Upload folder using huggingface_hub

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "/data/szaman/llava-finetuning/llava-v1.5-7b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd992ec710981c4ead6b9f71897958f9f4e286c3819c4f192e8c2384a118f2c
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51965e64bb2bf9e95e42bbd13fefed25f24596aa45c7c7deb046b72c3820e71d
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b42c09e3a6c07c91e30c8e4a2392fe0f95331d99c987971c65cc3d36c1136b4
+size 4239524944

model.safetensors.index.json

@@ -0,0 +1,693 @@
+{
+  "metadata": {
+    "total_size": 14125805568
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
+    "model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
+    "model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
+    "model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00003-of-00003.safetensors",
+    "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2814 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9989235737351991,
+  "eval_steps": 500,
+  "global_step": 464,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.6806,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.7444,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.7017,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.6305,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.5227,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.3905,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.269,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.1847,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 1.2008,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.2259,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 1.0843,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.1093,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 1.0567,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.0045,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999756307053947e-05,
+      "loss": 0.9836,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999025240093045e-05,
+      "loss": 0.9945,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997806834748455e-05,
+      "loss": 1.012,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9996101150403543e-05,
+      "loss": 1.0002,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999390827019096e-05,
+      "loss": 1.0176,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9991228300988586e-05,
+      "loss": 1.0494,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9988061373414342e-05,
+      "loss": 1.0395,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9984407641819812e-05,
+      "loss": 0.9945,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9980267284282718e-05,
+      "loss": 1.0104,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.9753,
+      "step": 24
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9970527522269204e-05,
+      "loss": 0.9829,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9964928592495046e-05,
+      "loss": 0.9406,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9958843986159705e-05,
+      "loss": 0.9735,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9952273999818312e-05,
+      "loss": 0.9919,
+      "step": 28
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 0.9872,
+      "step": 29
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9937679191605964e-05,
+      "loss": 0.93,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992965508106537e-05,
+      "loss": 0.9179,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.9876,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.991215540251542e-05,
+      "loss": 0.9884,
+      "step": 33
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.9792,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9892723329629885e-05,
+      "loss": 0.9702,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.988228381446553e-05,
+      "loss": 0.9575,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987136265072988e-05,
+      "loss": 0.9605,
+      "step": 37
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.985996037070505e-05,
+      "loss": 0.9465,
+      "step": 38
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.9438,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.983571470813386e-05,
+      "loss": 0.8716,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.982287250728689e-05,
+      "loss": 0.8425,
+      "step": 41
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9809551553491918e-05,
+      "loss": 0.8671,
+      "step": 42
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.979575249599344e-05,
+      "loss": 0.9382,
+      "step": 43
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.9426,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9766722783341682e-05,
+      "loss": 0.9615,
+      "step": 45
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9751493543055634e-05,
+      "loss": 0.9307,
+      "step": 46
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9735789028731603e-05,
+      "loss": 0.9455,
+      "step": 47
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9719610005785466e-05,
+      "loss": 0.915,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9702957262759964e-05,
+      "loss": 0.8733,
+      "step": 49
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.9304,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9668233886044597e-05,
+      "loss": 0.8837,
+      "step": 51
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9650164944723116e-05,
+      "loss": 0.9278,
+      "step": 52
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9631625667976584e-05,
+      "loss": 0.8601,
+      "step": 53
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.8639,
+      "step": 54
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9593139745400575e-05,
+      "loss": 0.8201,
+      "step": 55
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9573194975320672e-05,
+      "loss": 0.8901,
+      "step": 56
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9552783621223437e-05,
+      "loss": 0.8912,
+      "step": 57
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9531906677929472e-05,
+      "loss": 0.9046,
+      "step": 58
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.8824,
+      "step": 59
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9488760116444966e-05,
+      "loss": 0.8882,
+      "step": 60
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9466492601156964e-05,
+      "loss": 0.8873,
+      "step": 61
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.944376370237481e-05,
+      "loss": 0.9555,
+      "step": 62
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.942057452787297e-05,
+      "loss": 0.9429,
+      "step": 63
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.9233,
+      "step": 64
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.937281989491892e-05,
+      "loss": 0.9213,
+      "step": 65
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9348256763960146e-05,
+      "loss": 0.8389,
+      "step": 66
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9323238012155125e-05,
+      "loss": 0.8301,
+      "step": 67
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.9072,
+      "step": 68
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9271838545667876e-05,
+      "loss": 0.8944,
+      "step": 69
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9245460336123136e-05,
+      "loss": 0.8538,
+      "step": 70
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9218631515885007e-05,
+      "loss": 0.8686,
+      "step": 71
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9191353392552346e-05,
+      "loss": 0.8861,
+      "step": 72
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9163627295622397e-05,
+      "loss": 0.8764,
+      "step": 73
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.9213,
+      "step": 74
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.910683660806177e-05,
+      "loss": 0.8744,
+      "step": 75
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.907777478532909e-05,
+      "loss": 0.9065,
+      "step": 76
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9048270524660197e-05,
+      "loss": 0.8504,
+      "step": 77
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.901832526405114e-05,
+      "loss": 0.8971,
+      "step": 78
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8987940462991673e-05,
+      "loss": 0.806,
+      "step": 79
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.895711760239413e-05,
+      "loss": 0.9,
+      "step": 80
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.892585818452126e-05,
+      "loss": 0.9391,
+      "step": 81
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.889416373291298e-05,
+      "loss": 0.8273,
+      "step": 82
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8862035792312148e-05,
+      "loss": 0.8936,
+      "step": 83
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.7711,
+      "step": 84
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.879648572866617e-05,
+      "loss": 0.8493,
+      "step": 85
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.873,
+      "step": 86
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8729220772698096e-05,
+      "loss": 0.8214,
+      "step": 87
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.869494929505219e-05,
+      "loss": 0.86,
+      "step": 88
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.8474,
+      "step": 89
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8625136692072577e-05,
+      "loss": 0.8508,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8589598969306646e-05,
+      "loss": 0.8444,
+      "step": 91
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.855364260160507e-05,
+      "loss": 0.8501,
+      "step": 92
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.851726934143048e-05,
+      "loss": 0.839,
+      "step": 93
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.9062,
+      "step": 94
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8443279255020153e-05,
+      "loss": 0.9258,
+      "step": 95
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8405666034956842e-05,
+      "loss": 0.9218,
+      "step": 96
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.836764313458962e-05,
+      "loss": 0.8922,
+      "step": 97
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8329212407100996e-05,
+      "loss": 0.8281,
+      "step": 98
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 0.8925,
+      "step": 99
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8251134982782952e-05,
+      "loss": 0.886,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.821149209133704e-05,
+      "loss": 0.8394,
+      "step": 101
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8171448983351284e-05,
+      "loss": 0.8578,
+      "step": 102
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8131007610470278e-05,
+      "loss": 0.8895,
+      "step": 103
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.8173,
+      "step": 104
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.804893797355914e-05,
+      "loss": 0.8727,
+      "step": 105
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8007313709487334e-05,
+      "loss": 0.8706,
+      "step": 106
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7965299180241963e-05,
+      "loss": 0.8391,
+      "step": 107
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.792289643355191e-05,
+      "loss": 0.8228,
+      "step": 108
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 0.8564,
+      "step": 109
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.78369345732584e-05,
+      "loss": 0.8927,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7793379649314743e-05,
+      "loss": 0.7994,
+      "step": 111
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7749444887041797e-05,
+      "loss": 0.8048,
+      "step": 112
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7705132427757895e-05,
+      "loss": 0.8455,
+      "step": 113
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.8032,
+      "step": 114
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.761538307536737e-05,
+      "loss": 0.8482,
+      "step": 115
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7569950556517566e-05,
+      "loss": 0.8006,
+      "step": 116
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7524149088957244e-05,
+      "loss": 0.8869,
+      "step": 117
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.747798090498532e-05,
+      "loss": 0.7997,
+      "step": 118
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 0.8333,
+      "step": 119
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7384553406258842e-05,
+      "loss": 0.8226,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7337298645028764e-05,
+      "loss": 0.7886,
+      "step": 121
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.8996,
+      "step": 122
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7241718614374678e-05,
+      "loss": 0.8477,
+      "step": 123
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.878,
+      "step": 124
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7144726796328034e-05,
+      "loss": 0.8428,
+      "step": 125
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.709570736536521e-05,
+      "loss": 0.8092,
+      "step": 126
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7046342099635948e-05,
+      "loss": 0.8697,
+      "step": 127
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6996633405133656e-05,
+      "loss": 0.7754,
+      "step": 128
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 0.7986,
+      "step": 129
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.68961954373567e-05,
+      "loss": 0.8031,
+      "step": 130
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.684547105928689e-05,
+      "loss": 0.8354,
+      "step": 131
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6794413042615168e-05,
+      "loss": 0.8739,
+      "step": 132
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6743023875837233e-05,
+      "loss": 0.8048,
+      "step": 133
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.8386,
+      "step": 134
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6639262126522417e-05,
+      "loss": 0.7554,
+      "step": 135
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6586894601186804e-05,
+      "loss": 0.8475,
+      "step": 136
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6534206039901057e-05,
+      "loss": 0.8155,
+      "step": 137
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6481199010631312e-05,
+      "loss": 0.8429,
+      "step": 138
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.7883,
+      "step": 139
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.77,
+      "step": 140
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.632029302664851e-05,
+      "loss": 0.7894,
+      "step": 141
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6266038113644605e-05,
+      "loss": 0.8344,
+      "step": 142
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6211477802783105e-05,
+      "loss": 0.8601,
+      "step": 143
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.9022,
+      "step": 144
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.610145163901268e-05,
+      "loss": 0.8067,
+      "step": 145
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6045991148623752e-05,
+      "loss": 0.8004,
+      "step": 146
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.599023598515586e-05,
+      "loss": 0.8638,
+      "step": 147
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5934188866037017e-05,
+      "loss": 0.8481,
+      "step": 148
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.8726,
+      "step": 149
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5821229701572897e-05,
+      "loss": 0.8407,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5764323161697933e-05,
+      "loss": 0.7786,
+      "step": 151
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.570713567684432e-05,
+      "loss": 0.8233,
+      "step": 152
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.564967003424938e-05,
+      "loss": 0.8965,
+      "step": 153
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.7953,
+      "step": 154
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.553391549243344e-05,
+      "loss": 0.8382,
+      "step": 155
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5475632234925505e-05,
+      "loss": 0.8256,
+      "step": 156
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.54170821028274e-05,
+      "loss": 0.8488,
+      "step": 157
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.8986,
+      "step": 158
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 0.8572,
+      "step": 159
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5239859059700794e-05,
+      "loss": 0.8046,
+      "step": 160
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5180270093731305e-05,
+      "loss": 0.8461,
+      "step": 161
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5120428648705716e-05,
+      "loss": 0.8132,
+      "step": 162
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5060337641211637e-05,
+      "loss": 0.8497,
+      "step": 163
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8151,
+      "step": 164
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.493941866584231e-05,
+      "loss": 0.8352,
+      "step": 165
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4878596591387329e-05,
+      "loss": 0.8662,
+      "step": 166
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4817536741017153e-05,
+      "loss": 0.8644,
+      "step": 167
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4756242090702756e-05,
+      "loss": 0.8058,
+      "step": 168
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 0.8268,
+      "step": 169
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.463296035119862e-05,
+      "loss": 0.7497,
+      "step": 170
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4570979270586944e-05,
+      "loss": 0.7812,
+      "step": 171
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4508775406894308e-05,
+      "loss": 0.7519,
+      "step": 172
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4446351791849276e-05,
+      "loss": 0.9014,
+      "step": 173
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.7682,
+      "step": 174
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4320857488019826e-05,
+      "loss": 0.8379,
+      "step": 175
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.8332,
+      "step": 176
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4194520824461773e-05,
+      "loss": 0.7577,
+      "step": 177
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.413104429824542e-05,
+      "loss": 0.8506,
+      "step": 178
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.8465,
+      "step": 179
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.4003490325568953e-05,
+      "loss": 0.7704,
+      "step": 180
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3939419095909513e-05,
+      "loss": 0.8035,
+      "step": 181
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3875155864521031e-05,
+      "loss": 0.8743,
+      "step": 182
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3810703763502744e-05,
+      "loss": 0.8431,
+      "step": 183
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.797,
+      "step": 184
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3681245526846782e-05,
+      "loss": 0.7441,
+      "step": 185
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3616245700820922e-05,
+      "loss": 0.7876,
+      "step": 186
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3551069624081372e-05,
+      "loss": 0.7772,
+      "step": 187
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3485720473218153e-05,
+      "loss": 0.7836,
+      "step": 188
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.7715,
+      "step": 189
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3354515697502552e-05,
+      "loss": 0.7837,
+      "step": 190
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3288666467385834e-05,
+      "loss": 0.8376,
+      "step": 191
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3222656952305113e-05,
+      "loss": 0.7995,
+      "step": 192
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3156490369471026e-05,
+      "loss": 0.8232,
+      "step": 193
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.8618,
+      "step": 194
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3023698907504447e-05,
+      "loss": 0.8094,
+      "step": 195
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2957080500440469e-05,
+      "loss": 0.7832,
+      "step": 196
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2890317969444716e-05,
+      "loss": 0.8129,
+      "step": 197
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2823414568428767e-05,
+      "loss": 0.8238,
+      "step": 198
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 0.8246,
+      "step": 199
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2689198206152657e-05,
+      "loss": 0.8304,
+      "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2621891786408648e-05,
+      "loss": 0.7911,
+      "step": 201
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2554457579357906e-05,
+      "loss": 0.8427,
+      "step": 202
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2486898871648552e-05,
+      "loss": 0.7555,
+      "step": 203
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.7625,
+      "step": 204
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.23514211310259e-05,
+      "loss": 0.7994,
+      "step": 205
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2283508701106559e-05,
+      "loss": 0.8183,
+      "step": 206
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2215484976194675e-05,
+      "loss": 0.7922,
+      "step": 207
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2147353271670634e-05,
+      "loss": 0.7845,
+      "step": 208
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 0.8034,
+      "step": 209
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2010779211459649e-05,
+      "loss": 0.83,
+      "step": 210
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.194234351219972e-05,
+      "loss": 0.7644,
+      "step": 211
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.8275,
+      "step": 212
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1805191452505602e-05,
+      "loss": 0.8256,
+      "step": 213
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.796,
+      "step": 214
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1667687467161025e-05,
+      "loss": 0.7525,
+      "step": 215
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.159881187691835e-05,
+      "loss": 0.788,
+      "step": 216
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1529858362840383e-05,
+      "loss": 0.8071,
+      "step": 217
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1460830285624119e-05,
+      "loss": 0.7687,
+      "step": 218
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1391731009600655e-05,
+      "loss": 0.7793,
+      "step": 219
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1322563902571227e-05,
+      "loss": 0.7792,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1253332335643043e-05,
+      "loss": 0.753,
+      "step": 221
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1184039683065014e-05,
+      "loss": 0.8115,
+      "step": 222
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1114689322063255e-05,
+      "loss": 0.7863,
+      "step": 223
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.7875,
+      "step": 224
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0975828997591496e-05,
+      "loss": 0.7481,
+      "step": 225
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0906325801977804e-05,
+      "loss": 0.7768,
+      "step": 226
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.083677843332316e-05,
+      "loss": 0.7882,
+      "step": 227
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0767190281268187e-05,
+      "loss": 0.7586,
+      "step": 228
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.8614,
+      "step": 229
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.8085,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.055821504993164e-05,
+      "loss": 0.7757,
+      "step": 231
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0488497697956134e-05,
+      "loss": 0.7611,
+      "step": 232
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0418756537291996e-05,
+      "loss": 0.7021,
+      "step": 233
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.7667,
+      "step": 234
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0279216387235691e-05,
+      "loss": 0.7475,
+      "step": 235
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0209424198833571e-05,
+      "loss": 0.8029,
+      "step": 236
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0139621803391454e-05,
+      "loss": 0.7237,
+      "step": 237
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0069812602979617e-05,
+      "loss": 0.7464,
+      "step": 238
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1e-05,
+      "loss": 0.7393,
+      "step": 239
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.930187397020385e-06,
+      "loss": 0.7582,
+      "step": 240
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.860378196608549e-06,
+      "loss": 0.7435,
+      "step": 241
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.790575801166432e-06,
+      "loss": 0.7691,
+      "step": 242
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.720783612764314e-06,
+      "loss": 0.7905,
+      "step": 243
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.8642,
+      "step": 244
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.581243462708007e-06,
+      "loss": 0.779,
+      "step": 245
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.511502302043867e-06,
+      "loss": 0.7765,
+      "step": 246
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.441784950068362e-06,
+      "loss": 0.781,
+      "step": 247
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.674,
+      "step": 248
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.302435262558748e-06,
+      "loss": 0.7532,
+      "step": 249
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.232809718731815e-06,
+      "loss": 0.8772,
+      "step": 250
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.163221566676847e-06,
+      "loss": 0.7803,
+      "step": 251
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.093674198022201e-06,
+      "loss": 0.7963,
+      "step": 252
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.024171002408507e-06,
+      "loss": 0.7205,
+      "step": 253
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.8772,
+      "step": 254
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.885310677936746e-06,
+      "loss": 0.8081,
+      "step": 255
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.815960316934991e-06,
+      "loss": 0.733,
+      "step": 256
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.746667664356957e-06,
+      "loss": 0.7366,
+      "step": 257
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.677436097428775e-06,
+      "loss": 0.7818,
+      "step": 258
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.60826899039935e-06,
+      "loss": 0.7873,
+      "step": 259
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.539169714375885e-06,
+      "loss": 0.786,
+      "step": 260
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.47014163715962e-06,
+      "loss": 0.7075,
+      "step": 261
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.401188123081653e-06,
+      "loss": 0.8245,
+      "step": 262
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.332312532838978e-06,
+      "loss": 0.8094,
+      "step": 263
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.7889,
+      "step": 264
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.194808547494401e-06,
+      "loss": 0.7979,
+      "step": 265
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.7844,
+      "step": 266
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.057656487800283e-06,
+      "loss": 0.809,
+      "step": 267
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.989220788540356e-06,
+      "loss": 0.8085,
+      "step": 268
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.92088309182241e-06,
+      "loss": 0.7639,
+      "step": 269
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.852646728329368e-06,
+      "loss": 0.736,
+      "step": 270
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.784515023805328e-06,
+      "loss": 0.7265,
+      "step": 271
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.716491298893443e-06,
+      "loss": 0.749,
+      "step": 272
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.6485788689741e-06,
+      "loss": 0.8023,
+      "step": 273
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.7135,
+      "step": 274
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.513101128351454e-06,
+      "loss": 0.806,
+      "step": 275
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.445542420642097e-06,
+      "loss": 0.8008,
+      "step": 276
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.378108213591355e-06,
+      "loss": 0.7742,
+      "step": 277
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.310801793847344e-06,
+      "loss": 0.7987,
+      "step": 278
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.7829,
+      "step": 279
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.176585431571235e-06,
+      "loss": 0.7326,
+      "step": 280
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.109682030555283e-06,
+      "loss": 0.7526,
+      "step": 281
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.042919499559538e-06,
+      "loss": 0.6843,
+      "step": 282
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.976301092495556e-06,
+      "loss": 0.762,
+      "step": 283
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6768,
+      "step": 284
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.843509630528977e-06,
+      "loss": 0.737,
+      "step": 285
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.777343047694891e-06,
+      "loss": 0.832,
+      "step": 286
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.711333532614168e-06,
+      "loss": 0.8041,
+      "step": 287
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.645484302497452e-06,
+      "loss": 0.7919,
+      "step": 288
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.7579,
+      "step": 289
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.5142795267818505e-06,
+      "loss": 0.7704,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.448930375918632e-06,
+      "loss": 0.7676,
+      "step": 291
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.383754299179079e-06,
+      "loss": 0.7982,
+      "step": 292
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.318754473153221e-06,
+      "loss": 0.8056,
+      "step": 293
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.8174,
+      "step": 294
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.18929623649726e-06,
+      "loss": 0.842,
+      "step": 295
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.124844135478971e-06,
+      "loss": 0.7873,
+      "step": 296
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.06058090409049e-06,
+      "loss": 0.79,
+      "step": 297
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.996509674431053e-06,
+      "loss": 0.7586,
+      "step": 298
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.932633569242e-06,
+      "loss": 0.7266,
+      "step": 299
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.868955701754584e-06,
+      "loss": 0.7449,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.8054791755382286e-06,
+      "loss": 0.77,
+      "step": 301
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.7869,
+      "step": 302
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.679142511980176e-06,
+      "loss": 0.7365,
+      "step": 303
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.8115,
+      "step": 304
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.553648208150728e-06,
+      "loss": 0.7988,
+      "step": 305
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.491224593105695e-06,
+      "loss": 0.7903,
+      "step": 306
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.429020729413062e-06,
+      "loss": 0.7548,
+      "step": 307
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.367039648801386e-06,
+      "loss": 0.84,
+      "step": 308
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.305284372141095e-06,
+      "loss": 0.7513,
+      "step": 309
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.243757909297247e-06,
+      "loss": 0.7355,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.1824632589828465e-06,
+      "loss": 0.7603,
+      "step": 311
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.121403408612672e-06,
+      "loss": 0.756,
+      "step": 312
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.060581334157693e-06,
+      "loss": 0.797,
+      "step": 313
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.8073,
+      "step": 314
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.939662358788364e-06,
+      "loss": 0.7516,
+      "step": 315
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.879571351294287e-06,
+      "loss": 0.7729,
+      "step": 316
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.8197299062687e-06,
+      "loss": 0.7715,
+      "step": 317
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.76014094029921e-06,
+      "loss": 0.77,
+      "step": 318
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.700807357667953e-06,
+      "loss": 0.789,
+      "step": 319
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.7728,
+      "step": 320
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.582917897172603e-06,
+      "loss": 0.7791,
+      "step": 321
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.524367765074499e-06,
+      "loss": 0.7511,
+      "step": 322
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.46608450756656e-06,
+      "loss": 0.7562,
+      "step": 323
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.7865,
+      "step": 324
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.350329965750622e-06,
+      "loss": 0.7174,
+      "step": 325
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.292864323155684e-06,
+      "loss": 0.7345,
+      "step": 326
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.235676838302069e-06,
+      "loss": 0.778,
+      "step": 327
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.178770298427107e-06,
+      "loss": 0.795,
+      "step": 328
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.8197,
+      "step": 329
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.065811133962987e-06,
+      "loss": 0.7793,
+      "step": 330
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.009764014844143e-06,
+      "loss": 0.7559,
+      "step": 331
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.954008851376252e-06,
+      "loss": 0.7528,
+      "step": 332
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.898548360987325e-06,
+      "loss": 0.7598,
+      "step": 333
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.8453,
+      "step": 334
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7885221972168974e-06,
+      "loss": 0.7612,
+      "step": 335
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7339618863553983e-06,
+      "loss": 0.7027,
+      "step": 336
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.679706973351491e-06,
+      "loss": 0.8072,
+      "step": 337
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.7634,
+      "step": 338
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.7478,
+      "step": 339
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.5188009893686916e-06,
+      "loss": 0.7218,
+      "step": 340
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.4657939600989453e-06,
+      "loss": 0.7411,
+      "step": 341
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.4131053988131947e-06,
+      "loss": 0.7689,
+      "step": 342
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.360737873477584e-06,
+      "loss": 0.7517,
+      "step": 343
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.7562,
+      "step": 344
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2569761241627694e-06,
+      "loss": 0.7675,
+      "step": 345
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2055869573848374e-06,
+      "loss": 0.7715,
+      "step": 346
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1545289407131128e-06,
+      "loss": 0.7528,
+      "step": 347
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.103804562643302e-06,
+      "loss": 0.7722,
+      "step": 348
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0534162954100264e-06,
+      "loss": 0.7861,
+      "step": 349
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.003366594866345e-06,
+      "loss": 0.7526,
+      "step": 350
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.953657900364053e-06,
+      "loss": 0.7173,
+      "step": 351
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9042926346347932e-06,
+      "loss": 0.7175,
+      "step": 352
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.855273203671969e-06,
+      "loss": 0.7912,
+      "step": 353
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.8047,
+      "step": 354
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7582813856253276e-06,
+      "loss": 0.771,
+      "step": 355
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.7895,
+      "step": 356
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6627013549712355e-06,
+      "loss": 0.6981,
+      "step": 357
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.615446593741161e-06,
+      "loss": 0.7507,
+      "step": 358
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5685517452260566e-06,
+      "loss": 0.6642,
+      "step": 359
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.522019095014683e-06,
+      "loss": 0.759,
+      "step": 360
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4758509110427576e-06,
+      "loss": 0.7535,
+      "step": 361
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.4300494434824373e-06,
+      "loss": 0.7649,
+      "step": 362
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3846169246326345e-06,
+      "loss": 0.7926,
+      "step": 363
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.7479,
+      "step": 364
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2948675722421086e-06,
+      "loss": 0.7626,
+      "step": 365
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2505551129582047e-06,
+      "loss": 0.7163,
+      "step": 366
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.206620350685257e-06,
+      "loss": 0.8096,
+      "step": 367
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.163065426741603e-06,
+      "loss": 0.7981,
+      "step": 368
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.119892463932781e-06,
+      "loss": 0.7507,
+      "step": 369
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0771035664480944e-06,
+      "loss": 0.7346,
+      "step": 370
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0347008197580376e-06,
+      "loss": 0.7388,
+      "step": 371
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9926862905126663e-06,
+      "loss": 0.768,
+      "step": 372
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.95106202644086e-06,
+      "loss": 0.7726,
+      "step": 373
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.7567,
+      "step": 374
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8689923895297247e-06,
+      "loss": 0.7588,
+      "step": 375
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8285510166487154e-06,
+      "loss": 0.6654,
+      "step": 376
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7885079086629598e-06,
+      "loss": 0.7637,
+      "step": 377
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7488650172170496e-06,
+      "loss": 0.7029,
+      "step": 378
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.709624274449584e-06,
+      "loss": 0.7585,
+      "step": 379
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6707875928990059e-06,
+      "loss": 0.7061,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6323568654103838e-06,
+      "loss": 0.7368,
+      "step": 381
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5943339650431578e-06,
+      "loss": 0.7132,
+      "step": 382
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5567207449798517e-06,
+      "loss": 0.7341,
+      "step": 383
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.73,
+      "step": 384
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4827306585695234e-06,
+      "loss": 0.7187,
+      "step": 385
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.446357398394934e-06,
+      "loss": 0.6724,
+      "step": 386
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4104010306933558e-06,
+      "loss": 0.6546,
+      "step": 387
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3748633079274254e-06,
+      "loss": 0.7822,
+      "step": 388
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.7428,
+      "step": 389
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.30505070494781e-06,
+      "loss": 0.8222,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2707792273019049e-06,
+      "loss": 0.6602,
+      "step": 391
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.7266,
+      "step": 392
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2035142713338366e-06,
+      "loss": 0.7973,
+      "step": 393
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.69,
+      "step": 394
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1379642076878528e-06,
+      "loss": 0.7544,
+      "step": 395
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1058362670870248e-06,
+      "loss": 0.8371,
+      "step": 396
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0741418154787443e-06,
+      "loss": 0.7257,
+      "step": 397
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.042882397605871e-06,
+      "loss": 0.7834,
+      "step": 398
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.012059537008332e-06,
+      "loss": 0.7095,
+      "step": 399
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.816747359488632e-07,
+      "loss": 0.7552,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.517294753398066e-07,
+      "loss": 0.6726,
+      "step": 401
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.222252146709143e-07,
+      "loss": 0.7404,
+      "step": 402
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.931633919382299e-07,
+      "loss": 0.7394,
+      "step": 403
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.7101,
+      "step": 404
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.363727043776037e-07,
+      "loss": 0.7446,
+      "step": 405
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.086466074476562e-07,
+      "loss": 0.7659,
+      "step": 406
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.81368484114996e-07,
+      "loss": 0.7543,
+      "step": 407
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.545396638768698e-07,
+      "loss": 0.7727,
+      "step": 408
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.281614543321269e-07,
+      "loss": 0.7143,
+      "step": 409
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.7251,
+      "step": 410
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.767619878448783e-07,
+      "loss": 0.7893,
+      "step": 411
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.517432360398556e-07,
+      "loss": 0.7487,
+      "step": 412
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.271801050810856e-07,
+      "loss": 0.7105,
+      "step": 413
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.7616,
+      "step": 414
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.794254721270331e-07,
+      "loss": 0.7849,
+      "step": 415
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.562362976251901e-07,
+      "loss": 0.6783,
+      "step": 416
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.335073988430373e-07,
+      "loss": 0.6506,
+      "step": 417
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.112398835550348e-07,
+      "loss": 0.7298,
+      "step": 418
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.7401,
+      "step": 419
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.6809332207053083e-07,
+      "loss": 0.7586,
+      "step": 420
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4721637877656377e-07,
+      "loss": 0.6923,
+      "step": 421
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.268050246793276e-07,
+      "loss": 0.7255,
+      "step": 422
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.068602545994249e-07,
+      "loss": 0.7007,
+      "step": 423
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.7424,
+      "step": 424
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.68374332023419e-07,
+      "loss": 0.7398,
+      "step": 425
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.498350552768859e-07,
+      "loss": 0.705,
+      "step": 426
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3176611395540625e-07,
+      "loss": 0.6938,
+      "step": 427
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.7828,
+      "step": 428
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.970427372400353e-07,
+      "loss": 0.7369,
+      "step": 429
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.8038999421453827e-07,
+      "loss": 0.7793,
+      "step": 430
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6421097126839714e-07,
+      "loss": 0.7145,
+      "step": 431
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4850645694436736e-07,
+      "loss": 0.713,
+      "step": 432
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.332772166583208e-07,
+      "loss": 0.7325,
+      "step": 433
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.7161,
+      "step": 434
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0424750400655947e-07,
+      "loss": 0.7902,
+      "step": 435
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.9044844650808468e-07,
+      "loss": 0.705,
+      "step": 436
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.7712749271311392e-07,
+      "loss": 0.7681,
+      "step": 437
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6428529186614195e-07,
+      "loss": 0.8181,
+      "step": 438
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.6704,
+      "step": 439
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.400396292949513e-07,
+      "loss": 0.7066,
+      "step": 440
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2863734927012094e-07,
+      "loss": 0.8501,
+      "step": 441
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1771618553447217e-07,
+      "loss": 0.7451,
+      "step": 442
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0727667037011668e-07,
+      "loss": 0.7253,
+      "step": 443
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.7257,
+      "step": 444
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.784459748458318e-08,
+      "loss": 0.6626,
+      "step": 445
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.7767,
+      "step": 446
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.034491893463059e-08,
+      "loss": 0.7786,
+      "step": 447
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.232080839403631e-08,
+      "loss": 0.7652,
+      "step": 448
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.4781046317267103e-08,
+      "loss": 0.6881,
+      "step": 449
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.772600018168816e-08,
+      "loss": 0.8155,
+      "step": 450
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.115601384029666e-08,
+      "loss": 0.7628,
+      "step": 451
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.50714075049563e-08,
+      "loss": 0.7743,
+      "step": 452
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.947247773079753e-08,
+      "loss": 0.7125,
+      "step": 453
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.7575,
+      "step": 454
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.973271571728441e-08,
+      "loss": 0.7412,
+      "step": 455
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5592358180189782e-08,
+      "loss": 0.7395,
+      "step": 456
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1938626585660252e-08,
+      "loss": 0.7093,
+      "step": 457
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 8.771699011416169e-09,
+      "loss": 0.7632,
+      "step": 458
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.091729809042379e-09,
+      "loss": 0.7242,
+      "step": 459
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.898849596456477e-09,
+      "loss": 0.7168,
+      "step": 460
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.193165251545004e-09,
+      "loss": 0.7389,
+      "step": 461
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.74759906957612e-10,
+      "loss": 0.7733,
+      "step": 462
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.436929460525317e-10,
+      "loss": 0.8064,
+      "step": 463
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.7507,
+      "step": 464
+    },
+    {
+      "epoch": 1.0,
+      "step": 464,
+      "total_flos": 312662581837824.0,
+      "train_loss": 0.8204254103374893,
+      "train_runtime": 6409.4411,
+      "train_samples_per_second": 4.638,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 464,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "total_flos": 312662581837824.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50b23a85e7299094fbbbe4308c449675ac6f5675468d66d8edf83c1e28aff942
+size 6776