452409398646, + "grad_norm": 0.1941741406917572, + "learning_rate": 2.857648052976425e-05, + "loss": 0.0168, + "step": 6590 + }, + { + "epoch": 2.6284348864994027, + "grad_norm": 0.4398362338542938, + "learning_rate": 2.8427197715952047e-05, + "loss": 0.019, + "step": 6600 + }, + { + "epoch": 2.632417363600159, + "grad_norm": 0.434218168258667, + "learning_rate": 2.8278150818849393e-05, + "loss": 0.0188, + "step": 6610 + }, + { + "epoch": 2.636399840700916, + "grad_norm": 0.29979050159454346, + "learning_rate": 2.812934146840922e-05, + "loss": 0.0175, + "step": 6620 + }, + { + "epoch": 2.6403823178016728, + "grad_norm": 0.27494296431541443, + "learning_rate": 2.7980771291986764e-05, + "loss": 0.0175, + "step": 6630 + }, + { + "epoch": 2.644364794902429, + "grad_norm": 0.3515009582042694, + "learning_rate": 2.783244191432167e-05, + "loss": 0.0185, + "step": 6640 + }, + { + "epoch": 2.648347272003186, + "grad_norm": 0.3444755971431732, + "learning_rate": 2.768435495752022e-05, + "loss": 0.0171, + "step": 6650 + }, + { + "epoch": 2.652329749103943, + "grad_norm": 0.2616831362247467, + "learning_rate": 2.753651204103771e-05, + "loss": 0.02, + "step": 6660 + }, + { + "epoch": 2.656312226204699, + "grad_norm": 0.2663615643978119, + "learning_rate": 2.7388914781660523e-05, + "loss": 0.0149, + "step": 6670 + }, + { + "epoch": 2.660294703305456, + "grad_norm": 0.21043306589126587, + "learning_rate": 2.7241564793488693e-05, + "loss": 0.0202, + "step": 6680 + }, + { + "epoch": 2.664277180406213, + "grad_norm": 0.45657920837402344, + "learning_rate": 2.7094463687918037e-05, + "loss": 0.0151, + "step": 6690 + }, + { + "epoch": 2.6682596575069693, + "grad_norm": 0.37648776173591614, + "learning_rate": 2.694761307362268e-05, + "loss": 0.0192, + "step": 6700 + }, + { + "epoch": 2.672242134607726, + "grad_norm": 0.26603221893310547, + "learning_rate": 2.6801014556537467e-05, + "loss": 0.0169, + "step": 6710 + }, + { + "epoch": 2.6762246117084825, + "grad_norm": 0.3080855906009674, + "learning_rate": 2.6654669739840243e-05, + "loss": 0.0169, + "step": 6720 + }, + { + "epoch": 2.6802070888092393, + "grad_norm": 0.3766150176525116, + "learning_rate": 2.650858022393451e-05, + "loss": 0.0183, + "step": 6730 + }, + { + "epoch": 2.684189565909996, + "grad_norm": 0.2229013293981552, + "learning_rate": 2.6362747606431747e-05, + "loss": 0.0205, + "step": 6740 + }, + { + "epoch": 2.688172043010753, + "grad_norm": 0.24441877007484436, + "learning_rate": 2.6217173482134172e-05, + "loss": 0.0182, + "step": 6750 + }, + { + "epoch": 2.6921545201115094, + "grad_norm": 0.25608956813812256, + "learning_rate": 2.6071859443017044e-05, + "loss": 0.013, + "step": 6760 + }, + { + "epoch": 2.696136997212266, + "grad_norm": 0.3526802957057953, + "learning_rate": 2.5926807078211414e-05, + "loss": 0.0153, + "step": 6770 + }, + { + "epoch": 2.7001194743130226, + "grad_norm": 0.46395474672317505, + "learning_rate": 2.5782017973986728e-05, + "loss": 0.0181, + "step": 6780 + }, + { + "epoch": 2.7041019514137794, + "grad_norm": 0.23045793175697327, + "learning_rate": 2.5637493713733374e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 2.7080844285145362, + "grad_norm": 0.32080161571502686, + "learning_rate": 2.549323587794559e-05, + "loss": 0.0196, + "step": 6800 + }, + { + "epoch": 2.7120669056152926, + "grad_norm": 0.23438672721385956, + "learning_rate": 2.5349246044203895e-05, + "loss": 0.0143, + "step": 6810 + }, + { + "epoch": 2.7160493827160495, + "grad_norm": 0.33166348934173584, + "learning_rate": 2.520552578715808e-05, + "loss": 0.0144, + "step": 6820 + }, + { + "epoch": 2.720031859816806, + "grad_norm": 0.2601594626903534, + "learning_rate": 2.506207667850981e-05, + "loss": 0.0159, + "step": 6830 + }, + { + "epoch": 2.7240143369175627, + "grad_norm": 0.3093375265598297, + "learning_rate": 2.4918900286995555e-05, + "loss": 0.0141, + "step": 6840 + }, + { + "epoch": 2.7279968140183195, + "grad_norm": 0.15893106162548065, + "learning_rate": 2.4775998178369458e-05, + "loss": 0.0161, + "step": 6850 + }, + { + "epoch": 2.7319792911190763, + "grad_norm": 0.3865691125392914, + "learning_rate": 2.4633371915386017e-05, + "loss": 0.0188, + "step": 6860 + }, + { + "epoch": 2.7359617682198327, + "grad_norm": 0.2376730591058731, + "learning_rate": 2.4491023057783235e-05, + "loss": 0.0192, + "step": 6870 + }, + { + "epoch": 2.7399442453205896, + "grad_norm": 0.38163626194000244, + "learning_rate": 2.4348953162265375e-05, + "loss": 0.0182, + "step": 6880 + }, + { + "epoch": 2.743926722421346, + "grad_norm": 0.22240246832370758, + "learning_rate": 2.420716378248607e-05, + "loss": 0.0217, + "step": 6890 + }, + { + "epoch": 2.7479091995221028, + "grad_norm": 0.4573044180870056, + "learning_rate": 2.4065656469031266e-05, + "loss": 0.0165, + "step": 6900 + }, + { + "epoch": 2.7518916766228596, + "grad_norm": 0.22964206337928772, + "learning_rate": 2.3924432769402268e-05, + "loss": 0.0186, + "step": 6910 + }, + { + "epoch": 2.755874153723616, + "grad_norm": 0.30862241983413696, + "learning_rate": 2.3783494227998844e-05, + "loss": 0.0224, + "step": 6920 + }, + { + "epoch": 2.759856630824373, + "grad_norm": 0.22101591527462006, + "learning_rate": 2.3642842386102264e-05, + "loss": 0.0163, + "step": 6930 + }, + { + "epoch": 2.763839107925129, + "grad_norm": 0.2185278832912445, + "learning_rate": 2.3502478781858567e-05, + "loss": 0.0145, + "step": 6940 + }, + { + "epoch": 2.767821585025886, + "grad_norm": 0.24134941399097443, + "learning_rate": 2.3362404950261628e-05, + "loss": 0.019, + "step": 6950 + }, + { + "epoch": 2.771804062126643, + "grad_norm": 0.2902449071407318, + "learning_rate": 2.3222622423136458e-05, + "loss": 0.0165, + "step": 6960 + }, + { + "epoch": 2.7757865392273997, + "grad_norm": 0.3769952058792114, + "learning_rate": 2.3083132729122332e-05, + "loss": 0.0135, + "step": 6970 + }, + { + "epoch": 2.779769016328156, + "grad_norm": 0.22340670228004456, + "learning_rate": 2.294393739365621e-05, + "loss": 0.019, + "step": 6980 + }, + { + "epoch": 2.783751493428913, + "grad_norm": 0.33232781291007996, + "learning_rate": 2.2805037938956e-05, + "loss": 0.0162, + "step": 6990 + }, + { + "epoch": 2.7877339705296693, + "grad_norm": 0.33404746651649475, + "learning_rate": 2.266643588400386e-05, + "loss": 0.0162, + "step": 7000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-8000/config.json b/checkpoint-8000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-8000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-8000/experiment_cfg/metadata.json b/checkpoint-8000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-8000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-8000/model-00001-of-00002.safetensors b/checkpoint-8000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-8000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-8000/model-00002-of-00002.safetensors b/checkpoint-8000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35ffc393a15f6af95f9a3cfe56e549635603b94f --- /dev/null +++ b/checkpoint-8000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b8a95b9a98c61059711fe605141c966d8029578f3817615ff85066850b7fa0 +size 2586705312 diff --git a/checkpoint-8000/model.safetensors.index.json b/checkpoint-8000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-8000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-8000/optimizer.pt b/checkpoint-8000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..f221d7fdf3feadaaea2d469cb94a531c0d16d78e --- /dev/null +++ b/checkpoint-8000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71068dc4e5230fa9ab8029474c4d00b9cf103d745f386bf795aacc4bd2290099 +size 4147424698 diff --git a/checkpoint-8000/rng_state.pth b/checkpoint-8000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..82847572f9c5cd24e9fab18bd9f8111418e609e9 --- /dev/null +++ b/checkpoint-8000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c2579caa8be30247b2fd67c807b8ee03f800e30cbe7ea7f01f34b79c5de3fa +size 14244 diff --git a/checkpoint-8000/scheduler.pt b/checkpoint-8000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..01665aca6c1a1ea3bed19552046faacdf59fcad3 --- /dev/null +++ b/checkpoint-8000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00739e77892b3b90e07da5aa63424b8c4adff832abcfc91f97c4f8838af650db +size 1064 diff --git a/checkpoint-8000/trainer_state.json b/checkpoint-8000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..780d4c28a3dff985ee12276cb7dac3b539623182 --- /dev/null +++ b/checkpoint-8000/trainer_state.json @@ -0,0 +1,5634 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.1859816806053365, + "eval_steps": 500, + "global_step": 8000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + }, + { + "epoch": 2.393468737554759, + "grad_norm": 0.33681097626686096, + "learning_rate": 3.758152155160255e-05, + "loss": 0.0167, + "step": 6010 + }, + { + "epoch": 2.397451214655516, + "grad_norm": 0.4447823166847229, + "learning_rate": 3.742142385506999e-05, + "loss": 0.0187, + "step": 6020 + }, + { + "epoch": 2.4014336917562726, + "grad_norm": 0.32111281156539917, + "learning_rate": 3.72614637158309e-05, + "loss": 0.0167, + "step": 6030 + }, + { + "epoch": 2.405416168857029, + "grad_norm": 0.3327321708202362, + "learning_rate": 3.710164288318371e-05, + "loss": 0.021, + "step": 6040 + }, + { + "epoch": 2.409398645957786, + "grad_norm": 0.3221536874771118, + "learning_rate": 3.694196310490345e-05, + "loss": 0.0172, + "step": 6050 + }, + { + "epoch": 2.4133811230585422, + "grad_norm": 0.2384720742702484, + "learning_rate": 3.678242612722259e-05, + "loss": 0.0172, + "step": 6060 + }, + { + "epoch": 2.417363600159299, + "grad_norm": 0.4310377240180969, + "learning_rate": 3.6623033694811953e-05, + "loss": 0.0207, + "step": 6070 + }, + { + "epoch": 2.421346077260056, + "grad_norm": 0.2742801904678345, + "learning_rate": 3.6463787550761665e-05, + "loss": 0.0204, + "step": 6080 + }, + { + "epoch": 2.4253285543608123, + "grad_norm": 0.30959945917129517, + "learning_rate": 3.630468943656202e-05, + "loss": 0.0171, + "step": 6090 + }, + { + "epoch": 2.429311031461569, + "grad_norm": 0.23991258442401886, + "learning_rate": 3.6145741092084523e-05, + "loss": 0.0158, + "step": 6100 + }, + { + "epoch": 2.433293508562326, + "grad_norm": 0.3445211350917816, + "learning_rate": 3.598694425556278e-05, + "loss": 0.0171, + "step": 6110 + }, + { + "epoch": 2.4372759856630823, + "grad_norm": 0.23148199915885925, + "learning_rate": 3.58283006635736e-05, + "loss": 0.0168, + "step": 6120 + }, + { + "epoch": 2.441258462763839, + "grad_norm": 0.34516337513923645, + "learning_rate": 3.566981205101781e-05, + "loss": 0.0214, + "step": 6130 + }, + { + "epoch": 2.445240939864596, + "grad_norm": 0.2975906729698181, + "learning_rate": 3.5511480151101556e-05, + "loss": 0.0182, + "step": 6140 + }, + { + "epoch": 2.4492234169653524, + "grad_norm": 0.3364192545413971, + "learning_rate": 3.5353306695317104e-05, + "loss": 0.0149, + "step": 6150 + }, + { + "epoch": 2.4532058940661092, + "grad_norm": 0.32481926679611206, + "learning_rate": 3.519529341342402e-05, + "loss": 0.0205, + "step": 6160 + }, + { + "epoch": 2.4571883711668656, + "grad_norm": 0.35478660464286804, + "learning_rate": 3.503744203343026e-05, + "loss": 0.0184, + "step": 6170 + }, + { + "epoch": 2.4611708482676224, + "grad_norm": 0.40364179015159607, + "learning_rate": 3.487975428157318e-05, + "loss": 0.0213, + "step": 6180 + }, + { + "epoch": 2.4651533253683793, + "grad_norm": 0.2646041512489319, + "learning_rate": 3.472223188230083e-05, + "loss": 0.0182, + "step": 6190 + }, + { + "epoch": 2.4691358024691357, + "grad_norm": 0.21933303773403168, + "learning_rate": 3.4564876558252866e-05, + "loss": 0.02, + "step": 6200 + }, + { + "epoch": 2.4731182795698925, + "grad_norm": 0.41874152421951294, + "learning_rate": 3.440769003024195e-05, + "loss": 0.0192, + "step": 6210 + }, + { + "epoch": 2.4771007566706493, + "grad_norm": 0.40349701046943665, + "learning_rate": 3.425067401723477e-05, + "loss": 0.0195, + "step": 6220 + }, + { + "epoch": 2.4810832337714057, + "grad_norm": 0.36892589926719666, + "learning_rate": 3.409383023633325e-05, + "loss": 0.0214, + "step": 6230 + }, + { + "epoch": 2.4850657108721625, + "grad_norm": 0.3317766785621643, + "learning_rate": 3.3937160402755894e-05, + "loss": 0.0179, + "step": 6240 + }, + { + "epoch": 2.4890481879729194, + "grad_norm": 0.28070494532585144, + "learning_rate": 3.378066622981885e-05, + "loss": 0.0227, + "step": 6250 + }, + { + "epoch": 2.4930306650736758, + "grad_norm": 0.23878398537635803, + "learning_rate": 3.362434942891738e-05, + "loss": 0.0203, + "step": 6260 + }, + { + "epoch": 2.4970131421744326, + "grad_norm": 0.29855674505233765, + "learning_rate": 3.346821170950693e-05, + "loss": 0.0188, + "step": 6270 + }, + { + "epoch": 2.500995619275189, + "grad_norm": 0.35947370529174805, + "learning_rate": 3.3312254779084585e-05, + "loss": 0.0203, + "step": 6280 + }, + { + "epoch": 2.504978096375946, + "grad_norm": 0.38355863094329834, + "learning_rate": 3.315648034317039e-05, + "loss": 0.0229, + "step": 6290 + }, + { + "epoch": 2.5089605734767026, + "grad_norm": 0.20965726673603058, + "learning_rate": 3.3000890105288564e-05, + "loss": 0.0156, + "step": 6300 + }, + { + "epoch": 2.512943050577459, + "grad_norm": 0.21126852929592133, + "learning_rate": 3.284548576694908e-05, + "loss": 0.0221, + "step": 6310 + }, + { + "epoch": 2.516925527678216, + "grad_norm": 0.29997190833091736, + "learning_rate": 3.2690269027628815e-05, + "loss": 0.0163, + "step": 6320 + }, + { + "epoch": 2.5209080047789723, + "grad_norm": 0.2688118815422058, + "learning_rate": 3.253524158475324e-05, + "loss": 0.018, + "step": 6330 + }, + { + "epoch": 2.524890481879729, + "grad_norm": 0.3369862139225006, + "learning_rate": 3.238040513367757e-05, + "loss": 0.0182, + "step": 6340 + }, + { + "epoch": 2.528872958980486, + "grad_norm": 0.17766013741493225, + "learning_rate": 3.222576136766843e-05, + "loss": 0.0159, + "step": 6350 + }, + { + "epoch": 2.5328554360812428, + "grad_norm": 0.2567964494228363, + "learning_rate": 3.2071311977885324e-05, + "loss": 0.0183, + "step": 6360 + }, + { + "epoch": 2.536837913181999, + "grad_norm": 0.2693711519241333, + "learning_rate": 3.191705865336197e-05, + "loss": 0.0195, + "step": 6370 + }, + { + "epoch": 2.540820390282756, + "grad_norm": 0.2565217912197113, + "learning_rate": 3.1763003080988075e-05, + "loss": 0.0175, + "step": 6380 + }, + { + "epoch": 2.5448028673835124, + "grad_norm": 0.44722431898117065, + "learning_rate": 3.160914694549063e-05, + "loss": 0.0198, + "step": 6390 + }, + { + "epoch": 2.548785344484269, + "grad_norm": 0.3705827593803406, + "learning_rate": 3.145549192941573e-05, + "loss": 0.019, + "step": 6400 + }, + { + "epoch": 2.552767821585026, + "grad_norm": 0.3155789077281952, + "learning_rate": 3.130203971310999e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 2.5567502986857824, + "grad_norm": 0.29949137568473816, + "learning_rate": 3.114879197470225e-05, + "loss": 0.0188, + "step": 6420 + }, + { + "epoch": 2.5607327757865392, + "grad_norm": 0.3367830216884613, + "learning_rate": 3.0995750390085285e-05, + "loss": 0.0175, + "step": 6430 + }, + { + "epoch": 2.5647152528872956, + "grad_norm": 0.2421615719795227, + "learning_rate": 3.084291663289728e-05, + "loss": 0.0192, + "step": 6440 + }, + { + "epoch": 2.5686977299880525, + "grad_norm": 0.17980587482452393, + "learning_rate": 3.069029237450375e-05, + "loss": 0.0155, + "step": 6450 + }, + { + "epoch": 2.5726802070888093, + "grad_norm": 0.42298945784568787, + "learning_rate": 3.053787928397911e-05, + "loss": 0.0169, + "step": 6460 + }, + { + "epoch": 2.576662684189566, + "grad_norm": 0.2914910316467285, + "learning_rate": 3.0385679028088526e-05, + "loss": 0.0195, + "step": 6470 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 0.40466681122779846, + "learning_rate": 3.023369327126959e-05, + "loss": 0.0191, + "step": 6480 + }, + { + "epoch": 2.5846276383910793, + "grad_norm": 0.260161429643631, + "learning_rate": 3.0081923675614198e-05, + "loss": 0.0164, + "step": 6490 + }, + { + "epoch": 2.5886101154918357, + "grad_norm": 0.348817378282547, + "learning_rate": 2.993037190085034e-05, + "loss": 0.0155, + "step": 6500 + }, + { + "epoch": 2.5925925925925926, + "grad_norm": 0.22140339016914368, + "learning_rate": 2.977903960432392e-05, + "loss": 0.0192, + "step": 6510 + }, + { + "epoch": 2.5965750696933494, + "grad_norm": 0.3535783886909485, + "learning_rate": 2.9627928440980722e-05, + "loss": 0.0196, + "step": 6520 + }, + { + "epoch": 2.600557546794106, + "grad_norm": 0.229234978556633, + "learning_rate": 2.9477040063348183e-05, + "loss": 0.0206, + "step": 6530 + }, + { + "epoch": 2.6045400238948626, + "grad_norm": 0.30883148312568665, + "learning_rate": 2.9326376121517456e-05, + "loss": 0.0195, + "step": 6540 + }, + { + "epoch": 2.608522500995619, + "grad_norm": 0.4454684257507324, + "learning_rate": 2.9175938263125236e-05, + "loss": 0.024, + "step": 6550 + }, + { + "epoch": 2.612504978096376, + "grad_norm": 0.34252026677131653, + "learning_rate": 2.9025728133335873e-05, + "loss": 0.0206, + "step": 6560 + }, + { + "epoch": 2.6164874551971327, + "grad_norm": 0.410495400428772, + "learning_rate": 2.8875747374823288e-05, + "loss": 0.0201, + "step": 6570 + }, + { + "epoch": 2.6204699322978895, + "grad_norm": 0.2930971384048462, + "learning_rate": 2.872599762775298e-05, + "loss": 0.0242, + "step": 6580 + }, + { + "epoch": 2.624452409398646, + "grad_norm": 0.1941741406917572, + "learning_rate": 2.857648052976425e-05, + "loss": 0.0168, + "step": 6590 + }, + { + "epoch": 2.6284348864994027, + "grad_norm": 0.4398362338542938, + "learning_rate": 2.8427197715952047e-05, + "loss": 0.019, + "step": 6600 + }, + { + "epoch": 2.632417363600159, + "grad_norm": 0.434218168258667, + "learning_rate": 2.8278150818849393e-05, + "loss": 0.0188, + "step": 6610 + }, + { + "epoch": 2.636399840700916, + "grad_norm": 0.29979050159454346, + "learning_rate": 2.812934146840922e-05, + "loss": 0.0175, + "step": 6620 + }, + { + "epoch": 2.6403823178016728, + "grad_norm": 0.27494296431541443, + "learning_rate": 2.7980771291986764e-05, + "loss": 0.0175, + "step": 6630 + }, + { + "epoch": 2.644364794902429, + "grad_norm": 0.3515009582042694, + "learning_rate": 2.783244191432167e-05, + "loss": 0.0185, + "step": 6640 + }, + { + "epoch": 2.648347272003186, + "grad_norm": 0.3444755971431732, + "learning_rate": 2.768435495752022e-05, + "loss": 0.0171, + "step": 6650 + }, + { + "epoch": 2.652329749103943, + "grad_norm": 0.2616831362247467, + "learning_rate": 2.753651204103771e-05, + "loss": 0.02, + "step": 6660 + }, + { + "epoch": 2.656312226204699, + "grad_norm": 0.2663615643978119, + "learning_rate": 2.7388914781660523e-05, + "loss": 0.0149, + "step": 6670 + }, + { + "epoch": 2.660294703305456, + "grad_norm": 0.21043306589126587, + "learning_rate": 2.7241564793488693e-05, + "loss": 0.0202, + "step": 6680 + }, + { + "epoch": 2.664277180406213, + "grad_norm": 0.45657920837402344, + "learning_rate": 2.7094463687918037e-05, + "loss": 0.0151, + "step": 6690 + }, + { + "epoch": 2.6682596575069693, + "grad_norm": 0.37648776173591614, + "learning_rate": 2.694761307362268e-05, + "loss": 0.0192, + "step": 6700 + }, + { + "epoch": 2.672242134607726, + "grad_norm": 0.26603221893310547, + "learning_rate": 2.6801014556537467e-05, + "loss": 0.0169, + "step": 6710 + }, + { + "epoch": 2.6762246117084825, + "grad_norm": 0.3080855906009674, + "learning_rate": 2.6654669739840243e-05, + "loss": 0.0169, + "step": 6720 + }, + { + "epoch": 2.6802070888092393, + "grad_norm": 0.3766150176525116, + "learning_rate": 2.650858022393451e-05, + "loss": 0.0183, + "step": 6730 + }, + { + "epoch": 2.684189565909996, + "grad_norm": 0.2229013293981552, + "learning_rate": 2.6362747606431747e-05, + "loss": 0.0205, + "step": 6740 + }, + { + "epoch": 2.688172043010753, + "grad_norm": 0.24441877007484436, + "learning_rate": 2.6217173482134172e-05, + "loss": 0.0182, + "step": 6750 + }, + { + "epoch": 2.6921545201115094, + "grad_norm": 0.25608956813812256, + "learning_rate": 2.6071859443017044e-05, + "loss": 0.013, + "step": 6760 + }, + { + "epoch": 2.696136997212266, + "grad_norm": 0.3526802957057953, + "learning_rate": 2.5926807078211414e-05, + "loss": 0.0153, + "step": 6770 + }, + { + "epoch": 2.7001194743130226, + "grad_norm": 0.46395474672317505, + "learning_rate": 2.5782017973986728e-05, + "loss": 0.0181, + "step": 6780 + }, + { + "epoch": 2.7041019514137794, + "grad_norm": 0.23045793175697327, + "learning_rate": 2.5637493713733374e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 2.7080844285145362, + "grad_norm": 0.32080161571502686, + "learning_rate": 2.549323587794559e-05, + "loss": 0.0196, + "step": 6800 + }, + { + "epoch": 2.7120669056152926, + "grad_norm": 0.23438672721385956, + "learning_rate": 2.5349246044203895e-05, + "loss": 0.0143, + "step": 6810 + }, + { + "epoch": 2.7160493827160495, + "grad_norm": 0.33166348934173584, + "learning_rate": 2.520552578715808e-05, + "loss": 0.0144, + "step": 6820 + }, + { + "epoch": 2.720031859816806, + "grad_norm": 0.2601594626903534, + "learning_rate": 2.506207667850981e-05, + "loss": 0.0159, + "step": 6830 + }, + { + "epoch": 2.7240143369175627, + "grad_norm": 0.3093375265598297, + "learning_rate": 2.4918900286995555e-05, + "loss": 0.0141, + "step": 6840 + }, + { + "epoch": 2.7279968140183195, + "grad_norm": 0.15893106162548065, + "learning_rate": 2.4775998178369458e-05, + "loss": 0.0161, + "step": 6850 + }, + { + "epoch": 2.7319792911190763, + "grad_norm": 0.3865691125392914, + "learning_rate": 2.4633371915386017e-05, + "loss": 0.0188, + "step": 6860 + }, + { + "epoch": 2.7359617682198327, + "grad_norm": 0.2376730591058731, + "learning_rate": 2.4491023057783235e-05, + "loss": 0.0192, + "step": 6870 + }, + { + "epoch": 2.7399442453205896, + "grad_norm": 0.38163626194000244, + "learning_rate": 2.4348953162265375e-05, + "loss": 0.0182, + "step": 6880 + }, + { + "epoch": 2.743926722421346, + "grad_norm": 0.22240246832370758, + "learning_rate": 2.420716378248607e-05, + "loss": 0.0217, + "step": 6890 + }, + { + "epoch": 2.7479091995221028, + "grad_norm": 0.4573044180870056, + "learning_rate": 2.4065656469031266e-05, + "loss": 0.0165, + "step": 6900 + }, + { + "epoch": 2.7518916766228596, + "grad_norm": 0.22964206337928772, + "learning_rate": 2.3924432769402268e-05, + "loss": 0.0186, + "step": 6910 + }, + { + "epoch": 2.755874153723616, + "grad_norm": 0.30862241983413696, + "learning_rate": 2.3783494227998844e-05, + "loss": 0.0224, + "step": 6920 + }, + { + "epoch": 2.759856630824373, + "grad_norm": 0.22101591527462006, + "learning_rate": 2.3642842386102264e-05, + "loss": 0.0163, + "step": 6930 + }, + { + "epoch": 2.763839107925129, + "grad_norm": 0.2185278832912445, + "learning_rate": 2.3502478781858567e-05, + "loss": 0.0145, + "step": 6940 + }, + { + "epoch": 2.767821585025886, + "grad_norm": 0.24134941399097443, + "learning_rate": 2.3362404950261628e-05, + "loss": 0.019, + "step": 6950 + }, + { + "epoch": 2.771804062126643, + "grad_norm": 0.2902449071407318, + "learning_rate": 2.3222622423136458e-05, + "loss": 0.0165, + "step": 6960 + }, + { + "epoch": 2.7757865392273997, + "grad_norm": 0.3769952058792114, + "learning_rate": 2.3083132729122332e-05, + "loss": 0.0135, + "step": 6970 + }, + { + "epoch": 2.779769016328156, + "grad_norm": 0.22340670228004456, + "learning_rate": 2.294393739365621e-05, + "loss": 0.019, + "step": 6980 + }, + { + "epoch": 2.783751493428913, + "grad_norm": 0.33232781291007996, + "learning_rate": 2.2805037938956e-05, + "loss": 0.0162, + "step": 6990 + }, + { + "epoch": 2.7877339705296693, + "grad_norm": 0.33404746651649475, + "learning_rate": 2.266643588400386e-05, + "loss": 0.0162, + "step": 7000 + }, + { + "epoch": 2.791716447630426, + "grad_norm": 0.2362033873796463, + "learning_rate": 2.252813274452969e-05, + "loss": 0.0166, + "step": 7010 + }, + { + "epoch": 2.795698924731183, + "grad_norm": 0.15253150463104248, + "learning_rate": 2.2390130032994427e-05, + "loss": 0.0153, + "step": 7020 + }, + { + "epoch": 2.7996814018319394, + "grad_norm": 0.36513105034828186, + "learning_rate": 2.2252429258573633e-05, + "loss": 0.0172, + "step": 7030 + }, + { + "epoch": 2.803663878932696, + "grad_norm": 0.22622640430927277, + "learning_rate": 2.2115031927140904e-05, + "loss": 0.0158, + "step": 7040 + }, + { + "epoch": 2.8076463560334526, + "grad_norm": 0.3483319580554962, + "learning_rate": 2.1977939541251463e-05, + "loss": 0.0218, + "step": 7050 + }, + { + "epoch": 2.8116288331342094, + "grad_norm": 0.3104790449142456, + "learning_rate": 2.1841153600125684e-05, + "loss": 0.0165, + "step": 7060 + }, + { + "epoch": 2.8156113102349662, + "grad_norm": 0.2423543781042099, + "learning_rate": 2.170467559963267e-05, + "loss": 0.0167, + "step": 7070 + }, + { + "epoch": 2.819593787335723, + "grad_norm": 0.3841968774795532, + "learning_rate": 2.1568507032273982e-05, + "loss": 0.0135, + "step": 7080 + }, + { + "epoch": 2.8235762644364795, + "grad_norm": 0.2059573382139206, + "learning_rate": 2.1432649387167264e-05, + "loss": 0.015, + "step": 7090 + }, + { + "epoch": 2.8275587415372363, + "grad_norm": 0.22446751594543457, + "learning_rate": 2.1297104150029973e-05, + "loss": 0.0162, + "step": 7100 + }, + { + "epoch": 2.8315412186379927, + "grad_norm": 0.36766108870506287, + "learning_rate": 2.116187280316307e-05, + "loss": 0.0172, + "step": 7110 + }, + { + "epoch": 2.8355236957387495, + "grad_norm": 0.3884134292602539, + "learning_rate": 2.1026956825434908e-05, + "loss": 0.0182, + "step": 7120 + }, + { + "epoch": 2.8395061728395063, + "grad_norm": 0.3192227780818939, + "learning_rate": 2.0892357692265017e-05, + "loss": 0.0145, + "step": 7130 + }, + { + "epoch": 2.8434886499402627, + "grad_norm": 0.2538623511791229, + "learning_rate": 2.0758076875607947e-05, + "loss": 0.0191, + "step": 7140 + }, + { + "epoch": 2.8474711270410196, + "grad_norm": 0.2836097478866577, + "learning_rate": 2.0624115843937207e-05, + "loss": 0.0201, + "step": 7150 + }, + { + "epoch": 2.851453604141776, + "grad_norm": 0.2728939652442932, + "learning_rate": 2.0490476062229157e-05, + "loss": 0.0176, + "step": 7160 + }, + { + "epoch": 2.855436081242533, + "grad_norm": 0.3548661172389984, + "learning_rate": 2.035715899194704e-05, + "loss": 0.0161, + "step": 7170 + }, + { + "epoch": 2.8594185583432896, + "grad_norm": 0.3930123448371887, + "learning_rate": 2.022416609102499e-05, + "loss": 0.0177, + "step": 7180 + }, + { + "epoch": 2.8634010354440464, + "grad_norm": 0.510944664478302, + "learning_rate": 2.009149881385205e-05, + "loss": 0.0222, + "step": 7190 + }, + { + "epoch": 2.867383512544803, + "grad_norm": 0.3476032018661499, + "learning_rate": 1.995915861125634e-05, + "loss": 0.0176, + "step": 7200 + }, + { + "epoch": 2.8713659896455597, + "grad_norm": 0.2559760510921478, + "learning_rate": 1.9827146930489065e-05, + "loss": 0.0149, + "step": 7210 + }, + { + "epoch": 2.875348466746316, + "grad_norm": 0.20961345732212067, + "learning_rate": 1.9695465215208848e-05, + "loss": 0.018, + "step": 7220 + }, + { + "epoch": 2.879330943847073, + "grad_norm": 0.29862138628959656, + "learning_rate": 1.9564114905465813e-05, + "loss": 0.0156, + "step": 7230 + }, + { + "epoch": 2.8833134209478297, + "grad_norm": 0.3706551492214203, + "learning_rate": 1.9433097437685936e-05, + "loss": 0.0166, + "step": 7240 + }, + { + "epoch": 2.887295898048586, + "grad_norm": 0.4077451825141907, + "learning_rate": 1.930241424465521e-05, + "loss": 0.0139, + "step": 7250 + }, + { + "epoch": 2.891278375149343, + "grad_norm": 0.3151760399341583, + "learning_rate": 1.9172066755504115e-05, + "loss": 0.0164, + "step": 7260 + }, + { + "epoch": 2.8952608522500993, + "grad_norm": 0.29641613364219666, + "learning_rate": 1.9042056395691914e-05, + "loss": 0.0168, + "step": 7270 + }, + { + "epoch": 2.899243329350856, + "grad_norm": 0.3831641376018524, + "learning_rate": 1.8912384586991066e-05, + "loss": 0.0147, + "step": 7280 + }, + { + "epoch": 2.903225806451613, + "grad_norm": 0.3114636540412903, + "learning_rate": 1.8783052747471717e-05, + "loss": 0.0144, + "step": 7290 + }, + { + "epoch": 2.90720828355237, + "grad_norm": 0.26268333196640015, + "learning_rate": 1.865406229148611e-05, + "loss": 0.0185, + "step": 7300 + }, + { + "epoch": 2.911190760653126, + "grad_norm": 0.22112445533275604, + "learning_rate": 1.8525414629653233e-05, + "loss": 0.0203, + "step": 7310 + }, + { + "epoch": 2.915173237753883, + "grad_norm": 0.2656763195991516, + "learning_rate": 1.8397111168843255e-05, + "loss": 0.0158, + "step": 7320 + }, + { + "epoch": 2.9191557148546394, + "grad_norm": 0.341366171836853, + "learning_rate": 1.8269153312162323e-05, + "loss": 0.0176, + "step": 7330 + }, + { + "epoch": 2.9231381919553963, + "grad_norm": 0.27272844314575195, + "learning_rate": 1.8141542458937054e-05, + "loss": 0.0155, + "step": 7340 + }, + { + "epoch": 2.927120669056153, + "grad_norm": 0.4220792353153229, + "learning_rate": 1.8014280004699268e-05, + "loss": 0.0173, + "step": 7350 + }, + { + "epoch": 2.9311031461569095, + "grad_norm": 0.2644200325012207, + "learning_rate": 1.788736734117078e-05, + "loss": 0.0111, + "step": 7360 + }, + { + "epoch": 2.9350856232576663, + "grad_norm": 0.27255773544311523, + "learning_rate": 1.7760805856248152e-05, + "loss": 0.0166, + "step": 7370 + }, + { + "epoch": 2.9390681003584227, + "grad_norm": 0.17350824177265167, + "learning_rate": 1.7634596933987518e-05, + "loss": 0.016, + "step": 7380 + }, + { + "epoch": 2.9430505774591795, + "grad_norm": 0.23067346215248108, + "learning_rate": 1.7508741954589404e-05, + "loss": 0.0164, + "step": 7390 + }, + { + "epoch": 2.9470330545599364, + "grad_norm": 0.3143824636936188, + "learning_rate": 1.7383242294383717e-05, + "loss": 0.0166, + "step": 7400 + }, + { + "epoch": 2.951015531660693, + "grad_norm": 0.2438683658838272, + "learning_rate": 1.7258099325814632e-05, + "loss": 0.0129, + "step": 7410 + }, + { + "epoch": 2.9549980087614496, + "grad_norm": 0.31693488359451294, + "learning_rate": 1.7133314417425594e-05, + "loss": 0.02, + "step": 7420 + }, + { + "epoch": 2.9589804858622064, + "grad_norm": 0.26909369230270386, + "learning_rate": 1.7008888933844408e-05, + "loss": 0.0155, + "step": 7430 + }, + { + "epoch": 2.962962962962963, + "grad_norm": 0.29988786578178406, + "learning_rate": 1.6884824235768172e-05, + "loss": 0.0173, + "step": 7440 + }, + { + "epoch": 2.9669454400637196, + "grad_norm": 0.2735227048397064, + "learning_rate": 1.6761121679948592e-05, + "loss": 0.0148, + "step": 7450 + }, + { + "epoch": 2.9709279171644765, + "grad_norm": 0.23975975811481476, + "learning_rate": 1.663778261917695e-05, + "loss": 0.0177, + "step": 7460 + }, + { + "epoch": 2.974910394265233, + "grad_norm": 0.3303283452987671, + "learning_rate": 1.651480840226952e-05, + "loss": 0.0154, + "step": 7470 + }, + { + "epoch": 2.9788928713659897, + "grad_norm": 0.3179773688316345, + "learning_rate": 1.639220037405258e-05, + "loss": 0.017, + "step": 7480 + }, + { + "epoch": 2.982875348466746, + "grad_norm": 0.26732003688812256, + "learning_rate": 1.6269959875347906e-05, + "loss": 0.0162, + "step": 7490 + }, + { + "epoch": 2.986857825567503, + "grad_norm": 0.35051149129867554, + "learning_rate": 1.614808824295802e-05, + "loss": 0.0161, + "step": 7500 + }, + { + "epoch": 2.9908403026682597, + "grad_norm": 0.24838776886463165, + "learning_rate": 1.602658680965152e-05, + "loss": 0.0115, + "step": 7510 + }, + { + "epoch": 2.9948227797690166, + "grad_norm": 0.3378634452819824, + "learning_rate": 1.5905456904148686e-05, + "loss": 0.0183, + "step": 7520 + }, + { + "epoch": 2.998805256869773, + "grad_norm": 0.28400248289108276, + "learning_rate": 1.57846998511067e-05, + "loss": 0.0165, + "step": 7530 + }, + { + "epoch": 3.00278773397053, + "grad_norm": 0.2319607138633728, + "learning_rate": 1.566431697110538e-05, + "loss": 0.0137, + "step": 7540 + }, + { + "epoch": 3.006770211071286, + "grad_norm": 0.326729953289032, + "learning_rate": 1.554430958063259e-05, + "loss": 0.0135, + "step": 7550 + }, + { + "epoch": 3.010752688172043, + "grad_norm": 0.2378934919834137, + "learning_rate": 1.5424678992069912e-05, + "loss": 0.0152, + "step": 7560 + }, + { + "epoch": 3.0147351652728, + "grad_norm": 0.24295467138290405, + "learning_rate": 1.5305426513678362e-05, + "loss": 0.0142, + "step": 7570 + }, + { + "epoch": 3.018717642373556, + "grad_norm": 0.2576531767845154, + "learning_rate": 1.518655344958388e-05, + "loss": 0.0181, + "step": 7580 + }, + { + "epoch": 3.022700119474313, + "grad_norm": 0.18377450108528137, + "learning_rate": 1.5068061099763275e-05, + "loss": 0.0166, + "step": 7590 + }, + { + "epoch": 3.02668259657507, + "grad_norm": 0.27830517292022705, + "learning_rate": 1.494995076002988e-05, + "loss": 0.0154, + "step": 7600 + }, + { + "epoch": 3.0306650736758263, + "grad_norm": 0.21844340860843658, + "learning_rate": 1.4832223722019456e-05, + "loss": 0.012, + "step": 7610 + }, + { + "epoch": 3.034647550776583, + "grad_norm": 0.2617688775062561, + "learning_rate": 1.4714881273176035e-05, + "loss": 0.0174, + "step": 7620 + }, + { + "epoch": 3.0386300278773395, + "grad_norm": 0.32421252131462097, + "learning_rate": 1.4597924696737835e-05, + "loss": 0.0145, + "step": 7630 + }, + { + "epoch": 3.0426125049780963, + "grad_norm": 0.29088929295539856, + "learning_rate": 1.4481355271723252e-05, + "loss": 0.0159, + "step": 7640 + }, + { + "epoch": 3.046594982078853, + "grad_norm": 0.33224666118621826, + "learning_rate": 1.4365174272916809e-05, + "loss": 0.0172, + "step": 7650 + }, + { + "epoch": 3.0505774591796095, + "grad_norm": 0.28133267164230347, + "learning_rate": 1.4249382970855319e-05, + "loss": 0.0164, + "step": 7660 + }, + { + "epoch": 3.0545599362803664, + "grad_norm": 0.2961582839488983, + "learning_rate": 1.4133982631813903e-05, + "loss": 0.0174, + "step": 7670 + }, + { + "epoch": 3.058542413381123, + "grad_norm": 0.19143448770046234, + "learning_rate": 1.4018974517792194e-05, + "loss": 0.0148, + "step": 7680 + }, + { + "epoch": 3.0625248904818796, + "grad_norm": 0.26252588629722595, + "learning_rate": 1.390435988650048e-05, + "loss": 0.0143, + "step": 7690 + }, + { + "epoch": 3.0665073675826364, + "grad_norm": 0.19971930980682373, + "learning_rate": 1.3790139991346006e-05, + "loss": 0.0125, + "step": 7700 + }, + { + "epoch": 3.0704898446833933, + "grad_norm": 0.2495674192905426, + "learning_rate": 1.367631608141926e-05, + "loss": 0.0155, + "step": 7710 + }, + { + "epoch": 3.0744723217841496, + "grad_norm": 0.22202928364276886, + "learning_rate": 1.3562889401480278e-05, + "loss": 0.0148, + "step": 7720 + }, + { + "epoch": 3.0784547988849065, + "grad_norm": 0.4576508402824402, + "learning_rate": 1.3449861191945074e-05, + "loss": 0.0165, + "step": 7730 + }, + { + "epoch": 3.0824372759856633, + "grad_norm": 0.3544761836528778, + "learning_rate": 1.3337232688872009e-05, + "loss": 0.0139, + "step": 7740 + }, + { + "epoch": 3.0864197530864197, + "grad_norm": 0.3484187722206116, + "learning_rate": 1.3225005123948364e-05, + "loss": 0.0147, + "step": 7750 + }, + { + "epoch": 3.0904022301871765, + "grad_norm": 0.19573178887367249, + "learning_rate": 1.311317972447681e-05, + "loss": 0.0127, + "step": 7760 + }, + { + "epoch": 3.094384707287933, + "grad_norm": 0.19815529882907867, + "learning_rate": 1.3001757713361996e-05, + "loss": 0.0109, + "step": 7770 + }, + { + "epoch": 3.0983671843886897, + "grad_norm": 0.35429829359054565, + "learning_rate": 1.2890740309097204e-05, + "loss": 0.0161, + "step": 7780 + }, + { + "epoch": 3.1023496614894466, + "grad_norm": 0.2911655008792877, + "learning_rate": 1.2780128725750944e-05, + "loss": 0.0138, + "step": 7790 + }, + { + "epoch": 3.106332138590203, + "grad_norm": 0.270168662071228, + "learning_rate": 1.266992417295379e-05, + "loss": 0.015, + "step": 7800 + }, + { + "epoch": 3.11031461569096, + "grad_norm": 0.32108160853385925, + "learning_rate": 1.2560127855885073e-05, + "loss": 0.0163, + "step": 7810 + }, + { + "epoch": 3.1142970927917166, + "grad_norm": 0.24168479442596436, + "learning_rate": 1.2450740975259745e-05, + "loss": 0.0167, + "step": 7820 + }, + { + "epoch": 3.118279569892473, + "grad_norm": 0.30409395694732666, + "learning_rate": 1.234176472731517e-05, + "loss": 0.0221, + "step": 7830 + }, + { + "epoch": 3.12226204699323, + "grad_norm": 0.3229791522026062, + "learning_rate": 1.2233200303798158e-05, + "loss": 0.0147, + "step": 7840 + }, + { + "epoch": 3.1262445240939867, + "grad_norm": 0.26919838786125183, + "learning_rate": 1.2125048891951846e-05, + "loss": 0.0158, + "step": 7850 + }, + { + "epoch": 3.130227001194743, + "grad_norm": 0.23068082332611084, + "learning_rate": 1.2017311674502745e-05, + "loss": 0.013, + "step": 7860 + }, + { + "epoch": 3.1342094782955, + "grad_norm": 0.17686747014522552, + "learning_rate": 1.1909989829647822e-05, + "loss": 0.0144, + "step": 7870 + }, + { + "epoch": 3.1381919553962563, + "grad_norm": 0.45290425419807434, + "learning_rate": 1.1803084531041553e-05, + "loss": 0.0173, + "step": 7880 + }, + { + "epoch": 3.142174432497013, + "grad_norm": 0.2763400673866272, + "learning_rate": 1.1696596947783162e-05, + "loss": 0.0144, + "step": 7890 + }, + { + "epoch": 3.14615690959777, + "grad_norm": 0.2585810422897339, + "learning_rate": 1.1590528244403803e-05, + "loss": 0.0175, + "step": 7900 + }, + { + "epoch": 3.1501393866985263, + "grad_norm": 0.22105610370635986, + "learning_rate": 1.148487958085382e-05, + "loss": 0.0151, + "step": 7910 + }, + { + "epoch": 3.154121863799283, + "grad_norm": 0.21400152146816254, + "learning_rate": 1.1379652112490086e-05, + "loss": 0.0177, + "step": 7920 + }, + { + "epoch": 3.15810434090004, + "grad_norm": 0.1969025582075119, + "learning_rate": 1.1274846990063315e-05, + "loss": 0.0136, + "step": 7930 + }, + { + "epoch": 3.1620868180007964, + "grad_norm": 0.2094409465789795, + "learning_rate": 1.117046535970554e-05, + "loss": 0.0151, + "step": 7940 + }, + { + "epoch": 3.166069295101553, + "grad_norm": 0.29152101278305054, + "learning_rate": 1.106650836291755e-05, + "loss": 0.0195, + "step": 7950 + }, + { + "epoch": 3.17005177220231, + "grad_norm": 0.28160348534584045, + "learning_rate": 1.0962977136556418e-05, + "loss": 0.0184, + "step": 7960 + }, + { + "epoch": 3.1740342493030664, + "grad_norm": 0.3710784614086151, + "learning_rate": 1.0859872812823024e-05, + "loss": 0.0144, + "step": 7970 + }, + { + "epoch": 3.1780167264038233, + "grad_norm": 0.23486924171447754, + "learning_rate": 1.0757196519249747e-05, + "loss": 0.0189, + "step": 7980 + }, + { + "epoch": 3.1819992035045797, + "grad_norm": 0.31155335903167725, + "learning_rate": 1.0654949378688077e-05, + "loss": 0.0156, + "step": 7990 + }, + { + "epoch": 3.1859816806053365, + "grad_norm": 0.21536493301391602, + "learning_rate": 1.0553132509296376e-05, + "loss": 0.0146, + "step": 8000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-9000/config.json b/checkpoint-9000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/checkpoint-9000/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/checkpoint-9000/experiment_cfg/metadata.json b/checkpoint-9000/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/checkpoint-9000/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/checkpoint-9000/model-00001-of-00002.safetensors b/checkpoint-9000/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/checkpoint-9000/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/checkpoint-9000/model-00002-of-00002.safetensors b/checkpoint-9000/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b6d073915520bc4d541324b88a7660839363ccd --- /dev/null +++ b/checkpoint-9000/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8c3d3db763023c3d2a8cf8af1116675509dba44d0bd56cab932b647689a957 +size 2586705312 diff --git a/checkpoint-9000/model.safetensors.index.json b/checkpoint-9000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/checkpoint-9000/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-9000/optimizer.pt b/checkpoint-9000/optimizer.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb7f2a9c909e859c2db8adcb7baf6cdf98f1c4b1 --- /dev/null +++ b/checkpoint-9000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:904ee5b3d63227da55bc2fe22569ad62f53a088880133b5a544f249f536178b0 +size 4147424698 diff --git a/checkpoint-9000/rng_state.pth b/checkpoint-9000/rng_state.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6ee0ffe7060ccbdffa43d4bade46ed32f19aef0 --- /dev/null +++ b/checkpoint-9000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58dfd43d9318102f41d01c51319ccd9faace63ec06ab7a1560f0a20416b8b00 +size 14244 diff --git a/checkpoint-9000/scheduler.pt b/checkpoint-9000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1284fbfc0aff3eb0ffd7ee90f36ce105f6e06839 --- /dev/null +++ b/checkpoint-9000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c26823aa5685497db4fe82a648513d12cb6c26d9be110887b197c10fe3a44ac +size 1064 diff --git a/checkpoint-9000/trainer_state.json b/checkpoint-9000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..c23900b5b5048a9529c3915b6c70c132c2328e70 --- /dev/null +++ b/checkpoint-9000/trainer_state.json @@ -0,0 +1,6334 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.5842293906810037, + "eval_steps": 500, + "global_step": 9000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + }, + { + "epoch": 2.393468737554759, + "grad_norm": 0.33681097626686096, + "learning_rate": 3.758152155160255e-05, + "loss": 0.0167, + "step": 6010 + }, + { + "epoch": 2.397451214655516, + "grad_norm": 0.4447823166847229, + "learning_rate": 3.742142385506999e-05, + "loss": 0.0187, + "step": 6020 + }, + { + "epoch": 2.4014336917562726, + "grad_norm": 0.32111281156539917, + "learning_rate": 3.72614637158309e-05, + "loss": 0.0167, + "step": 6030 + }, + { + "epoch": 2.405416168857029, + "grad_norm": 0.3327321708202362, + "learning_rate": 3.710164288318371e-05, + "loss": 0.021, + "step": 6040 + }, + { + "epoch": 2.409398645957786, + "grad_norm": 0.3221536874771118, + "learning_rate": 3.694196310490345e-05, + "loss": 0.0172, + "step": 6050 + }, + { + "epoch": 2.4133811230585422, + "grad_norm": 0.2384720742702484, + "learning_rate": 3.678242612722259e-05, + "loss": 0.0172, + "step": 6060 + }, + { + "epoch": 2.417363600159299, + "grad_norm": 0.4310377240180969, + "learning_rate": 3.6623033694811953e-05, + "loss": 0.0207, + "step": 6070 + }, + { + "epoch": 2.421346077260056, + "grad_norm": 0.2742801904678345, + "learning_rate": 3.6463787550761665e-05, + "loss": 0.0204, + "step": 6080 + }, + { + "epoch": 2.4253285543608123, + "grad_norm": 0.30959945917129517, + "learning_rate": 3.630468943656202e-05, + "loss": 0.0171, + "step": 6090 + }, + { + "epoch": 2.429311031461569, + "grad_norm": 0.23991258442401886, + "learning_rate": 3.6145741092084523e-05, + "loss": 0.0158, + "step": 6100 + }, + { + "epoch": 2.433293508562326, + "grad_norm": 0.3445211350917816, + "learning_rate": 3.598694425556278e-05, + "loss": 0.0171, + "step": 6110 + }, + { + "epoch": 2.4372759856630823, + "grad_norm": 0.23148199915885925, + "learning_rate": 3.58283006635736e-05, + "loss": 0.0168, + "step": 6120 + }, + { + "epoch": 2.441258462763839, + "grad_norm": 0.34516337513923645, + "learning_rate": 3.566981205101781e-05, + "loss": 0.0214, + "step": 6130 + }, + { + "epoch": 2.445240939864596, + "grad_norm": 0.2975906729698181, + "learning_rate": 3.5511480151101556e-05, + "loss": 0.0182, + "step": 6140 + }, + { + "epoch": 2.4492234169653524, + "grad_norm": 0.3364192545413971, + "learning_rate": 3.5353306695317104e-05, + "loss": 0.0149, + "step": 6150 + }, + { + "epoch": 2.4532058940661092, + "grad_norm": 0.32481926679611206, + "learning_rate": 3.519529341342402e-05, + "loss": 0.0205, + "step": 6160 + }, + { + "epoch": 2.4571883711668656, + "grad_norm": 0.35478660464286804, + "learning_rate": 3.503744203343026e-05, + "loss": 0.0184, + "step": 6170 + }, + { + "epoch": 2.4611708482676224, + "grad_norm": 0.40364179015159607, + "learning_rate": 3.487975428157318e-05, + "loss": 0.0213, + "step": 6180 + }, + { + "epoch": 2.4651533253683793, + "grad_norm": 0.2646041512489319, + "learning_rate": 3.472223188230083e-05, + "loss": 0.0182, + "step": 6190 + }, + { + "epoch": 2.4691358024691357, + "grad_norm": 0.21933303773403168, + "learning_rate": 3.4564876558252866e-05, + "loss": 0.02, + "step": 6200 + }, + { + "epoch": 2.4731182795698925, + "grad_norm": 0.41874152421951294, + "learning_rate": 3.440769003024195e-05, + "loss": 0.0192, + "step": 6210 + }, + { + "epoch": 2.4771007566706493, + "grad_norm": 0.40349701046943665, + "learning_rate": 3.425067401723477e-05, + "loss": 0.0195, + "step": 6220 + }, + { + "epoch": 2.4810832337714057, + "grad_norm": 0.36892589926719666, + "learning_rate": 3.409383023633325e-05, + "loss": 0.0214, + "step": 6230 + }, + { + "epoch": 2.4850657108721625, + "grad_norm": 0.3317766785621643, + "learning_rate": 3.3937160402755894e-05, + "loss": 0.0179, + "step": 6240 + }, + { + "epoch": 2.4890481879729194, + "grad_norm": 0.28070494532585144, + "learning_rate": 3.378066622981885e-05, + "loss": 0.0227, + "step": 6250 + }, + { + "epoch": 2.4930306650736758, + "grad_norm": 0.23878398537635803, + "learning_rate": 3.362434942891738e-05, + "loss": 0.0203, + "step": 6260 + }, + { + "epoch": 2.4970131421744326, + "grad_norm": 0.29855674505233765, + "learning_rate": 3.346821170950693e-05, + "loss": 0.0188, + "step": 6270 + }, + { + "epoch": 2.500995619275189, + "grad_norm": 0.35947370529174805, + "learning_rate": 3.3312254779084585e-05, + "loss": 0.0203, + "step": 6280 + }, + { + "epoch": 2.504978096375946, + "grad_norm": 0.38355863094329834, + "learning_rate": 3.315648034317039e-05, + "loss": 0.0229, + "step": 6290 + }, + { + "epoch": 2.5089605734767026, + "grad_norm": 0.20965726673603058, + "learning_rate": 3.3000890105288564e-05, + "loss": 0.0156, + "step": 6300 + }, + { + "epoch": 2.512943050577459, + "grad_norm": 0.21126852929592133, + "learning_rate": 3.284548576694908e-05, + "loss": 0.0221, + "step": 6310 + }, + { + "epoch": 2.516925527678216, + "grad_norm": 0.29997190833091736, + "learning_rate": 3.2690269027628815e-05, + "loss": 0.0163, + "step": 6320 + }, + { + "epoch": 2.5209080047789723, + "grad_norm": 0.2688118815422058, + "learning_rate": 3.253524158475324e-05, + "loss": 0.018, + "step": 6330 + }, + { + "epoch": 2.524890481879729, + "grad_norm": 0.3369862139225006, + "learning_rate": 3.238040513367757e-05, + "loss": 0.0182, + "step": 6340 + }, + { + "epoch": 2.528872958980486, + "grad_norm": 0.17766013741493225, + "learning_rate": 3.222576136766843e-05, + "loss": 0.0159, + "step": 6350 + }, + { + "epoch": 2.5328554360812428, + "grad_norm": 0.2567964494228363, + "learning_rate": 3.2071311977885324e-05, + "loss": 0.0183, + "step": 6360 + }, + { + "epoch": 2.536837913181999, + "grad_norm": 0.2693711519241333, + "learning_rate": 3.191705865336197e-05, + "loss": 0.0195, + "step": 6370 + }, + { + "epoch": 2.540820390282756, + "grad_norm": 0.2565217912197113, + "learning_rate": 3.1763003080988075e-05, + "loss": 0.0175, + "step": 6380 + }, + { + "epoch": 2.5448028673835124, + "grad_norm": 0.44722431898117065, + "learning_rate": 3.160914694549063e-05, + "loss": 0.0198, + "step": 6390 + }, + { + "epoch": 2.548785344484269, + "grad_norm": 0.3705827593803406, + "learning_rate": 3.145549192941573e-05, + "loss": 0.019, + "step": 6400 + }, + { + "epoch": 2.552767821585026, + "grad_norm": 0.3155789077281952, + "learning_rate": 3.130203971310999e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 2.5567502986857824, + "grad_norm": 0.29949137568473816, + "learning_rate": 3.114879197470225e-05, + "loss": 0.0188, + "step": 6420 + }, + { + "epoch": 2.5607327757865392, + "grad_norm": 0.3367830216884613, + "learning_rate": 3.0995750390085285e-05, + "loss": 0.0175, + "step": 6430 + }, + { + "epoch": 2.5647152528872956, + "grad_norm": 0.2421615719795227, + "learning_rate": 3.084291663289728e-05, + "loss": 0.0192, + "step": 6440 + }, + { + "epoch": 2.5686977299880525, + "grad_norm": 0.17980587482452393, + "learning_rate": 3.069029237450375e-05, + "loss": 0.0155, + "step": 6450 + }, + { + "epoch": 2.5726802070888093, + "grad_norm": 0.42298945784568787, + "learning_rate": 3.053787928397911e-05, + "loss": 0.0169, + "step": 6460 + }, + { + "epoch": 2.576662684189566, + "grad_norm": 0.2914910316467285, + "learning_rate": 3.0385679028088526e-05, + "loss": 0.0195, + "step": 6470 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 0.40466681122779846, + "learning_rate": 3.023369327126959e-05, + "loss": 0.0191, + "step": 6480 + }, + { + "epoch": 2.5846276383910793, + "grad_norm": 0.260161429643631, + "learning_rate": 3.0081923675614198e-05, + "loss": 0.0164, + "step": 6490 + }, + { + "epoch": 2.5886101154918357, + "grad_norm": 0.348817378282547, + "learning_rate": 2.993037190085034e-05, + "loss": 0.0155, + "step": 6500 + }, + { + "epoch": 2.5925925925925926, + "grad_norm": 0.22140339016914368, + "learning_rate": 2.977903960432392e-05, + "loss": 0.0192, + "step": 6510 + }, + { + "epoch": 2.5965750696933494, + "grad_norm": 0.3535783886909485, + "learning_rate": 2.9627928440980722e-05, + "loss": 0.0196, + "step": 6520 + }, + { + "epoch": 2.600557546794106, + "grad_norm": 0.229234978556633, + "learning_rate": 2.9477040063348183e-05, + "loss": 0.0206, + "step": 6530 + }, + { + "epoch": 2.6045400238948626, + "grad_norm": 0.30883148312568665, + "learning_rate": 2.9326376121517456e-05, + "loss": 0.0195, + "step": 6540 + }, + { + "epoch": 2.608522500995619, + "grad_norm": 0.4454684257507324, + "learning_rate": 2.9175938263125236e-05, + "loss": 0.024, + "step": 6550 + }, + { + "epoch": 2.612504978096376, + "grad_norm": 0.34252026677131653, + "learning_rate": 2.9025728133335873e-05, + "loss": 0.0206, + "step": 6560 + }, + { + "epoch": 2.6164874551971327, + "grad_norm": 0.410495400428772, + "learning_rate": 2.8875747374823288e-05, + "loss": 0.0201, + "step": 6570 + }, + { + "epoch": 2.6204699322978895, + "grad_norm": 0.2930971384048462, + "learning_rate": 2.872599762775298e-05, + "loss": 0.0242, + "step": 6580 + }, + { + "epoch": 2.624452409398646, + "grad_norm": 0.1941741406917572, + "learning_rate": 2.857648052976425e-05, + "loss": 0.0168, + "step": 6590 + }, + { + "epoch": 2.6284348864994027, + "grad_norm": 0.4398362338542938, + "learning_rate": 2.8427197715952047e-05, + "loss": 0.019, + "step": 6600 + }, + { + "epoch": 2.632417363600159, + "grad_norm": 0.434218168258667, + "learning_rate": 2.8278150818849393e-05, + "loss": 0.0188, + "step": 6610 + }, + { + "epoch": 2.636399840700916, + "grad_norm": 0.29979050159454346, + "learning_rate": 2.812934146840922e-05, + "loss": 0.0175, + "step": 6620 + }, + { + "epoch": 2.6403823178016728, + "grad_norm": 0.27494296431541443, + "learning_rate": 2.7980771291986764e-05, + "loss": 0.0175, + "step": 6630 + }, + { + "epoch": 2.644364794902429, + "grad_norm": 0.3515009582042694, + "learning_rate": 2.783244191432167e-05, + "loss": 0.0185, + "step": 6640 + }, + { + "epoch": 2.648347272003186, + "grad_norm": 0.3444755971431732, + "learning_rate": 2.768435495752022e-05, + "loss": 0.0171, + "step": 6650 + }, + { + "epoch": 2.652329749103943, + "grad_norm": 0.2616831362247467, + "learning_rate": 2.753651204103771e-05, + "loss": 0.02, + "step": 6660 + }, + { + "epoch": 2.656312226204699, + "grad_norm": 0.2663615643978119, + "learning_rate": 2.7388914781660523e-05, + "loss": 0.0149, + "step": 6670 + }, + { + "epoch": 2.660294703305456, + "grad_norm": 0.21043306589126587, + "learning_rate": 2.7241564793488693e-05, + "loss": 0.0202, + "step": 6680 + }, + { + "epoch": 2.664277180406213, + "grad_norm": 0.45657920837402344, + "learning_rate": 2.7094463687918037e-05, + "loss": 0.0151, + "step": 6690 + }, + { + "epoch": 2.6682596575069693, + "grad_norm": 0.37648776173591614, + "learning_rate": 2.694761307362268e-05, + "loss": 0.0192, + "step": 6700 + }, + { + "epoch": 2.672242134607726, + "grad_norm": 0.26603221893310547, + "learning_rate": 2.6801014556537467e-05, + "loss": 0.0169, + "step": 6710 + }, + { + "epoch": 2.6762246117084825, + "grad_norm": 0.3080855906009674, + "learning_rate": 2.6654669739840243e-05, + "loss": 0.0169, + "step": 6720 + }, + { + "epoch": 2.6802070888092393, + "grad_norm": 0.3766150176525116, + "learning_rate": 2.650858022393451e-05, + "loss": 0.0183, + "step": 6730 + }, + { + "epoch": 2.684189565909996, + "grad_norm": 0.2229013293981552, + "learning_rate": 2.6362747606431747e-05, + "loss": 0.0205, + "step": 6740 + }, + { + "epoch": 2.688172043010753, + "grad_norm": 0.24441877007484436, + "learning_rate": 2.6217173482134172e-05, + "loss": 0.0182, + "step": 6750 + }, + { + "epoch": 2.6921545201115094, + "grad_norm": 0.25608956813812256, + "learning_rate": 2.6071859443017044e-05, + "loss": 0.013, + "step": 6760 + }, + { + "epoch": 2.696136997212266, + "grad_norm": 0.3526802957057953, + "learning_rate": 2.5926807078211414e-05, + "loss": 0.0153, + "step": 6770 + }, + { + "epoch": 2.7001194743130226, + "grad_norm": 0.46395474672317505, + "learning_rate": 2.5782017973986728e-05, + "loss": 0.0181, + "step": 6780 + }, + { + "epoch": 2.7041019514137794, + "grad_norm": 0.23045793175697327, + "learning_rate": 2.5637493713733374e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 2.7080844285145362, + "grad_norm": 0.32080161571502686, + "learning_rate": 2.549323587794559e-05, + "loss": 0.0196, + "step": 6800 + }, + { + "epoch": 2.7120669056152926, + "grad_norm": 0.23438672721385956, + "learning_rate": 2.5349246044203895e-05, + "loss": 0.0143, + "step": 6810 + }, + { + "epoch": 2.7160493827160495, + "grad_norm": 0.33166348934173584, + "learning_rate": 2.520552578715808e-05, + "loss": 0.0144, + "step": 6820 + }, + { + "epoch": 2.720031859816806, + "grad_norm": 0.2601594626903534, + "learning_rate": 2.506207667850981e-05, + "loss": 0.0159, + "step": 6830 + }, + { + "epoch": 2.7240143369175627, + "grad_norm": 0.3093375265598297, + "learning_rate": 2.4918900286995555e-05, + "loss": 0.0141, + "step": 6840 + }, + { + "epoch": 2.7279968140183195, + "grad_norm": 0.15893106162548065, + "learning_rate": 2.4775998178369458e-05, + "loss": 0.0161, + "step": 6850 + }, + { + "epoch": 2.7319792911190763, + "grad_norm": 0.3865691125392914, + "learning_rate": 2.4633371915386017e-05, + "loss": 0.0188, + "step": 6860 + }, + { + "epoch": 2.7359617682198327, + "grad_norm": 0.2376730591058731, + "learning_rate": 2.4491023057783235e-05, + "loss": 0.0192, + "step": 6870 + }, + { + "epoch": 2.7399442453205896, + "grad_norm": 0.38163626194000244, + "learning_rate": 2.4348953162265375e-05, + "loss": 0.0182, + "step": 6880 + }, + { + "epoch": 2.743926722421346, + "grad_norm": 0.22240246832370758, + "learning_rate": 2.420716378248607e-05, + "loss": 0.0217, + "step": 6890 + }, + { + "epoch": 2.7479091995221028, + "grad_norm": 0.4573044180870056, + "learning_rate": 2.4065656469031266e-05, + "loss": 0.0165, + "step": 6900 + }, + { + "epoch": 2.7518916766228596, + "grad_norm": 0.22964206337928772, + "learning_rate": 2.3924432769402268e-05, + "loss": 0.0186, + "step": 6910 + }, + { + "epoch": 2.755874153723616, + "grad_norm": 0.30862241983413696, + "learning_rate": 2.3783494227998844e-05, + "loss": 0.0224, + "step": 6920 + }, + { + "epoch": 2.759856630824373, + "grad_norm": 0.22101591527462006, + "learning_rate": 2.3642842386102264e-05, + "loss": 0.0163, + "step": 6930 + }, + { + "epoch": 2.763839107925129, + "grad_norm": 0.2185278832912445, + "learning_rate": 2.3502478781858567e-05, + "loss": 0.0145, + "step": 6940 + }, + { + "epoch": 2.767821585025886, + "grad_norm": 0.24134941399097443, + "learning_rate": 2.3362404950261628e-05, + "loss": 0.019, + "step": 6950 + }, + { + "epoch": 2.771804062126643, + "grad_norm": 0.2902449071407318, + "learning_rate": 2.3222622423136458e-05, + "loss": 0.0165, + "step": 6960 + }, + { + "epoch": 2.7757865392273997, + "grad_norm": 0.3769952058792114, + "learning_rate": 2.3083132729122332e-05, + "loss": 0.0135, + "step": 6970 + }, + { + "epoch": 2.779769016328156, + "grad_norm": 0.22340670228004456, + "learning_rate": 2.294393739365621e-05, + "loss": 0.019, + "step": 6980 + }, + { + "epoch": 2.783751493428913, + "grad_norm": 0.33232781291007996, + "learning_rate": 2.2805037938956e-05, + "loss": 0.0162, + "step": 6990 + }, + { + "epoch": 2.7877339705296693, + "grad_norm": 0.33404746651649475, + "learning_rate": 2.266643588400386e-05, + "loss": 0.0162, + "step": 7000 + }, + { + "epoch": 2.791716447630426, + "grad_norm": 0.2362033873796463, + "learning_rate": 2.252813274452969e-05, + "loss": 0.0166, + "step": 7010 + }, + { + "epoch": 2.795698924731183, + "grad_norm": 0.15253150463104248, + "learning_rate": 2.2390130032994427e-05, + "loss": 0.0153, + "step": 7020 + }, + { + "epoch": 2.7996814018319394, + "grad_norm": 0.36513105034828186, + "learning_rate": 2.2252429258573633e-05, + "loss": 0.0172, + "step": 7030 + }, + { + "epoch": 2.803663878932696, + "grad_norm": 0.22622640430927277, + "learning_rate": 2.2115031927140904e-05, + "loss": 0.0158, + "step": 7040 + }, + { + "epoch": 2.8076463560334526, + "grad_norm": 0.3483319580554962, + "learning_rate": 2.1977939541251463e-05, + "loss": 0.0218, + "step": 7050 + }, + { + "epoch": 2.8116288331342094, + "grad_norm": 0.3104790449142456, + "learning_rate": 2.1841153600125684e-05, + "loss": 0.0165, + "step": 7060 + }, + { + "epoch": 2.8156113102349662, + "grad_norm": 0.2423543781042099, + "learning_rate": 2.170467559963267e-05, + "loss": 0.0167, + "step": 7070 + }, + { + "epoch": 2.819593787335723, + "grad_norm": 0.3841968774795532, + "learning_rate": 2.1568507032273982e-05, + "loss": 0.0135, + "step": 7080 + }, + { + "epoch": 2.8235762644364795, + "grad_norm": 0.2059573382139206, + "learning_rate": 2.1432649387167264e-05, + "loss": 0.015, + "step": 7090 + }, + { + "epoch": 2.8275587415372363, + "grad_norm": 0.22446751594543457, + "learning_rate": 2.1297104150029973e-05, + "loss": 0.0162, + "step": 7100 + }, + { + "epoch": 2.8315412186379927, + "grad_norm": 0.36766108870506287, + "learning_rate": 2.116187280316307e-05, + "loss": 0.0172, + "step": 7110 + }, + { + "epoch": 2.8355236957387495, + "grad_norm": 0.3884134292602539, + "learning_rate": 2.1026956825434908e-05, + "loss": 0.0182, + "step": 7120 + }, + { + "epoch": 2.8395061728395063, + "grad_norm": 0.3192227780818939, + "learning_rate": 2.0892357692265017e-05, + "loss": 0.0145, + "step": 7130 + }, + { + "epoch": 2.8434886499402627, + "grad_norm": 0.2538623511791229, + "learning_rate": 2.0758076875607947e-05, + "loss": 0.0191, + "step": 7140 + }, + { + "epoch": 2.8474711270410196, + "grad_norm": 0.2836097478866577, + "learning_rate": 2.0624115843937207e-05, + "loss": 0.0201, + "step": 7150 + }, + { + "epoch": 2.851453604141776, + "grad_norm": 0.2728939652442932, + "learning_rate": 2.0490476062229157e-05, + "loss": 0.0176, + "step": 7160 + }, + { + "epoch": 2.855436081242533, + "grad_norm": 0.3548661172389984, + "learning_rate": 2.035715899194704e-05, + "loss": 0.0161, + "step": 7170 + }, + { + "epoch": 2.8594185583432896, + "grad_norm": 0.3930123448371887, + "learning_rate": 2.022416609102499e-05, + "loss": 0.0177, + "step": 7180 + }, + { + "epoch": 2.8634010354440464, + "grad_norm": 0.510944664478302, + "learning_rate": 2.009149881385205e-05, + "loss": 0.0222, + "step": 7190 + }, + { + "epoch": 2.867383512544803, + "grad_norm": 0.3476032018661499, + "learning_rate": 1.995915861125634e-05, + "loss": 0.0176, + "step": 7200 + }, + { + "epoch": 2.8713659896455597, + "grad_norm": 0.2559760510921478, + "learning_rate": 1.9827146930489065e-05, + "loss": 0.0149, + "step": 7210 + }, + { + "epoch": 2.875348466746316, + "grad_norm": 0.20961345732212067, + "learning_rate": 1.9695465215208848e-05, + "loss": 0.018, + "step": 7220 + }, + { + "epoch": 2.879330943847073, + "grad_norm": 0.29862138628959656, + "learning_rate": 1.9564114905465813e-05, + "loss": 0.0156, + "step": 7230 + }, + { + "epoch": 2.8833134209478297, + "grad_norm": 0.3706551492214203, + "learning_rate": 1.9433097437685936e-05, + "loss": 0.0166, + "step": 7240 + }, + { + "epoch": 2.887295898048586, + "grad_norm": 0.4077451825141907, + "learning_rate": 1.930241424465521e-05, + "loss": 0.0139, + "step": 7250 + }, + { + "epoch": 2.891278375149343, + "grad_norm": 0.3151760399341583, + "learning_rate": 1.9172066755504115e-05, + "loss": 0.0164, + "step": 7260 + }, + { + "epoch": 2.8952608522500993, + "grad_norm": 0.29641613364219666, + "learning_rate": 1.9042056395691914e-05, + "loss": 0.0168, + "step": 7270 + }, + { + "epoch": 2.899243329350856, + "grad_norm": 0.3831641376018524, + "learning_rate": 1.8912384586991066e-05, + "loss": 0.0147, + "step": 7280 + }, + { + "epoch": 2.903225806451613, + "grad_norm": 0.3114636540412903, + "learning_rate": 1.8783052747471717e-05, + "loss": 0.0144, + "step": 7290 + }, + { + "epoch": 2.90720828355237, + "grad_norm": 0.26268333196640015, + "learning_rate": 1.865406229148611e-05, + "loss": 0.0185, + "step": 7300 + }, + { + "epoch": 2.911190760653126, + "grad_norm": 0.22112445533275604, + "learning_rate": 1.8525414629653233e-05, + "loss": 0.0203, + "step": 7310 + }, + { + "epoch": 2.915173237753883, + "grad_norm": 0.2656763195991516, + "learning_rate": 1.8397111168843255e-05, + "loss": 0.0158, + "step": 7320 + }, + { + "epoch": 2.9191557148546394, + "grad_norm": 0.341366171836853, + "learning_rate": 1.8269153312162323e-05, + "loss": 0.0176, + "step": 7330 + }, + { + "epoch": 2.9231381919553963, + "grad_norm": 0.27272844314575195, + "learning_rate": 1.8141542458937054e-05, + "loss": 0.0155, + "step": 7340 + }, + { + "epoch": 2.927120669056153, + "grad_norm": 0.4220792353153229, + "learning_rate": 1.8014280004699268e-05, + "loss": 0.0173, + "step": 7350 + }, + { + "epoch": 2.9311031461569095, + "grad_norm": 0.2644200325012207, + "learning_rate": 1.788736734117078e-05, + "loss": 0.0111, + "step": 7360 + }, + { + "epoch": 2.9350856232576663, + "grad_norm": 0.27255773544311523, + "learning_rate": 1.7760805856248152e-05, + "loss": 0.0166, + "step": 7370 + }, + { + "epoch": 2.9390681003584227, + "grad_norm": 0.17350824177265167, + "learning_rate": 1.7634596933987518e-05, + "loss": 0.016, + "step": 7380 + }, + { + "epoch": 2.9430505774591795, + "grad_norm": 0.23067346215248108, + "learning_rate": 1.7508741954589404e-05, + "loss": 0.0164, + "step": 7390 + }, + { + "epoch": 2.9470330545599364, + "grad_norm": 0.3143824636936188, + "learning_rate": 1.7383242294383717e-05, + "loss": 0.0166, + "step": 7400 + }, + { + "epoch": 2.951015531660693, + "grad_norm": 0.2438683658838272, + "learning_rate": 1.7258099325814632e-05, + "loss": 0.0129, + "step": 7410 + }, + { + "epoch": 2.9549980087614496, + "grad_norm": 0.31693488359451294, + "learning_rate": 1.7133314417425594e-05, + "loss": 0.02, + "step": 7420 + }, + { + "epoch": 2.9589804858622064, + "grad_norm": 0.26909369230270386, + "learning_rate": 1.7008888933844408e-05, + "loss": 0.0155, + "step": 7430 + }, + { + "epoch": 2.962962962962963, + "grad_norm": 0.29988786578178406, + "learning_rate": 1.6884824235768172e-05, + "loss": 0.0173, + "step": 7440 + }, + { + "epoch": 2.9669454400637196, + "grad_norm": 0.2735227048397064, + "learning_rate": 1.6761121679948592e-05, + "loss": 0.0148, + "step": 7450 + }, + { + "epoch": 2.9709279171644765, + "grad_norm": 0.23975975811481476, + "learning_rate": 1.663778261917695e-05, + "loss": 0.0177, + "step": 7460 + }, + { + "epoch": 2.974910394265233, + "grad_norm": 0.3303283452987671, + "learning_rate": 1.651480840226952e-05, + "loss": 0.0154, + "step": 7470 + }, + { + "epoch": 2.9788928713659897, + "grad_norm": 0.3179773688316345, + "learning_rate": 1.639220037405258e-05, + "loss": 0.017, + "step": 7480 + }, + { + "epoch": 2.982875348466746, + "grad_norm": 0.26732003688812256, + "learning_rate": 1.6269959875347906e-05, + "loss": 0.0162, + "step": 7490 + }, + { + "epoch": 2.986857825567503, + "grad_norm": 0.35051149129867554, + "learning_rate": 1.614808824295802e-05, + "loss": 0.0161, + "step": 7500 + }, + { + "epoch": 2.9908403026682597, + "grad_norm": 0.24838776886463165, + "learning_rate": 1.602658680965152e-05, + "loss": 0.0115, + "step": 7510 + }, + { + "epoch": 2.9948227797690166, + "grad_norm": 0.3378634452819824, + "learning_rate": 1.5905456904148686e-05, + "loss": 0.0183, + "step": 7520 + }, + { + "epoch": 2.998805256869773, + "grad_norm": 0.28400248289108276, + "learning_rate": 1.57846998511067e-05, + "loss": 0.0165, + "step": 7530 + }, + { + "epoch": 3.00278773397053, + "grad_norm": 0.2319607138633728, + "learning_rate": 1.566431697110538e-05, + "loss": 0.0137, + "step": 7540 + }, + { + "epoch": 3.006770211071286, + "grad_norm": 0.326729953289032, + "learning_rate": 1.554430958063259e-05, + "loss": 0.0135, + "step": 7550 + }, + { + "epoch": 3.010752688172043, + "grad_norm": 0.2378934919834137, + "learning_rate": 1.5424678992069912e-05, + "loss": 0.0152, + "step": 7560 + }, + { + "epoch": 3.0147351652728, + "grad_norm": 0.24295467138290405, + "learning_rate": 1.5305426513678362e-05, + "loss": 0.0142, + "step": 7570 + }, + { + "epoch": 3.018717642373556, + "grad_norm": 0.2576531767845154, + "learning_rate": 1.518655344958388e-05, + "loss": 0.0181, + "step": 7580 + }, + { + "epoch": 3.022700119474313, + "grad_norm": 0.18377450108528137, + "learning_rate": 1.5068061099763275e-05, + "loss": 0.0166, + "step": 7590 + }, + { + "epoch": 3.02668259657507, + "grad_norm": 0.27830517292022705, + "learning_rate": 1.494995076002988e-05, + "loss": 0.0154, + "step": 7600 + }, + { + "epoch": 3.0306650736758263, + "grad_norm": 0.21844340860843658, + "learning_rate": 1.4832223722019456e-05, + "loss": 0.012, + "step": 7610 + }, + { + "epoch": 3.034647550776583, + "grad_norm": 0.2617688775062561, + "learning_rate": 1.4714881273176035e-05, + "loss": 0.0174, + "step": 7620 + }, + { + "epoch": 3.0386300278773395, + "grad_norm": 0.32421252131462097, + "learning_rate": 1.4597924696737835e-05, + "loss": 0.0145, + "step": 7630 + }, + { + "epoch": 3.0426125049780963, + "grad_norm": 0.29088929295539856, + "learning_rate": 1.4481355271723252e-05, + "loss": 0.0159, + "step": 7640 + }, + { + "epoch": 3.046594982078853, + "grad_norm": 0.33224666118621826, + "learning_rate": 1.4365174272916809e-05, + "loss": 0.0172, + "step": 7650 + }, + { + "epoch": 3.0505774591796095, + "grad_norm": 0.28133267164230347, + "learning_rate": 1.4249382970855319e-05, + "loss": 0.0164, + "step": 7660 + }, + { + "epoch": 3.0545599362803664, + "grad_norm": 0.2961582839488983, + "learning_rate": 1.4133982631813903e-05, + "loss": 0.0174, + "step": 7670 + }, + { + "epoch": 3.058542413381123, + "grad_norm": 0.19143448770046234, + "learning_rate": 1.4018974517792194e-05, + "loss": 0.0148, + "step": 7680 + }, + { + "epoch": 3.0625248904818796, + "grad_norm": 0.26252588629722595, + "learning_rate": 1.390435988650048e-05, + "loss": 0.0143, + "step": 7690 + }, + { + "epoch": 3.0665073675826364, + "grad_norm": 0.19971930980682373, + "learning_rate": 1.3790139991346006e-05, + "loss": 0.0125, + "step": 7700 + }, + { + "epoch": 3.0704898446833933, + "grad_norm": 0.2495674192905426, + "learning_rate": 1.367631608141926e-05, + "loss": 0.0155, + "step": 7710 + }, + { + "epoch": 3.0744723217841496, + "grad_norm": 0.22202928364276886, + "learning_rate": 1.3562889401480278e-05, + "loss": 0.0148, + "step": 7720 + }, + { + "epoch": 3.0784547988849065, + "grad_norm": 0.4576508402824402, + "learning_rate": 1.3449861191945074e-05, + "loss": 0.0165, + "step": 7730 + }, + { + "epoch": 3.0824372759856633, + "grad_norm": 0.3544761836528778, + "learning_rate": 1.3337232688872009e-05, + "loss": 0.0139, + "step": 7740 + }, + { + "epoch": 3.0864197530864197, + "grad_norm": 0.3484187722206116, + "learning_rate": 1.3225005123948364e-05, + "loss": 0.0147, + "step": 7750 + }, + { + "epoch": 3.0904022301871765, + "grad_norm": 0.19573178887367249, + "learning_rate": 1.311317972447681e-05, + "loss": 0.0127, + "step": 7760 + }, + { + "epoch": 3.094384707287933, + "grad_norm": 0.19815529882907867, + "learning_rate": 1.3001757713361996e-05, + "loss": 0.0109, + "step": 7770 + }, + { + "epoch": 3.0983671843886897, + "grad_norm": 0.35429829359054565, + "learning_rate": 1.2890740309097204e-05, + "loss": 0.0161, + "step": 7780 + }, + { + "epoch": 3.1023496614894466, + "grad_norm": 0.2911655008792877, + "learning_rate": 1.2780128725750944e-05, + "loss": 0.0138, + "step": 7790 + }, + { + "epoch": 3.106332138590203, + "grad_norm": 0.270168662071228, + "learning_rate": 1.266992417295379e-05, + "loss": 0.015, + "step": 7800 + }, + { + "epoch": 3.11031461569096, + "grad_norm": 0.32108160853385925, + "learning_rate": 1.2560127855885073e-05, + "loss": 0.0163, + "step": 7810 + }, + { + "epoch": 3.1142970927917166, + "grad_norm": 0.24168479442596436, + "learning_rate": 1.2450740975259745e-05, + "loss": 0.0167, + "step": 7820 + }, + { + "epoch": 3.118279569892473, + "grad_norm": 0.30409395694732666, + "learning_rate": 1.234176472731517e-05, + "loss": 0.0221, + "step": 7830 + }, + { + "epoch": 3.12226204699323, + "grad_norm": 0.3229791522026062, + "learning_rate": 1.2233200303798158e-05, + "loss": 0.0147, + "step": 7840 + }, + { + "epoch": 3.1262445240939867, + "grad_norm": 0.26919838786125183, + "learning_rate": 1.2125048891951846e-05, + "loss": 0.0158, + "step": 7850 + }, + { + "epoch": 3.130227001194743, + "grad_norm": 0.23068082332611084, + "learning_rate": 1.2017311674502745e-05, + "loss": 0.013, + "step": 7860 + }, + { + "epoch": 3.1342094782955, + "grad_norm": 0.17686747014522552, + "learning_rate": 1.1909989829647822e-05, + "loss": 0.0144, + "step": 7870 + }, + { + "epoch": 3.1381919553962563, + "grad_norm": 0.45290425419807434, + "learning_rate": 1.1803084531041553e-05, + "loss": 0.0173, + "step": 7880 + }, + { + "epoch": 3.142174432497013, + "grad_norm": 0.2763400673866272, + "learning_rate": 1.1696596947783162e-05, + "loss": 0.0144, + "step": 7890 + }, + { + "epoch": 3.14615690959777, + "grad_norm": 0.2585810422897339, + "learning_rate": 1.1590528244403803e-05, + "loss": 0.0175, + "step": 7900 + }, + { + "epoch": 3.1501393866985263, + "grad_norm": 0.22105610370635986, + "learning_rate": 1.148487958085382e-05, + "loss": 0.0151, + "step": 7910 + }, + { + "epoch": 3.154121863799283, + "grad_norm": 0.21400152146816254, + "learning_rate": 1.1379652112490086e-05, + "loss": 0.0177, + "step": 7920 + }, + { + "epoch": 3.15810434090004, + "grad_norm": 0.1969025582075119, + "learning_rate": 1.1274846990063315e-05, + "loss": 0.0136, + "step": 7930 + }, + { + "epoch": 3.1620868180007964, + "grad_norm": 0.2094409465789795, + "learning_rate": 1.117046535970554e-05, + "loss": 0.0151, + "step": 7940 + }, + { + "epoch": 3.166069295101553, + "grad_norm": 0.29152101278305054, + "learning_rate": 1.106650836291755e-05, + "loss": 0.0195, + "step": 7950 + }, + { + "epoch": 3.17005177220231, + "grad_norm": 0.28160348534584045, + "learning_rate": 1.0962977136556418e-05, + "loss": 0.0184, + "step": 7960 + }, + { + "epoch": 3.1740342493030664, + "grad_norm": 0.3710784614086151, + "learning_rate": 1.0859872812823024e-05, + "loss": 0.0144, + "step": 7970 + }, + { + "epoch": 3.1780167264038233, + "grad_norm": 0.23486924171447754, + "learning_rate": 1.0757196519249747e-05, + "loss": 0.0189, + "step": 7980 + }, + { + "epoch": 3.1819992035045797, + "grad_norm": 0.31155335903167725, + "learning_rate": 1.0654949378688077e-05, + "loss": 0.0156, + "step": 7990 + }, + { + "epoch": 3.1859816806053365, + "grad_norm": 0.21536493301391602, + "learning_rate": 1.0553132509296376e-05, + "loss": 0.0146, + "step": 8000 + }, + { + "epoch": 3.1899641577060933, + "grad_norm": 0.25504568219184875, + "learning_rate": 1.0451747024527613e-05, + "loss": 0.0139, + "step": 8010 + }, + { + "epoch": 3.1939466348068497, + "grad_norm": 0.43125614523887634, + "learning_rate": 1.0350794033117189e-05, + "loss": 0.017, + "step": 8020 + }, + { + "epoch": 3.1979291119076065, + "grad_norm": 0.3463977873325348, + "learning_rate": 1.0250274639070856e-05, + "loss": 0.0153, + "step": 8030 + }, + { + "epoch": 3.2019115890083634, + "grad_norm": 0.33657532930374146, + "learning_rate": 1.0150189941652599e-05, + "loss": 0.0136, + "step": 8040 + }, + { + "epoch": 3.2058940661091198, + "grad_norm": 0.27286818623542786, + "learning_rate": 1.0050541035372635e-05, + "loss": 0.0123, + "step": 8050 + }, + { + "epoch": 3.2098765432098766, + "grad_norm": 0.3115975260734558, + "learning_rate": 9.951329009975458e-06, + "loss": 0.0149, + "step": 8060 + }, + { + "epoch": 3.2138590203106334, + "grad_norm": 0.2783370018005371, + "learning_rate": 9.852554950427845e-06, + "loss": 0.015, + "step": 8070 + }, + { + "epoch": 3.21784149741139, + "grad_norm": 0.2135641872882843, + "learning_rate": 9.754219936907105e-06, + "loss": 0.0145, + "step": 8080 + }, + { + "epoch": 3.2218239745121466, + "grad_norm": 0.2889596223831177, + "learning_rate": 9.656325044789194e-06, + "loss": 0.0125, + "step": 8090 + }, + { + "epoch": 3.225806451612903, + "grad_norm": 0.16843768954277039, + "learning_rate": 9.55887134463697e-06, + "loss": 0.0116, + "step": 8100 + }, + { + "epoch": 3.22978892871366, + "grad_norm": 0.22345881164073944, + "learning_rate": 9.461859902188475e-06, + "loss": 0.0133, + "step": 8110 + }, + { + "epoch": 3.2337714058144167, + "grad_norm": 0.4386395812034607, + "learning_rate": 9.365291778345303e-06, + "loss": 0.0166, + "step": 8120 + }, + { + "epoch": 3.237753882915173, + "grad_norm": 0.15999703109264374, + "learning_rate": 9.269168029160991e-06, + "loss": 0.0103, + "step": 8130 + }, + { + "epoch": 3.24173636001593, + "grad_norm": 0.33131685853004456, + "learning_rate": 9.173489705829447e-06, + "loss": 0.0152, + "step": 8140 + }, + { + "epoch": 3.2457188371166867, + "grad_norm": 0.18595287203788757, + "learning_rate": 9.078257854673516e-06, + "loss": 0.0136, + "step": 8150 + }, + { + "epoch": 3.249701314217443, + "grad_norm": 0.18805378675460815, + "learning_rate": 8.983473517133429e-06, + "loss": 0.0141, + "step": 8160 + }, + { + "epoch": 3.2536837913182, + "grad_norm": 0.15438763797283173, + "learning_rate": 8.889137729755537e-06, + "loss": 0.013, + "step": 8170 + }, + { + "epoch": 3.257666268418957, + "grad_norm": 0.27492639422416687, + "learning_rate": 8.79525152418087e-06, + "loss": 0.0169, + "step": 8180 + }, + { + "epoch": 3.261648745519713, + "grad_norm": 0.28761956095695496, + "learning_rate": 8.701815927133961e-06, + "loss": 0.014, + "step": 8190 + }, + { + "epoch": 3.26563122262047, + "grad_norm": 0.17063534259796143, + "learning_rate": 8.608831960411534e-06, + "loss": 0.0139, + "step": 8200 + }, + { + "epoch": 3.2696136997212264, + "grad_norm": 0.22604522109031677, + "learning_rate": 8.516300640871321e-06, + "loss": 0.0164, + "step": 8210 + }, + { + "epoch": 3.2735961768219832, + "grad_norm": 0.27093005180358887, + "learning_rate": 8.424222980421038e-06, + "loss": 0.0165, + "step": 8220 + }, + { + "epoch": 3.27757865392274, + "grad_norm": 0.2355274260044098, + "learning_rate": 8.332599986007184e-06, + "loss": 0.0151, + "step": 8230 + }, + { + "epoch": 3.2815611310234964, + "grad_norm": 0.23121079802513123, + "learning_rate": 8.241432659604203e-06, + "loss": 0.0144, + "step": 8240 + }, + { + "epoch": 3.2855436081242533, + "grad_norm": 0.1323615461587906, + "learning_rate": 8.150721998203331e-06, + "loss": 0.0128, + "step": 8250 + }, + { + "epoch": 3.28952608522501, + "grad_norm": 0.24003800749778748, + "learning_rate": 8.06046899380184e-06, + "loss": 0.0123, + "step": 8260 + }, + { + "epoch": 3.2935085623257665, + "grad_norm": 0.24698399007320404, + "learning_rate": 7.970674633392133e-06, + "loss": 0.0166, + "step": 8270 + }, + { + "epoch": 3.2974910394265233, + "grad_norm": 0.38070154190063477, + "learning_rate": 7.881339898950924e-06, + "loss": 0.018, + "step": 8280 + }, + { + "epoch": 3.30147351652728, + "grad_norm": 0.1986345499753952, + "learning_rate": 7.792465767428597e-06, + "loss": 0.0136, + "step": 8290 + }, + { + "epoch": 3.3054559936280365, + "grad_norm": 0.21766434609889984, + "learning_rate": 7.704053210738376e-06, + "loss": 0.0132, + "step": 8300 + }, + { + "epoch": 3.3094384707287934, + "grad_norm": 0.20243440568447113, + "learning_rate": 7.6161031957458494e-06, + "loss": 0.0152, + "step": 8310 + }, + { + "epoch": 3.3134209478295498, + "grad_norm": 0.2816754877567291, + "learning_rate": 7.5286166842582605e-06, + "loss": 0.0148, + "step": 8320 + }, + { + "epoch": 3.3174034249303066, + "grad_norm": 0.2514406442642212, + "learning_rate": 7.4415946330140814e-06, + "loss": 0.0145, + "step": 8330 + }, + { + "epoch": 3.3213859020310634, + "grad_norm": 0.2709660530090332, + "learning_rate": 7.3550379936725644e-06, + "loss": 0.0141, + "step": 8340 + }, + { + "epoch": 3.32536837913182, + "grad_norm": 0.2837410569190979, + "learning_rate": 7.2689477128032035e-06, + "loss": 0.018, + "step": 8350 + }, + { + "epoch": 3.3293508562325766, + "grad_norm": 0.131383016705513, + "learning_rate": 7.183324731875551e-06, + "loss": 0.0105, + "step": 8360 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.31221866607666016, + "learning_rate": 7.098169987248782e-06, + "loss": 0.012, + "step": 8370 + }, + { + "epoch": 3.33731581043409, + "grad_norm": 0.2039610892534256, + "learning_rate": 7.013484410161553e-06, + "loss": 0.0135, + "step": 8380 + }, + { + "epoch": 3.3412982875348467, + "grad_norm": 0.22186747193336487, + "learning_rate": 6.92926892672176e-06, + "loss": 0.0131, + "step": 8390 + }, + { + "epoch": 3.3452807646356035, + "grad_norm": 0.1861848533153534, + "learning_rate": 6.845524457896446e-06, + "loss": 0.0124, + "step": 8400 + }, + { + "epoch": 3.34926324173636, + "grad_norm": 0.23007585108280182, + "learning_rate": 6.7622519195017165e-06, + "loss": 0.0126, + "step": 8410 + }, + { + "epoch": 3.3532457188371168, + "grad_norm": 0.26495233178138733, + "learning_rate": 6.679452222192684e-06, + "loss": 0.0136, + "step": 8420 + }, + { + "epoch": 3.357228195937873, + "grad_norm": 0.2193382978439331, + "learning_rate": 6.597126271453579e-06, + "loss": 0.011, + "step": 8430 + }, + { + "epoch": 3.36121067303863, + "grad_norm": 0.10426363348960876, + "learning_rate": 6.51527496758782e-06, + "loss": 0.0114, + "step": 8440 + }, + { + "epoch": 3.365193150139387, + "grad_norm": 0.16592855751514435, + "learning_rate": 6.433899205708155e-06, + "loss": 0.0131, + "step": 8450 + }, + { + "epoch": 3.369175627240143, + "grad_norm": 0.1602918803691864, + "learning_rate": 6.352999875726856e-06, + "loss": 0.0121, + "step": 8460 + }, + { + "epoch": 3.3731581043409, + "grad_norm": 0.16960707306861877, + "learning_rate": 6.272577862346052e-06, + "loss": 0.0115, + "step": 8470 + }, + { + "epoch": 3.377140581441657, + "grad_norm": 0.29499271512031555, + "learning_rate": 6.192634045047996e-06, + "loss": 0.0129, + "step": 8480 + }, + { + "epoch": 3.3811230585424132, + "grad_norm": 0.23193804919719696, + "learning_rate": 6.113169298085458e-06, + "loss": 0.0194, + "step": 8490 + }, + { + "epoch": 3.38510553564317, + "grad_norm": 0.3416202962398529, + "learning_rate": 6.034184490472195e-06, + "loss": 0.0114, + "step": 8500 + }, + { + "epoch": 3.389088012743927, + "grad_norm": 0.22498588263988495, + "learning_rate": 5.955680485973386e-06, + "loss": 0.0156, + "step": 8510 + }, + { + "epoch": 3.3930704898446833, + "grad_norm": 0.3182886838912964, + "learning_rate": 5.877658143096265e-06, + "loss": 0.0132, + "step": 8520 + }, + { + "epoch": 3.39705296694544, + "grad_norm": 0.1463838666677475, + "learning_rate": 5.800118315080661e-06, + "loss": 0.0129, + "step": 8530 + }, + { + "epoch": 3.4010354440461965, + "grad_norm": 0.23471392691135406, + "learning_rate": 5.723061849889716e-06, + "loss": 0.0126, + "step": 8540 + }, + { + "epoch": 3.4050179211469533, + "grad_norm": 0.1969936192035675, + "learning_rate": 5.646489590200604e-06, + "loss": 0.0161, + "step": 8550 + }, + { + "epoch": 3.40900039824771, + "grad_norm": 0.15309295058250427, + "learning_rate": 5.570402373395256e-06, + "loss": 0.0125, + "step": 8560 + }, + { + "epoch": 3.4129828753484666, + "grad_norm": 0.4474526643753052, + "learning_rate": 5.494801031551305e-06, + "loss": 0.0163, + "step": 8570 + }, + { + "epoch": 3.4169653524492234, + "grad_norm": 0.18500779569149017, + "learning_rate": 5.41968639143291e-06, + "loss": 0.0139, + "step": 8580 + }, + { + "epoch": 3.4209478295499802, + "grad_norm": 0.19193483889102936, + "learning_rate": 5.345059274481751e-06, + "loss": 0.0127, + "step": 8590 + }, + { + "epoch": 3.4249303066507366, + "grad_norm": 0.15665030479431152, + "learning_rate": 5.270920496808002e-06, + "loss": 0.0159, + "step": 8600 + }, + { + "epoch": 3.4289127837514934, + "grad_norm": 0.16787682473659515, + "learning_rate": 5.1972708691814695e-06, + "loss": 0.0116, + "step": 8610 + }, + { + "epoch": 3.4328952608522503, + "grad_norm": 0.29282400012016296, + "learning_rate": 5.124111197022674e-06, + "loss": 0.0145, + "step": 8620 + }, + { + "epoch": 3.4368777379530067, + "grad_norm": 0.1538035124540329, + "learning_rate": 5.051442280394081e-06, + "loss": 0.0118, + "step": 8630 + }, + { + "epoch": 3.4408602150537635, + "grad_norm": 0.16790461540222168, + "learning_rate": 4.979264913991322e-06, + "loss": 0.0132, + "step": 8640 + }, + { + "epoch": 3.44484269215452, + "grad_norm": 0.1722331941127777, + "learning_rate": 4.907579887134489e-06, + "loss": 0.0134, + "step": 8650 + }, + { + "epoch": 3.4488251692552767, + "grad_norm": 0.21935425698757172, + "learning_rate": 4.836387983759572e-06, + "loss": 0.0137, + "step": 8660 + }, + { + "epoch": 3.4528076463560335, + "grad_norm": 0.2668359875679016, + "learning_rate": 4.765689982409816e-06, + "loss": 0.0121, + "step": 8670 + }, + { + "epoch": 3.45679012345679, + "grad_norm": 0.34474870562553406, + "learning_rate": 4.695486656227233e-06, + "loss": 0.0178, + "step": 8680 + }, + { + "epoch": 3.4607726005575468, + "grad_norm": 0.3360903859138489, + "learning_rate": 4.625778772944156e-06, + "loss": 0.013, + "step": 8690 + }, + { + "epoch": 3.4647550776583036, + "grad_norm": 0.1198967769742012, + "learning_rate": 4.556567094874825e-06, + "loss": 0.0139, + "step": 8700 + }, + { + "epoch": 3.46873755475906, + "grad_norm": 0.12995925545692444, + "learning_rate": 4.487852378907059e-06, + "loss": 0.0099, + "step": 8710 + }, + { + "epoch": 3.472720031859817, + "grad_norm": 0.14079661667346954, + "learning_rate": 4.419635376493986e-06, + "loss": 0.0133, + "step": 8720 + }, + { + "epoch": 3.4767025089605736, + "grad_norm": 0.23179714381694794, + "learning_rate": 4.351916833645825e-06, + "loss": 0.0145, + "step": 8730 + }, + { + "epoch": 3.48068498606133, + "grad_norm": 0.19353191554546356, + "learning_rate": 4.284697490921691e-06, + "loss": 0.013, + "step": 8740 + }, + { + "epoch": 3.484667463162087, + "grad_norm": 0.2545132040977478, + "learning_rate": 4.2179780834215585e-06, + "loss": 0.0161, + "step": 8750 + }, + { + "epoch": 3.4886499402628433, + "grad_norm": 0.22561277449131012, + "learning_rate": 4.151759340778178e-06, + "loss": 0.0142, + "step": 8760 + }, + { + "epoch": 3.4926324173636, + "grad_norm": 0.25932180881500244, + "learning_rate": 4.086041987149109e-06, + "loss": 0.0131, + "step": 8770 + }, + { + "epoch": 3.496614894464357, + "grad_norm": 0.23832671344280243, + "learning_rate": 4.020826741208811e-06, + "loss": 0.016, + "step": 8780 + }, + { + "epoch": 3.5005973715651137, + "grad_norm": 0.1888727992773056, + "learning_rate": 3.956114316140746e-06, + "loss": 0.0165, + "step": 8790 + }, + { + "epoch": 3.50457984866587, + "grad_norm": 0.2623044550418854, + "learning_rate": 3.891905419629643e-06, + "loss": 0.0125, + "step": 8800 + }, + { + "epoch": 3.508562325766627, + "grad_norm": 0.25887444615364075, + "learning_rate": 3.8282007538536946e-06, + "loss": 0.0164, + "step": 8810 + }, + { + "epoch": 3.5125448028673834, + "grad_norm": 0.21378953754901886, + "learning_rate": 3.7650010154769265e-06, + "loss": 0.0126, + "step": 8820 + }, + { + "epoch": 3.51652727996814, + "grad_norm": 0.2530067563056946, + "learning_rate": 3.7023068956415608e-06, + "loss": 0.0168, + "step": 8830 + }, + { + "epoch": 3.520509757068897, + "grad_norm": 0.27777713537216187, + "learning_rate": 3.6401190799604303e-06, + "loss": 0.0132, + "step": 8840 + }, + { + "epoch": 3.5244922341696534, + "grad_norm": 0.16841277480125427, + "learning_rate": 3.578438248509536e-06, + "loss": 0.015, + "step": 8850 + }, + { + "epoch": 3.5284747112704102, + "grad_norm": 0.22934165596961975, + "learning_rate": 3.5172650758205583e-06, + "loss": 0.0158, + "step": 8860 + }, + { + "epoch": 3.5324571883711666, + "grad_norm": 0.2117910385131836, + "learning_rate": 3.45660023087353e-06, + "loss": 0.0138, + "step": 8870 + }, + { + "epoch": 3.5364396654719235, + "grad_norm": 0.12349478155374527, + "learning_rate": 3.3964443770894528e-06, + "loss": 0.0115, + "step": 8880 + }, + { + "epoch": 3.5404221425726803, + "grad_norm": 0.25816065073013306, + "learning_rate": 3.3367981723231245e-06, + "loss": 0.013, + "step": 8890 + }, + { + "epoch": 3.544404619673437, + "grad_norm": 0.24896445870399475, + "learning_rate": 3.2776622688558746e-06, + "loss": 0.0134, + "step": 8900 + }, + { + "epoch": 3.5483870967741935, + "grad_norm": 0.20246760547161102, + "learning_rate": 3.2190373133884677e-06, + "loss": 0.0141, + "step": 8910 + }, + { + "epoch": 3.5523695738749503, + "grad_norm": 0.17225037515163422, + "learning_rate": 3.1609239470340446e-06, + "loss": 0.0125, + "step": 8920 + }, + { + "epoch": 3.5563520509757067, + "grad_norm": 0.16104808449745178, + "learning_rate": 3.1033228053110373e-06, + "loss": 0.0127, + "step": 8930 + }, + { + "epoch": 3.5603345280764636, + "grad_norm": 0.25064268708229065, + "learning_rate": 3.0462345181363314e-06, + "loss": 0.0121, + "step": 8940 + }, + { + "epoch": 3.5643170051772204, + "grad_norm": 0.177175834774971, + "learning_rate": 2.9896597098182654e-06, + "loss": 0.0145, + "step": 8950 + }, + { + "epoch": 3.5682994822779768, + "grad_norm": 0.23675449192523956, + "learning_rate": 2.933598999049891e-06, + "loss": 0.0133, + "step": 8960 + }, + { + "epoch": 3.5722819593787336, + "grad_norm": 0.19365286827087402, + "learning_rate": 2.8780529989021697e-06, + "loss": 0.0126, + "step": 8970 + }, + { + "epoch": 3.57626443647949, + "grad_norm": 0.3542676270008087, + "learning_rate": 2.823022316817242e-06, + "loss": 0.0162, + "step": 8980 + }, + { + "epoch": 3.580246913580247, + "grad_norm": 0.2057904750108719, + "learning_rate": 2.7685075546018456e-06, + "loss": 0.0134, + "step": 8990 + }, + { + "epoch": 3.5842293906810037, + "grad_norm": 0.19681024551391602, + "learning_rate": 2.7145093084206598e-06, + "loss": 0.0158, + "step": 9000 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70 --- /dev/null +++ b/config.json @@ -0,0 +1,64 @@ +{ + "action_dim": 32, + "action_head_cfg": { + "action_dim": 32, + "action_horizon": 16, + "add_pos_embed": true, + "backbone_embedding_dim": 2048, + "diffusion_model_cfg": { + "attention_head_dim": 48, + "cross_attention_dim": 2048, + "dropout": 0.2, + "final_dropout": true, + "interleave_self_attention": true, + "norm_type": "ada_norm", + "num_attention_heads": 32, + "num_layers": 16, + "output_dim": 1024, + "positional_embeddings": null + }, + "hidden_size": 1024, + "input_embedding_dim": 1536, + "max_action_dim": 32, + "max_state_dim": 64, + "model_dtype": "float32", + "noise_beta_alpha": 1.5, + "noise_beta_beta": 1.0, + "noise_s": 0.999, + "num_inference_timesteps": 4, + "num_target_vision_tokens": 32, + "num_timestep_buckets": 1000, + "tune_diffusion_model": true, + "tune_projector": true, + "use_vlln": true, + "vl_self_attention_cfg": { + "attention_head_dim": 64, + "dropout": 0.2, + "final_dropout": true, + "num_attention_heads": 32, + "num_layers": 4, + "positional_embeddings": null + } + }, + "action_horizon": 16, + "architectures": [ + "GR00T_N1_5" + ], + "attn_implementation": null, + "backbone_cfg": { + "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops", + "load_bf16": false, + "project_to_dim": null, + "reproject_vision": false, + "select_layer": 12, + "tune_llm": false, + "tune_visual": true, + "use_flash_attention": true + }, + "compute_dtype": "bfloat16", + "hidden_size": 2048, + "model_dtype": "float32", + "model_type": "gr00t_n1_5", + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3" +} diff --git a/experiment_cfg/metadata.json b/experiment_cfg/metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..752502a109297273be15c62a01d91e3ad6490049 --- /dev/null +++ b/experiment_cfg/metadata.json @@ -0,0 +1,195 @@ +{ + "new_embodiment": { + "statistics": { + "state": { + "single_arm": { + "max": [ + 33.22265625, + 86.1328125, + 84.7265625, + 101.337890625, + 32.783203125 + ], + "min": [ + -87.275390625, + -103.974609375, + -106.435546875, + -16.34765625, + -170.068359375 + ], + "mean": [ + -26.84341812133789, + 6.497307777404785, + -22.14896583557129, + 74.85757446289062, + -111.02351379394531 + ], + "std": [ + 27.50257110595703, + 41.151065826416016, + 48.41417694091797, + 20.208982467651367, + 46.13625717163086 + ], + "q01": [ + -79.013671875, + -103.271484375, + -104.0625, + 19.187402343750005, + -169.892578125 + ], + "q99": [ + 24.169921875, + 73.30078125, + 84.375, + 101.07421875, + 11.162109375 + ] + }, + "gripper": { + "max": [ + 92.373046875 + ], + "min": [ + -0.615234375 + ], + "mean": [ + 14.521344184875488 + ], + "std": [ + 13.066176414489746 + ], + "q01": [ + 0.0 + ], + "q99": [ + 52.470703125 + ] + } + }, + "action": { + "single_arm": { + "max": [ + 33.662109375, + 86.484375, + 85.078125, + 102.65625, + 33.3984375 + ], + "min": [ + -87.890625, + -104.4140625, + -110.7421875, + -19.599609375, + -173.3203125 + ], + "mean": [ + -26.84657096862793, + 4.594353199005127, + -23.747364044189453, + 74.75859832763672, + -111.30194854736328 + ], + "std": [ + 27.627857208251953, + 40.672019958496094, + 48.966896057128906, + 20.728727340698242, + 46.57689666748047 + ], + "q01": [ + -79.453125, + -102.744140625, + -109.6875, + 17.9296875, + -172.177734375 + ], + "q99": [ + 24.08203125, + 72.685546875, + 83.84765625, + 101.77734375, + 10.72265625 + ] + }, + "gripper": { + "max": [ + 92.63671875 + ], + "min": [ + -3.076171875 + ], + "mean": [ + 12.46182632446289 + ], + "std": [ + 14.029601097106934 + ], + "q01": [ + -0.52734375 + ], + "q99": [ + 52.91015625 + ] + } + } + }, + "modalities": { + "video": { + "front": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + }, + "laptop": { + "resolution": [ + 640, + 480 + ], + "channels": 3, + "fps": 30.0 + } + }, + "state": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + }, + "action": { + "single_arm": { + "absolute": true, + "rotation_type": null, + "shape": [ + 5 + ], + "continuous": true + }, + "gripper": { + "absolute": true, + "rotation_type": null, + "shape": [ + 1 + ], + "continuous": true + } + } + }, + "embodiment_tag": "new_embodiment" + } +} \ No newline at end of file diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a3edcaffb1f5ad108cd1d8518cefe40d281be0c --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e65895a7b6c052e58b679bdd68bff54a68694a81f38e23d3e03a92059b3600b +size 4999367032 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5638d6605794948913af78767d4111f090178848 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595f7bca8c51123b14908af4b1eac93a96d52a59a6b0fe7d8bae323aa957c147 +size 2586705312 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,906 @@ +{ + "metadata": { + "total_size": 7585939328 + }, + "weight_map": { + "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors", + "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors", + "action_head.future_tokens.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors", + "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors", + "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors", + "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-of-00002.safetensors", + "action_head.position_embedding.weight": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors", + "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors", + "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors", + "action_head.vlln.bias": "model-00002-of-00002.safetensors", + "action_head.vlln.weight": "model-00002-of-00002.safetensors", + "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dffd3487c6b793ca6f8b7ad22eb2f246f99f5112 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,7043 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.982477100756671, + "eval_steps": 500, + "global_step": 10000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00398247710075667, + "grad_norm": 10.328946113586426, + "learning_rate": 1.8e-06, + "loss": 0.9415, + "step": 10 + }, + { + "epoch": 0.00796495420151334, + "grad_norm": 6.881450176239014, + "learning_rate": 3.8e-06, + "loss": 0.8639, + "step": 20 + }, + { + "epoch": 0.011947431302270013, + "grad_norm": 2.251582384109497, + "learning_rate": 5.8e-06, + "loss": 0.4771, + "step": 30 + }, + { + "epoch": 0.01592990840302668, + "grad_norm": 1.6325163841247559, + "learning_rate": 7.8e-06, + "loss": 0.2953, + "step": 40 + }, + { + "epoch": 0.019912385503783353, + "grad_norm": 0.9643872976303101, + "learning_rate": 9.800000000000001e-06, + "loss": 0.2403, + "step": 50 + }, + { + "epoch": 0.023894862604540025, + "grad_norm": 1.4014142751693726, + "learning_rate": 1.18e-05, + "loss": 0.2213, + "step": 60 + }, + { + "epoch": 0.027877339705296694, + "grad_norm": 1.3301987648010254, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.2048, + "step": 70 + }, + { + "epoch": 0.03185981680605336, + "grad_norm": 1.5023683309555054, + "learning_rate": 1.58e-05, + "loss": 0.1658, + "step": 80 + }, + { + "epoch": 0.035842293906810034, + "grad_norm": 1.7575840950012207, + "learning_rate": 1.78e-05, + "loss": 0.146, + "step": 90 + }, + { + "epoch": 0.039824771007566706, + "grad_norm": 1.4768755435943604, + "learning_rate": 1.9800000000000004e-05, + "loss": 0.154, + "step": 100 + }, + { + "epoch": 0.04380724810832338, + "grad_norm": 1.43697988986969, + "learning_rate": 2.18e-05, + "loss": 0.1419, + "step": 110 + }, + { + "epoch": 0.04778972520908005, + "grad_norm": 1.6363322734832764, + "learning_rate": 2.38e-05, + "loss": 0.1243, + "step": 120 + }, + { + "epoch": 0.051772202309836715, + "grad_norm": 1.29106605052948, + "learning_rate": 2.58e-05, + "loss": 0.1273, + "step": 130 + }, + { + "epoch": 0.05575467941059339, + "grad_norm": 0.849351704120636, + "learning_rate": 2.7800000000000005e-05, + "loss": 0.1199, + "step": 140 + }, + { + "epoch": 0.05973715651135006, + "grad_norm": 1.442665934562683, + "learning_rate": 2.98e-05, + "loss": 0.1068, + "step": 150 + }, + { + "epoch": 0.06371963361210672, + "grad_norm": 1.277969241142273, + "learning_rate": 3.18e-05, + "loss": 0.11, + "step": 160 + }, + { + "epoch": 0.0677021107128634, + "grad_norm": 1.636638879776001, + "learning_rate": 3.38e-05, + "loss": 0.1001, + "step": 170 + }, + { + "epoch": 0.07168458781362007, + "grad_norm": 1.0019601583480835, + "learning_rate": 3.58e-05, + "loss": 0.1126, + "step": 180 + }, + { + "epoch": 0.07566706491437675, + "grad_norm": 0.9693198204040527, + "learning_rate": 3.7800000000000004e-05, + "loss": 0.0867, + "step": 190 + }, + { + "epoch": 0.07964954201513341, + "grad_norm": 0.7893789410591125, + "learning_rate": 3.9800000000000005e-05, + "loss": 0.1002, + "step": 200 + }, + { + "epoch": 0.08363201911589008, + "grad_norm": 1.736881136894226, + "learning_rate": 4.18e-05, + "loss": 0.1015, + "step": 210 + }, + { + "epoch": 0.08761449621664676, + "grad_norm": 0.7016027569770813, + "learning_rate": 4.38e-05, + "loss": 0.0895, + "step": 220 + }, + { + "epoch": 0.09159697331740342, + "grad_norm": 1.6043905019760132, + "learning_rate": 4.58e-05, + "loss": 0.0857, + "step": 230 + }, + { + "epoch": 0.0955794504181601, + "grad_norm": 1.4260313510894775, + "learning_rate": 4.78e-05, + "loss": 0.0818, + "step": 240 + }, + { + "epoch": 0.09956192751891677, + "grad_norm": 0.9992408156394958, + "learning_rate": 4.9800000000000004e-05, + "loss": 0.0763, + "step": 250 + }, + { + "epoch": 0.10354440461967343, + "grad_norm": 0.5259194374084473, + "learning_rate": 5.1800000000000005e-05, + "loss": 0.0728, + "step": 260 + }, + { + "epoch": 0.10752688172043011, + "grad_norm": 0.8904138207435608, + "learning_rate": 5.380000000000001e-05, + "loss": 0.0741, + "step": 270 + }, + { + "epoch": 0.11150935882118677, + "grad_norm": 0.8944669961929321, + "learning_rate": 5.580000000000001e-05, + "loss": 0.0646, + "step": 280 + }, + { + "epoch": 0.11549183592194345, + "grad_norm": 1.0091243982315063, + "learning_rate": 5.7799999999999995e-05, + "loss": 0.07, + "step": 290 + }, + { + "epoch": 0.11947431302270012, + "grad_norm": 0.7492197155952454, + "learning_rate": 5.9800000000000003e-05, + "loss": 0.0726, + "step": 300 + }, + { + "epoch": 0.12345679012345678, + "grad_norm": 0.9669196605682373, + "learning_rate": 6.18e-05, + "loss": 0.068, + "step": 310 + }, + { + "epoch": 0.12743926722421345, + "grad_norm": 0.8658894896507263, + "learning_rate": 6.38e-05, + "loss": 0.0605, + "step": 320 + }, + { + "epoch": 0.13142174432497014, + "grad_norm": 0.6594343185424805, + "learning_rate": 6.58e-05, + "loss": 0.06, + "step": 330 + }, + { + "epoch": 0.1354042214257268, + "grad_norm": 0.9863249659538269, + "learning_rate": 6.780000000000001e-05, + "loss": 0.0582, + "step": 340 + }, + { + "epoch": 0.13938669852648347, + "grad_norm": 0.8012584447860718, + "learning_rate": 6.98e-05, + "loss": 0.0581, + "step": 350 + }, + { + "epoch": 0.14336917562724014, + "grad_norm": 0.8694135546684265, + "learning_rate": 7.18e-05, + "loss": 0.06, + "step": 360 + }, + { + "epoch": 0.1473516527279968, + "grad_norm": 0.8341110944747925, + "learning_rate": 7.38e-05, + "loss": 0.0551, + "step": 370 + }, + { + "epoch": 0.1513341298287535, + "grad_norm": 0.8546151518821716, + "learning_rate": 7.58e-05, + "loss": 0.0504, + "step": 380 + }, + { + "epoch": 0.15531660692951016, + "grad_norm": 0.8565087914466858, + "learning_rate": 7.780000000000001e-05, + "loss": 0.0544, + "step": 390 + }, + { + "epoch": 0.15929908403026682, + "grad_norm": 0.9835138320922852, + "learning_rate": 7.98e-05, + "loss": 0.0528, + "step": 400 + }, + { + "epoch": 0.1632815611310235, + "grad_norm": 0.9852800965309143, + "learning_rate": 8.18e-05, + "loss": 0.0556, + "step": 410 + }, + { + "epoch": 0.16726403823178015, + "grad_norm": 0.9271975755691528, + "learning_rate": 8.38e-05, + "loss": 0.053, + "step": 420 + }, + { + "epoch": 0.17124651533253685, + "grad_norm": 0.843838632106781, + "learning_rate": 8.58e-05, + "loss": 0.0536, + "step": 430 + }, + { + "epoch": 0.1752289924332935, + "grad_norm": 0.6337900161743164, + "learning_rate": 8.78e-05, + "loss": 0.0501, + "step": 440 + }, + { + "epoch": 0.17921146953405018, + "grad_norm": 0.8339642882347107, + "learning_rate": 8.98e-05, + "loss": 0.0535, + "step": 450 + }, + { + "epoch": 0.18319394663480684, + "grad_norm": 0.8911416530609131, + "learning_rate": 9.180000000000001e-05, + "loss": 0.0599, + "step": 460 + }, + { + "epoch": 0.1871764237355635, + "grad_norm": 0.7793362736701965, + "learning_rate": 9.38e-05, + "loss": 0.0585, + "step": 470 + }, + { + "epoch": 0.1911589008363202, + "grad_norm": 1.1783093214035034, + "learning_rate": 9.58e-05, + "loss": 0.0509, + "step": 480 + }, + { + "epoch": 0.19514137793707687, + "grad_norm": 0.9017106294631958, + "learning_rate": 9.78e-05, + "loss": 0.0558, + "step": 490 + }, + { + "epoch": 0.19912385503783353, + "grad_norm": 1.0761146545410156, + "learning_rate": 9.98e-05, + "loss": 0.0519, + "step": 500 + }, + { + "epoch": 0.2031063321385902, + "grad_norm": 0.5883626937866211, + "learning_rate": 9.9999778549206e-05, + "loss": 0.0527, + "step": 510 + }, + { + "epoch": 0.20708880923934686, + "grad_norm": 0.6159175634384155, + "learning_rate": 9.999901304280685e-05, + "loss": 0.0488, + "step": 520 + }, + { + "epoch": 0.21107128634010355, + "grad_norm": 0.6942933797836304, + "learning_rate": 9.999770075521164e-05, + "loss": 0.0524, + "step": 530 + }, + { + "epoch": 0.21505376344086022, + "grad_norm": 1.0295978784561157, + "learning_rate": 9.99958417007713e-05, + "loss": 0.049, + "step": 540 + }, + { + "epoch": 0.21903624054161688, + "grad_norm": 0.7261350154876709, + "learning_rate": 9.999343589981615e-05, + "loss": 0.0467, + "step": 550 + }, + { + "epoch": 0.22301871764237355, + "grad_norm": 0.7238365411758423, + "learning_rate": 9.999048337865568e-05, + "loss": 0.0477, + "step": 560 + }, + { + "epoch": 0.2270011947431302, + "grad_norm": 1.1104141473770142, + "learning_rate": 9.998698416957815e-05, + "loss": 0.0519, + "step": 570 + }, + { + "epoch": 0.2309836718438869, + "grad_norm": 1.2086730003356934, + "learning_rate": 9.998293831085037e-05, + "loss": 0.0524, + "step": 580 + }, + { + "epoch": 0.23496614894464357, + "grad_norm": 0.5849373936653137, + "learning_rate": 9.997834584671719e-05, + "loss": 0.0514, + "step": 590 + }, + { + "epoch": 0.23894862604540024, + "grad_norm": 0.9337085485458374, + "learning_rate": 9.997320682740107e-05, + "loss": 0.0565, + "step": 600 + }, + { + "epoch": 0.2429311031461569, + "grad_norm": 0.7592830061912537, + "learning_rate": 9.996752130910149e-05, + "loss": 0.0521, + "step": 610 + }, + { + "epoch": 0.24691358024691357, + "grad_norm": 0.8495620489120483, + "learning_rate": 9.99612893539944e-05, + "loss": 0.0501, + "step": 620 + }, + { + "epoch": 0.25089605734767023, + "grad_norm": 0.44615253806114197, + "learning_rate": 9.995451103023144e-05, + "loss": 0.0428, + "step": 630 + }, + { + "epoch": 0.2548785344484269, + "grad_norm": 1.046374797821045, + "learning_rate": 9.994718641193928e-05, + "loss": 0.0459, + "step": 640 + }, + { + "epoch": 0.2588610115491836, + "grad_norm": 0.7210455536842346, + "learning_rate": 9.993931557921874e-05, + "loss": 0.0508, + "step": 650 + }, + { + "epoch": 0.2628434886499403, + "grad_norm": 0.7506885528564453, + "learning_rate": 9.993089861814402e-05, + "loss": 0.0499, + "step": 660 + }, + { + "epoch": 0.26682596575069695, + "grad_norm": 0.6320833563804626, + "learning_rate": 9.992193562076166e-05, + "loss": 0.0579, + "step": 670 + }, + { + "epoch": 0.2708084428514536, + "grad_norm": 0.48116907477378845, + "learning_rate": 9.991242668508954e-05, + "loss": 0.0533, + "step": 680 + }, + { + "epoch": 0.2747909199522103, + "grad_norm": 0.5594539046287537, + "learning_rate": 9.990237191511587e-05, + "loss": 0.0479, + "step": 690 + }, + { + "epoch": 0.27877339705296694, + "grad_norm": 0.6126905083656311, + "learning_rate": 9.989177142079802e-05, + "loss": 0.0449, + "step": 700 + }, + { + "epoch": 0.2827558741537236, + "grad_norm": 0.8031131625175476, + "learning_rate": 9.988062531806126e-05, + "loss": 0.0485, + "step": 710 + }, + { + "epoch": 0.2867383512544803, + "grad_norm": 0.4269757568836212, + "learning_rate": 9.986893372879762e-05, + "loss": 0.0463, + "step": 720 + }, + { + "epoch": 0.29072082835523694, + "grad_norm": 0.8300117254257202, + "learning_rate": 9.985669678086443e-05, + "loss": 0.0505, + "step": 730 + }, + { + "epoch": 0.2947033054559936, + "grad_norm": 0.6425809264183044, + "learning_rate": 9.984391460808298e-05, + "loss": 0.0407, + "step": 740 + }, + { + "epoch": 0.2986857825567503, + "grad_norm": 0.4019189774990082, + "learning_rate": 9.983058735023709e-05, + "loss": 0.044, + "step": 750 + }, + { + "epoch": 0.302668259657507, + "grad_norm": 1.2118290662765503, + "learning_rate": 9.98167151530715e-05, + "loss": 0.0435, + "step": 760 + }, + { + "epoch": 0.30665073675826365, + "grad_norm": 0.4535205662250519, + "learning_rate": 9.980229816829034e-05, + "loss": 0.043, + "step": 770 + }, + { + "epoch": 0.3106332138590203, + "grad_norm": 0.7236475348472595, + "learning_rate": 9.978733655355544e-05, + "loss": 0.0479, + "step": 780 + }, + { + "epoch": 0.314615690959777, + "grad_norm": 1.045904278755188, + "learning_rate": 9.977183047248464e-05, + "loss": 0.0458, + "step": 790 + }, + { + "epoch": 0.31859816806053365, + "grad_norm": 0.8453964591026306, + "learning_rate": 9.975578009464992e-05, + "loss": 0.0489, + "step": 800 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 0.8722575902938843, + "learning_rate": 9.97391855955757e-05, + "loss": 0.0496, + "step": 810 + }, + { + "epoch": 0.326563122262047, + "grad_norm": 0.5823293328285217, + "learning_rate": 9.972204715673669e-05, + "loss": 0.0444, + "step": 820 + }, + { + "epoch": 0.33054559936280364, + "grad_norm": 0.426830917596817, + "learning_rate": 9.970436496555617e-05, + "loss": 0.0429, + "step": 830 + }, + { + "epoch": 0.3345280764635603, + "grad_norm": 0.6528297066688538, + "learning_rate": 9.968613921540373e-05, + "loss": 0.0462, + "step": 840 + }, + { + "epoch": 0.33851055356431703, + "grad_norm": 0.8501228094100952, + "learning_rate": 9.966737010559326e-05, + "loss": 0.0483, + "step": 850 + }, + { + "epoch": 0.3424930306650737, + "grad_norm": 0.6673285365104675, + "learning_rate": 9.964805784138072e-05, + "loss": 0.0483, + "step": 860 + }, + { + "epoch": 0.34647550776583036, + "grad_norm": 0.6113673448562622, + "learning_rate": 9.962820263396195e-05, + "loss": 0.0439, + "step": 870 + }, + { + "epoch": 0.350457984866587, + "grad_norm": 0.8236457705497742, + "learning_rate": 9.960780470047033e-05, + "loss": 0.0425, + "step": 880 + }, + { + "epoch": 0.3544404619673437, + "grad_norm": 0.4798528552055359, + "learning_rate": 9.958686426397437e-05, + "loss": 0.0397, + "step": 890 + }, + { + "epoch": 0.35842293906810035, + "grad_norm": 0.5209172964096069, + "learning_rate": 9.956538155347534e-05, + "loss": 0.0496, + "step": 900 + }, + { + "epoch": 0.362405416168857, + "grad_norm": 0.549393892288208, + "learning_rate": 9.95433568039047e-05, + "loss": 0.0388, + "step": 910 + }, + { + "epoch": 0.3663878932696137, + "grad_norm": 0.6078306436538696, + "learning_rate": 9.952079025612162e-05, + "loss": 0.0467, + "step": 920 + }, + { + "epoch": 0.37037037037037035, + "grad_norm": 0.47643283009529114, + "learning_rate": 9.949768215691022e-05, + "loss": 0.0392, + "step": 930 + }, + { + "epoch": 0.374352847471127, + "grad_norm": 0.5230958461761475, + "learning_rate": 9.9474032758977e-05, + "loss": 0.0414, + "step": 940 + }, + { + "epoch": 0.37833532457188374, + "grad_norm": 0.5619562864303589, + "learning_rate": 9.944984232094794e-05, + "loss": 0.0448, + "step": 950 + }, + { + "epoch": 0.3823178016726404, + "grad_norm": 0.7934162616729736, + "learning_rate": 9.942511110736584e-05, + "loss": 0.0389, + "step": 960 + }, + { + "epoch": 0.38630027877339707, + "grad_norm": 0.7610427737236023, + "learning_rate": 9.939983938868726e-05, + "loss": 0.0383, + "step": 970 + }, + { + "epoch": 0.39028275587415373, + "grad_norm": 0.6311072111129761, + "learning_rate": 9.93740274412797e-05, + "loss": 0.0449, + "step": 980 + }, + { + "epoch": 0.3942652329749104, + "grad_norm": 0.3925153613090515, + "learning_rate": 9.934767554741846e-05, + "loss": 0.043, + "step": 990 + }, + { + "epoch": 0.39824771007566706, + "grad_norm": 0.4677866995334625, + "learning_rate": 9.932078399528361e-05, + "loss": 0.0414, + "step": 1000 + }, + { + "epoch": 0.4022301871764237, + "grad_norm": 0.38546767830848694, + "learning_rate": 9.929335307895689e-05, + "loss": 0.0342, + "step": 1010 + }, + { + "epoch": 0.4062126642771804, + "grad_norm": 0.5453174710273743, + "learning_rate": 9.926538309841839e-05, + "loss": 0.0421, + "step": 1020 + }, + { + "epoch": 0.41019514137793706, + "grad_norm": 0.34743279218673706, + "learning_rate": 9.923687435954334e-05, + "loss": 0.0387, + "step": 1030 + }, + { + "epoch": 0.4141776184786937, + "grad_norm": 0.554025411605835, + "learning_rate": 9.920782717409873e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.41816009557945044, + "grad_norm": 0.6354169249534607, + "learning_rate": 9.917824185973994e-05, + "loss": 0.0411, + "step": 1050 + }, + { + "epoch": 0.4221425726802071, + "grad_norm": 0.46389538049697876, + "learning_rate": 9.914811874000723e-05, + "loss": 0.0447, + "step": 1060 + }, + { + "epoch": 0.42612504978096377, + "grad_norm": 0.8935972452163696, + "learning_rate": 9.911745814432218e-05, + "loss": 0.0454, + "step": 1070 + }, + { + "epoch": 0.43010752688172044, + "grad_norm": 1.0306254625320435, + "learning_rate": 9.90862604079842e-05, + "loss": 0.0438, + "step": 1080 + }, + { + "epoch": 0.4340900039824771, + "grad_norm": 0.5918930768966675, + "learning_rate": 9.90545258721667e-05, + "loss": 0.0389, + "step": 1090 + }, + { + "epoch": 0.43807248108323377, + "grad_norm": 0.5646054148674011, + "learning_rate": 9.90222548839135e-05, + "loss": 0.0395, + "step": 1100 + }, + { + "epoch": 0.44205495818399043, + "grad_norm": 0.5279185175895691, + "learning_rate": 9.898944779613495e-05, + "loss": 0.0438, + "step": 1110 + }, + { + "epoch": 0.4460374352847471, + "grad_norm": 0.41257861256599426, + "learning_rate": 9.89561049676041e-05, + "loss": 0.0397, + "step": 1120 + }, + { + "epoch": 0.45001991238550376, + "grad_norm": 0.36252203583717346, + "learning_rate": 9.89222267629528e-05, + "loss": 0.043, + "step": 1130 + }, + { + "epoch": 0.4540023894862604, + "grad_norm": 0.8424637913703918, + "learning_rate": 9.888781355266763e-05, + "loss": 0.0433, + "step": 1140 + }, + { + "epoch": 0.45798486658701715, + "grad_norm": 0.5604090690612793, + "learning_rate": 9.885286571308598e-05, + "loss": 0.0452, + "step": 1150 + }, + { + "epoch": 0.4619673436877738, + "grad_norm": 0.7178535461425781, + "learning_rate": 9.881738362639182e-05, + "loss": 0.0401, + "step": 1160 + }, + { + "epoch": 0.4659498207885305, + "grad_norm": 0.7291957139968872, + "learning_rate": 9.878136768061154e-05, + "loss": 0.0368, + "step": 1170 + }, + { + "epoch": 0.46993229788928714, + "grad_norm": 0.48816534876823425, + "learning_rate": 9.874481826960979e-05, + "loss": 0.039, + "step": 1180 + }, + { + "epoch": 0.4739147749900438, + "grad_norm": 0.813832700252533, + "learning_rate": 9.870773579308503e-05, + "loss": 0.0417, + "step": 1190 + }, + { + "epoch": 0.4778972520908005, + "grad_norm": 0.5479532480239868, + "learning_rate": 9.867012065656533e-05, + "loss": 0.0428, + "step": 1200 + }, + { + "epoch": 0.48187972919155714, + "grad_norm": 0.7760400772094727, + "learning_rate": 9.863197327140376e-05, + "loss": 0.0454, + "step": 1210 + }, + { + "epoch": 0.4858622062923138, + "grad_norm": 0.6200589537620544, + "learning_rate": 9.859329405477403e-05, + "loss": 0.0377, + "step": 1220 + }, + { + "epoch": 0.48984468339307047, + "grad_norm": 0.7709351778030396, + "learning_rate": 9.855408342966585e-05, + "loss": 0.045, + "step": 1230 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 0.44105854630470276, + "learning_rate": 9.851434182488033e-05, + "loss": 0.0374, + "step": 1240 + }, + { + "epoch": 0.49780963759458385, + "grad_norm": 0.4224795401096344, + "learning_rate": 9.84740696750253e-05, + "loss": 0.0403, + "step": 1250 + }, + { + "epoch": 0.5017921146953405, + "grad_norm": 0.49829116463661194, + "learning_rate": 9.843326742051055e-05, + "loss": 0.0427, + "step": 1260 + }, + { + "epoch": 0.5057745917960972, + "grad_norm": 0.42388513684272766, + "learning_rate": 9.839193550754297e-05, + "loss": 0.0407, + "step": 1270 + }, + { + "epoch": 0.5097570688968538, + "grad_norm": 0.8282580375671387, + "learning_rate": 9.835007438812177e-05, + "loss": 0.0422, + "step": 1280 + }, + { + "epoch": 0.5137395459976105, + "grad_norm": 0.7779645323753357, + "learning_rate": 9.830768452003341e-05, + "loss": 0.044, + "step": 1290 + }, + { + "epoch": 0.5177220230983672, + "grad_norm": 0.6992411017417908, + "learning_rate": 9.826476636684671e-05, + "loss": 0.0422, + "step": 1300 + }, + { + "epoch": 0.5217045001991238, + "grad_norm": 0.5714141130447388, + "learning_rate": 9.822132039790773e-05, + "loss": 0.0394, + "step": 1310 + }, + { + "epoch": 0.5256869772998806, + "grad_norm": 0.8175871968269348, + "learning_rate": 9.817734708833461e-05, + "loss": 0.0498, + "step": 1320 + }, + { + "epoch": 0.5296694544006372, + "grad_norm": 0.6209958791732788, + "learning_rate": 9.813284691901243e-05, + "loss": 0.04, + "step": 1330 + }, + { + "epoch": 0.5336519315013939, + "grad_norm": 0.39030686020851135, + "learning_rate": 9.808782037658792e-05, + "loss": 0.0414, + "step": 1340 + }, + { + "epoch": 0.5376344086021505, + "grad_norm": 0.5858843922615051, + "learning_rate": 9.804226795346411e-05, + "loss": 0.0384, + "step": 1350 + }, + { + "epoch": 0.5416168857029072, + "grad_norm": 0.812506914138794, + "learning_rate": 9.799619014779503e-05, + "loss": 0.0428, + "step": 1360 + }, + { + "epoch": 0.5455993628036638, + "grad_norm": 0.5438332557678223, + "learning_rate": 9.794958746348013e-05, + "loss": 0.0344, + "step": 1370 + }, + { + "epoch": 0.5495818399044206, + "grad_norm": 0.4357604384422302, + "learning_rate": 9.790246041015896e-05, + "loss": 0.0429, + "step": 1380 + }, + { + "epoch": 0.5535643170051773, + "grad_norm": 0.6829274892807007, + "learning_rate": 9.785480950320538e-05, + "loss": 0.0352, + "step": 1390 + }, + { + "epoch": 0.5575467941059339, + "grad_norm": 0.46741291880607605, + "learning_rate": 9.78066352637221e-05, + "loss": 0.0387, + "step": 1400 + }, + { + "epoch": 0.5615292712066906, + "grad_norm": 0.8722621202468872, + "learning_rate": 9.775793821853488e-05, + "loss": 0.0364, + "step": 1410 + }, + { + "epoch": 0.5655117483074472, + "grad_norm": 0.6563253402709961, + "learning_rate": 9.77087189001868e-05, + "loss": 0.0409, + "step": 1420 + }, + { + "epoch": 0.5694942254082039, + "grad_norm": 0.6959318518638611, + "learning_rate": 9.765897784693243e-05, + "loss": 0.0349, + "step": 1430 + }, + { + "epoch": 0.5734767025089605, + "grad_norm": 0.34205693006515503, + "learning_rate": 9.760871560273197e-05, + "loss": 0.036, + "step": 1440 + }, + { + "epoch": 0.5774591796097173, + "grad_norm": 0.7076167464256287, + "learning_rate": 9.755793271724526e-05, + "loss": 0.0413, + "step": 1450 + }, + { + "epoch": 0.5814416567104739, + "grad_norm": 0.6335232257843018, + "learning_rate": 9.750662974582584e-05, + "loss": 0.0392, + "step": 1460 + }, + { + "epoch": 0.5854241338112306, + "grad_norm": 0.7028225660324097, + "learning_rate": 9.745480724951473e-05, + "loss": 0.0391, + "step": 1470 + }, + { + "epoch": 0.5894066109119872, + "grad_norm": 0.5494594573974609, + "learning_rate": 9.740246579503447e-05, + "loss": 0.0469, + "step": 1480 + }, + { + "epoch": 0.5933890880127439, + "grad_norm": 0.3793744146823883, + "learning_rate": 9.734960595478284e-05, + "loss": 0.0372, + "step": 1490 + }, + { + "epoch": 0.5973715651135006, + "grad_norm": 0.6068878769874573, + "learning_rate": 9.729622830682657e-05, + "loss": 0.0443, + "step": 1500 + }, + { + "epoch": 0.6013540422142573, + "grad_norm": 0.6348056197166443, + "learning_rate": 9.724233343489504e-05, + "loss": 0.0388, + "step": 1510 + }, + { + "epoch": 0.605336519315014, + "grad_norm": 0.7185152173042297, + "learning_rate": 9.718792192837396e-05, + "loss": 0.0394, + "step": 1520 + }, + { + "epoch": 0.6093189964157706, + "grad_norm": 0.29940369725227356, + "learning_rate": 9.713299438229886e-05, + "loss": 0.0373, + "step": 1530 + }, + { + "epoch": 0.6133014735165273, + "grad_norm": 0.608589768409729, + "learning_rate": 9.707755139734855e-05, + "loss": 0.0444, + "step": 1540 + }, + { + "epoch": 0.6172839506172839, + "grad_norm": 0.6535037755966187, + "learning_rate": 9.702159357983866e-05, + "loss": 0.0418, + "step": 1550 + }, + { + "epoch": 0.6212664277180406, + "grad_norm": 0.389615923166275, + "learning_rate": 9.696512154171492e-05, + "loss": 0.0394, + "step": 1560 + }, + { + "epoch": 0.6252489048187972, + "grad_norm": 0.5415939092636108, + "learning_rate": 9.690813590054645e-05, + "loss": 0.0374, + "step": 1570 + }, + { + "epoch": 0.629231381919554, + "grad_norm": 0.6598183512687683, + "learning_rate": 9.685063727951914e-05, + "loss": 0.0364, + "step": 1580 + }, + { + "epoch": 0.6332138590203107, + "grad_norm": 0.4346562325954437, + "learning_rate": 9.679262630742865e-05, + "loss": 0.0368, + "step": 1590 + }, + { + "epoch": 0.6371963361210673, + "grad_norm": 0.7525681257247925, + "learning_rate": 9.673410361867373e-05, + "loss": 0.037, + "step": 1600 + }, + { + "epoch": 0.641178813221824, + "grad_norm": 0.4621691405773163, + "learning_rate": 9.667506985324909e-05, + "loss": 0.0313, + "step": 1610 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 0.5039979219436646, + "learning_rate": 9.661552565673855e-05, + "loss": 0.0309, + "step": 1620 + }, + { + "epoch": 0.6491437674233373, + "grad_norm": 0.29736581444740295, + "learning_rate": 9.655547168030789e-05, + "loss": 0.0369, + "step": 1630 + }, + { + "epoch": 0.653126244524094, + "grad_norm": 0.4153502583503723, + "learning_rate": 9.649490858069777e-05, + "loss": 0.0349, + "step": 1640 + }, + { + "epoch": 0.6571087216248507, + "grad_norm": 0.64329993724823, + "learning_rate": 9.643383702021658e-05, + "loss": 0.0422, + "step": 1650 + }, + { + "epoch": 0.6610911987256073, + "grad_norm": 0.39090660214424133, + "learning_rate": 9.637225766673307e-05, + "loss": 0.0332, + "step": 1660 + }, + { + "epoch": 0.665073675826364, + "grad_norm": 0.4412473440170288, + "learning_rate": 9.631017119366922e-05, + "loss": 0.0374, + "step": 1670 + }, + { + "epoch": 0.6690561529271206, + "grad_norm": 0.28402477502822876, + "learning_rate": 9.624757827999273e-05, + "loss": 0.0364, + "step": 1680 + }, + { + "epoch": 0.6730386300278773, + "grad_norm": 0.5480361580848694, + "learning_rate": 9.618447961020971e-05, + "loss": 0.0381, + "step": 1690 + }, + { + "epoch": 0.6770211071286341, + "grad_norm": 0.6572909355163574, + "learning_rate": 9.612087587435707e-05, + "loss": 0.037, + "step": 1700 + }, + { + "epoch": 0.6810035842293907, + "grad_norm": 0.6667490601539612, + "learning_rate": 9.605676776799508e-05, + "loss": 0.04, + "step": 1710 + }, + { + "epoch": 0.6849860613301474, + "grad_norm": 0.29837551712989807, + "learning_rate": 9.599215599219973e-05, + "loss": 0.0351, + "step": 1720 + }, + { + "epoch": 0.688968538430904, + "grad_norm": 0.6289225220680237, + "learning_rate": 9.592704125355505e-05, + "loss": 0.0377, + "step": 1730 + }, + { + "epoch": 0.6929510155316607, + "grad_norm": 0.4489145576953888, + "learning_rate": 9.586142426414538e-05, + "loss": 0.0391, + "step": 1740 + }, + { + "epoch": 0.6969334926324173, + "grad_norm": 0.5505160093307495, + "learning_rate": 9.57953057415476e-05, + "loss": 0.0371, + "step": 1750 + }, + { + "epoch": 0.700915969733174, + "grad_norm": 0.48338383436203003, + "learning_rate": 9.572868640882328e-05, + "loss": 0.0399, + "step": 1760 + }, + { + "epoch": 0.7048984468339307, + "grad_norm": 0.3950949013233185, + "learning_rate": 9.56615669945108e-05, + "loss": 0.0411, + "step": 1770 + }, + { + "epoch": 0.7088809239346874, + "grad_norm": 0.7186228036880493, + "learning_rate": 9.55939482326173e-05, + "loss": 0.0358, + "step": 1780 + }, + { + "epoch": 0.7128634010354441, + "grad_norm": 0.36578911542892456, + "learning_rate": 9.552583086261069e-05, + "loss": 0.0402, + "step": 1790 + }, + { + "epoch": 0.7168458781362007, + "grad_norm": 0.48990169167518616, + "learning_rate": 9.545721562941168e-05, + "loss": 0.0353, + "step": 1800 + }, + { + "epoch": 0.7208283552369574, + "grad_norm": 0.37718433141708374, + "learning_rate": 9.538810328338543e-05, + "loss": 0.0385, + "step": 1810 + }, + { + "epoch": 0.724810832337714, + "grad_norm": 0.40954500436782837, + "learning_rate": 9.531849458033349e-05, + "loss": 0.0334, + "step": 1820 + }, + { + "epoch": 0.7287933094384708, + "grad_norm": 0.6403422951698303, + "learning_rate": 9.524839028148547e-05, + "loss": 0.0385, + "step": 1830 + }, + { + "epoch": 0.7327757865392274, + "grad_norm": 0.4989095628261566, + "learning_rate": 9.517779115349077e-05, + "loss": 0.0374, + "step": 1840 + }, + { + "epoch": 0.7367582636399841, + "grad_norm": 0.4369076192378998, + "learning_rate": 9.510669796841014e-05, + "loss": 0.0353, + "step": 1850 + }, + { + "epoch": 0.7407407407407407, + "grad_norm": 0.6268195509910583, + "learning_rate": 9.503511150370727e-05, + "loss": 0.0407, + "step": 1860 + }, + { + "epoch": 0.7447232178414974, + "grad_norm": 0.40719932317733765, + "learning_rate": 9.496303254224024e-05, + "loss": 0.037, + "step": 1870 + }, + { + "epoch": 0.748705694942254, + "grad_norm": 0.41097119450569153, + "learning_rate": 9.489046187225306e-05, + "loss": 0.0338, + "step": 1880 + }, + { + "epoch": 0.7526881720430108, + "grad_norm": 0.3966093361377716, + "learning_rate": 9.481740028736692e-05, + "loss": 0.0318, + "step": 1890 + }, + { + "epoch": 0.7566706491437675, + "grad_norm": 0.6017296314239502, + "learning_rate": 9.474384858657164e-05, + "loss": 0.0375, + "step": 1900 + }, + { + "epoch": 0.7606531262445241, + "grad_norm": 0.6876013278961182, + "learning_rate": 9.466980757421679e-05, + "loss": 0.0381, + "step": 1910 + }, + { + "epoch": 0.7646356033452808, + "grad_norm": 0.4606328010559082, + "learning_rate": 9.459527806000305e-05, + "loss": 0.0379, + "step": 1920 + }, + { + "epoch": 0.7686180804460374, + "grad_norm": 0.9279587268829346, + "learning_rate": 9.452026085897325e-05, + "loss": 0.0351, + "step": 1930 + }, + { + "epoch": 0.7726005575467941, + "grad_norm": 0.5607491135597229, + "learning_rate": 9.444475679150348e-05, + "loss": 0.0397, + "step": 1940 + }, + { + "epoch": 0.7765830346475507, + "grad_norm": 0.7617636322975159, + "learning_rate": 9.436876668329411e-05, + "loss": 0.0357, + "step": 1950 + }, + { + "epoch": 0.7805655117483075, + "grad_norm": 0.40550336241722107, + "learning_rate": 9.429229136536079e-05, + "loss": 0.0326, + "step": 1960 + }, + { + "epoch": 0.7845479888490641, + "grad_norm": 0.7706924676895142, + "learning_rate": 9.421533167402534e-05, + "loss": 0.0395, + "step": 1970 + }, + { + "epoch": 0.7885304659498208, + "grad_norm": 0.5256568789482117, + "learning_rate": 9.413788845090666e-05, + "loss": 0.04, + "step": 1980 + }, + { + "epoch": 0.7925129430505775, + "grad_norm": 0.4805433452129364, + "learning_rate": 9.405996254291136e-05, + "loss": 0.0358, + "step": 1990 + }, + { + "epoch": 0.7964954201513341, + "grad_norm": 0.4774327874183655, + "learning_rate": 9.398155480222474e-05, + "loss": 0.0323, + "step": 2000 + }, + { + "epoch": 0.8004778972520908, + "grad_norm": 0.42436131834983826, + "learning_rate": 9.390266608630128e-05, + "loss": 0.0351, + "step": 2010 + }, + { + "epoch": 0.8044603743528475, + "grad_norm": 0.43557778000831604, + "learning_rate": 9.38232972578553e-05, + "loss": 0.0385, + "step": 2020 + }, + { + "epoch": 0.8084428514536042, + "grad_norm": 0.47707608342170715, + "learning_rate": 9.374344918485164e-05, + "loss": 0.0371, + "step": 2030 + }, + { + "epoch": 0.8124253285543608, + "grad_norm": 0.4659009873867035, + "learning_rate": 9.366312274049602e-05, + "loss": 0.0407, + "step": 2040 + }, + { + "epoch": 0.8164078056551175, + "grad_norm": 0.4538560211658478, + "learning_rate": 9.358231880322554e-05, + "loss": 0.0349, + "step": 2050 + }, + { + "epoch": 0.8203902827558741, + "grad_norm": 0.6766425967216492, + "learning_rate": 9.350103825669916e-05, + "loss": 0.0311, + "step": 2060 + }, + { + "epoch": 0.8243727598566308, + "grad_norm": 0.3502272963523865, + "learning_rate": 9.341928198978787e-05, + "loss": 0.0347, + "step": 2070 + }, + { + "epoch": 0.8283552369573874, + "grad_norm": 0.5337536931037903, + "learning_rate": 9.333705089656512e-05, + "loss": 0.03, + "step": 2080 + }, + { + "epoch": 0.8323377140581442, + "grad_norm": 0.6512131690979004, + "learning_rate": 9.325434587629698e-05, + "loss": 0.0329, + "step": 2090 + }, + { + "epoch": 0.8363201911589009, + "grad_norm": 0.5638608336448669, + "learning_rate": 9.31711678334323e-05, + "loss": 0.0311, + "step": 2100 + }, + { + "epoch": 0.8403026682596575, + "grad_norm": 0.3121340572834015, + "learning_rate": 9.308751767759282e-05, + "loss": 0.0319, + "step": 2110 + }, + { + "epoch": 0.8442851453604142, + "grad_norm": 0.6195731163024902, + "learning_rate": 9.300339632356325e-05, + "loss": 0.0318, + "step": 2120 + }, + { + "epoch": 0.8482676224611708, + "grad_norm": 0.6970657110214233, + "learning_rate": 9.291880469128124e-05, + "loss": 0.0337, + "step": 2130 + }, + { + "epoch": 0.8522500995619275, + "grad_norm": 0.5600506663322449, + "learning_rate": 9.283374370582732e-05, + "loss": 0.0371, + "step": 2140 + }, + { + "epoch": 0.8562325766626842, + "grad_norm": 0.47252482175827026, + "learning_rate": 9.274821429741482e-05, + "loss": 0.0399, + "step": 2150 + }, + { + "epoch": 0.8602150537634409, + "grad_norm": 0.511959969997406, + "learning_rate": 9.266221740137961e-05, + "loss": 0.0336, + "step": 2160 + }, + { + "epoch": 0.8641975308641975, + "grad_norm": 0.4836970567703247, + "learning_rate": 9.257575395817001e-05, + "loss": 0.0297, + "step": 2170 + }, + { + "epoch": 0.8681800079649542, + "grad_norm": 0.6154841184616089, + "learning_rate": 9.248882491333637e-05, + "loss": 0.0369, + "step": 2180 + }, + { + "epoch": 0.8721624850657109, + "grad_norm": 0.6111750602722168, + "learning_rate": 9.240143121752076e-05, + "loss": 0.0325, + "step": 2190 + }, + { + "epoch": 0.8761449621664675, + "grad_norm": 0.4122430980205536, + "learning_rate": 9.23135738264467e-05, + "loss": 0.0325, + "step": 2200 + }, + { + "epoch": 0.8801274392672243, + "grad_norm": 0.35100454092025757, + "learning_rate": 9.222525370090849e-05, + "loss": 0.0313, + "step": 2210 + }, + { + "epoch": 0.8841099163679809, + "grad_norm": 0.5073012113571167, + "learning_rate": 9.213647180676088e-05, + "loss": 0.0337, + "step": 2220 + }, + { + "epoch": 0.8880923934687376, + "grad_norm": 0.6666367650032043, + "learning_rate": 9.204722911490846e-05, + "loss": 0.0357, + "step": 2230 + }, + { + "epoch": 0.8920748705694942, + "grad_norm": 0.43829846382141113, + "learning_rate": 9.1957526601295e-05, + "loss": 0.0309, + "step": 2240 + }, + { + "epoch": 0.8960573476702509, + "grad_norm": 0.41505926847457886, + "learning_rate": 9.186736524689281e-05, + "loss": 0.0362, + "step": 2250 + }, + { + "epoch": 0.9000398247710075, + "grad_norm": 0.585198700428009, + "learning_rate": 9.177674603769204e-05, + "loss": 0.0373, + "step": 2260 + }, + { + "epoch": 0.9040223018717642, + "grad_norm": 0.5691582560539246, + "learning_rate": 9.168566996468983e-05, + "loss": 0.0297, + "step": 2270 + }, + { + "epoch": 0.9080047789725209, + "grad_norm": 0.568215012550354, + "learning_rate": 9.159413802387951e-05, + "loss": 0.0375, + "step": 2280 + }, + { + "epoch": 0.9119872560732776, + "grad_norm": 0.41294440627098083, + "learning_rate": 9.150215121623974e-05, + "loss": 0.0348, + "step": 2290 + }, + { + "epoch": 0.9159697331740343, + "grad_norm": 0.5145776271820068, + "learning_rate": 9.140971054772349e-05, + "loss": 0.0318, + "step": 2300 + }, + { + "epoch": 0.9199522102747909, + "grad_norm": 0.4824906289577484, + "learning_rate": 9.131681702924713e-05, + "loss": 0.0383, + "step": 2310 + }, + { + "epoch": 0.9239346873755476, + "grad_norm": 0.5607543587684631, + "learning_rate": 9.122347167667926e-05, + "loss": 0.0288, + "step": 2320 + }, + { + "epoch": 0.9279171644763042, + "grad_norm": 0.7051650285720825, + "learning_rate": 9.112967551082973e-05, + "loss": 0.0393, + "step": 2330 + }, + { + "epoch": 0.931899641577061, + "grad_norm": 0.4049379825592041, + "learning_rate": 9.103542955743835e-05, + "loss": 0.0322, + "step": 2340 + }, + { + "epoch": 0.9358821186778176, + "grad_norm": 0.3805215060710907, + "learning_rate": 9.094073484716381e-05, + "loss": 0.0357, + "step": 2350 + }, + { + "epoch": 0.9398645957785743, + "grad_norm": 0.44789791107177734, + "learning_rate": 9.084559241557226e-05, + "loss": 0.0291, + "step": 2360 + }, + { + "epoch": 0.9438470728793309, + "grad_norm": 0.6356040835380554, + "learning_rate": 9.075000330312608e-05, + "loss": 0.0322, + "step": 2370 + }, + { + "epoch": 0.9478295499800876, + "grad_norm": 0.504687488079071, + "learning_rate": 9.065396855517253e-05, + "loss": 0.03, + "step": 2380 + }, + { + "epoch": 0.9518120270808443, + "grad_norm": 0.4105326533317566, + "learning_rate": 9.055748922193219e-05, + "loss": 0.0349, + "step": 2390 + }, + { + "epoch": 0.955794504181601, + "grad_norm": 0.4912046790122986, + "learning_rate": 9.046056635848761e-05, + "loss": 0.0384, + "step": 2400 + }, + { + "epoch": 0.9597769812823577, + "grad_norm": 0.7549566030502319, + "learning_rate": 9.036320102477169e-05, + "loss": 0.0327, + "step": 2410 + }, + { + "epoch": 0.9637594583831143, + "grad_norm": 0.36022019386291504, + "learning_rate": 9.02653942855561e-05, + "loss": 0.0331, + "step": 2420 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 0.48688042163848877, + "learning_rate": 9.016714721043971e-05, + "loss": 0.0318, + "step": 2430 + }, + { + "epoch": 0.9717244125846276, + "grad_norm": 0.3235294222831726, + "learning_rate": 9.006846087383675e-05, + "loss": 0.0327, + "step": 2440 + }, + { + "epoch": 0.9757068896853843, + "grad_norm": 0.5939168334007263, + "learning_rate": 8.996933635496523e-05, + "loss": 0.0314, + "step": 2450 + }, + { + "epoch": 0.9796893667861409, + "grad_norm": 0.7387416958808899, + "learning_rate": 8.986977473783498e-05, + "loss": 0.0374, + "step": 2460 + }, + { + "epoch": 0.9836718438868977, + "grad_norm": 0.48453521728515625, + "learning_rate": 8.97697771112359e-05, + "loss": 0.0317, + "step": 2470 + }, + { + "epoch": 0.9876543209876543, + "grad_norm": 0.40206247568130493, + "learning_rate": 8.966934456872602e-05, + "loss": 0.0303, + "step": 2480 + }, + { + "epoch": 0.991636798088411, + "grad_norm": 0.5897948741912842, + "learning_rate": 8.95684782086195e-05, + "loss": 0.0293, + "step": 2490 + }, + { + "epoch": 0.9956192751891677, + "grad_norm": 0.3984488546848297, + "learning_rate": 8.946717913397476e-05, + "loss": 0.0374, + "step": 2500 + }, + { + "epoch": 0.9996017522899243, + "grad_norm": 0.3679232597351074, + "learning_rate": 8.93654484525822e-05, + "loss": 0.0311, + "step": 2510 + }, + { + "epoch": 1.003584229390681, + "grad_norm": 0.3514699637889862, + "learning_rate": 8.926328727695226e-05, + "loss": 0.0282, + "step": 2520 + }, + { + "epoch": 1.0075667064914378, + "grad_norm": 0.34111514687538147, + "learning_rate": 8.916069672430319e-05, + "loss": 0.0272, + "step": 2530 + }, + { + "epoch": 1.0115491835921944, + "grad_norm": 0.3726666569709778, + "learning_rate": 8.905767791654884e-05, + "loss": 0.0315, + "step": 2540 + }, + { + "epoch": 1.015531660692951, + "grad_norm": 0.5761587619781494, + "learning_rate": 8.895423198028638e-05, + "loss": 0.0363, + "step": 2550 + }, + { + "epoch": 1.0195141377937076, + "grad_norm": 0.5593805909156799, + "learning_rate": 8.885036004678402e-05, + "loss": 0.0311, + "step": 2560 + }, + { + "epoch": 1.0234966148944644, + "grad_norm": 0.3937326669692993, + "learning_rate": 8.874606325196857e-05, + "loss": 0.0339, + "step": 2570 + }, + { + "epoch": 1.027479091995221, + "grad_norm": 0.5169225931167603, + "learning_rate": 8.864134273641304e-05, + "loss": 0.03, + "step": 2580 + }, + { + "epoch": 1.0314615690959776, + "grad_norm": 0.5744480490684509, + "learning_rate": 8.853619964532427e-05, + "loss": 0.0324, + "step": 2590 + }, + { + "epoch": 1.0354440461967345, + "grad_norm": 0.555366039276123, + "learning_rate": 8.843063512853019e-05, + "loss": 0.0289, + "step": 2600 + }, + { + "epoch": 1.039426523297491, + "grad_norm": 0.4377165734767914, + "learning_rate": 8.832465034046749e-05, + "loss": 0.0296, + "step": 2610 + }, + { + "epoch": 1.0434090003982477, + "grad_norm": 0.5874027013778687, + "learning_rate": 8.821824644016882e-05, + "loss": 0.0317, + "step": 2620 + }, + { + "epoch": 1.0473914774990043, + "grad_norm": 0.7405006289482117, + "learning_rate": 8.811142459125019e-05, + "loss": 0.0308, + "step": 2630 + }, + { + "epoch": 1.0513739545997611, + "grad_norm": 0.4106619954109192, + "learning_rate": 8.800418596189822e-05, + "loss": 0.0252, + "step": 2640 + }, + { + "epoch": 1.0553564317005177, + "grad_norm": 0.510388195514679, + "learning_rate": 8.789653172485737e-05, + "loss": 0.0297, + "step": 2650 + }, + { + "epoch": 1.0593389088012743, + "grad_norm": 0.5874786972999573, + "learning_rate": 8.778846305741715e-05, + "loss": 0.0359, + "step": 2660 + }, + { + "epoch": 1.063321385902031, + "grad_norm": 0.5348223447799683, + "learning_rate": 8.767998114139918e-05, + "loss": 0.0313, + "step": 2670 + }, + { + "epoch": 1.0673038630027878, + "grad_norm": 0.3929119408130646, + "learning_rate": 8.757108716314429e-05, + "loss": 0.0329, + "step": 2680 + }, + { + "epoch": 1.0712863401035444, + "grad_norm": 0.5612719058990479, + "learning_rate": 8.746178231349962e-05, + "loss": 0.0312, + "step": 2690 + }, + { + "epoch": 1.075268817204301, + "grad_norm": 0.37800925970077515, + "learning_rate": 8.735206778780549e-05, + "loss": 0.0349, + "step": 2700 + }, + { + "epoch": 1.0792512943050578, + "grad_norm": 0.43637755513191223, + "learning_rate": 8.724194478588234e-05, + "loss": 0.0307, + "step": 2710 + }, + { + "epoch": 1.0832337714058144, + "grad_norm": 0.3608951270580292, + "learning_rate": 8.713141451201772e-05, + "loss": 0.0277, + "step": 2720 + }, + { + "epoch": 1.087216248506571, + "grad_norm": 0.5240746140480042, + "learning_rate": 8.702047817495295e-05, + "loss": 0.0302, + "step": 2730 + }, + { + "epoch": 1.0911987256073277, + "grad_norm": 0.3599265515804291, + "learning_rate": 8.69091369878701e-05, + "loss": 0.0313, + "step": 2740 + }, + { + "epoch": 1.0951812027080845, + "grad_norm": 0.6075289845466614, + "learning_rate": 8.679739216837849e-05, + "loss": 0.0296, + "step": 2750 + }, + { + "epoch": 1.099163679808841, + "grad_norm": 0.4289771318435669, + "learning_rate": 8.66852449385016e-05, + "loss": 0.0276, + "step": 2760 + }, + { + "epoch": 1.1031461569095977, + "grad_norm": 0.3706158697605133, + "learning_rate": 8.657269652466356e-05, + "loss": 0.0278, + "step": 2770 + }, + { + "epoch": 1.1071286340103543, + "grad_norm": 0.6201577186584473, + "learning_rate": 8.645974815767577e-05, + "loss": 0.0315, + "step": 2780 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.5606251358985901, + "learning_rate": 8.634640107272351e-05, + "loss": 0.0274, + "step": 2790 + }, + { + "epoch": 1.1150935882118678, + "grad_norm": 0.4653207063674927, + "learning_rate": 8.623265650935234e-05, + "loss": 0.0293, + "step": 2800 + }, + { + "epoch": 1.1190760653126244, + "grad_norm": 0.4102509915828705, + "learning_rate": 8.611851571145456e-05, + "loss": 0.0311, + "step": 2810 + }, + { + "epoch": 1.1230585424133812, + "grad_norm": 0.5217996835708618, + "learning_rate": 8.600397992725566e-05, + "loss": 0.0248, + "step": 2820 + }, + { + "epoch": 1.1270410195141378, + "grad_norm": 0.5519301295280457, + "learning_rate": 8.588905040930061e-05, + "loss": 0.0314, + "step": 2830 + }, + { + "epoch": 1.1310234966148944, + "grad_norm": 0.43869367241859436, + "learning_rate": 8.577372841444022e-05, + "loss": 0.0289, + "step": 2840 + }, + { + "epoch": 1.135005973715651, + "grad_norm": 0.4673241078853607, + "learning_rate": 8.565801520381736e-05, + "loss": 0.026, + "step": 2850 + }, + { + "epoch": 1.1389884508164079, + "grad_norm": 0.4510667622089386, + "learning_rate": 8.554191204285313e-05, + "loss": 0.0319, + "step": 2860 + }, + { + "epoch": 1.1429709279171645, + "grad_norm": 0.473105788230896, + "learning_rate": 8.542542020123315e-05, + "loss": 0.032, + "step": 2870 + }, + { + "epoch": 1.146953405017921, + "grad_norm": 0.4328536093235016, + "learning_rate": 8.530854095289347e-05, + "loss": 0.029, + "step": 2880 + }, + { + "epoch": 1.1509358821186777, + "grad_norm": 0.45955684781074524, + "learning_rate": 8.519127557600688e-05, + "loss": 0.0274, + "step": 2890 + }, + { + "epoch": 1.1549183592194345, + "grad_norm": 0.3034651577472687, + "learning_rate": 8.507362535296871e-05, + "loss": 0.0286, + "step": 2900 + }, + { + "epoch": 1.1589008363201911, + "grad_norm": 0.6441288590431213, + "learning_rate": 8.495559157038299e-05, + "loss": 0.0377, + "step": 2910 + }, + { + "epoch": 1.1628833134209478, + "grad_norm": 0.43017473816871643, + "learning_rate": 8.483717551904823e-05, + "loss": 0.0297, + "step": 2920 + }, + { + "epoch": 1.1668657905217046, + "grad_norm": 0.5794181227684021, + "learning_rate": 8.47183784939434e-05, + "loss": 0.0281, + "step": 2930 + }, + { + "epoch": 1.1708482676224612, + "grad_norm": 0.32613155245780945, + "learning_rate": 8.459920179421374e-05, + "loss": 0.0324, + "step": 2940 + }, + { + "epoch": 1.1748307447232178, + "grad_norm": 0.514627993106842, + "learning_rate": 8.447964672315656e-05, + "loss": 0.0275, + "step": 2950 + }, + { + "epoch": 1.1788132218239746, + "grad_norm": 0.30379730463027954, + "learning_rate": 8.435971458820692e-05, + "loss": 0.0322, + "step": 2960 + }, + { + "epoch": 1.1827956989247312, + "grad_norm": 0.5878794193267822, + "learning_rate": 8.423940670092345e-05, + "loss": 0.0318, + "step": 2970 + }, + { + "epoch": 1.1867781760254879, + "grad_norm": 0.3879925012588501, + "learning_rate": 8.411872437697394e-05, + "loss": 0.0323, + "step": 2980 + }, + { + "epoch": 1.1907606531262445, + "grad_norm": 0.2640171945095062, + "learning_rate": 8.399766893612096e-05, + "loss": 0.0265, + "step": 2990 + }, + { + "epoch": 1.194743130227001, + "grad_norm": 0.4299219846725464, + "learning_rate": 8.38762417022074e-05, + "loss": 0.0312, + "step": 3000 + }, + { + "epoch": 1.198725607327758, + "grad_norm": 0.3073621690273285, + "learning_rate": 8.375444400314204e-05, + "loss": 0.0253, + "step": 3010 + }, + { + "epoch": 1.2027080844285145, + "grad_norm": 0.26146814227104187, + "learning_rate": 8.3632277170885e-05, + "loss": 0.0312, + "step": 3020 + }, + { + "epoch": 1.2066905615292711, + "grad_norm": 0.2975267767906189, + "learning_rate": 8.350974254143318e-05, + "loss": 0.0271, + "step": 3030 + }, + { + "epoch": 1.210673038630028, + "grad_norm": 0.20422956347465515, + "learning_rate": 8.338684145480566e-05, + "loss": 0.0259, + "step": 3040 + }, + { + "epoch": 1.2146555157307846, + "grad_norm": 0.31191202998161316, + "learning_rate": 8.326357525502904e-05, + "loss": 0.0304, + "step": 3050 + }, + { + "epoch": 1.2186379928315412, + "grad_norm": 0.5126979947090149, + "learning_rate": 8.313994529012273e-05, + "loss": 0.0294, + "step": 3060 + }, + { + "epoch": 1.222620469932298, + "grad_norm": 0.3219705820083618, + "learning_rate": 8.301595291208422e-05, + "loss": 0.0305, + "step": 3070 + }, + { + "epoch": 1.2266029470330546, + "grad_norm": 0.4278619587421417, + "learning_rate": 8.289159947687427e-05, + "loss": 0.0297, + "step": 3080 + }, + { + "epoch": 1.2305854241338112, + "grad_norm": 0.5774158239364624, + "learning_rate": 8.276688634440216e-05, + "loss": 0.0296, + "step": 3090 + }, + { + "epoch": 1.2345679012345678, + "grad_norm": 0.5146026015281677, + "learning_rate": 8.26418148785107e-05, + "loss": 0.0311, + "step": 3100 + }, + { + "epoch": 1.2385503783353247, + "grad_norm": 0.347504198551178, + "learning_rate": 8.251638644696141e-05, + "loss": 0.0345, + "step": 3110 + }, + { + "epoch": 1.2425328554360813, + "grad_norm": 0.5153434872627258, + "learning_rate": 8.23906024214195e-05, + "loss": 0.0276, + "step": 3120 + }, + { + "epoch": 1.2465153325368379, + "grad_norm": 0.31597134470939636, + "learning_rate": 8.226446417743897e-05, + "loss": 0.0343, + "step": 3130 + }, + { + "epoch": 1.2504978096375945, + "grad_norm": 0.4005573093891144, + "learning_rate": 8.213797309444742e-05, + "loss": 0.0294, + "step": 3140 + }, + { + "epoch": 1.2544802867383513, + "grad_norm": 0.3009648025035858, + "learning_rate": 8.201113055573105e-05, + "loss": 0.0287, + "step": 3150 + }, + { + "epoch": 1.258462763839108, + "grad_norm": 0.6014096140861511, + "learning_rate": 8.188393794841958e-05, + "loss": 0.0261, + "step": 3160 + }, + { + "epoch": 1.2624452409398645, + "grad_norm": 0.38871604204177856, + "learning_rate": 8.175639666347094e-05, + "loss": 0.0316, + "step": 3170 + }, + { + "epoch": 1.2664277180406214, + "grad_norm": 0.4298296570777893, + "learning_rate": 8.162850809565623e-05, + "loss": 0.0248, + "step": 3180 + }, + { + "epoch": 1.270410195141378, + "grad_norm": 0.3726460039615631, + "learning_rate": 8.150027364354431e-05, + "loss": 0.0312, + "step": 3190 + }, + { + "epoch": 1.2743926722421346, + "grad_norm": 0.5679003000259399, + "learning_rate": 8.137169470948662e-05, + "loss": 0.0346, + "step": 3200 + }, + { + "epoch": 1.2783751493428912, + "grad_norm": 0.3676661252975464, + "learning_rate": 8.124277269960179e-05, + "loss": 0.0298, + "step": 3210 + }, + { + "epoch": 1.2823576264436478, + "grad_norm": 0.34625566005706787, + "learning_rate": 8.111350902376023e-05, + "loss": 0.0276, + "step": 3220 + }, + { + "epoch": 1.2863401035444046, + "grad_norm": 0.37914222478866577, + "learning_rate": 8.098390509556883e-05, + "loss": 0.028, + "step": 3230 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 0.6115908622741699, + "learning_rate": 8.085396233235536e-05, + "loss": 0.027, + "step": 3240 + }, + { + "epoch": 1.2943050577459179, + "grad_norm": 0.3943430781364441, + "learning_rate": 8.072368215515306e-05, + "loss": 0.0264, + "step": 3250 + }, + { + "epoch": 1.2982875348466747, + "grad_norm": 0.4377286434173584, + "learning_rate": 8.059306598868506e-05, + "loss": 0.0334, + "step": 3260 + }, + { + "epoch": 1.3022700119474313, + "grad_norm": 0.28060171008110046, + "learning_rate": 8.046211526134888e-05, + "loss": 0.0284, + "step": 3270 + }, + { + "epoch": 1.306252489048188, + "grad_norm": 0.4140307605266571, + "learning_rate": 8.033083140520065e-05, + "loss": 0.027, + "step": 3280 + }, + { + "epoch": 1.3102349661489447, + "grad_norm": 0.334888756275177, + "learning_rate": 8.019921585593962e-05, + "loss": 0.0295, + "step": 3290 + }, + { + "epoch": 1.3142174432497014, + "grad_norm": 0.5044397115707397, + "learning_rate": 8.006727005289232e-05, + "loss": 0.0239, + "step": 3300 + }, + { + "epoch": 1.318199920350458, + "grad_norm": 0.39227598905563354, + "learning_rate": 7.993499543899692e-05, + "loss": 0.029, + "step": 3310 + }, + { + "epoch": 1.3221823974512146, + "grad_norm": 0.5009192824363708, + "learning_rate": 7.980239346078742e-05, + "loss": 0.0276, + "step": 3320 + }, + { + "epoch": 1.3261648745519714, + "grad_norm": 0.33442339301109314, + "learning_rate": 7.966946556837778e-05, + "loss": 0.025, + "step": 3330 + }, + { + "epoch": 1.330147351652728, + "grad_norm": 0.44179999828338623, + "learning_rate": 7.953621321544616e-05, + "loss": 0.0292, + "step": 3340 + }, + { + "epoch": 1.3341298287534846, + "grad_norm": 0.48963797092437744, + "learning_rate": 7.940263785921896e-05, + "loss": 0.0287, + "step": 3350 + }, + { + "epoch": 1.3381123058542412, + "grad_norm": 0.35747164487838745, + "learning_rate": 7.926874096045482e-05, + "loss": 0.0257, + "step": 3360 + }, + { + "epoch": 1.342094782954998, + "grad_norm": 0.6534529328346252, + "learning_rate": 7.913452398342881e-05, + "loss": 0.036, + "step": 3370 + }, + { + "epoch": 1.3460772600557547, + "grad_norm": 0.4266543686389923, + "learning_rate": 7.89999883959163e-05, + "loss": 0.0307, + "step": 3380 + }, + { + "epoch": 1.3500597371565113, + "grad_norm": 0.5537866950035095, + "learning_rate": 7.886513566917687e-05, + "loss": 0.0307, + "step": 3390 + }, + { + "epoch": 1.3540422142572681, + "grad_norm": 0.35446301102638245, + "learning_rate": 7.872996727793838e-05, + "loss": 0.0323, + "step": 3400 + }, + { + "epoch": 1.3580246913580247, + "grad_norm": 0.4526813328266144, + "learning_rate": 7.859448470038069e-05, + "loss": 0.0275, + "step": 3410 + }, + { + "epoch": 1.3620071684587813, + "grad_norm": 0.49604639410972595, + "learning_rate": 7.845868941811956e-05, + "loss": 0.0317, + "step": 3420 + }, + { + "epoch": 1.3659896455595382, + "grad_norm": 0.3144626319408417, + "learning_rate": 7.832258291619043e-05, + "loss": 0.0276, + "step": 3430 + }, + { + "epoch": 1.3699721226602948, + "grad_norm": 0.5718449354171753, + "learning_rate": 7.81861666830322e-05, + "loss": 0.0261, + "step": 3440 + }, + { + "epoch": 1.3739545997610514, + "grad_norm": 0.3567497134208679, + "learning_rate": 7.804944221047097e-05, + "loss": 0.027, + "step": 3450 + }, + { + "epoch": 1.377937076861808, + "grad_norm": 0.5491267442703247, + "learning_rate": 7.791241099370364e-05, + "loss": 0.033, + "step": 3460 + }, + { + "epoch": 1.3819195539625646, + "grad_norm": 0.46909114718437195, + "learning_rate": 7.777507453128163e-05, + "loss": 0.0298, + "step": 3470 + }, + { + "epoch": 1.3859020310633214, + "grad_norm": 0.4308125376701355, + "learning_rate": 7.763743432509451e-05, + "loss": 0.0278, + "step": 3480 + }, + { + "epoch": 1.389884508164078, + "grad_norm": 0.4042797088623047, + "learning_rate": 7.749949188035353e-05, + "loss": 0.0312, + "step": 3490 + }, + { + "epoch": 1.3938669852648347, + "grad_norm": 0.4012243151664734, + "learning_rate": 7.736124870557516e-05, + "loss": 0.0296, + "step": 3500 + }, + { + "epoch": 1.3978494623655915, + "grad_norm": 0.31076422333717346, + "learning_rate": 7.722270631256459e-05, + "loss": 0.0306, + "step": 3510 + }, + { + "epoch": 1.401831939466348, + "grad_norm": 0.4105532467365265, + "learning_rate": 7.708386621639925e-05, + "loss": 0.0262, + "step": 3520 + }, + { + "epoch": 1.4058144165671047, + "grad_norm": 0.4460810124874115, + "learning_rate": 7.694472993541219e-05, + "loss": 0.0269, + "step": 3530 + }, + { + "epoch": 1.4097968936678615, + "grad_norm": 0.4327501952648163, + "learning_rate": 7.680529899117547e-05, + "loss": 0.0313, + "step": 3540 + }, + { + "epoch": 1.4137793707686181, + "grad_norm": 0.4426930248737335, + "learning_rate": 7.666557490848358e-05, + "loss": 0.0289, + "step": 3550 + }, + { + "epoch": 1.4177618478693748, + "grad_norm": 0.4433678388595581, + "learning_rate": 7.65255592153367e-05, + "loss": 0.0307, + "step": 3560 + }, + { + "epoch": 1.4217443249701314, + "grad_norm": 0.39277946949005127, + "learning_rate": 7.638525344292402e-05, + "loss": 0.0321, + "step": 3570 + }, + { + "epoch": 1.425726802070888, + "grad_norm": 0.4349759817123413, + "learning_rate": 7.624465912560697e-05, + "loss": 0.0319, + "step": 3580 + }, + { + "epoch": 1.4297092791716448, + "grad_norm": 0.36243054270744324, + "learning_rate": 7.610377780090249e-05, + "loss": 0.025, + "step": 3590 + }, + { + "epoch": 1.4336917562724014, + "grad_norm": 0.23596417903900146, + "learning_rate": 7.596261100946618e-05, + "loss": 0.0274, + "step": 3600 + }, + { + "epoch": 1.437674233373158, + "grad_norm": 0.3828240633010864, + "learning_rate": 7.582116029507542e-05, + "loss": 0.0259, + "step": 3610 + }, + { + "epoch": 1.4416567104739149, + "grad_norm": 0.4790317714214325, + "learning_rate": 7.56794272046126e-05, + "loss": 0.0278, + "step": 3620 + }, + { + "epoch": 1.4456391875746715, + "grad_norm": 0.46134695410728455, + "learning_rate": 7.55374132880481e-05, + "loss": 0.0298, + "step": 3630 + }, + { + "epoch": 1.449621664675428, + "grad_norm": 0.4513108730316162, + "learning_rate": 7.539512009842333e-05, + "loss": 0.0313, + "step": 3640 + }, + { + "epoch": 1.453604141776185, + "grad_norm": 0.5272055268287659, + "learning_rate": 7.525254919183382e-05, + "loss": 0.0283, + "step": 3650 + }, + { + "epoch": 1.4575866188769415, + "grad_norm": 0.43485143780708313, + "learning_rate": 7.510970212741215e-05, + "loss": 0.0272, + "step": 3660 + }, + { + "epoch": 1.4615690959776981, + "grad_norm": 0.44522616267204285, + "learning_rate": 7.496658046731096e-05, + "loss": 0.0281, + "step": 3670 + }, + { + "epoch": 1.4655515730784547, + "grad_norm": 0.7030194997787476, + "learning_rate": 7.482318577668578e-05, + "loss": 0.0336, + "step": 3680 + }, + { + "epoch": 1.4695340501792113, + "grad_norm": 0.47834673523902893, + "learning_rate": 7.467951962367796e-05, + "loss": 0.0276, + "step": 3690 + }, + { + "epoch": 1.4735165272799682, + "grad_norm": 0.4326513409614563, + "learning_rate": 7.453558357939755e-05, + "loss": 0.0268, + "step": 3700 + }, + { + "epoch": 1.4774990043807248, + "grad_norm": 0.4779656231403351, + "learning_rate": 7.439137921790606e-05, + "loss": 0.0322, + "step": 3710 + }, + { + "epoch": 1.4814814814814814, + "grad_norm": 0.5998985767364502, + "learning_rate": 7.42469081161993e-05, + "loss": 0.0257, + "step": 3720 + }, + { + "epoch": 1.4854639585822382, + "grad_norm": 0.44799843430519104, + "learning_rate": 7.410217185419006e-05, + "loss": 0.0235, + "step": 3730 + }, + { + "epoch": 1.4894464356829948, + "grad_norm": 0.335964560508728, + "learning_rate": 7.395717201469095e-05, + "loss": 0.0286, + "step": 3740 + }, + { + "epoch": 1.4934289127837514, + "grad_norm": 0.5583806037902832, + "learning_rate": 7.381191018339696e-05, + "loss": 0.0292, + "step": 3750 + }, + { + "epoch": 1.4974113898845083, + "grad_norm": 0.40853527188301086, + "learning_rate": 7.36663879488682e-05, + "loss": 0.024, + "step": 3760 + }, + { + "epoch": 1.5013938669852647, + "grad_norm": 0.5366830825805664, + "learning_rate": 7.352060690251254e-05, + "loss": 0.0278, + "step": 3770 + }, + { + "epoch": 1.5053763440860215, + "grad_norm": 0.5075726509094238, + "learning_rate": 7.337456863856811e-05, + "loss": 0.031, + "step": 3780 + }, + { + "epoch": 1.5093588211867783, + "grad_norm": 0.4533558487892151, + "learning_rate": 7.3228274754086e-05, + "loss": 0.0232, + "step": 3790 + }, + { + "epoch": 1.5133412982875347, + "grad_norm": 0.4715867340564728, + "learning_rate": 7.308172684891267e-05, + "loss": 0.0319, + "step": 3800 + }, + { + "epoch": 1.5173237753882916, + "grad_norm": 0.2563737630844116, + "learning_rate": 7.293492652567255e-05, + "loss": 0.0239, + "step": 3810 + }, + { + "epoch": 1.5213062524890482, + "grad_norm": 0.3013695478439331, + "learning_rate": 7.278787538975043e-05, + "loss": 0.0302, + "step": 3820 + }, + { + "epoch": 1.5252887295898048, + "grad_norm": 0.39960938692092896, + "learning_rate": 7.2640575049274e-05, + "loss": 0.0251, + "step": 3830 + }, + { + "epoch": 1.5292712066905616, + "grad_norm": 0.380015105009079, + "learning_rate": 7.249302711509616e-05, + "loss": 0.0231, + "step": 3840 + }, + { + "epoch": 1.5332536837913182, + "grad_norm": 0.2648374140262604, + "learning_rate": 7.23452332007775e-05, + "loss": 0.0225, + "step": 3850 + }, + { + "epoch": 1.5372361608920748, + "grad_norm": 0.32741981744766235, + "learning_rate": 7.219719492256858e-05, + "loss": 0.0272, + "step": 3860 + }, + { + "epoch": 1.5412186379928317, + "grad_norm": 0.5281572341918945, + "learning_rate": 7.20489138993923e-05, + "loss": 0.025, + "step": 3870 + }, + { + "epoch": 1.5452011150935883, + "grad_norm": 0.3067561388015747, + "learning_rate": 7.190039175282614e-05, + "loss": 0.0261, + "step": 3880 + }, + { + "epoch": 1.5491835921943449, + "grad_norm": 0.4421009421348572, + "learning_rate": 7.175163010708455e-05, + "loss": 0.0245, + "step": 3890 + }, + { + "epoch": 1.5531660692951017, + "grad_norm": 0.3433239758014679, + "learning_rate": 7.1602630589001e-05, + "loss": 0.027, + "step": 3900 + }, + { + "epoch": 1.557148546395858, + "grad_norm": 0.30050766468048096, + "learning_rate": 7.14533948280104e-05, + "loss": 0.0269, + "step": 3910 + }, + { + "epoch": 1.561131023496615, + "grad_norm": 0.3128851056098938, + "learning_rate": 7.130392445613109e-05, + "loss": 0.03, + "step": 3920 + }, + { + "epoch": 1.5651135005973715, + "grad_norm": 0.3643544912338257, + "learning_rate": 7.115422110794711e-05, + "loss": 0.0278, + "step": 3930 + }, + { + "epoch": 1.5690959776981281, + "grad_norm": 0.4426794648170471, + "learning_rate": 7.100428642059033e-05, + "loss": 0.0303, + "step": 3940 + }, + { + "epoch": 1.573078454798885, + "grad_norm": 0.3874496817588806, + "learning_rate": 7.08541220337224e-05, + "loss": 0.0277, + "step": 3950 + }, + { + "epoch": 1.5770609318996416, + "grad_norm": 0.3397146761417389, + "learning_rate": 7.070372958951706e-05, + "loss": 0.0271, + "step": 3960 + }, + { + "epoch": 1.5810434090003982, + "grad_norm": 0.6062551736831665, + "learning_rate": 7.055311073264194e-05, + "loss": 0.0334, + "step": 3970 + }, + { + "epoch": 1.585025886101155, + "grad_norm": 0.2893720269203186, + "learning_rate": 7.040226711024077e-05, + "loss": 0.0276, + "step": 3980 + }, + { + "epoch": 1.5890083632019116, + "grad_norm": 0.28936243057250977, + "learning_rate": 7.02512003719152e-05, + "loss": 0.0239, + "step": 3990 + }, + { + "epoch": 1.5929908403026682, + "grad_norm": 0.4626624286174774, + "learning_rate": 7.00999121697069e-05, + "loss": 0.0304, + "step": 4000 + }, + { + "epoch": 1.596973317403425, + "grad_norm": 0.4734528362751007, + "learning_rate": 6.99484041580794e-05, + "loss": 0.0228, + "step": 4010 + }, + { + "epoch": 1.6009557945041815, + "grad_norm": 0.6309609413146973, + "learning_rate": 6.979667799390004e-05, + "loss": 0.026, + "step": 4020 + }, + { + "epoch": 1.6049382716049383, + "grad_norm": 0.4279467463493347, + "learning_rate": 6.964473533642185e-05, + "loss": 0.0298, + "step": 4030 + }, + { + "epoch": 1.608920748705695, + "grad_norm": 0.29877039790153503, + "learning_rate": 6.949257784726539e-05, + "loss": 0.0328, + "step": 4040 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 0.48857632279396057, + "learning_rate": 6.934020719040056e-05, + "loss": 0.0262, + "step": 4050 + }, + { + "epoch": 1.6168857029072083, + "grad_norm": 0.5152528882026672, + "learning_rate": 6.918762503212848e-05, + "loss": 0.0283, + "step": 4060 + }, + { + "epoch": 1.620868180007965, + "grad_norm": 0.3721228241920471, + "learning_rate": 6.903483304106319e-05, + "loss": 0.0265, + "step": 4070 + }, + { + "epoch": 1.6248506571087216, + "grad_norm": 0.3533932864665985, + "learning_rate": 6.888183288811341e-05, + "loss": 0.0258, + "step": 4080 + }, + { + "epoch": 1.6288331342094784, + "grad_norm": 0.2944384217262268, + "learning_rate": 6.87286262464643e-05, + "loss": 0.0244, + "step": 4090 + }, + { + "epoch": 1.632815611310235, + "grad_norm": 0.2960841953754425, + "learning_rate": 6.857521479155915e-05, + "loss": 0.0287, + "step": 4100 + }, + { + "epoch": 1.6367980884109916, + "grad_norm": 0.494831383228302, + "learning_rate": 6.842160020108104e-05, + "loss": 0.026, + "step": 4110 + }, + { + "epoch": 1.6407805655117484, + "grad_norm": 0.652524471282959, + "learning_rate": 6.826778415493455e-05, + "loss": 0.0254, + "step": 4120 + }, + { + "epoch": 1.6447630426125048, + "grad_norm": 0.315049409866333, + "learning_rate": 6.811376833522729e-05, + "loss": 0.0251, + "step": 4130 + }, + { + "epoch": 1.6487455197132617, + "grad_norm": 0.3198871910572052, + "learning_rate": 6.795955442625159e-05, + "loss": 0.0277, + "step": 4140 + }, + { + "epoch": 1.6527279968140183, + "grad_norm": 0.523373544216156, + "learning_rate": 6.780514411446608e-05, + "loss": 0.0255, + "step": 4150 + }, + { + "epoch": 1.6567104739147749, + "grad_norm": 0.4847145080566406, + "learning_rate": 6.765053908847716e-05, + "loss": 0.0197, + "step": 4160 + }, + { + "epoch": 1.6606929510155317, + "grad_norm": 0.4315938353538513, + "learning_rate": 6.749574103902064e-05, + "loss": 0.027, + "step": 4170 + }, + { + "epoch": 1.6646754281162883, + "grad_norm": 0.3840107023715973, + "learning_rate": 6.734075165894317e-05, + "loss": 0.0286, + "step": 4180 + }, + { + "epoch": 1.668657905217045, + "grad_norm": 0.42311540246009827, + "learning_rate": 6.71855726431838e-05, + "loss": 0.028, + "step": 4190 + }, + { + "epoch": 1.6726403823178018, + "grad_norm": 0.38411083817481995, + "learning_rate": 6.703020568875538e-05, + "loss": 0.0263, + "step": 4200 + }, + { + "epoch": 1.6766228594185584, + "grad_norm": 0.368691623210907, + "learning_rate": 6.687465249472603e-05, + "loss": 0.0266, + "step": 4210 + }, + { + "epoch": 1.680605336519315, + "grad_norm": 0.5589401125907898, + "learning_rate": 6.671891476220055e-05, + "loss": 0.0255, + "step": 4220 + }, + { + "epoch": 1.6845878136200718, + "grad_norm": 0.5339823365211487, + "learning_rate": 6.656299419430183e-05, + "loss": 0.0248, + "step": 4230 + }, + { + "epoch": 1.6885702907208282, + "grad_norm": 0.3141709566116333, + "learning_rate": 6.640689249615223e-05, + "loss": 0.0261, + "step": 4240 + }, + { + "epoch": 1.692552767821585, + "grad_norm": 0.31322765350341797, + "learning_rate": 6.625061137485491e-05, + "loss": 0.0275, + "step": 4250 + }, + { + "epoch": 1.6965352449223416, + "grad_norm": 0.35308682918548584, + "learning_rate": 6.609415253947517e-05, + "loss": 0.0288, + "step": 4260 + }, + { + "epoch": 1.7005177220230983, + "grad_norm": 0.32278379797935486, + "learning_rate": 6.593751770102178e-05, + "loss": 0.0214, + "step": 4270 + }, + { + "epoch": 1.704500199123855, + "grad_norm": 0.2799319922924042, + "learning_rate": 6.578070857242823e-05, + "loss": 0.0246, + "step": 4280 + }, + { + "epoch": 1.7084826762246117, + "grad_norm": 0.4078690707683563, + "learning_rate": 6.562372686853402e-05, + "loss": 0.022, + "step": 4290 + }, + { + "epoch": 1.7124651533253683, + "grad_norm": 0.32824915647506714, + "learning_rate": 6.546657430606593e-05, + "loss": 0.0226, + "step": 4300 + }, + { + "epoch": 1.7164476304261251, + "grad_norm": 0.4191490411758423, + "learning_rate": 6.530925260361918e-05, + "loss": 0.0237, + "step": 4310 + }, + { + "epoch": 1.7204301075268817, + "grad_norm": 0.37340426445007324, + "learning_rate": 6.515176348163871e-05, + "loss": 0.026, + "step": 4320 + }, + { + "epoch": 1.7244125846276384, + "grad_norm": 0.44565045833587646, + "learning_rate": 6.499410866240032e-05, + "loss": 0.0217, + "step": 4330 + }, + { + "epoch": 1.7283950617283952, + "grad_norm": 0.37896549701690674, + "learning_rate": 6.48362898699919e-05, + "loss": 0.0215, + "step": 4340 + }, + { + "epoch": 1.7323775388291516, + "grad_norm": 0.42717358469963074, + "learning_rate": 6.467830883029443e-05, + "loss": 0.0241, + "step": 4350 + }, + { + "epoch": 1.7363600159299084, + "grad_norm": 0.5169128179550171, + "learning_rate": 6.452016727096326e-05, + "loss": 0.0244, + "step": 4360 + }, + { + "epoch": 1.7403424930306652, + "grad_norm": 0.4041356146335602, + "learning_rate": 6.436186692140916e-05, + "loss": 0.0234, + "step": 4370 + }, + { + "epoch": 1.7443249701314216, + "grad_norm": 0.41365042328834534, + "learning_rate": 6.420340951277938e-05, + "loss": 0.0214, + "step": 4380 + }, + { + "epoch": 1.7483074472321785, + "grad_norm": 0.5286877155303955, + "learning_rate": 6.404479677793874e-05, + "loss": 0.0259, + "step": 4390 + }, + { + "epoch": 1.752289924332935, + "grad_norm": 0.3863738775253296, + "learning_rate": 6.388603045145075e-05, + "loss": 0.0271, + "step": 4400 + }, + { + "epoch": 1.7562724014336917, + "grad_norm": 0.3407500088214874, + "learning_rate": 6.372711226955843e-05, + "loss": 0.0248, + "step": 4410 + }, + { + "epoch": 1.7602548785344485, + "grad_norm": 0.4132188558578491, + "learning_rate": 6.356804397016564e-05, + "loss": 0.0232, + "step": 4420 + }, + { + "epoch": 1.7642373556352051, + "grad_norm": 0.5538100004196167, + "learning_rate": 6.340882729281779e-05, + "loss": 0.0257, + "step": 4430 + }, + { + "epoch": 1.7682198327359617, + "grad_norm": 0.5813969969749451, + "learning_rate": 6.324946397868294e-05, + "loss": 0.0289, + "step": 4440 + }, + { + "epoch": 1.7722023098367186, + "grad_norm": 0.381994366645813, + "learning_rate": 6.308995577053276e-05, + "loss": 0.0241, + "step": 4450 + }, + { + "epoch": 1.776184786937475, + "grad_norm": 0.49612873792648315, + "learning_rate": 6.293030441272347e-05, + "loss": 0.0267, + "step": 4460 + }, + { + "epoch": 1.7801672640382318, + "grad_norm": 0.5249873995780945, + "learning_rate": 6.277051165117677e-05, + "loss": 0.0246, + "step": 4470 + }, + { + "epoch": 1.7841497411389886, + "grad_norm": 0.3832807242870331, + "learning_rate": 6.261057923336064e-05, + "loss": 0.0267, + "step": 4480 + }, + { + "epoch": 1.788132218239745, + "grad_norm": 0.31773999333381653, + "learning_rate": 6.245050890827042e-05, + "loss": 0.0276, + "step": 4490 + }, + { + "epoch": 1.7921146953405018, + "grad_norm": 0.275312215089798, + "learning_rate": 6.229030242640952e-05, + "loss": 0.0238, + "step": 4500 + }, + { + "epoch": 1.7960971724412584, + "grad_norm": 0.5737529397010803, + "learning_rate": 6.212996153977037e-05, + "loss": 0.0308, + "step": 4510 + }, + { + "epoch": 1.800079649542015, + "grad_norm": 0.33575618267059326, + "learning_rate": 6.196948800181523e-05, + "loss": 0.0258, + "step": 4520 + }, + { + "epoch": 1.8040621266427719, + "grad_norm": 0.6271135807037354, + "learning_rate": 6.180888356745695e-05, + "loss": 0.0267, + "step": 4530 + }, + { + "epoch": 1.8080446037435285, + "grad_norm": 0.5151987075805664, + "learning_rate": 6.164814999303995e-05, + "loss": 0.0239, + "step": 4540 + }, + { + "epoch": 1.812027080844285, + "grad_norm": 0.26632851362228394, + "learning_rate": 6.148728903632081e-05, + "loss": 0.0222, + "step": 4550 + }, + { + "epoch": 1.816009557945042, + "grad_norm": 0.4331364929676056, + "learning_rate": 6.132630245644921e-05, + "loss": 0.0226, + "step": 4560 + }, + { + "epoch": 1.8199920350457985, + "grad_norm": 0.26644977927207947, + "learning_rate": 6.116519201394857e-05, + "loss": 0.0242, + "step": 4570 + }, + { + "epoch": 1.8239745121465551, + "grad_norm": 0.45340025424957275, + "learning_rate": 6.10039594706969e-05, + "loss": 0.0233, + "step": 4580 + }, + { + "epoch": 1.827956989247312, + "grad_norm": 0.3398999869823456, + "learning_rate": 6.084260658990744e-05, + "loss": 0.0226, + "step": 4590 + }, + { + "epoch": 1.8319394663480684, + "grad_norm": 0.6932306885719299, + "learning_rate": 6.068113513610943e-05, + "loss": 0.0239, + "step": 4600 + }, + { + "epoch": 1.8359219434488252, + "grad_norm": 0.23555903136730194, + "learning_rate": 6.0519546875128876e-05, + "loss": 0.0249, + "step": 4610 + }, + { + "epoch": 1.8399044205495818, + "grad_norm": 0.49692243337631226, + "learning_rate": 6.035784357406906e-05, + "loss": 0.0241, + "step": 4620 + }, + { + "epoch": 1.8438868976503384, + "grad_norm": 0.32976606488227844, + "learning_rate": 6.01960270012914e-05, + "loss": 0.0237, + "step": 4630 + }, + { + "epoch": 1.8478693747510953, + "grad_norm": 0.4834267199039459, + "learning_rate": 6.003409892639599e-05, + "loss": 0.027, + "step": 4640 + }, + { + "epoch": 1.8518518518518519, + "grad_norm": 0.4596833884716034, + "learning_rate": 5.9872061120202336e-05, + "loss": 0.0246, + "step": 4650 + }, + { + "epoch": 1.8558343289526085, + "grad_norm": 0.427120178937912, + "learning_rate": 5.9709915354729914e-05, + "loss": 0.0269, + "step": 4660 + }, + { + "epoch": 1.8598168060533653, + "grad_norm": 0.2686680257320404, + "learning_rate": 5.9547663403178824e-05, + "loss": 0.0239, + "step": 4670 + }, + { + "epoch": 1.863799283154122, + "grad_norm": 0.3082379698753357, + "learning_rate": 5.9385307039910445e-05, + "loss": 0.0204, + "step": 4680 + }, + { + "epoch": 1.8677817602548785, + "grad_norm": 0.34263017773628235, + "learning_rate": 5.922284804042792e-05, + "loss": 0.0249, + "step": 4690 + }, + { + "epoch": 1.8717642373556354, + "grad_norm": 0.23308919370174408, + "learning_rate": 5.906028818135687e-05, + "loss": 0.0248, + "step": 4700 + }, + { + "epoch": 1.8757467144563917, + "grad_norm": 0.29352062940597534, + "learning_rate": 5.889762924042585e-05, + "loss": 0.0231, + "step": 4710 + }, + { + "epoch": 1.8797291915571486, + "grad_norm": 0.45019692182540894, + "learning_rate": 5.873487299644699e-05, + "loss": 0.0265, + "step": 4720 + }, + { + "epoch": 1.8837116686579052, + "grad_norm": 0.4193218946456909, + "learning_rate": 5.857202122929649e-05, + "loss": 0.0228, + "step": 4730 + }, + { + "epoch": 1.8876941457586618, + "grad_norm": 0.5292001366615295, + "learning_rate": 5.840907571989518e-05, + "loss": 0.0218, + "step": 4740 + }, + { + "epoch": 1.8916766228594186, + "grad_norm": 0.36202308535575867, + "learning_rate": 5.824603825018904e-05, + "loss": 0.0229, + "step": 4750 + }, + { + "epoch": 1.8956590999601752, + "grad_norm": 0.2474525272846222, + "learning_rate": 5.808291060312975e-05, + "loss": 0.0259, + "step": 4760 + }, + { + "epoch": 1.8996415770609318, + "grad_norm": 0.23628737032413483, + "learning_rate": 5.7919694562655083e-05, + "loss": 0.0218, + "step": 4770 + }, + { + "epoch": 1.9036240541616887, + "grad_norm": 0.38689592480659485, + "learning_rate": 5.775639191366954e-05, + "loss": 0.0246, + "step": 4780 + }, + { + "epoch": 1.9076065312624453, + "grad_norm": 0.3524068593978882, + "learning_rate": 5.75930044420247e-05, + "loss": 0.0209, + "step": 4790 + }, + { + "epoch": 1.911589008363202, + "grad_norm": 0.3510373830795288, + "learning_rate": 5.74295339344998e-05, + "loss": 0.026, + "step": 4800 + }, + { + "epoch": 1.9155714854639587, + "grad_norm": 0.5862729549407959, + "learning_rate": 5.726598217878211e-05, + "loss": 0.0229, + "step": 4810 + }, + { + "epoch": 1.919553962564715, + "grad_norm": 0.47685012221336365, + "learning_rate": 5.71023509634474e-05, + "loss": 0.0229, + "step": 4820 + }, + { + "epoch": 1.923536439665472, + "grad_norm": 0.5108020901679993, + "learning_rate": 5.693864207794049e-05, + "loss": 0.0281, + "step": 4830 + }, + { + "epoch": 1.9275189167662286, + "grad_norm": 0.45045313239097595, + "learning_rate": 5.677485731255545e-05, + "loss": 0.0287, + "step": 4840 + }, + { + "epoch": 1.9315013938669852, + "grad_norm": 0.3624630868434906, + "learning_rate": 5.6610998458416296e-05, + "loss": 0.027, + "step": 4850 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 0.3359379768371582, + "learning_rate": 5.644706730745716e-05, + "loss": 0.0205, + "step": 4860 + }, + { + "epoch": 1.9394663480684986, + "grad_norm": 0.2658320963382721, + "learning_rate": 5.628306565240287e-05, + "loss": 0.0222, + "step": 4870 + }, + { + "epoch": 1.9434488251692552, + "grad_norm": 0.16451801359653473, + "learning_rate": 5.611899528674923e-05, + "loss": 0.0249, + "step": 4880 + }, + { + "epoch": 1.947431302270012, + "grad_norm": 0.24440331757068634, + "learning_rate": 5.595485800474349e-05, + "loss": 0.0217, + "step": 4890 + }, + { + "epoch": 1.9514137793707687, + "grad_norm": 0.34016168117523193, + "learning_rate": 5.579065560136467e-05, + "loss": 0.0253, + "step": 4900 + }, + { + "epoch": 1.9553962564715253, + "grad_norm": 0.47430235147476196, + "learning_rate": 5.562638987230392e-05, + "loss": 0.0239, + "step": 4910 + }, + { + "epoch": 1.959378733572282, + "grad_norm": 0.40641021728515625, + "learning_rate": 5.546206261394498e-05, + "loss": 0.0216, + "step": 4920 + }, + { + "epoch": 1.9633612106730385, + "grad_norm": 0.39244401454925537, + "learning_rate": 5.529767562334437e-05, + "loss": 0.0236, + "step": 4930 + }, + { + "epoch": 1.9673436877737953, + "grad_norm": 0.3444770276546478, + "learning_rate": 5.5133230698211926e-05, + "loss": 0.0229, + "step": 4940 + }, + { + "epoch": 1.971326164874552, + "grad_norm": 0.40012794733047485, + "learning_rate": 5.496872963689096e-05, + "loss": 0.0233, + "step": 4950 + }, + { + "epoch": 1.9753086419753085, + "grad_norm": 0.39745375514030457, + "learning_rate": 5.4804174238338756e-05, + "loss": 0.0205, + "step": 4960 + }, + { + "epoch": 1.9792911190760654, + "grad_norm": 0.36429905891418457, + "learning_rate": 5.463956630210678e-05, + "loss": 0.0272, + "step": 4970 + }, + { + "epoch": 1.983273596176822, + "grad_norm": 0.3775866627693176, + "learning_rate": 5.4474907628321046e-05, + "loss": 0.0254, + "step": 4980 + }, + { + "epoch": 1.9872560732775786, + "grad_norm": 0.2797946333885193, + "learning_rate": 5.431020001766244e-05, + "loss": 0.0232, + "step": 4990 + }, + { + "epoch": 1.9912385503783354, + "grad_norm": 0.31640321016311646, + "learning_rate": 5.4145445271346986e-05, + "loss": 0.0236, + "step": 5000 + }, + { + "epoch": 1.995221027479092, + "grad_norm": 0.25763505697250366, + "learning_rate": 5.398064519110622e-05, + "loss": 0.025, + "step": 5010 + }, + { + "epoch": 1.9992035045798486, + "grad_norm": 0.3182986080646515, + "learning_rate": 5.3815801579167394e-05, + "loss": 0.0231, + "step": 5020 + }, + { + "epoch": 2.0031859816806055, + "grad_norm": 0.2998727262020111, + "learning_rate": 5.365091623823382e-05, + "loss": 0.0228, + "step": 5030 + }, + { + "epoch": 2.007168458781362, + "grad_norm": 0.3551591634750366, + "learning_rate": 5.348599097146521e-05, + "loss": 0.0232, + "step": 5040 + }, + { + "epoch": 2.0111509358821187, + "grad_norm": 0.3020910620689392, + "learning_rate": 5.3321027582457836e-05, + "loss": 0.0207, + "step": 5050 + }, + { + "epoch": 2.0151334129828755, + "grad_norm": 0.19936051964759827, + "learning_rate": 5.315602787522491e-05, + "loss": 0.0226, + "step": 5060 + }, + { + "epoch": 2.019115890083632, + "grad_norm": 0.3585205078125, + "learning_rate": 5.299099365417678e-05, + "loss": 0.0198, + "step": 5070 + }, + { + "epoch": 2.0230983671843887, + "grad_norm": 0.3065052926540375, + "learning_rate": 5.2825926724101236e-05, + "loss": 0.0224, + "step": 5080 + }, + { + "epoch": 2.0270808442851456, + "grad_norm": 0.420714408159256, + "learning_rate": 5.26608288901438e-05, + "loss": 0.0227, + "step": 5090 + }, + { + "epoch": 2.031063321385902, + "grad_norm": 0.43053722381591797, + "learning_rate": 5.24957019577879e-05, + "loss": 0.025, + "step": 5100 + }, + { + "epoch": 2.035045798486659, + "grad_norm": 0.2843393385410309, + "learning_rate": 5.2330547732835266e-05, + "loss": 0.02, + "step": 5110 + }, + { + "epoch": 2.039028275587415, + "grad_norm": 0.43334928154945374, + "learning_rate": 5.2165368021385996e-05, + "loss": 0.027, + "step": 5120 + }, + { + "epoch": 2.043010752688172, + "grad_norm": 0.362897664308548, + "learning_rate": 5.200016462981897e-05, + "loss": 0.02, + "step": 5130 + }, + { + "epoch": 2.046993229788929, + "grad_norm": 0.23573912680149078, + "learning_rate": 5.1834939364772015e-05, + "loss": 0.0214, + "step": 5140 + }, + { + "epoch": 2.0509757068896852, + "grad_norm": 0.4564460217952728, + "learning_rate": 5.166969403312214e-05, + "loss": 0.0191, + "step": 5150 + }, + { + "epoch": 2.054958183990442, + "grad_norm": 0.3464418351650238, + "learning_rate": 5.1504430441965844e-05, + "loss": 0.0227, + "step": 5160 + }, + { + "epoch": 2.058940661091199, + "grad_norm": 0.31323158740997314, + "learning_rate": 5.133915039859923e-05, + "loss": 0.0165, + "step": 5170 + }, + { + "epoch": 2.0629231381919553, + "grad_norm": 0.3442908823490143, + "learning_rate": 5.1173855710498444e-05, + "loss": 0.0184, + "step": 5180 + }, + { + "epoch": 2.066905615292712, + "grad_norm": 0.34509140253067017, + "learning_rate": 5.100854818529967e-05, + "loss": 0.0221, + "step": 5190 + }, + { + "epoch": 2.070888092393469, + "grad_norm": 0.42281949520111084, + "learning_rate": 5.084322963077951e-05, + "loss": 0.0254, + "step": 5200 + }, + { + "epoch": 2.0748705694942253, + "grad_norm": 0.37458059191703796, + "learning_rate": 5.067790185483522e-05, + "loss": 0.0242, + "step": 5210 + }, + { + "epoch": 2.078853046594982, + "grad_norm": 0.32702142000198364, + "learning_rate": 5.0512566665464844e-05, + "loss": 0.022, + "step": 5220 + }, + { + "epoch": 2.0828355236957385, + "grad_norm": 0.3271017074584961, + "learning_rate": 5.034722587074755e-05, + "loss": 0.0221, + "step": 5230 + }, + { + "epoch": 2.0868180007964954, + "grad_norm": 0.24677887558937073, + "learning_rate": 5.018188127882375e-05, + "loss": 0.021, + "step": 5240 + }, + { + "epoch": 2.090800477897252, + "grad_norm": 0.46573442220687866, + "learning_rate": 5.0016534697875417e-05, + "loss": 0.0205, + "step": 5250 + }, + { + "epoch": 2.0947829549980086, + "grad_norm": 0.3796365261077881, + "learning_rate": 4.9851187936106294e-05, + "loss": 0.0234, + "step": 5260 + }, + { + "epoch": 2.0987654320987654, + "grad_norm": 0.43988627195358276, + "learning_rate": 4.968584280172206e-05, + "loss": 0.0215, + "step": 5270 + }, + { + "epoch": 2.1027479091995223, + "grad_norm": 0.33803004026412964, + "learning_rate": 4.95205011029106e-05, + "loss": 0.0259, + "step": 5280 + }, + { + "epoch": 2.1067303863002786, + "grad_norm": 0.41677144169807434, + "learning_rate": 4.935516464782227e-05, + "loss": 0.0228, + "step": 5290 + }, + { + "epoch": 2.1107128634010355, + "grad_norm": 0.42126816511154175, + "learning_rate": 4.918983524455003e-05, + "loss": 0.0203, + "step": 5300 + }, + { + "epoch": 2.1146953405017923, + "grad_norm": 0.37511423230171204, + "learning_rate": 4.9024514701109766e-05, + "loss": 0.0235, + "step": 5310 + }, + { + "epoch": 2.1186778176025487, + "grad_norm": 0.39171236753463745, + "learning_rate": 4.885920482542043e-05, + "loss": 0.0213, + "step": 5320 + }, + { + "epoch": 2.1226602947033055, + "grad_norm": 0.18626952171325684, + "learning_rate": 4.869390742528438e-05, + "loss": 0.0218, + "step": 5330 + }, + { + "epoch": 2.126642771804062, + "grad_norm": 0.3419274687767029, + "learning_rate": 4.852862430836744e-05, + "loss": 0.0223, + "step": 5340 + }, + { + "epoch": 2.1306252489048187, + "grad_norm": 0.33058205246925354, + "learning_rate": 4.836335728217933e-05, + "loss": 0.0207, + "step": 5350 + }, + { + "epoch": 2.1346077260055756, + "grad_norm": 0.3550313115119934, + "learning_rate": 4.819810815405379e-05, + "loss": 0.0242, + "step": 5360 + }, + { + "epoch": 2.138590203106332, + "grad_norm": 0.19980837404727936, + "learning_rate": 4.803287873112877e-05, + "loss": 0.0228, + "step": 5370 + }, + { + "epoch": 2.142572680207089, + "grad_norm": 0.31689023971557617, + "learning_rate": 4.786767082032681e-05, + "loss": 0.0233, + "step": 5380 + }, + { + "epoch": 2.1465551573078456, + "grad_norm": 0.41753360629081726, + "learning_rate": 4.77024862283351e-05, + "loss": 0.0203, + "step": 5390 + }, + { + "epoch": 2.150537634408602, + "grad_norm": 0.39587217569351196, + "learning_rate": 4.753732676158593e-05, + "loss": 0.0228, + "step": 5400 + }, + { + "epoch": 2.154520111509359, + "grad_norm": 0.2790881097316742, + "learning_rate": 4.737219422623672e-05, + "loss": 0.0209, + "step": 5410 + }, + { + "epoch": 2.1585025886101157, + "grad_norm": 0.30612117052078247, + "learning_rate": 4.720709042815044e-05, + "loss": 0.0196, + "step": 5420 + }, + { + "epoch": 2.162485065710872, + "grad_norm": 0.281535804271698, + "learning_rate": 4.704201717287578e-05, + "loss": 0.021, + "step": 5430 + }, + { + "epoch": 2.166467542811629, + "grad_norm": 0.3152558505535126, + "learning_rate": 4.6876976265627404e-05, + "loss": 0.0207, + "step": 5440 + }, + { + "epoch": 2.1704500199123853, + "grad_norm": 0.34031733870506287, + "learning_rate": 4.671196951126626e-05, + "loss": 0.0237, + "step": 5450 + }, + { + "epoch": 2.174432497013142, + "grad_norm": 0.3888844847679138, + "learning_rate": 4.654699871427971e-05, + "loss": 0.0228, + "step": 5460 + }, + { + "epoch": 2.178414974113899, + "grad_norm": 0.4517046809196472, + "learning_rate": 4.6382065678762034e-05, + "loss": 0.0207, + "step": 5470 + }, + { + "epoch": 2.1823974512146553, + "grad_norm": 0.47930458188056946, + "learning_rate": 4.6217172208394424e-05, + "loss": 0.0191, + "step": 5480 + }, + { + "epoch": 2.186379928315412, + "grad_norm": 0.45588383078575134, + "learning_rate": 4.605232010642549e-05, + "loss": 0.0183, + "step": 5490 + }, + { + "epoch": 2.190362405416169, + "grad_norm": 0.4268426299095154, + "learning_rate": 4.588751117565142e-05, + "loss": 0.0185, + "step": 5500 + }, + { + "epoch": 2.1943448825169254, + "grad_norm": 0.3531598746776581, + "learning_rate": 4.5722747218396214e-05, + "loss": 0.022, + "step": 5510 + }, + { + "epoch": 2.198327359617682, + "grad_norm": 0.40506526827812195, + "learning_rate": 4.5558030036492194e-05, + "loss": 0.0159, + "step": 5520 + }, + { + "epoch": 2.202309836718439, + "grad_norm": 0.40846410393714905, + "learning_rate": 4.539336143125999e-05, + "loss": 0.0242, + "step": 5530 + }, + { + "epoch": 2.2062923138191954, + "grad_norm": 0.32607802748680115, + "learning_rate": 4.522874320348916e-05, + "loss": 0.0191, + "step": 5540 + }, + { + "epoch": 2.2102747909199523, + "grad_norm": 0.2733158767223358, + "learning_rate": 4.506417715341821e-05, + "loss": 0.0162, + "step": 5550 + }, + { + "epoch": 2.2142572680207087, + "grad_norm": 0.33395612239837646, + "learning_rate": 4.489966508071511e-05, + "loss": 0.0218, + "step": 5560 + }, + { + "epoch": 2.2182397451214655, + "grad_norm": 0.41164472699165344, + "learning_rate": 4.4735208784457575e-05, + "loss": 0.0174, + "step": 5570 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.36547839641571045, + "learning_rate": 4.457081006311325e-05, + "loss": 0.0218, + "step": 5580 + }, + { + "epoch": 2.2262046993229787, + "grad_norm": 0.29824769496917725, + "learning_rate": 4.440647071452027e-05, + "loss": 0.0211, + "step": 5590 + }, + { + "epoch": 2.2301871764237355, + "grad_norm": 0.39595574140548706, + "learning_rate": 4.424219253586737e-05, + "loss": 0.0198, + "step": 5600 + }, + { + "epoch": 2.2341696535244924, + "grad_norm": 0.41299372911453247, + "learning_rate": 4.407797732367443e-05, + "loss": 0.0235, + "step": 5610 + }, + { + "epoch": 2.2381521306252488, + "grad_norm": 0.37849029898643494, + "learning_rate": 4.391382687377268e-05, + "loss": 0.0205, + "step": 5620 + }, + { + "epoch": 2.2421346077260056, + "grad_norm": 0.28084832429885864, + "learning_rate": 4.374974298128512e-05, + "loss": 0.0193, + "step": 5630 + }, + { + "epoch": 2.2461170848267624, + "grad_norm": 0.21386095881462097, + "learning_rate": 4.358572744060699e-05, + "loss": 0.0194, + "step": 5640 + }, + { + "epoch": 2.250099561927519, + "grad_norm": 0.4740445017814636, + "learning_rate": 4.342178204538588e-05, + "loss": 0.0188, + "step": 5650 + }, + { + "epoch": 2.2540820390282756, + "grad_norm": 0.4500332474708557, + "learning_rate": 4.325790858850241e-05, + "loss": 0.0186, + "step": 5660 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 0.640240490436554, + "learning_rate": 4.309410886205043e-05, + "loss": 0.022, + "step": 5670 + }, + { + "epoch": 2.262046993229789, + "grad_norm": 0.27766144275665283, + "learning_rate": 4.293038465731752e-05, + "loss": 0.0201, + "step": 5680 + }, + { + "epoch": 2.2660294703305457, + "grad_norm": 0.33782440423965454, + "learning_rate": 4.276673776476533e-05, + "loss": 0.021, + "step": 5690 + }, + { + "epoch": 2.270011947431302, + "grad_norm": 0.23944371938705444, + "learning_rate": 4.260316997401007e-05, + "loss": 0.0151, + "step": 5700 + }, + { + "epoch": 2.273994424532059, + "grad_norm": 0.39826247096061707, + "learning_rate": 4.243968307380293e-05, + "loss": 0.0209, + "step": 5710 + }, + { + "epoch": 2.2779769016328157, + "grad_norm": 0.3525907099246979, + "learning_rate": 4.22762788520104e-05, + "loss": 0.0229, + "step": 5720 + }, + { + "epoch": 2.281959378733572, + "grad_norm": 0.31052958965301514, + "learning_rate": 4.211295909559491e-05, + "loss": 0.0246, + "step": 5730 + }, + { + "epoch": 2.285941855834329, + "grad_norm": 0.25942838191986084, + "learning_rate": 4.194972559059511e-05, + "loss": 0.016, + "step": 5740 + }, + { + "epoch": 2.289924332935086, + "grad_norm": 0.25356385111808777, + "learning_rate": 4.178658012210651e-05, + "loss": 0.0191, + "step": 5750 + }, + { + "epoch": 2.293906810035842, + "grad_norm": 0.23378008604049683, + "learning_rate": 4.162352447426177e-05, + "loss": 0.0193, + "step": 5760 + }, + { + "epoch": 2.297889287136599, + "grad_norm": 0.4612410366535187, + "learning_rate": 4.146056043021135e-05, + "loss": 0.0191, + "step": 5770 + }, + { + "epoch": 2.3018717642373554, + "grad_norm": 0.32934215664863586, + "learning_rate": 4.1297689772103944e-05, + "loss": 0.0222, + "step": 5780 + }, + { + "epoch": 2.3058542413381122, + "grad_norm": 0.32064372301101685, + "learning_rate": 4.113491428106694e-05, + "loss": 0.019, + "step": 5790 + }, + { + "epoch": 2.309836718438869, + "grad_norm": 0.28313177824020386, + "learning_rate": 4.0972235737187055e-05, + "loss": 0.0194, + "step": 5800 + }, + { + "epoch": 2.313819195539626, + "grad_norm": 0.2753656208515167, + "learning_rate": 4.080965591949076e-05, + "loss": 0.0187, + "step": 5810 + }, + { + "epoch": 2.3178016726403823, + "grad_norm": 0.4407680928707123, + "learning_rate": 4.0647176605924924e-05, + "loss": 0.019, + "step": 5820 + }, + { + "epoch": 2.321784149741139, + "grad_norm": 0.3289397060871124, + "learning_rate": 4.0484799573337255e-05, + "loss": 0.0222, + "step": 5830 + }, + { + "epoch": 2.3257666268418955, + "grad_norm": 0.19007883965969086, + "learning_rate": 4.032252659745699e-05, + "loss": 0.0215, + "step": 5840 + }, + { + "epoch": 2.3297491039426523, + "grad_norm": 0.3026656210422516, + "learning_rate": 4.016035945287539e-05, + "loss": 0.0249, + "step": 5850 + }, + { + "epoch": 2.333731581043409, + "grad_norm": 0.33095115423202515, + "learning_rate": 3.999829991302635e-05, + "loss": 0.0199, + "step": 5860 + }, + { + "epoch": 2.3377140581441656, + "grad_norm": 0.3494427800178528, + "learning_rate": 3.983634975016707e-05, + "loss": 0.0193, + "step": 5870 + }, + { + "epoch": 2.3416965352449224, + "grad_norm": 0.45006734132766724, + "learning_rate": 3.967451073535854e-05, + "loss": 0.0214, + "step": 5880 + }, + { + "epoch": 2.3456790123456788, + "grad_norm": 0.34191861748695374, + "learning_rate": 3.951278463844633e-05, + "loss": 0.0205, + "step": 5890 + }, + { + "epoch": 2.3496614894464356, + "grad_norm": 0.2956344187259674, + "learning_rate": 3.935117322804111e-05, + "loss": 0.0216, + "step": 5900 + }, + { + "epoch": 2.3536439665471924, + "grad_norm": 0.29354357719421387, + "learning_rate": 3.918967827149938e-05, + "loss": 0.0198, + "step": 5910 + }, + { + "epoch": 2.3576264436479493, + "grad_norm": 0.28611132502555847, + "learning_rate": 3.9028301534904094e-05, + "loss": 0.0209, + "step": 5920 + }, + { + "epoch": 2.3616089207487057, + "grad_norm": 0.3092572093009949, + "learning_rate": 3.88670447830454e-05, + "loss": 0.0186, + "step": 5930 + }, + { + "epoch": 2.3655913978494625, + "grad_norm": 0.3288320004940033, + "learning_rate": 3.870590977940132e-05, + "loss": 0.0195, + "step": 5940 + }, + { + "epoch": 2.369573874950219, + "grad_norm": 0.4887750446796417, + "learning_rate": 3.8544898286118404e-05, + "loss": 0.0204, + "step": 5950 + }, + { + "epoch": 2.3735563520509757, + "grad_norm": 0.23452717065811157, + "learning_rate": 3.838401206399257e-05, + "loss": 0.0158, + "step": 5960 + }, + { + "epoch": 2.3775388291517325, + "grad_norm": 0.3787887394428253, + "learning_rate": 3.822325287244975e-05, + "loss": 0.0175, + "step": 5970 + }, + { + "epoch": 2.381521306252489, + "grad_norm": 0.35094520449638367, + "learning_rate": 3.8062622469526725e-05, + "loss": 0.0194, + "step": 5980 + }, + { + "epoch": 2.3855037833532458, + "grad_norm": 0.5035432577133179, + "learning_rate": 3.790212261185183e-05, + "loss": 0.0161, + "step": 5990 + }, + { + "epoch": 2.389486260454002, + "grad_norm": 0.2279941737651825, + "learning_rate": 3.7741755054625794e-05, + "loss": 0.0198, + "step": 6000 + }, + { + "epoch": 2.393468737554759, + "grad_norm": 0.33681097626686096, + "learning_rate": 3.758152155160255e-05, + "loss": 0.0167, + "step": 6010 + }, + { + "epoch": 2.397451214655516, + "grad_norm": 0.4447823166847229, + "learning_rate": 3.742142385506999e-05, + "loss": 0.0187, + "step": 6020 + }, + { + "epoch": 2.4014336917562726, + "grad_norm": 0.32111281156539917, + "learning_rate": 3.72614637158309e-05, + "loss": 0.0167, + "step": 6030 + }, + { + "epoch": 2.405416168857029, + "grad_norm": 0.3327321708202362, + "learning_rate": 3.710164288318371e-05, + "loss": 0.021, + "step": 6040 + }, + { + "epoch": 2.409398645957786, + "grad_norm": 0.3221536874771118, + "learning_rate": 3.694196310490345e-05, + "loss": 0.0172, + "step": 6050 + }, + { + "epoch": 2.4133811230585422, + "grad_norm": 0.2384720742702484, + "learning_rate": 3.678242612722259e-05, + "loss": 0.0172, + "step": 6060 + }, + { + "epoch": 2.417363600159299, + "grad_norm": 0.4310377240180969, + "learning_rate": 3.6623033694811953e-05, + "loss": 0.0207, + "step": 6070 + }, + { + "epoch": 2.421346077260056, + "grad_norm": 0.2742801904678345, + "learning_rate": 3.6463787550761665e-05, + "loss": 0.0204, + "step": 6080 + }, + { + "epoch": 2.4253285543608123, + "grad_norm": 0.30959945917129517, + "learning_rate": 3.630468943656202e-05, + "loss": 0.0171, + "step": 6090 + }, + { + "epoch": 2.429311031461569, + "grad_norm": 0.23991258442401886, + "learning_rate": 3.6145741092084523e-05, + "loss": 0.0158, + "step": 6100 + }, + { + "epoch": 2.433293508562326, + "grad_norm": 0.3445211350917816, + "learning_rate": 3.598694425556278e-05, + "loss": 0.0171, + "step": 6110 + }, + { + "epoch": 2.4372759856630823, + "grad_norm": 0.23148199915885925, + "learning_rate": 3.58283006635736e-05, + "loss": 0.0168, + "step": 6120 + }, + { + "epoch": 2.441258462763839, + "grad_norm": 0.34516337513923645, + "learning_rate": 3.566981205101781e-05, + "loss": 0.0214, + "step": 6130 + }, + { + "epoch": 2.445240939864596, + "grad_norm": 0.2975906729698181, + "learning_rate": 3.5511480151101556e-05, + "loss": 0.0182, + "step": 6140 + }, + { + "epoch": 2.4492234169653524, + "grad_norm": 0.3364192545413971, + "learning_rate": 3.5353306695317104e-05, + "loss": 0.0149, + "step": 6150 + }, + { + "epoch": 2.4532058940661092, + "grad_norm": 0.32481926679611206, + "learning_rate": 3.519529341342402e-05, + "loss": 0.0205, + "step": 6160 + }, + { + "epoch": 2.4571883711668656, + "grad_norm": 0.35478660464286804, + "learning_rate": 3.503744203343026e-05, + "loss": 0.0184, + "step": 6170 + }, + { + "epoch": 2.4611708482676224, + "grad_norm": 0.40364179015159607, + "learning_rate": 3.487975428157318e-05, + "loss": 0.0213, + "step": 6180 + }, + { + "epoch": 2.4651533253683793, + "grad_norm": 0.2646041512489319, + "learning_rate": 3.472223188230083e-05, + "loss": 0.0182, + "step": 6190 + }, + { + "epoch": 2.4691358024691357, + "grad_norm": 0.21933303773403168, + "learning_rate": 3.4564876558252866e-05, + "loss": 0.02, + "step": 6200 + }, + { + "epoch": 2.4731182795698925, + "grad_norm": 0.41874152421951294, + "learning_rate": 3.440769003024195e-05, + "loss": 0.0192, + "step": 6210 + }, + { + "epoch": 2.4771007566706493, + "grad_norm": 0.40349701046943665, + "learning_rate": 3.425067401723477e-05, + "loss": 0.0195, + "step": 6220 + }, + { + "epoch": 2.4810832337714057, + "grad_norm": 0.36892589926719666, + "learning_rate": 3.409383023633325e-05, + "loss": 0.0214, + "step": 6230 + }, + { + "epoch": 2.4850657108721625, + "grad_norm": 0.3317766785621643, + "learning_rate": 3.3937160402755894e-05, + "loss": 0.0179, + "step": 6240 + }, + { + "epoch": 2.4890481879729194, + "grad_norm": 0.28070494532585144, + "learning_rate": 3.378066622981885e-05, + "loss": 0.0227, + "step": 6250 + }, + { + "epoch": 2.4930306650736758, + "grad_norm": 0.23878398537635803, + "learning_rate": 3.362434942891738e-05, + "loss": 0.0203, + "step": 6260 + }, + { + "epoch": 2.4970131421744326, + "grad_norm": 0.29855674505233765, + "learning_rate": 3.346821170950693e-05, + "loss": 0.0188, + "step": 6270 + }, + { + "epoch": 2.500995619275189, + "grad_norm": 0.35947370529174805, + "learning_rate": 3.3312254779084585e-05, + "loss": 0.0203, + "step": 6280 + }, + { + "epoch": 2.504978096375946, + "grad_norm": 0.38355863094329834, + "learning_rate": 3.315648034317039e-05, + "loss": 0.0229, + "step": 6290 + }, + { + "epoch": 2.5089605734767026, + "grad_norm": 0.20965726673603058, + "learning_rate": 3.3000890105288564e-05, + "loss": 0.0156, + "step": 6300 + }, + { + "epoch": 2.512943050577459, + "grad_norm": 0.21126852929592133, + "learning_rate": 3.284548576694908e-05, + "loss": 0.0221, + "step": 6310 + }, + { + "epoch": 2.516925527678216, + "grad_norm": 0.29997190833091736, + "learning_rate": 3.2690269027628815e-05, + "loss": 0.0163, + "step": 6320 + }, + { + "epoch": 2.5209080047789723, + "grad_norm": 0.2688118815422058, + "learning_rate": 3.253524158475324e-05, + "loss": 0.018, + "step": 6330 + }, + { + "epoch": 2.524890481879729, + "grad_norm": 0.3369862139225006, + "learning_rate": 3.238040513367757e-05, + "loss": 0.0182, + "step": 6340 + }, + { + "epoch": 2.528872958980486, + "grad_norm": 0.17766013741493225, + "learning_rate": 3.222576136766843e-05, + "loss": 0.0159, + "step": 6350 + }, + { + "epoch": 2.5328554360812428, + "grad_norm": 0.2567964494228363, + "learning_rate": 3.2071311977885324e-05, + "loss": 0.0183, + "step": 6360 + }, + { + "epoch": 2.536837913181999, + "grad_norm": 0.2693711519241333, + "learning_rate": 3.191705865336197e-05, + "loss": 0.0195, + "step": 6370 + }, + { + "epoch": 2.540820390282756, + "grad_norm": 0.2565217912197113, + "learning_rate": 3.1763003080988075e-05, + "loss": 0.0175, + "step": 6380 + }, + { + "epoch": 2.5448028673835124, + "grad_norm": 0.44722431898117065, + "learning_rate": 3.160914694549063e-05, + "loss": 0.0198, + "step": 6390 + }, + { + "epoch": 2.548785344484269, + "grad_norm": 0.3705827593803406, + "learning_rate": 3.145549192941573e-05, + "loss": 0.019, + "step": 6400 + }, + { + "epoch": 2.552767821585026, + "grad_norm": 0.3155789077281952, + "learning_rate": 3.130203971310999e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 2.5567502986857824, + "grad_norm": 0.29949137568473816, + "learning_rate": 3.114879197470225e-05, + "loss": 0.0188, + "step": 6420 + }, + { + "epoch": 2.5607327757865392, + "grad_norm": 0.3367830216884613, + "learning_rate": 3.0995750390085285e-05, + "loss": 0.0175, + "step": 6430 + }, + { + "epoch": 2.5647152528872956, + "grad_norm": 0.2421615719795227, + "learning_rate": 3.084291663289728e-05, + "loss": 0.0192, + "step": 6440 + }, + { + "epoch": 2.5686977299880525, + "grad_norm": 0.17980587482452393, + "learning_rate": 3.069029237450375e-05, + "loss": 0.0155, + "step": 6450 + }, + { + "epoch": 2.5726802070888093, + "grad_norm": 0.42298945784568787, + "learning_rate": 3.053787928397911e-05, + "loss": 0.0169, + "step": 6460 + }, + { + "epoch": 2.576662684189566, + "grad_norm": 0.2914910316467285, + "learning_rate": 3.0385679028088526e-05, + "loss": 0.0195, + "step": 6470 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 0.40466681122779846, + "learning_rate": 3.023369327126959e-05, + "loss": 0.0191, + "step": 6480 + }, + { + "epoch": 2.5846276383910793, + "grad_norm": 0.260161429643631, + "learning_rate": 3.0081923675614198e-05, + "loss": 0.0164, + "step": 6490 + }, + { + "epoch": 2.5886101154918357, + "grad_norm": 0.348817378282547, + "learning_rate": 2.993037190085034e-05, + "loss": 0.0155, + "step": 6500 + }, + { + "epoch": 2.5925925925925926, + "grad_norm": 0.22140339016914368, + "learning_rate": 2.977903960432392e-05, + "loss": 0.0192, + "step": 6510 + }, + { + "epoch": 2.5965750696933494, + "grad_norm": 0.3535783886909485, + "learning_rate": 2.9627928440980722e-05, + "loss": 0.0196, + "step": 6520 + }, + { + "epoch": 2.600557546794106, + "grad_norm": 0.229234978556633, + "learning_rate": 2.9477040063348183e-05, + "loss": 0.0206, + "step": 6530 + }, + { + "epoch": 2.6045400238948626, + "grad_norm": 0.30883148312568665, + "learning_rate": 2.9326376121517456e-05, + "loss": 0.0195, + "step": 6540 + }, + { + "epoch": 2.608522500995619, + "grad_norm": 0.4454684257507324, + "learning_rate": 2.9175938263125236e-05, + "loss": 0.024, + "step": 6550 + }, + { + "epoch": 2.612504978096376, + "grad_norm": 0.34252026677131653, + "learning_rate": 2.9025728133335873e-05, + "loss": 0.0206, + "step": 6560 + }, + { + "epoch": 2.6164874551971327, + "grad_norm": 0.410495400428772, + "learning_rate": 2.8875747374823288e-05, + "loss": 0.0201, + "step": 6570 + }, + { + "epoch": 2.6204699322978895, + "grad_norm": 0.2930971384048462, + "learning_rate": 2.872599762775298e-05, + "loss": 0.0242, + "step": 6580 + }, + { + "epoch": 2.624452409398646, + "grad_norm": 0.1941741406917572, + "learning_rate": 2.857648052976425e-05, + "loss": 0.0168, + "step": 6590 + }, + { + "epoch": 2.6284348864994027, + "grad_norm": 0.4398362338542938, + "learning_rate": 2.8427197715952047e-05, + "loss": 0.019, + "step": 6600 + }, + { + "epoch": 2.632417363600159, + "grad_norm": 0.434218168258667, + "learning_rate": 2.8278150818849393e-05, + "loss": 0.0188, + "step": 6610 + }, + { + "epoch": 2.636399840700916, + "grad_norm": 0.29979050159454346, + "learning_rate": 2.812934146840922e-05, + "loss": 0.0175, + "step": 6620 + }, + { + "epoch": 2.6403823178016728, + "grad_norm": 0.27494296431541443, + "learning_rate": 2.7980771291986764e-05, + "loss": 0.0175, + "step": 6630 + }, + { + "epoch": 2.644364794902429, + "grad_norm": 0.3515009582042694, + "learning_rate": 2.783244191432167e-05, + "loss": 0.0185, + "step": 6640 + }, + { + "epoch": 2.648347272003186, + "grad_norm": 0.3444755971431732, + "learning_rate": 2.768435495752022e-05, + "loss": 0.0171, + "step": 6650 + }, + { + "epoch": 2.652329749103943, + "grad_norm": 0.2616831362247467, + "learning_rate": 2.753651204103771e-05, + "loss": 0.02, + "step": 6660 + }, + { + "epoch": 2.656312226204699, + "grad_norm": 0.2663615643978119, + "learning_rate": 2.7388914781660523e-05, + "loss": 0.0149, + "step": 6670 + }, + { + "epoch": 2.660294703305456, + "grad_norm": 0.21043306589126587, + "learning_rate": 2.7241564793488693e-05, + "loss": 0.0202, + "step": 6680 + }, + { + "epoch": 2.664277180406213, + "grad_norm": 0.45657920837402344, + "learning_rate": 2.7094463687918037e-05, + "loss": 0.0151, + "step": 6690 + }, + { + "epoch": 2.6682596575069693, + "grad_norm": 0.37648776173591614, + "learning_rate": 2.694761307362268e-05, + "loss": 0.0192, + "step": 6700 + }, + { + "epoch": 2.672242134607726, + "grad_norm": 0.26603221893310547, + "learning_rate": 2.6801014556537467e-05, + "loss": 0.0169, + "step": 6710 + }, + { + "epoch": 2.6762246117084825, + "grad_norm": 0.3080855906009674, + "learning_rate": 2.6654669739840243e-05, + "loss": 0.0169, + "step": 6720 + }, + { + "epoch": 2.6802070888092393, + "grad_norm": 0.3766150176525116, + "learning_rate": 2.650858022393451e-05, + "loss": 0.0183, + "step": 6730 + }, + { + "epoch": 2.684189565909996, + "grad_norm": 0.2229013293981552, + "learning_rate": 2.6362747606431747e-05, + "loss": 0.0205, + "step": 6740 + }, + { + "epoch": 2.688172043010753, + "grad_norm": 0.24441877007484436, + "learning_rate": 2.6217173482134172e-05, + "loss": 0.0182, + "step": 6750 + }, + { + "epoch": 2.6921545201115094, + "grad_norm": 0.25608956813812256, + "learning_rate": 2.6071859443017044e-05, + "loss": 0.013, + "step": 6760 + }, + { + "epoch": 2.696136997212266, + "grad_norm": 0.3526802957057953, + "learning_rate": 2.5926807078211414e-05, + "loss": 0.0153, + "step": 6770 + }, + { + "epoch": 2.7001194743130226, + "grad_norm": 0.46395474672317505, + "learning_rate": 2.5782017973986728e-05, + "loss": 0.0181, + "step": 6780 + }, + { + "epoch": 2.7041019514137794, + "grad_norm": 0.23045793175697327, + "learning_rate": 2.5637493713733374e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 2.7080844285145362, + "grad_norm": 0.32080161571502686, + "learning_rate": 2.549323587794559e-05, + "loss": 0.0196, + "step": 6800 + }, + { + "epoch": 2.7120669056152926, + "grad_norm": 0.23438672721385956, + "learning_rate": 2.5349246044203895e-05, + "loss": 0.0143, + "step": 6810 + }, + { + "epoch": 2.7160493827160495, + "grad_norm": 0.33166348934173584, + "learning_rate": 2.520552578715808e-05, + "loss": 0.0144, + "step": 6820 + }, + { + "epoch": 2.720031859816806, + "grad_norm": 0.2601594626903534, + "learning_rate": 2.506207667850981e-05, + "loss": 0.0159, + "step": 6830 + }, + { + "epoch": 2.7240143369175627, + "grad_norm": 0.3093375265598297, + "learning_rate": 2.4918900286995555e-05, + "loss": 0.0141, + "step": 6840 + }, + { + "epoch": 2.7279968140183195, + "grad_norm": 0.15893106162548065, + "learning_rate": 2.4775998178369458e-05, + "loss": 0.0161, + "step": 6850 + }, + { + "epoch": 2.7319792911190763, + "grad_norm": 0.3865691125392914, + "learning_rate": 2.4633371915386017e-05, + "loss": 0.0188, + "step": 6860 + }, + { + "epoch": 2.7359617682198327, + "grad_norm": 0.2376730591058731, + "learning_rate": 2.4491023057783235e-05, + "loss": 0.0192, + "step": 6870 + }, + { + "epoch": 2.7399442453205896, + "grad_norm": 0.38163626194000244, + "learning_rate": 2.4348953162265375e-05, + "loss": 0.0182, + "step": 6880 + }, + { + "epoch": 2.743926722421346, + "grad_norm": 0.22240246832370758, + "learning_rate": 2.420716378248607e-05, + "loss": 0.0217, + "step": 6890 + }, + { + "epoch": 2.7479091995221028, + "grad_norm": 0.4573044180870056, + "learning_rate": 2.4065656469031266e-05, + "loss": 0.0165, + "step": 6900 + }, + { + "epoch": 2.7518916766228596, + "grad_norm": 0.22964206337928772, + "learning_rate": 2.3924432769402268e-05, + "loss": 0.0186, + "step": 6910 + }, + { + "epoch": 2.755874153723616, + "grad_norm": 0.30862241983413696, + "learning_rate": 2.3783494227998844e-05, + "loss": 0.0224, + "step": 6920 + }, + { + "epoch": 2.759856630824373, + "grad_norm": 0.22101591527462006, + "learning_rate": 2.3642842386102264e-05, + "loss": 0.0163, + "step": 6930 + }, + { + "epoch": 2.763839107925129, + "grad_norm": 0.2185278832912445, + "learning_rate": 2.3502478781858567e-05, + "loss": 0.0145, + "step": 6940 + }, + { + "epoch": 2.767821585025886, + "grad_norm": 0.24134941399097443, + "learning_rate": 2.3362404950261628e-05, + "loss": 0.019, + "step": 6950 + }, + { + "epoch": 2.771804062126643, + "grad_norm": 0.2902449071407318, + "learning_rate": 2.3222622423136458e-05, + "loss": 0.0165, + "step": 6960 + }, + { + "epoch": 2.7757865392273997, + "grad_norm": 0.3769952058792114, + "learning_rate": 2.3083132729122332e-05, + "loss": 0.0135, + "step": 6970 + }, + { + "epoch": 2.779769016328156, + "grad_norm": 0.22340670228004456, + "learning_rate": 2.294393739365621e-05, + "loss": 0.019, + "step": 6980 + }, + { + "epoch": 2.783751493428913, + "grad_norm": 0.33232781291007996, + "learning_rate": 2.2805037938956e-05, + "loss": 0.0162, + "step": 6990 + }, + { + "epoch": 2.7877339705296693, + "grad_norm": 0.33404746651649475, + "learning_rate": 2.266643588400386e-05, + "loss": 0.0162, + "step": 7000 + }, + { + "epoch": 2.791716447630426, + "grad_norm": 0.2362033873796463, + "learning_rate": 2.252813274452969e-05, + "loss": 0.0166, + "step": 7010 + }, + { + "epoch": 2.795698924731183, + "grad_norm": 0.15253150463104248, + "learning_rate": 2.2390130032994427e-05, + "loss": 0.0153, + "step": 7020 + }, + { + "epoch": 2.7996814018319394, + "grad_norm": 0.36513105034828186, + "learning_rate": 2.2252429258573633e-05, + "loss": 0.0172, + "step": 7030 + }, + { + "epoch": 2.803663878932696, + "grad_norm": 0.22622640430927277, + "learning_rate": 2.2115031927140904e-05, + "loss": 0.0158, + "step": 7040 + }, + { + "epoch": 2.8076463560334526, + "grad_norm": 0.3483319580554962, + "learning_rate": 2.1977939541251463e-05, + "loss": 0.0218, + "step": 7050 + }, + { + "epoch": 2.8116288331342094, + "grad_norm": 0.3104790449142456, + "learning_rate": 2.1841153600125684e-05, + "loss": 0.0165, + "step": 7060 + }, + { + "epoch": 2.8156113102349662, + "grad_norm": 0.2423543781042099, + "learning_rate": 2.170467559963267e-05, + "loss": 0.0167, + "step": 7070 + }, + { + "epoch": 2.819593787335723, + "grad_norm": 0.3841968774795532, + "learning_rate": 2.1568507032273982e-05, + "loss": 0.0135, + "step": 7080 + }, + { + "epoch": 2.8235762644364795, + "grad_norm": 0.2059573382139206, + "learning_rate": 2.1432649387167264e-05, + "loss": 0.015, + "step": 7090 + }, + { + "epoch": 2.8275587415372363, + "grad_norm": 0.22446751594543457, + "learning_rate": 2.1297104150029973e-05, + "loss": 0.0162, + "step": 7100 + }, + { + "epoch": 2.8315412186379927, + "grad_norm": 0.36766108870506287, + "learning_rate": 2.116187280316307e-05, + "loss": 0.0172, + "step": 7110 + }, + { + "epoch": 2.8355236957387495, + "grad_norm": 0.3884134292602539, + "learning_rate": 2.1026956825434908e-05, + "loss": 0.0182, + "step": 7120 + }, + { + "epoch": 2.8395061728395063, + "grad_norm": 0.3192227780818939, + "learning_rate": 2.0892357692265017e-05, + "loss": 0.0145, + "step": 7130 + }, + { + "epoch": 2.8434886499402627, + "grad_norm": 0.2538623511791229, + "learning_rate": 2.0758076875607947e-05, + "loss": 0.0191, + "step": 7140 + }, + { + "epoch": 2.8474711270410196, + "grad_norm": 0.2836097478866577, + "learning_rate": 2.0624115843937207e-05, + "loss": 0.0201, + "step": 7150 + }, + { + "epoch": 2.851453604141776, + "grad_norm": 0.2728939652442932, + "learning_rate": 2.0490476062229157e-05, + "loss": 0.0176, + "step": 7160 + }, + { + "epoch": 2.855436081242533, + "grad_norm": 0.3548661172389984, + "learning_rate": 2.035715899194704e-05, + "loss": 0.0161, + "step": 7170 + }, + { + "epoch": 2.8594185583432896, + "grad_norm": 0.3930123448371887, + "learning_rate": 2.022416609102499e-05, + "loss": 0.0177, + "step": 7180 + }, + { + "epoch": 2.8634010354440464, + "grad_norm": 0.510944664478302, + "learning_rate": 2.009149881385205e-05, + "loss": 0.0222, + "step": 7190 + }, + { + "epoch": 2.867383512544803, + "grad_norm": 0.3476032018661499, + "learning_rate": 1.995915861125634e-05, + "loss": 0.0176, + "step": 7200 + }, + { + "epoch": 2.8713659896455597, + "grad_norm": 0.2559760510921478, + "learning_rate": 1.9827146930489065e-05, + "loss": 0.0149, + "step": 7210 + }, + { + "epoch": 2.875348466746316, + "grad_norm": 0.20961345732212067, + "learning_rate": 1.9695465215208848e-05, + "loss": 0.018, + "step": 7220 + }, + { + "epoch": 2.879330943847073, + "grad_norm": 0.29862138628959656, + "learning_rate": 1.9564114905465813e-05, + "loss": 0.0156, + "step": 7230 + }, + { + "epoch": 2.8833134209478297, + "grad_norm": 0.3706551492214203, + "learning_rate": 1.9433097437685936e-05, + "loss": 0.0166, + "step": 7240 + }, + { + "epoch": 2.887295898048586, + "grad_norm": 0.4077451825141907, + "learning_rate": 1.930241424465521e-05, + "loss": 0.0139, + "step": 7250 + }, + { + "epoch": 2.891278375149343, + "grad_norm": 0.3151760399341583, + "learning_rate": 1.9172066755504115e-05, + "loss": 0.0164, + "step": 7260 + }, + { + "epoch": 2.8952608522500993, + "grad_norm": 0.29641613364219666, + "learning_rate": 1.9042056395691914e-05, + "loss": 0.0168, + "step": 7270 + }, + { + "epoch": 2.899243329350856, + "grad_norm": 0.3831641376018524, + "learning_rate": 1.8912384586991066e-05, + "loss": 0.0147, + "step": 7280 + }, + { + "epoch": 2.903225806451613, + "grad_norm": 0.3114636540412903, + "learning_rate": 1.8783052747471717e-05, + "loss": 0.0144, + "step": 7290 + }, + { + "epoch": 2.90720828355237, + "grad_norm": 0.26268333196640015, + "learning_rate": 1.865406229148611e-05, + "loss": 0.0185, + "step": 7300 + }, + { + "epoch": 2.911190760653126, + "grad_norm": 0.22112445533275604, + "learning_rate": 1.8525414629653233e-05, + "loss": 0.0203, + "step": 7310 + }, + { + "epoch": 2.915173237753883, + "grad_norm": 0.2656763195991516, + "learning_rate": 1.8397111168843255e-05, + "loss": 0.0158, + "step": 7320 + }, + { + "epoch": 2.9191557148546394, + "grad_norm": 0.341366171836853, + "learning_rate": 1.8269153312162323e-05, + "loss": 0.0176, + "step": 7330 + }, + { + "epoch": 2.9231381919553963, + "grad_norm": 0.27272844314575195, + "learning_rate": 1.8141542458937054e-05, + "loss": 0.0155, + "step": 7340 + }, + { + "epoch": 2.927120669056153, + "grad_norm": 0.4220792353153229, + "learning_rate": 1.8014280004699268e-05, + "loss": 0.0173, + "step": 7350 + }, + { + "epoch": 2.9311031461569095, + "grad_norm": 0.2644200325012207, + "learning_rate": 1.788736734117078e-05, + "loss": 0.0111, + "step": 7360 + }, + { + "epoch": 2.9350856232576663, + "grad_norm": 0.27255773544311523, + "learning_rate": 1.7760805856248152e-05, + "loss": 0.0166, + "step": 7370 + }, + { + "epoch": 2.9390681003584227, + "grad_norm": 0.17350824177265167, + "learning_rate": 1.7634596933987518e-05, + "loss": 0.016, + "step": 7380 + }, + { + "epoch": 2.9430505774591795, + "grad_norm": 0.23067346215248108, + "learning_rate": 1.7508741954589404e-05, + "loss": 0.0164, + "step": 7390 + }, + { + "epoch": 2.9470330545599364, + "grad_norm": 0.3143824636936188, + "learning_rate": 1.7383242294383717e-05, + "loss": 0.0166, + "step": 7400 + }, + { + "epoch": 2.951015531660693, + "grad_norm": 0.2438683658838272, + "learning_rate": 1.7258099325814632e-05, + "loss": 0.0129, + "step": 7410 + }, + { + "epoch": 2.9549980087614496, + "grad_norm": 0.31693488359451294, + "learning_rate": 1.7133314417425594e-05, + "loss": 0.02, + "step": 7420 + }, + { + "epoch": 2.9589804858622064, + "grad_norm": 0.26909369230270386, + "learning_rate": 1.7008888933844408e-05, + "loss": 0.0155, + "step": 7430 + }, + { + "epoch": 2.962962962962963, + "grad_norm": 0.29988786578178406, + "learning_rate": 1.6884824235768172e-05, + "loss": 0.0173, + "step": 7440 + }, + { + "epoch": 2.9669454400637196, + "grad_norm": 0.2735227048397064, + "learning_rate": 1.6761121679948592e-05, + "loss": 0.0148, + "step": 7450 + }, + { + "epoch": 2.9709279171644765, + "grad_norm": 0.23975975811481476, + "learning_rate": 1.663778261917695e-05, + "loss": 0.0177, + "step": 7460 + }, + { + "epoch": 2.974910394265233, + "grad_norm": 0.3303283452987671, + "learning_rate": 1.651480840226952e-05, + "loss": 0.0154, + "step": 7470 + }, + { + "epoch": 2.9788928713659897, + "grad_norm": 0.3179773688316345, + "learning_rate": 1.639220037405258e-05, + "loss": 0.017, + "step": 7480 + }, + { + "epoch": 2.982875348466746, + "grad_norm": 0.26732003688812256, + "learning_rate": 1.6269959875347906e-05, + "loss": 0.0162, + "step": 7490 + }, + { + "epoch": 2.986857825567503, + "grad_norm": 0.35051149129867554, + "learning_rate": 1.614808824295802e-05, + "loss": 0.0161, + "step": 7500 + }, + { + "epoch": 2.9908403026682597, + "grad_norm": 0.24838776886463165, + "learning_rate": 1.602658680965152e-05, + "loss": 0.0115, + "step": 7510 + }, + { + "epoch": 2.9948227797690166, + "grad_norm": 0.3378634452819824, + "learning_rate": 1.5905456904148686e-05, + "loss": 0.0183, + "step": 7520 + }, + { + "epoch": 2.998805256869773, + "grad_norm": 0.28400248289108276, + "learning_rate": 1.57846998511067e-05, + "loss": 0.0165, + "step": 7530 + }, + { + "epoch": 3.00278773397053, + "grad_norm": 0.2319607138633728, + "learning_rate": 1.566431697110538e-05, + "loss": 0.0137, + "step": 7540 + }, + { + "epoch": 3.006770211071286, + "grad_norm": 0.326729953289032, + "learning_rate": 1.554430958063259e-05, + "loss": 0.0135, + "step": 7550 + }, + { + "epoch": 3.010752688172043, + "grad_norm": 0.2378934919834137, + "learning_rate": 1.5424678992069912e-05, + "loss": 0.0152, + "step": 7560 + }, + { + "epoch": 3.0147351652728, + "grad_norm": 0.24295467138290405, + "learning_rate": 1.5305426513678362e-05, + "loss": 0.0142, + "step": 7570 + }, + { + "epoch": 3.018717642373556, + "grad_norm": 0.2576531767845154, + "learning_rate": 1.518655344958388e-05, + "loss": 0.0181, + "step": 7580 + }, + { + "epoch": 3.022700119474313, + "grad_norm": 0.18377450108528137, + "learning_rate": 1.5068061099763275e-05, + "loss": 0.0166, + "step": 7590 + }, + { + "epoch": 3.02668259657507, + "grad_norm": 0.27830517292022705, + "learning_rate": 1.494995076002988e-05, + "loss": 0.0154, + "step": 7600 + }, + { + "epoch": 3.0306650736758263, + "grad_norm": 0.21844340860843658, + "learning_rate": 1.4832223722019456e-05, + "loss": 0.012, + "step": 7610 + }, + { + "epoch": 3.034647550776583, + "grad_norm": 0.2617688775062561, + "learning_rate": 1.4714881273176035e-05, + "loss": 0.0174, + "step": 7620 + }, + { + "epoch": 3.0386300278773395, + "grad_norm": 0.32421252131462097, + "learning_rate": 1.4597924696737835e-05, + "loss": 0.0145, + "step": 7630 + }, + { + "epoch": 3.0426125049780963, + "grad_norm": 0.29088929295539856, + "learning_rate": 1.4481355271723252e-05, + "loss": 0.0159, + "step": 7640 + }, + { + "epoch": 3.046594982078853, + "grad_norm": 0.33224666118621826, + "learning_rate": 1.4365174272916809e-05, + "loss": 0.0172, + "step": 7650 + }, + { + "epoch": 3.0505774591796095, + "grad_norm": 0.28133267164230347, + "learning_rate": 1.4249382970855319e-05, + "loss": 0.0164, + "step": 7660 + }, + { + "epoch": 3.0545599362803664, + "grad_norm": 0.2961582839488983, + "learning_rate": 1.4133982631813903e-05, + "loss": 0.0174, + "step": 7670 + }, + { + "epoch": 3.058542413381123, + "grad_norm": 0.19143448770046234, + "learning_rate": 1.4018974517792194e-05, + "loss": 0.0148, + "step": 7680 + }, + { + "epoch": 3.0625248904818796, + "grad_norm": 0.26252588629722595, + "learning_rate": 1.390435988650048e-05, + "loss": 0.0143, + "step": 7690 + }, + { + "epoch": 3.0665073675826364, + "grad_norm": 0.19971930980682373, + "learning_rate": 1.3790139991346006e-05, + "loss": 0.0125, + "step": 7700 + }, + { + "epoch": 3.0704898446833933, + "grad_norm": 0.2495674192905426, + "learning_rate": 1.367631608141926e-05, + "loss": 0.0155, + "step": 7710 + }, + { + "epoch": 3.0744723217841496, + "grad_norm": 0.22202928364276886, + "learning_rate": 1.3562889401480278e-05, + "loss": 0.0148, + "step": 7720 + }, + { + "epoch": 3.0784547988849065, + "grad_norm": 0.4576508402824402, + "learning_rate": 1.3449861191945074e-05, + "loss": 0.0165, + "step": 7730 + }, + { + "epoch": 3.0824372759856633, + "grad_norm": 0.3544761836528778, + "learning_rate": 1.3337232688872009e-05, + "loss": 0.0139, + "step": 7740 + }, + { + "epoch": 3.0864197530864197, + "grad_norm": 0.3484187722206116, + "learning_rate": 1.3225005123948364e-05, + "loss": 0.0147, + "step": 7750 + }, + { + "epoch": 3.0904022301871765, + "grad_norm": 0.19573178887367249, + "learning_rate": 1.311317972447681e-05, + "loss": 0.0127, + "step": 7760 + }, + { + "epoch": 3.094384707287933, + "grad_norm": 0.19815529882907867, + "learning_rate": 1.3001757713361996e-05, + "loss": 0.0109, + "step": 7770 + }, + { + "epoch": 3.0983671843886897, + "grad_norm": 0.35429829359054565, + "learning_rate": 1.2890740309097204e-05, + "loss": 0.0161, + "step": 7780 + }, + { + "epoch": 3.1023496614894466, + "grad_norm": 0.2911655008792877, + "learning_rate": 1.2780128725750944e-05, + "loss": 0.0138, + "step": 7790 + }, + { + "epoch": 3.106332138590203, + "grad_norm": 0.270168662071228, + "learning_rate": 1.266992417295379e-05, + "loss": 0.015, + "step": 7800 + }, + { + "epoch": 3.11031461569096, + "grad_norm": 0.32108160853385925, + "learning_rate": 1.2560127855885073e-05, + "loss": 0.0163, + "step": 7810 + }, + { + "epoch": 3.1142970927917166, + "grad_norm": 0.24168479442596436, + "learning_rate": 1.2450740975259745e-05, + "loss": 0.0167, + "step": 7820 + }, + { + "epoch": 3.118279569892473, + "grad_norm": 0.30409395694732666, + "learning_rate": 1.234176472731517e-05, + "loss": 0.0221, + "step": 7830 + }, + { + "epoch": 3.12226204699323, + "grad_norm": 0.3229791522026062, + "learning_rate": 1.2233200303798158e-05, + "loss": 0.0147, + "step": 7840 + }, + { + "epoch": 3.1262445240939867, + "grad_norm": 0.26919838786125183, + "learning_rate": 1.2125048891951846e-05, + "loss": 0.0158, + "step": 7850 + }, + { + "epoch": 3.130227001194743, + "grad_norm": 0.23068082332611084, + "learning_rate": 1.2017311674502745e-05, + "loss": 0.013, + "step": 7860 + }, + { + "epoch": 3.1342094782955, + "grad_norm": 0.17686747014522552, + "learning_rate": 1.1909989829647822e-05, + "loss": 0.0144, + "step": 7870 + }, + { + "epoch": 3.1381919553962563, + "grad_norm": 0.45290425419807434, + "learning_rate": 1.1803084531041553e-05, + "loss": 0.0173, + "step": 7880 + }, + { + "epoch": 3.142174432497013, + "grad_norm": 0.2763400673866272, + "learning_rate": 1.1696596947783162e-05, + "loss": 0.0144, + "step": 7890 + }, + { + "epoch": 3.14615690959777, + "grad_norm": 0.2585810422897339, + "learning_rate": 1.1590528244403803e-05, + "loss": 0.0175, + "step": 7900 + }, + { + "epoch": 3.1501393866985263, + "grad_norm": 0.22105610370635986, + "learning_rate": 1.148487958085382e-05, + "loss": 0.0151, + "step": 7910 + }, + { + "epoch": 3.154121863799283, + "grad_norm": 0.21400152146816254, + "learning_rate": 1.1379652112490086e-05, + "loss": 0.0177, + "step": 7920 + }, + { + "epoch": 3.15810434090004, + "grad_norm": 0.1969025582075119, + "learning_rate": 1.1274846990063315e-05, + "loss": 0.0136, + "step": 7930 + }, + { + "epoch": 3.1620868180007964, + "grad_norm": 0.2094409465789795, + "learning_rate": 1.117046535970554e-05, + "loss": 0.0151, + "step": 7940 + }, + { + "epoch": 3.166069295101553, + "grad_norm": 0.29152101278305054, + "learning_rate": 1.106650836291755e-05, + "loss": 0.0195, + "step": 7950 + }, + { + "epoch": 3.17005177220231, + "grad_norm": 0.28160348534584045, + "learning_rate": 1.0962977136556418e-05, + "loss": 0.0184, + "step": 7960 + }, + { + "epoch": 3.1740342493030664, + "grad_norm": 0.3710784614086151, + "learning_rate": 1.0859872812823024e-05, + "loss": 0.0144, + "step": 7970 + }, + { + "epoch": 3.1780167264038233, + "grad_norm": 0.23486924171447754, + "learning_rate": 1.0757196519249747e-05, + "loss": 0.0189, + "step": 7980 + }, + { + "epoch": 3.1819992035045797, + "grad_norm": 0.31155335903167725, + "learning_rate": 1.0654949378688077e-05, + "loss": 0.0156, + "step": 7990 + }, + { + "epoch": 3.1859816806053365, + "grad_norm": 0.21536493301391602, + "learning_rate": 1.0553132509296376e-05, + "loss": 0.0146, + "step": 8000 + }, + { + "epoch": 3.1899641577060933, + "grad_norm": 0.25504568219184875, + "learning_rate": 1.0451747024527613e-05, + "loss": 0.0139, + "step": 8010 + }, + { + "epoch": 3.1939466348068497, + "grad_norm": 0.43125614523887634, + "learning_rate": 1.0350794033117189e-05, + "loss": 0.017, + "step": 8020 + }, + { + "epoch": 3.1979291119076065, + "grad_norm": 0.3463977873325348, + "learning_rate": 1.0250274639070856e-05, + "loss": 0.0153, + "step": 8030 + }, + { + "epoch": 3.2019115890083634, + "grad_norm": 0.33657532930374146, + "learning_rate": 1.0150189941652599e-05, + "loss": 0.0136, + "step": 8040 + }, + { + "epoch": 3.2058940661091198, + "grad_norm": 0.27286818623542786, + "learning_rate": 1.0050541035372635e-05, + "loss": 0.0123, + "step": 8050 + }, + { + "epoch": 3.2098765432098766, + "grad_norm": 0.3115975260734558, + "learning_rate": 9.951329009975458e-06, + "loss": 0.0149, + "step": 8060 + }, + { + "epoch": 3.2138590203106334, + "grad_norm": 0.2783370018005371, + "learning_rate": 9.852554950427845e-06, + "loss": 0.015, + "step": 8070 + }, + { + "epoch": 3.21784149741139, + "grad_norm": 0.2135641872882843, + "learning_rate": 9.754219936907105e-06, + "loss": 0.0145, + "step": 8080 + }, + { + "epoch": 3.2218239745121466, + "grad_norm": 0.2889596223831177, + "learning_rate": 9.656325044789194e-06, + "loss": 0.0125, + "step": 8090 + }, + { + "epoch": 3.225806451612903, + "grad_norm": 0.16843768954277039, + "learning_rate": 9.55887134463697e-06, + "loss": 0.0116, + "step": 8100 + }, + { + "epoch": 3.22978892871366, + "grad_norm": 0.22345881164073944, + "learning_rate": 9.461859902188475e-06, + "loss": 0.0133, + "step": 8110 + }, + { + "epoch": 3.2337714058144167, + "grad_norm": 0.4386395812034607, + "learning_rate": 9.365291778345303e-06, + "loss": 0.0166, + "step": 8120 + }, + { + "epoch": 3.237753882915173, + "grad_norm": 0.15999703109264374, + "learning_rate": 9.269168029160991e-06, + "loss": 0.0103, + "step": 8130 + }, + { + "epoch": 3.24173636001593, + "grad_norm": 0.33131685853004456, + "learning_rate": 9.173489705829447e-06, + "loss": 0.0152, + "step": 8140 + }, + { + "epoch": 3.2457188371166867, + "grad_norm": 0.18595287203788757, + "learning_rate": 9.078257854673516e-06, + "loss": 0.0136, + "step": 8150 + }, + { + "epoch": 3.249701314217443, + "grad_norm": 0.18805378675460815, + "learning_rate": 8.983473517133429e-06, + "loss": 0.0141, + "step": 8160 + }, + { + "epoch": 3.2536837913182, + "grad_norm": 0.15438763797283173, + "learning_rate": 8.889137729755537e-06, + "loss": 0.013, + "step": 8170 + }, + { + "epoch": 3.257666268418957, + "grad_norm": 0.27492639422416687, + "learning_rate": 8.79525152418087e-06, + "loss": 0.0169, + "step": 8180 + }, + { + "epoch": 3.261648745519713, + "grad_norm": 0.28761956095695496, + "learning_rate": 8.701815927133961e-06, + "loss": 0.014, + "step": 8190 + }, + { + "epoch": 3.26563122262047, + "grad_norm": 0.17063534259796143, + "learning_rate": 8.608831960411534e-06, + "loss": 0.0139, + "step": 8200 + }, + { + "epoch": 3.2696136997212264, + "grad_norm": 0.22604522109031677, + "learning_rate": 8.516300640871321e-06, + "loss": 0.0164, + "step": 8210 + }, + { + "epoch": 3.2735961768219832, + "grad_norm": 0.27093005180358887, + "learning_rate": 8.424222980421038e-06, + "loss": 0.0165, + "step": 8220 + }, + { + "epoch": 3.27757865392274, + "grad_norm": 0.2355274260044098, + "learning_rate": 8.332599986007184e-06, + "loss": 0.0151, + "step": 8230 + }, + { + "epoch": 3.2815611310234964, + "grad_norm": 0.23121079802513123, + "learning_rate": 8.241432659604203e-06, + "loss": 0.0144, + "step": 8240 + }, + { + "epoch": 3.2855436081242533, + "grad_norm": 0.1323615461587906, + "learning_rate": 8.150721998203331e-06, + "loss": 0.0128, + "step": 8250 + }, + { + "epoch": 3.28952608522501, + "grad_norm": 0.24003800749778748, + "learning_rate": 8.06046899380184e-06, + "loss": 0.0123, + "step": 8260 + }, + { + "epoch": 3.2935085623257665, + "grad_norm": 0.24698399007320404, + "learning_rate": 7.970674633392133e-06, + "loss": 0.0166, + "step": 8270 + }, + { + "epoch": 3.2974910394265233, + "grad_norm": 0.38070154190063477, + "learning_rate": 7.881339898950924e-06, + "loss": 0.018, + "step": 8280 + }, + { + "epoch": 3.30147351652728, + "grad_norm": 0.1986345499753952, + "learning_rate": 7.792465767428597e-06, + "loss": 0.0136, + "step": 8290 + }, + { + "epoch": 3.3054559936280365, + "grad_norm": 0.21766434609889984, + "learning_rate": 7.704053210738376e-06, + "loss": 0.0132, + "step": 8300 + }, + { + "epoch": 3.3094384707287934, + "grad_norm": 0.20243440568447113, + "learning_rate": 7.6161031957458494e-06, + "loss": 0.0152, + "step": 8310 + }, + { + "epoch": 3.3134209478295498, + "grad_norm": 0.2816754877567291, + "learning_rate": 7.5286166842582605e-06, + "loss": 0.0148, + "step": 8320 + }, + { + "epoch": 3.3174034249303066, + "grad_norm": 0.2514406442642212, + "learning_rate": 7.4415946330140814e-06, + "loss": 0.0145, + "step": 8330 + }, + { + "epoch": 3.3213859020310634, + "grad_norm": 0.2709660530090332, + "learning_rate": 7.3550379936725644e-06, + "loss": 0.0141, + "step": 8340 + }, + { + "epoch": 3.32536837913182, + "grad_norm": 0.2837410569190979, + "learning_rate": 7.2689477128032035e-06, + "loss": 0.018, + "step": 8350 + }, + { + "epoch": 3.3293508562325766, + "grad_norm": 0.131383016705513, + "learning_rate": 7.183324731875551e-06, + "loss": 0.0105, + "step": 8360 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.31221866607666016, + "learning_rate": 7.098169987248782e-06, + "loss": 0.012, + "step": 8370 + }, + { + "epoch": 3.33731581043409, + "grad_norm": 0.2039610892534256, + "learning_rate": 7.013484410161553e-06, + "loss": 0.0135, + "step": 8380 + }, + { + "epoch": 3.3412982875348467, + "grad_norm": 0.22186747193336487, + "learning_rate": 6.92926892672176e-06, + "loss": 0.0131, + "step": 8390 + }, + { + "epoch": 3.3452807646356035, + "grad_norm": 0.1861848533153534, + "learning_rate": 6.845524457896446e-06, + "loss": 0.0124, + "step": 8400 + }, + { + "epoch": 3.34926324173636, + "grad_norm": 0.23007585108280182, + "learning_rate": 6.7622519195017165e-06, + "loss": 0.0126, + "step": 8410 + }, + { + "epoch": 3.3532457188371168, + "grad_norm": 0.26495233178138733, + "learning_rate": 6.679452222192684e-06, + "loss": 0.0136, + "step": 8420 + }, + { + "epoch": 3.357228195937873, + "grad_norm": 0.2193382978439331, + "learning_rate": 6.597126271453579e-06, + "loss": 0.011, + "step": 8430 + }, + { + "epoch": 3.36121067303863, + "grad_norm": 0.10426363348960876, + "learning_rate": 6.51527496758782e-06, + "loss": 0.0114, + "step": 8440 + }, + { + "epoch": 3.365193150139387, + "grad_norm": 0.16592855751514435, + "learning_rate": 6.433899205708155e-06, + "loss": 0.0131, + "step": 8450 + }, + { + "epoch": 3.369175627240143, + "grad_norm": 0.1602918803691864, + "learning_rate": 6.352999875726856e-06, + "loss": 0.0121, + "step": 8460 + }, + { + "epoch": 3.3731581043409, + "grad_norm": 0.16960707306861877, + "learning_rate": 6.272577862346052e-06, + "loss": 0.0115, + "step": 8470 + }, + { + "epoch": 3.377140581441657, + "grad_norm": 0.29499271512031555, + "learning_rate": 6.192634045047996e-06, + "loss": 0.0129, + "step": 8480 + }, + { + "epoch": 3.3811230585424132, + "grad_norm": 0.23193804919719696, + "learning_rate": 6.113169298085458e-06, + "loss": 0.0194, + "step": 8490 + }, + { + "epoch": 3.38510553564317, + "grad_norm": 0.3416202962398529, + "learning_rate": 6.034184490472195e-06, + "loss": 0.0114, + "step": 8500 + }, + { + "epoch": 3.389088012743927, + "grad_norm": 0.22498588263988495, + "learning_rate": 5.955680485973386e-06, + "loss": 0.0156, + "step": 8510 + }, + { + "epoch": 3.3930704898446833, + "grad_norm": 0.3182886838912964, + "learning_rate": 5.877658143096265e-06, + "loss": 0.0132, + "step": 8520 + }, + { + "epoch": 3.39705296694544, + "grad_norm": 0.1463838666677475, + "learning_rate": 5.800118315080661e-06, + "loss": 0.0129, + "step": 8530 + }, + { + "epoch": 3.4010354440461965, + "grad_norm": 0.23471392691135406, + "learning_rate": 5.723061849889716e-06, + "loss": 0.0126, + "step": 8540 + }, + { + "epoch": 3.4050179211469533, + "grad_norm": 0.1969936192035675, + "learning_rate": 5.646489590200604e-06, + "loss": 0.0161, + "step": 8550 + }, + { + "epoch": 3.40900039824771, + "grad_norm": 0.15309295058250427, + "learning_rate": 5.570402373395256e-06, + "loss": 0.0125, + "step": 8560 + }, + { + "epoch": 3.4129828753484666, + "grad_norm": 0.4474526643753052, + "learning_rate": 5.494801031551305e-06, + "loss": 0.0163, + "step": 8570 + }, + { + "epoch": 3.4169653524492234, + "grad_norm": 0.18500779569149017, + "learning_rate": 5.41968639143291e-06, + "loss": 0.0139, + "step": 8580 + }, + { + "epoch": 3.4209478295499802, + "grad_norm": 0.19193483889102936, + "learning_rate": 5.345059274481751e-06, + "loss": 0.0127, + "step": 8590 + }, + { + "epoch": 3.4249303066507366, + "grad_norm": 0.15665030479431152, + "learning_rate": 5.270920496808002e-06, + "loss": 0.0159, + "step": 8600 + }, + { + "epoch": 3.4289127837514934, + "grad_norm": 0.16787682473659515, + "learning_rate": 5.1972708691814695e-06, + "loss": 0.0116, + "step": 8610 + }, + { + "epoch": 3.4328952608522503, + "grad_norm": 0.29282400012016296, + "learning_rate": 5.124111197022674e-06, + "loss": 0.0145, + "step": 8620 + }, + { + "epoch": 3.4368777379530067, + "grad_norm": 0.1538035124540329, + "learning_rate": 5.051442280394081e-06, + "loss": 0.0118, + "step": 8630 + }, + { + "epoch": 3.4408602150537635, + "grad_norm": 0.16790461540222168, + "learning_rate": 4.979264913991322e-06, + "loss": 0.0132, + "step": 8640 + }, + { + "epoch": 3.44484269215452, + "grad_norm": 0.1722331941127777, + "learning_rate": 4.907579887134489e-06, + "loss": 0.0134, + "step": 8650 + }, + { + "epoch": 3.4488251692552767, + "grad_norm": 0.21935425698757172, + "learning_rate": 4.836387983759572e-06, + "loss": 0.0137, + "step": 8660 + }, + { + "epoch": 3.4528076463560335, + "grad_norm": 0.2668359875679016, + "learning_rate": 4.765689982409816e-06, + "loss": 0.0121, + "step": 8670 + }, + { + "epoch": 3.45679012345679, + "grad_norm": 0.34474870562553406, + "learning_rate": 4.695486656227233e-06, + "loss": 0.0178, + "step": 8680 + }, + { + "epoch": 3.4607726005575468, + "grad_norm": 0.3360903859138489, + "learning_rate": 4.625778772944156e-06, + "loss": 0.013, + "step": 8690 + }, + { + "epoch": 3.4647550776583036, + "grad_norm": 0.1198967769742012, + "learning_rate": 4.556567094874825e-06, + "loss": 0.0139, + "step": 8700 + }, + { + "epoch": 3.46873755475906, + "grad_norm": 0.12995925545692444, + "learning_rate": 4.487852378907059e-06, + "loss": 0.0099, + "step": 8710 + }, + { + "epoch": 3.472720031859817, + "grad_norm": 0.14079661667346954, + "learning_rate": 4.419635376493986e-06, + "loss": 0.0133, + "step": 8720 + }, + { + "epoch": 3.4767025089605736, + "grad_norm": 0.23179714381694794, + "learning_rate": 4.351916833645825e-06, + "loss": 0.0145, + "step": 8730 + }, + { + "epoch": 3.48068498606133, + "grad_norm": 0.19353191554546356, + "learning_rate": 4.284697490921691e-06, + "loss": 0.013, + "step": 8740 + }, + { + "epoch": 3.484667463162087, + "grad_norm": 0.2545132040977478, + "learning_rate": 4.2179780834215585e-06, + "loss": 0.0161, + "step": 8750 + }, + { + "epoch": 3.4886499402628433, + "grad_norm": 0.22561277449131012, + "learning_rate": 4.151759340778178e-06, + "loss": 0.0142, + "step": 8760 + }, + { + "epoch": 3.4926324173636, + "grad_norm": 0.25932180881500244, + "learning_rate": 4.086041987149109e-06, + "loss": 0.0131, + "step": 8770 + }, + { + "epoch": 3.496614894464357, + "grad_norm": 0.23832671344280243, + "learning_rate": 4.020826741208811e-06, + "loss": 0.016, + "step": 8780 + }, + { + "epoch": 3.5005973715651137, + "grad_norm": 0.1888727992773056, + "learning_rate": 3.956114316140746e-06, + "loss": 0.0165, + "step": 8790 + }, + { + "epoch": 3.50457984866587, + "grad_norm": 0.2623044550418854, + "learning_rate": 3.891905419629643e-06, + "loss": 0.0125, + "step": 8800 + }, + { + "epoch": 3.508562325766627, + "grad_norm": 0.25887444615364075, + "learning_rate": 3.8282007538536946e-06, + "loss": 0.0164, + "step": 8810 + }, + { + "epoch": 3.5125448028673834, + "grad_norm": 0.21378953754901886, + "learning_rate": 3.7650010154769265e-06, + "loss": 0.0126, + "step": 8820 + }, + { + "epoch": 3.51652727996814, + "grad_norm": 0.2530067563056946, + "learning_rate": 3.7023068956415608e-06, + "loss": 0.0168, + "step": 8830 + }, + { + "epoch": 3.520509757068897, + "grad_norm": 0.27777713537216187, + "learning_rate": 3.6401190799604303e-06, + "loss": 0.0132, + "step": 8840 + }, + { + "epoch": 3.5244922341696534, + "grad_norm": 0.16841277480125427, + "learning_rate": 3.578438248509536e-06, + "loss": 0.015, + "step": 8850 + }, + { + "epoch": 3.5284747112704102, + "grad_norm": 0.22934165596961975, + "learning_rate": 3.5172650758205583e-06, + "loss": 0.0158, + "step": 8860 + }, + { + "epoch": 3.5324571883711666, + "grad_norm": 0.2117910385131836, + "learning_rate": 3.45660023087353e-06, + "loss": 0.0138, + "step": 8870 + }, + { + "epoch": 3.5364396654719235, + "grad_norm": 0.12349478155374527, + "learning_rate": 3.3964443770894528e-06, + "loss": 0.0115, + "step": 8880 + }, + { + "epoch": 3.5404221425726803, + "grad_norm": 0.25816065073013306, + "learning_rate": 3.3367981723231245e-06, + "loss": 0.013, + "step": 8890 + }, + { + "epoch": 3.544404619673437, + "grad_norm": 0.24896445870399475, + "learning_rate": 3.2776622688558746e-06, + "loss": 0.0134, + "step": 8900 + }, + { + "epoch": 3.5483870967741935, + "grad_norm": 0.20246760547161102, + "learning_rate": 3.2190373133884677e-06, + "loss": 0.0141, + "step": 8910 + }, + { + "epoch": 3.5523695738749503, + "grad_norm": 0.17225037515163422, + "learning_rate": 3.1609239470340446e-06, + "loss": 0.0125, + "step": 8920 + }, + { + "epoch": 3.5563520509757067, + "grad_norm": 0.16104808449745178, + "learning_rate": 3.1033228053110373e-06, + "loss": 0.0127, + "step": 8930 + }, + { + "epoch": 3.5603345280764636, + "grad_norm": 0.25064268708229065, + "learning_rate": 3.0462345181363314e-06, + "loss": 0.0121, + "step": 8940 + }, + { + "epoch": 3.5643170051772204, + "grad_norm": 0.177175834774971, + "learning_rate": 2.9896597098182654e-06, + "loss": 0.0145, + "step": 8950 + }, + { + "epoch": 3.5682994822779768, + "grad_norm": 0.23675449192523956, + "learning_rate": 2.933598999049891e-06, + "loss": 0.0133, + "step": 8960 + }, + { + "epoch": 3.5722819593787336, + "grad_norm": 0.19365286827087402, + "learning_rate": 2.8780529989021697e-06, + "loss": 0.0126, + "step": 8970 + }, + { + "epoch": 3.57626443647949, + "grad_norm": 0.3542676270008087, + "learning_rate": 2.823022316817242e-06, + "loss": 0.0162, + "step": 8980 + }, + { + "epoch": 3.580246913580247, + "grad_norm": 0.2057904750108719, + "learning_rate": 2.7685075546018456e-06, + "loss": 0.0134, + "step": 8990 + }, + { + "epoch": 3.5842293906810037, + "grad_norm": 0.19681024551391602, + "learning_rate": 2.7145093084206598e-06, + "loss": 0.0158, + "step": 9000 + }, + { + "epoch": 3.5882118677817605, + "grad_norm": 0.11298860609531403, + "learning_rate": 2.661028168789892e-06, + "loss": 0.0114, + "step": 9010 + }, + { + "epoch": 3.592194344882517, + "grad_norm": 0.20377224683761597, + "learning_rate": 2.6080647205706855e-06, + "loss": 0.0115, + "step": 9020 + }, + { + "epoch": 3.5961768219832737, + "grad_norm": 0.20502862334251404, + "learning_rate": 2.555619542962834e-06, + "loss": 0.0141, + "step": 9030 + }, + { + "epoch": 3.60015929908403, + "grad_norm": 0.2239837795495987, + "learning_rate": 2.503693209498409e-06, + "loss": 0.0108, + "step": 9040 + }, + { + "epoch": 3.604141776184787, + "grad_norm": 0.21607056260108948, + "learning_rate": 2.452286288035449e-06, + "loss": 0.0138, + "step": 9050 + }, + { + "epoch": 3.6081242532855438, + "grad_norm": 0.23609691858291626, + "learning_rate": 2.4013993407518363e-06, + "loss": 0.0129, + "step": 9060 + }, + { + "epoch": 3.6121067303863, + "grad_norm": 0.20945118367671967, + "learning_rate": 2.351032924139063e-06, + "loss": 0.0117, + "step": 9070 + }, + { + "epoch": 3.616089207487057, + "grad_norm": 0.180077463388443, + "learning_rate": 2.30118758899619e-06, + "loss": 0.0146, + "step": 9080 + }, + { + "epoch": 3.6200716845878134, + "grad_norm": 0.25069552659988403, + "learning_rate": 2.2518638804238157e-06, + "loss": 0.0135, + "step": 9090 + }, + { + "epoch": 3.62405416168857, + "grad_norm": 0.14733609557151794, + "learning_rate": 2.203062337818118e-06, + "loss": 0.0135, + "step": 9100 + }, + { + "epoch": 3.628036638789327, + "grad_norm": 0.27784958481788635, + "learning_rate": 2.1547834948649483e-06, + "loss": 0.014, + "step": 9110 + }, + { + "epoch": 3.632019115890084, + "grad_norm": 0.18988502025604248, + "learning_rate": 2.1070278795340017e-06, + "loss": 0.0148, + "step": 9120 + }, + { + "epoch": 3.6360015929908402, + "grad_norm": 0.15056854486465454, + "learning_rate": 2.059796014073029e-06, + "loss": 0.0098, + "step": 9130 + }, + { + "epoch": 3.639984070091597, + "grad_norm": 0.25632742047309875, + "learning_rate": 2.01308841500214e-06, + "loss": 0.0121, + "step": 9140 + }, + { + "epoch": 3.6439665471923535, + "grad_norm": 0.33377549052238464, + "learning_rate": 1.9669055931081704e-06, + "loss": 0.0153, + "step": 9150 + }, + { + "epoch": 3.6479490242931103, + "grad_norm": 0.24696041643619537, + "learning_rate": 1.9212480534390507e-06, + "loss": 0.0153, + "step": 9160 + }, + { + "epoch": 3.651931501393867, + "grad_norm": 0.1778692901134491, + "learning_rate": 1.8761162952983246e-06, + "loss": 0.0139, + "step": 9170 + }, + { + "epoch": 3.6559139784946235, + "grad_norm": 0.31593841314315796, + "learning_rate": 1.8315108122396618e-06, + "loss": 0.0148, + "step": 9180 + }, + { + "epoch": 3.6598964555953803, + "grad_norm": 0.2725008726119995, + "learning_rate": 1.787432092061475e-06, + "loss": 0.0126, + "step": 9190 + }, + { + "epoch": 3.6638789326961367, + "grad_norm": 0.2079121172428131, + "learning_rate": 1.743880616801602e-06, + "loss": 0.0168, + "step": 9200 + }, + { + "epoch": 3.6678614097968936, + "grad_norm": 0.1617252379655838, + "learning_rate": 1.7008568627319865e-06, + "loss": 0.0125, + "step": 9210 + }, + { + "epoch": 3.6718438868976504, + "grad_norm": 0.23413202166557312, + "learning_rate": 1.6583613003535226e-06, + "loss": 0.0139, + "step": 9220 + }, + { + "epoch": 3.6758263639984072, + "grad_norm": 0.20422157645225525, + "learning_rate": 1.6163943943908522e-06, + "loss": 0.0129, + "step": 9230 + }, + { + "epoch": 3.6798088410991636, + "grad_norm": 0.3413521349430084, + "learning_rate": 1.5749566037873476e-06, + "loss": 0.0133, + "step": 9240 + }, + { + "epoch": 3.6837913181999205, + "grad_norm": 0.1363775134086609, + "learning_rate": 1.5340483817000428e-06, + "loss": 0.012, + "step": 9250 + }, + { + "epoch": 3.687773795300677, + "grad_norm": 0.11363986134529114, + "learning_rate": 1.4936701754947101e-06, + "loss": 0.0116, + "step": 9260 + }, + { + "epoch": 3.6917562724014337, + "grad_norm": 0.27134454250335693, + "learning_rate": 1.4538224267409361e-06, + "loss": 0.0147, + "step": 9270 + }, + { + "epoch": 3.6957387495021905, + "grad_norm": 0.16270877420902252, + "learning_rate": 1.414505571207314e-06, + "loss": 0.0111, + "step": 9280 + }, + { + "epoch": 3.699721226602947, + "grad_norm": 0.23508696258068085, + "learning_rate": 1.3757200388566816e-06, + "loss": 0.0122, + "step": 9290 + }, + { + "epoch": 3.7037037037037037, + "grad_norm": 0.18475975096225739, + "learning_rate": 1.3374662538414074e-06, + "loss": 0.0147, + "step": 9300 + }, + { + "epoch": 3.70768618080446, + "grad_norm": 0.23747357726097107, + "learning_rate": 1.2997446344987617e-06, + "loss": 0.0127, + "step": 9310 + }, + { + "epoch": 3.711668657905217, + "grad_norm": 0.25293728709220886, + "learning_rate": 1.262555593346315e-06, + "loss": 0.0124, + "step": 9320 + }, + { + "epoch": 3.7156511350059738, + "grad_norm": 0.3373745381832123, + "learning_rate": 1.2258995370774685e-06, + "loss": 0.0153, + "step": 9330 + }, + { + "epoch": 3.7196336121067306, + "grad_norm": 0.21809877455234528, + "learning_rate": 1.1897768665569798e-06, + "loss": 0.0164, + "step": 9340 + }, + { + "epoch": 3.723616089207487, + "grad_norm": 0.21654918789863586, + "learning_rate": 1.1541879768165954e-06, + "loss": 0.0111, + "step": 9350 + }, + { + "epoch": 3.727598566308244, + "grad_norm": 0.19067105650901794, + "learning_rate": 1.1191332570507085e-06, + "loss": 0.0143, + "step": 9360 + }, + { + "epoch": 3.731581043409, + "grad_norm": 0.20294006168842316, + "learning_rate": 1.0846130906121132e-06, + "loss": 0.0172, + "step": 9370 + }, + { + "epoch": 3.735563520509757, + "grad_norm": 0.2206583172082901, + "learning_rate": 1.0506278550078131e-06, + "loss": 0.0137, + "step": 9380 + }, + { + "epoch": 3.739545997610514, + "grad_norm": 0.18981283903121948, + "learning_rate": 1.0171779218949185e-06, + "loss": 0.0158, + "step": 9390 + }, + { + "epoch": 3.7435284747112703, + "grad_norm": 0.21733026206493378, + "learning_rate": 9.842636570765174e-07, + "loss": 0.0133, + "step": 9400 + }, + { + "epoch": 3.747510951812027, + "grad_norm": 0.2571982741355896, + "learning_rate": 9.518854204977612e-07, + "loss": 0.013, + "step": 9410 + }, + { + "epoch": 3.7514934289127835, + "grad_norm": 0.2336360365152359, + "learning_rate": 9.200435662418349e-07, + "loss": 0.0144, + "step": 9420 + }, + { + "epoch": 3.7554759060135403, + "grad_norm": 0.25008511543273926, + "learning_rate": 8.887384425261658e-07, + "loss": 0.0111, + "step": 9430 + }, + { + "epoch": 3.759458383114297, + "grad_norm": 0.23758894205093384, + "learning_rate": 8.579703916985648e-07, + "loss": 0.0137, + "step": 9440 + }, + { + "epoch": 3.763440860215054, + "grad_norm": 0.27957940101623535, + "learning_rate": 8.277397502335194e-07, + "loss": 0.0143, + "step": 9450 + }, + { + "epoch": 3.7674233373158104, + "grad_norm": 0.2032625526189804, + "learning_rate": 7.980468487284675e-07, + "loss": 0.0153, + "step": 9460 + }, + { + "epoch": 3.771405814416567, + "grad_norm": 0.2791658341884613, + "learning_rate": 7.688920119002297e-07, + "loss": 0.0126, + "step": 9470 + }, + { + "epoch": 3.7753882915173236, + "grad_norm": 0.14666704833507538, + "learning_rate": 7.402755585814269e-07, + "loss": 0.0126, + "step": 9480 + }, + { + "epoch": 3.7793707686180804, + "grad_norm": 0.2378731667995453, + "learning_rate": 7.121978017170073e-07, + "loss": 0.0145, + "step": 9490 + }, + { + "epoch": 3.7833532457188372, + "grad_norm": 0.3094591796398163, + "learning_rate": 6.846590483608306e-07, + "loss": 0.0122, + "step": 9500 + }, + { + "epoch": 3.7873357228195936, + "grad_norm": 0.14007677137851715, + "learning_rate": 6.576595996722834e-07, + "loss": 0.016, + "step": 9510 + }, + { + "epoch": 3.7913181999203505, + "grad_norm": 0.24854406714439392, + "learning_rate": 6.311997509130141e-07, + "loss": 0.013, + "step": 9520 + }, + { + "epoch": 3.7953006770211073, + "grad_norm": 0.22404152154922485, + "learning_rate": 6.052797914436803e-07, + "loss": 0.0152, + "step": 9530 + }, + { + "epoch": 3.7992831541218637, + "grad_norm": 0.2653384804725647, + "learning_rate": 5.799000047208181e-07, + "loss": 0.0149, + "step": 9540 + }, + { + "epoch": 3.8032656312226205, + "grad_norm": 0.1700735241174698, + "learning_rate": 5.550606682937054e-07, + "loss": 0.0148, + "step": 9550 + }, + { + "epoch": 3.8072481083233773, + "grad_norm": 0.3729400336742401, + "learning_rate": 5.307620538013481e-07, + "loss": 0.0163, + "step": 9560 + }, + { + "epoch": 3.8112305854241337, + "grad_norm": 0.28273651003837585, + "learning_rate": 5.070044269694874e-07, + "loss": 0.0148, + "step": 9570 + }, + { + "epoch": 3.8152130625248906, + "grad_norm": 0.25636887550354004, + "learning_rate": 4.837880476077417e-07, + "loss": 0.0149, + "step": 9580 + }, + { + "epoch": 3.819195539625647, + "grad_norm": 0.11277643591165543, + "learning_rate": 4.6111316960670835e-07, + "loss": 0.0132, + "step": 9590 + }, + { + "epoch": 3.823178016726404, + "grad_norm": 0.31709930300712585, + "learning_rate": 4.389800409352218e-07, + "loss": 0.0141, + "step": 9600 + }, + { + "epoch": 3.8271604938271606, + "grad_norm": 0.1908944696187973, + "learning_rate": 4.173889036376277e-07, + "loss": 0.015, + "step": 9610 + }, + { + "epoch": 3.831142970927917, + "grad_norm": 0.2939547300338745, + "learning_rate": 3.963399938311463e-07, + "loss": 0.0177, + "step": 9620 + }, + { + "epoch": 3.835125448028674, + "grad_norm": 0.20435106754302979, + "learning_rate": 3.7583354170328545e-07, + "loss": 0.0137, + "step": 9630 + }, + { + "epoch": 3.8391079251294307, + "grad_norm": 0.177963525056839, + "learning_rate": 3.558697715093207e-07, + "loss": 0.0117, + "step": 9640 + }, + { + "epoch": 3.843090402230187, + "grad_norm": 0.23722724616527557, + "learning_rate": 3.3644890156983576e-07, + "loss": 0.0142, + "step": 9650 + }, + { + "epoch": 3.847072879330944, + "grad_norm": 0.24979689717292786, + "learning_rate": 3.175711442683638e-07, + "loss": 0.0139, + "step": 9660 + }, + { + "epoch": 3.8510553564317007, + "grad_norm": 0.13695870339870453, + "learning_rate": 2.9923670604902197e-07, + "loss": 0.0127, + "step": 9670 + }, + { + "epoch": 3.855037833532457, + "grad_norm": 0.2963074743747711, + "learning_rate": 2.814457874143028e-07, + "loss": 0.0165, + "step": 9680 + }, + { + "epoch": 3.859020310633214, + "grad_norm": 0.2667098641395569, + "learning_rate": 2.641985829228366e-07, + "loss": 0.0134, + "step": 9690 + }, + { + "epoch": 3.8630027877339703, + "grad_norm": 0.21023236215114594, + "learning_rate": 2.474952811872877e-07, + "loss": 0.0131, + "step": 9700 + }, + { + "epoch": 3.866985264834727, + "grad_norm": 0.21310463547706604, + "learning_rate": 2.3133606487228397e-07, + "loss": 0.0135, + "step": 9710 + }, + { + "epoch": 3.870967741935484, + "grad_norm": 0.2762566804885864, + "learning_rate": 2.157211106924295e-07, + "loss": 0.0148, + "step": 9720 + }, + { + "epoch": 3.874950219036241, + "grad_norm": 0.2990756928920746, + "learning_rate": 2.006505894103672e-07, + "loss": 0.0147, + "step": 9730 + }, + { + "epoch": 3.878932696136997, + "grad_norm": 0.17009320855140686, + "learning_rate": 1.8612466583489696e-07, + "loss": 0.0143, + "step": 9740 + }, + { + "epoch": 3.882915173237754, + "grad_norm": 0.1569436490535736, + "learning_rate": 1.7214349881918834e-07, + "loss": 0.0132, + "step": 9750 + }, + { + "epoch": 3.8868976503385104, + "grad_norm": 0.12430369853973389, + "learning_rate": 1.5870724125904845e-07, + "loss": 0.0106, + "step": 9760 + }, + { + "epoch": 3.8908801274392673, + "grad_norm": 0.2661726176738739, + "learning_rate": 1.4581604009124006e-07, + "loss": 0.0132, + "step": 9770 + }, + { + "epoch": 3.894862604540024, + "grad_norm": 0.10029175132513046, + "learning_rate": 1.334700362918717e-07, + "loss": 0.0113, + "step": 9780 + }, + { + "epoch": 3.8988450816407805, + "grad_norm": 0.24978956580162048, + "learning_rate": 1.2166936487486015e-07, + "loss": 0.0125, + "step": 9790 + }, + { + "epoch": 3.9028275587415373, + "grad_norm": 0.4270276725292206, + "learning_rate": 1.1041415489045914e-07, + "loss": 0.0131, + "step": 9800 + }, + { + "epoch": 3.9068100358422937, + "grad_norm": 0.22719305753707886, + "learning_rate": 9.970452942384412e-08, + "loss": 0.0126, + "step": 9810 + }, + { + "epoch": 3.9107925129430505, + "grad_norm": 0.20977602899074554, + "learning_rate": 8.954060559375754e-08, + "loss": 0.0114, + "step": 9820 + }, + { + "epoch": 3.9147749900438074, + "grad_norm": 0.1370612531900406, + "learning_rate": 7.99224945512489e-08, + "loss": 0.018, + "step": 9830 + }, + { + "epoch": 3.918757467144564, + "grad_norm": 0.17637065052986145, + "learning_rate": 7.085030147843675e-08, + "loss": 0.0149, + "step": 9840 + }, + { + "epoch": 3.9227399442453206, + "grad_norm": 0.22800922393798828, + "learning_rate": 6.232412558736523e-08, + "loss": 0.0166, + "step": 9850 + }, + { + "epoch": 3.9267224213460774, + "grad_norm": 0.23249153792858124, + "learning_rate": 5.434406011893822e-08, + "loss": 0.0172, + "step": 9860 + }, + { + "epoch": 3.930704898446834, + "grad_norm": 0.17791615426540375, + "learning_rate": 4.6910192341864664e-08, + "loss": 0.0113, + "step": 9870 + }, + { + "epoch": 3.9346873755475906, + "grad_norm": 0.21019835770130157, + "learning_rate": 4.0022603551737035e-08, + "loss": 0.0146, + "step": 9880 + }, + { + "epoch": 3.9386698526483475, + "grad_norm": 0.1602124720811844, + "learning_rate": 3.3681369070120985e-08, + "loss": 0.0127, + "step": 9890 + }, + { + "epoch": 3.942652329749104, + "grad_norm": 0.17522773146629333, + "learning_rate": 2.7886558243744866e-08, + "loss": 0.0145, + "step": 9900 + }, + { + "epoch": 3.9466348068498607, + "grad_norm": 0.2072092741727829, + "learning_rate": 2.2638234443722596e-08, + "loss": 0.0123, + "step": 9910 + }, + { + "epoch": 3.950617283950617, + "grad_norm": 0.1036510095000267, + "learning_rate": 1.7936455064887504e-08, + "loss": 0.016, + "step": 9920 + }, + { + "epoch": 3.954599761051374, + "grad_norm": 0.08399386703968048, + "learning_rate": 1.378127152514841e-08, + "loss": 0.0114, + "step": 9930 + }, + { + "epoch": 3.9585822381521307, + "grad_norm": 0.27939972281455994, + "learning_rate": 1.0172729264917857e-08, + "loss": 0.0167, + "step": 9940 + }, + { + "epoch": 3.9625647152528876, + "grad_norm": 0.17596809566020966, + "learning_rate": 7.1108677466458215e-09, + "loss": 0.0142, + "step": 9950 + }, + { + "epoch": 3.966547192353644, + "grad_norm": 0.1545400619506836, + "learning_rate": 4.595720454353414e-09, + "loss": 0.0145, + "step": 9960 + }, + { + "epoch": 3.970529669454401, + "grad_norm": 0.24510076642036438, + "learning_rate": 2.627314893294264e-09, + "loss": 0.0124, + "step": 9970 + }, + { + "epoch": 3.974512146555157, + "grad_norm": 0.2673027217388153, + "learning_rate": 1.2056725896270048e-09, + "loss": 0.0118, + "step": 9980 + }, + { + "epoch": 3.978494623655914, + "grad_norm": 0.2962305545806885, + "learning_rate": 3.308090902098826e-10, + "loss": 0.0156, + "step": 9990 + }, + { + "epoch": 3.982477100756671, + "grad_norm": 0.3653580844402313, + "learning_rate": 2.7339624120159555e-12, + "loss": 0.0137, + "step": 10000 + }, + { + "epoch": 3.982477100756671, + "step": 10000, + "total_flos": 0.0, + "train_loss": 0.029824630606919526, + "train_runtime": 5859.1243, + "train_samples_per_second": 54.616, + "train_steps_per_second": 1.707 + } + ], + "logging_steps": 10, + "max_steps": 10000, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 32, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1cc6b13bad500b1913c2ae225362d195aeeedb5 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e007b5f421b0dc7ee312e8ebf0f15871ce9ea2989cc2cb5ee33733e4be89fa +size 5304