Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.8058284866381398,
+    "train_runtime": 31310.8966,
+    "train_samples": 68459,
+    "train_samples_per_second": 5.802,
+    "train_steps_per_second": 0.091
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-7B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0146321d97396c24df715d6ca26af42826e1ef607942ac39fd80feb0712ff2c9
+size 4986106736

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb48a35fedbd4bf7d0c280bbcea5652837e273a224a54016e995f3d0da69fe75
+size 4981244328

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169b5340c377482cb5d523a04ce439fdc126f83690635ec26424cb2b379f2b42
+size 4228306968

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8438c4d292ccac293d7ae8a3cb85675c08f8a637397ee8f9a4f0014ccafc6aa1
+size 1242284160

model.safetensors.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 15437897728
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.8058284866381398,
+    "train_runtime": 31310.8966,
+    "train_samples": 68459,
+    "train_samples_per_second": 5.802,
+    "train_steps_per_second": 0.091
+}

trainer_state.json

@@ -0,0 +1,4006 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.999207397622193,
+  "eval_steps": 500,
+  "global_step": 2838,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 54.60578280011217,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 2.0852,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 42.54745106429926,
+      "learning_rate": 1.724137931034483e-06,
+      "loss": 2.0381,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 9.212853479586382,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 1.6632,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.314912275996213,
+      "learning_rate": 5.172413793103449e-06,
+      "loss": 1.3468,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.03433890035307,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 1.2538,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.6447411660183016,
+      "learning_rate": 8.620689655172414e-06,
+      "loss": 1.2604,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.1857065034640795,
+      "learning_rate": 9.999996872939885e-06,
+      "loss": 1.1935,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7526909326796276,
+      "learning_rate": 9.999887426246524e-06,
+      "loss": 1.1939,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.5378704654179458,
+      "learning_rate": 9.999621630458743e-06,
+      "loss": 1.1626,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.3071739468687105,
+      "learning_rate": 9.999199493888118e-06,
+      "loss": 1.122,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.1982413397341172,
+      "learning_rate": 9.998621029735082e-06,
+      "loss": 1.1191,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0956550608235818,
+      "learning_rate": 9.997886256088507e-06,
+      "loss": 1.123,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0821639142212824,
+      "learning_rate": 9.996995195925152e-06,
+      "loss": 1.0751,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.0865870956103822,
+      "learning_rate": 9.995947877108933e-06,
+      "loss": 1.114,
+      "step": 65
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.0582468505041362,
+      "learning_rate": 9.99474433239006e-06,
+      "loss": 1.0609,
+      "step": 70
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0556893008132,
+      "learning_rate": 9.993384599404001e-06,
+      "loss": 1.0861,
+      "step": 75
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.053104954690895,
+      "learning_rate": 9.991868720670322e-06,
+      "loss": 1.0792,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.069931327549148,
+      "learning_rate": 9.990196743591341e-06,
+      "loss": 1.0722,
+      "step": 85
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0793525694046096,
+      "learning_rate": 9.988368720450656e-06,
+      "loss": 1.0561,
+      "step": 90
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.0449093375062701,
+      "learning_rate": 9.986384708411507e-06,
+      "loss": 1.0675,
+      "step": 95
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.9947694351867048,
+      "learning_rate": 9.984244769514988e-06,
+      "loss": 1.0395,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.0281907914775885,
+      "learning_rate": 9.981948970678107e-06,
+      "loss": 1.0455,
+      "step": 105
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.0429607059919377,
+      "learning_rate": 9.979497383691695e-06,
+      "loss": 1.014,
+      "step": 110
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1551790238118493,
+      "learning_rate": 9.976890085218157e-06,
+      "loss": 1.0335,
+      "step": 115
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.0958017153997939,
+      "learning_rate": 9.974127156789082e-06,
+      "loss": 1.0566,
+      "step": 120
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.0545164230640043,
+      "learning_rate": 9.971208684802686e-06,
+      "loss": 1.0234,
+      "step": 125
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.1119539198620567,
+      "learning_rate": 9.968134760521114e-06,
+      "loss": 0.9956,
+      "step": 130
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.045532676163788,
+      "learning_rate": 9.964905480067585e-06,
+      "loss": 1.0103,
+      "step": 135
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.0818099938062198,
+      "learning_rate": 9.96152094442339e-06,
+      "loss": 0.987,
+      "step": 140
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.06916616510137,
+      "learning_rate": 9.957981259424724e-06,
+      "loss": 1.0189,
+      "step": 145
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.1000812098052206,
+      "learning_rate": 9.954286535759394e-06,
+      "loss": 1.0025,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.0740685860653156,
+      "learning_rate": 9.950436888963337e-06,
+      "loss": 1.0394,
+      "step": 155
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.0578416601226404,
+      "learning_rate": 9.946432439417021e-06,
+      "loss": 1.0419,
+      "step": 160
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.1378367934770748,
+      "learning_rate": 9.942273312341679e-06,
+      "loss": 1.04,
+      "step": 165
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.106141894903122,
+      "learning_rate": 9.937959637795389e-06,
+      "loss": 1.0112,
+      "step": 170
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0459501547982482,
+      "learning_rate": 9.93349155066901e-06,
+      "loss": 0.9959,
+      "step": 175
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.1420602608538855,
+      "learning_rate": 9.928869190681964e-06,
+      "loss": 0.9952,
+      "step": 180
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.0748374838181862,
+      "learning_rate": 9.924092702377863e-06,
+      "loss": 1.0094,
+      "step": 185
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.0535011085546289,
+      "learning_rate": 9.919162235119996e-06,
+      "loss": 1.0054,
+      "step": 190
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.0310625793824704,
+      "learning_rate": 9.91407794308665e-06,
+      "loss": 1.0117,
+      "step": 195
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.0359842004906923,
+      "learning_rate": 9.908839985266297e-06,
+      "loss": 0.9982,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.084059570369228,
+      "learning_rate": 9.903448525452618e-06,
+      "loss": 1.0127,
+      "step": 205
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1227120329409497,
+      "learning_rate": 9.89790373223938e-06,
+      "loss": 1.048,
+      "step": 210
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0615021518173307,
+      "learning_rate": 9.892205779015167e-06,
+      "loss": 1.0021,
+      "step": 215
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.070318683802529,
+      "learning_rate": 9.886354843957953e-06,
+      "loss": 1.0043,
+      "step": 220
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0419755132096296,
+      "learning_rate": 9.88035111002954e-06,
+      "loss": 0.9743,
+      "step": 225
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1796172322040084,
+      "learning_rate": 9.874194764969827e-06,
+      "loss": 0.9957,
+      "step": 230
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.0933963352790785,
+      "learning_rate": 9.867886001290943e-06,
+      "loss": 0.9814,
+      "step": 235
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.1066280030775704,
+      "learning_rate": 9.861425016271227e-06,
+      "loss": 0.9832,
+      "step": 240
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.1138948008724274,
+      "learning_rate": 9.854812011949059e-06,
+      "loss": 0.9871,
+      "step": 245
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.0644401239508805,
+      "learning_rate": 9.848047195116543e-06,
+      "loss": 0.9951,
+      "step": 250
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.1880183474724784,
+      "learning_rate": 9.841130777313039e-06,
+      "loss": 0.9902,
+      "step": 255
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.0747113009717828,
+      "learning_rate": 9.834062974818547e-06,
+      "loss": 0.9433,
+      "step": 260
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.1442114734348945,
+      "learning_rate": 9.826844008646949e-06,
+      "loss": 0.9703,
+      "step": 265
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.0895758630826766,
+      "learning_rate": 9.81947410453909e-06,
+      "loss": 1.0236,
+      "step": 270
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.996075250542336,
+      "learning_rate": 9.811953492955728e-06,
+      "loss": 0.9577,
+      "step": 275
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.1734623195649692,
+      "learning_rate": 9.80428240907032e-06,
+      "loss": 0.9752,
+      "step": 280
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.282701051609298,
+      "learning_rate": 9.796461092761668e-06,
+      "loss": 0.987,
+      "step": 285
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.0721992980205135,
+      "learning_rate": 9.788489788606423e-06,
+      "loss": 0.944,
+      "step": 290
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.105694230535082,
+      "learning_rate": 9.780368745871438e-06,
+      "loss": 0.9804,
+      "step": 295
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1121587653939105,
+      "learning_rate": 9.772098218505963e-06,
+      "loss": 1.0099,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1073177873687883,
+      "learning_rate": 9.763678465133712e-06,
+      "loss": 0.9887,
+      "step": 305
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.1986141459298305,
+      "learning_rate": 9.755109749044781e-06,
+      "loss": 0.9749,
+      "step": 310
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 1.0864391212895972,
+      "learning_rate": 9.7463923381874e-06,
+      "loss": 0.9767,
+      "step": 315
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0595953209575595,
+      "learning_rate": 9.737526505159564e-06,
+      "loss": 0.9297,
+      "step": 320
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.083224438455533,
+      "learning_rate": 9.728512527200509e-06,
+      "loss": 0.9498,
+      "step": 325
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.1306776282190978,
+      "learning_rate": 9.719350686182041e-06,
+      "loss": 0.982,
+      "step": 330
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.07939319367538,
+      "learning_rate": 9.710041268599718e-06,
+      "loss": 0.9669,
+      "step": 335
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1100410279851476,
+      "learning_rate": 9.700584565563897e-06,
+      "loss": 0.956,
+      "step": 340
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.0917533373255544,
+      "learning_rate": 9.690980872790627e-06,
+      "loss": 0.9878,
+      "step": 345
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.1287494016251205,
+      "learning_rate": 9.681230490592403e-06,
+      "loss": 0.9604,
+      "step": 350
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0366025693971206,
+      "learning_rate": 9.671333723868773e-06,
+      "loss": 0.9809,
+      "step": 355
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.1876939558601538,
+      "learning_rate": 9.66129088209681e-06,
+      "loss": 0.9324,
+      "step": 360
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.1296469706806582,
+      "learning_rate": 9.651102279321429e-06,
+      "loss": 0.98,
+      "step": 365
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.0920615981549329,
+      "learning_rate": 9.640768234145563e-06,
+      "loss": 0.9474,
+      "step": 370
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.045353192143218,
+      "learning_rate": 9.630289069720213e-06,
+      "loss": 0.9416,
+      "step": 375
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.0546831730532094,
+      "learning_rate": 9.619665113734327e-06,
+      "loss": 0.9583,
+      "step": 380
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.120397617115956,
+      "learning_rate": 9.608896698404567e-06,
+      "loss": 0.9739,
+      "step": 385
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0897789727469696,
+      "learning_rate": 9.597984160464908e-06,
+      "loss": 0.9882,
+      "step": 390
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.0655227440534312,
+      "learning_rate": 9.586927841156121e-06,
+      "loss": 0.973,
+      "step": 395
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.024445190271631,
+      "learning_rate": 9.575728086215093e-06,
+      "loss": 0.9488,
+      "step": 400
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.0957551302719917,
+      "learning_rate": 9.564385245864015e-06,
+      "loss": 0.9395,
+      "step": 405
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.0348921383964815,
+      "learning_rate": 9.552899674799438e-06,
+      "loss": 0.9618,
+      "step": 410
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1320917241343242,
+      "learning_rate": 9.541271732181174e-06,
+      "loss": 0.9737,
+      "step": 415
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.0955620287950987,
+      "learning_rate": 9.52950178162107e-06,
+      "loss": 0.9765,
+      "step": 420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.0865957472837047,
+      "learning_rate": 9.517590191171638e-06,
+      "loss": 0.9402,
+      "step": 425
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.0608004961340336,
+      "learning_rate": 9.505537333314534e-06,
+      "loss": 0.938,
+      "step": 430
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0436288259170787,
+      "learning_rate": 9.493343584948931e-06,
+      "loss": 0.9495,
+      "step": 435
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0827000850655668,
+      "learning_rate": 9.481009327379714e-06,
+      "loss": 0.9505,
+      "step": 440
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 1.0958366892000795,
+      "learning_rate": 9.46853494630557e-06,
+      "loss": 0.9536,
+      "step": 445
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.0431220913897328,
+      "learning_rate": 9.455920831806917e-06,
+      "loss": 0.942,
+      "step": 450
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.1372655798293543,
+      "learning_rate": 9.443167378333711e-06,
+      "loss": 0.9447,
+      "step": 455
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.0890187843066097,
+      "learning_rate": 9.43027498469311e-06,
+      "loss": 0.9291,
+      "step": 460
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.128255566030822,
+      "learning_rate": 9.41724405403701e-06,
+      "loss": 0.9418,
+      "step": 465
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0200134644324146,
+      "learning_rate": 9.404074993849421e-06,
+      "loss": 0.927,
+      "step": 470
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.0912622433950008,
+      "learning_rate": 9.390768215933746e-06,
+      "loss": 0.943,
+      "step": 475
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.1784430852167105,
+      "learning_rate": 9.377324136399887e-06,
+      "loss": 0.9409,
+      "step": 480
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.0732445497397998,
+      "learning_rate": 9.36374317565124e-06,
+      "loss": 0.9401,
+      "step": 485
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.1241973380928443,
+      "learning_rate": 9.350025758371554e-06,
+      "loss": 0.9188,
+      "step": 490
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0680249447424572,
+      "learning_rate": 9.336172313511636e-06,
+      "loss": 0.9304,
+      "step": 495
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.0400938648362148,
+      "learning_rate": 9.322183274275954e-06,
+      "loss": 0.9465,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.1484166178621282,
+      "learning_rate": 9.308059078109078e-06,
+      "loss": 0.9431,
+      "step": 505
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0928763685485705,
+      "learning_rate": 9.29380016668201e-06,
+      "loss": 0.9368,
+      "step": 510
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.0470334802413224,
+      "learning_rate": 9.279406985878367e-06,
+      "loss": 0.9529,
+      "step": 515
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.055693577627048,
+      "learning_rate": 9.264879985780436e-06,
+      "loss": 0.9237,
+      "step": 520
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0582407523485609,
+      "learning_rate": 9.250219620655112e-06,
+      "loss": 0.9455,
+      "step": 525
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.0392740863841614,
+      "learning_rate": 9.235426348939674e-06,
+      "loss": 0.9866,
+      "step": 530
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.087021743413759,
+      "learning_rate": 9.220500633227467e-06,
+      "loss": 0.9797,
+      "step": 535
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 1.0905659766649087,
+      "learning_rate": 9.205442940253426e-06,
+      "loss": 0.9231,
+      "step": 540
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.0838061353931883,
+      "learning_rate": 9.190253740879484e-06,
+      "loss": 0.9155,
+      "step": 545
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1721559515157844,
+      "learning_rate": 9.174933510079847e-06,
+      "loss": 0.9132,
+      "step": 550
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0711291424853389,
+      "learning_rate": 9.159482726926147e-06,
+      "loss": 0.9368,
+      "step": 555
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.0906836737125443,
+      "learning_rate": 9.14390187457245e-06,
+      "loss": 0.9652,
+      "step": 560
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2147816750505283,
+      "learning_rate": 9.128191440240159e-06,
+      "loss": 0.922,
+      "step": 565
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.0745698856829782,
+      "learning_rate": 9.11235191520277e-06,
+      "loss": 0.9267,
+      "step": 570
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.1107563079565528,
+      "learning_rate": 9.096383794770513e-06,
+      "loss": 0.9403,
+      "step": 575
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.0645734678937102,
+      "learning_rate": 9.080287578274866e-06,
+      "loss": 0.9149,
+      "step": 580
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.1729380707889032,
+      "learning_rate": 9.064063769052933e-06,
+      "loss": 0.9236,
+      "step": 585
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0634029251400858,
+      "learning_rate": 9.047712874431716e-06,
+      "loss": 0.9264,
+      "step": 590
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.185148731024843,
+      "learning_rate": 9.031235405712239e-06,
+      "loss": 0.9632,
+      "step": 595
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.1238661801404854,
+      "learning_rate": 9.014631878153564e-06,
+      "loss": 0.9364,
+      "step": 600
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1101591200426506,
+      "learning_rate": 8.997902810956682e-06,
+      "loss": 0.9121,
+      "step": 605
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.1328306862765927,
+      "learning_rate": 8.98104872724827e-06,
+      "loss": 0.9637,
+      "step": 610
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.1182389860600772,
+      "learning_rate": 8.964070154064343e-06,
+      "loss": 0.9431,
+      "step": 615
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.2315329373588069,
+      "learning_rate": 8.94696762233376e-06,
+      "loss": 0.9261,
+      "step": 620
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.0785263989248792,
+      "learning_rate": 8.92974166686163e-06,
+      "loss": 0.9218,
+      "step": 625
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0293877329539916,
+      "learning_rate": 8.912392826312595e-06,
+      "loss": 0.9516,
+      "step": 630
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0797961930582287,
+      "learning_rate": 8.894921643193966e-06,
+      "loss": 0.94,
+      "step": 635
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0052477432214972,
+      "learning_rate": 8.877328663838776e-06,
+      "loss": 0.9207,
+      "step": 640
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0126272743426095,
+      "learning_rate": 8.85961443838869e-06,
+      "loss": 0.9292,
+      "step": 645
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.0166858946265631,
+      "learning_rate": 8.841779520776803e-06,
+      "loss": 0.9171,
+      "step": 650
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.0674058891203713,
+      "learning_rate": 8.823824468710312e-06,
+      "loss": 0.9238,
+      "step": 655
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0826543746678357,
+      "learning_rate": 8.805749843653086e-06,
+      "loss": 0.8903,
+      "step": 660
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0474293060948185,
+      "learning_rate": 8.787556210808101e-06,
+      "loss": 0.8952,
+      "step": 665
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.1092322508696293,
+      "learning_rate": 8.769244139099774e-06,
+      "loss": 0.9191,
+      "step": 670
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.0453618423472522,
+      "learning_rate": 8.750814201156157e-06,
+      "loss": 0.9287,
+      "step": 675
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0150902528617922,
+      "learning_rate": 8.732266973291053e-06,
+      "loss": 0.9005,
+      "step": 680
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.111573072134849,
+      "learning_rate": 8.713603035485972e-06,
+      "loss": 0.9061,
+      "step": 685
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.0266552996471214,
+      "learning_rate": 8.694822971372012e-06,
+      "loss": 0.8981,
+      "step": 690
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.026959416886306,
+      "learning_rate": 8.675927368211599e-06,
+      "loss": 0.9119,
+      "step": 695
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.990879098356618,
+      "learning_rate": 8.656916816880122e-06,
+      "loss": 0.934,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.016936193517629,
+      "learning_rate": 8.637791911847462e-06,
+      "loss": 0.9031,
+      "step": 705
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.0105346034407392,
+      "learning_rate": 8.618553251159405e-06,
+      "loss": 0.8918,
+      "step": 710
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0219526658502593,
+      "learning_rate": 8.599201436418927e-06,
+      "loss": 0.9202,
+      "step": 715
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0611008297726183,
+      "learning_rate": 8.579737072767396e-06,
+      "loss": 0.8956,
+      "step": 720
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.0532525094762688,
+      "learning_rate": 8.560160768865642e-06,
+      "loss": 0.8782,
+      "step": 725
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.0472370063073,
+      "learning_rate": 8.540473136874926e-06,
+      "loss": 0.9215,
+      "step": 730
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0503901600633805,
+      "learning_rate": 8.520674792437793e-06,
+      "loss": 0.905,
+      "step": 735
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.0699401745712223,
+      "learning_rate": 8.50076635465883e-06,
+      "loss": 0.8914,
+      "step": 740
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.1604934245734189,
+      "learning_rate": 8.480748446085293e-06,
+      "loss": 0.923,
+      "step": 745
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.0575469862405844,
+      "learning_rate": 8.460621692687656e-06,
+      "loss": 0.91,
+      "step": 750
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1861862918344839,
+      "learning_rate": 8.44038672384002e-06,
+      "loss": 0.9183,
+      "step": 755
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0866238920331526,
+      "learning_rate": 8.420044172300443e-06,
+      "loss": 0.9012,
+      "step": 760
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0963030089254635,
+      "learning_rate": 8.399594674191147e-06,
+      "loss": 0.8867,
+      "step": 765
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 1.0516263694748806,
+      "learning_rate": 8.379038868978635e-06,
+      "loss": 0.9204,
+      "step": 770
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0602404388082067,
+      "learning_rate": 8.358377399453684e-06,
+      "loss": 0.8975,
+      "step": 775
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.0524212623827451,
+      "learning_rate": 8.337610911711248e-06,
+      "loss": 0.9182,
+      "step": 780
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.0486851629524967,
+      "learning_rate": 8.316740055130263e-06,
+      "loss": 0.8996,
+      "step": 785
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.0382393662171674,
+      "learning_rate": 8.295765482353326e-06,
+      "loss": 0.8898,
+      "step": 790
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.0801053233779676,
+      "learning_rate": 8.274687849266295e-06,
+      "loss": 0.8942,
+      "step": 795
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.082914632918619,
+      "learning_rate": 8.253507814977779e-06,
+      "loss": 0.9335,
+      "step": 800
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.115797305584172,
+      "learning_rate": 8.232226041798528e-06,
+      "loss": 0.8733,
+      "step": 805
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.0758274816242523,
+      "learning_rate": 8.210843195220717e-06,
+      "loss": 0.9121,
+      "step": 810
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.9966437564306923,
+      "learning_rate": 8.189359943897137e-06,
+      "loss": 0.9126,
+      "step": 815
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.1254388184304862,
+      "learning_rate": 8.167776959620298e-06,
+      "loss": 0.9113,
+      "step": 820
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.033615919920944,
+      "learning_rate": 8.1460949173014e-06,
+      "loss": 0.8863,
+      "step": 825
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0126421627367477,
+      "learning_rate": 8.124314494949247e-06,
+      "loss": 0.9044,
+      "step": 830
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.0545539629522227,
+      "learning_rate": 8.102436373649029e-06,
+      "loss": 0.8942,
+      "step": 835
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.004956283976033,
+      "learning_rate": 8.080461237541049e-06,
+      "loss": 0.9255,
+      "step": 840
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.0862660155528163,
+      "learning_rate": 8.0583897737993e-06,
+      "loss": 0.9275,
+      "step": 845
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0697124134441602,
+      "learning_rate": 8.036222672609994e-06,
+      "loss": 0.9161,
+      "step": 850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0639070724236763,
+      "learning_rate": 8.013960627149981e-06,
+      "loss": 0.8874,
+      "step": 855
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.166900094582672,
+      "learning_rate": 7.991604333565062e-06,
+      "loss": 0.8897,
+      "step": 860
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.1335592965754175,
+      "learning_rate": 7.969154490948225e-06,
+      "loss": 0.8964,
+      "step": 865
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0520381511921073,
+      "learning_rate": 7.946611801317794e-06,
+      "loss": 0.8736,
+      "step": 870
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.16753848747216,
+      "learning_rate": 7.923976969595459e-06,
+      "loss": 0.9112,
+      "step": 875
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0772133099773151,
+      "learning_rate": 7.901250703584245e-06,
+      "loss": 0.9155,
+      "step": 880
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.1464686627860388,
+      "learning_rate": 7.878433713946373e-06,
+      "loss": 0.8962,
+      "step": 885
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.0835779136854178,
+      "learning_rate": 7.855526714181041e-06,
+      "loss": 0.9058,
+      "step": 890
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.171366478493349,
+      "learning_rate": 7.832530420602113e-06,
+      "loss": 0.8756,
+      "step": 895
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.040168900901505,
+      "learning_rate": 7.809445552315714e-06,
+      "loss": 0.8594,
+      "step": 900
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.02166560480321,
+      "learning_rate": 7.786272831197745e-06,
+      "loss": 0.8935,
+      "step": 905
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.1107392454183416,
+      "learning_rate": 7.763012981871314e-06,
+      "loss": 0.904,
+      "step": 910
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9896358057101541,
+      "learning_rate": 7.739666731684073e-06,
+      "loss": 0.9068,
+      "step": 915
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.9788741930391702,
+      "learning_rate": 7.716234810685476e-06,
+      "loss": 0.8846,
+      "step": 920
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.9931045191442167,
+      "learning_rate": 7.692717951603942e-06,
+      "loss": 0.8584,
+      "step": 925
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.0645481368236074,
+      "learning_rate": 7.669116889823955e-06,
+      "loss": 0.8992,
+      "step": 930
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9816731950451545,
+      "learning_rate": 7.645432363363057e-06,
+      "loss": 0.8851,
+      "step": 935
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9899142833993008,
+      "learning_rate": 7.621665112848776e-06,
+      "loss": 0.8845,
+      "step": 940
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0638888300871174,
+      "learning_rate": 7.597815881495465e-06,
+      "loss": 0.8773,
+      "step": 945
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.031662431521578,
+      "learning_rate": 7.573885415081059e-06,
+      "loss": 0.8258,
+      "step": 950
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.040426497974828,
+      "learning_rate": 7.54987446192376e-06,
+      "loss": 0.7907,
+      "step": 955
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.9887566903005512,
+      "learning_rate": 7.525783772858624e-06,
+      "loss": 0.8091,
+      "step": 960
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 1.0542179478307365,
+      "learning_rate": 7.5016141012141e-06,
+      "loss": 0.7815,
+      "step": 965
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.0738731959256824,
+      "learning_rate": 7.477366202788456e-06,
+      "loss": 0.7734,
+      "step": 970
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.9975806760235982,
+      "learning_rate": 7.45304083582616e-06,
+      "loss": 0.7824,
+      "step": 975
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.005274019925314,
+      "learning_rate": 7.4286387609941544e-06,
+      "loss": 0.769,
+      "step": 980
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.0937329481520819,
+      "learning_rate": 7.40416074135808e-06,
+      "loss": 0.791,
+      "step": 985
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.9987999174071854,
+      "learning_rate": 7.379607542358414e-06,
+      "loss": 0.7983,
+      "step": 990
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.074721973505265,
+      "learning_rate": 7.3549799317865235e-06,
+      "loss": 0.8264,
+      "step": 995
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.0023766389640552,
+      "learning_rate": 7.330278679760673e-06,
+      "loss": 0.8166,
+      "step": 1000
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.0263488491446793,
+      "learning_rate": 7.3055045587019315e-06,
+      "loss": 0.7756,
+      "step": 1005
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.222252310199244,
+      "learning_rate": 7.280658343310016e-06,
+      "loss": 0.8113,
+      "step": 1010
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 1.0803171037496995,
+      "learning_rate": 7.255740810539078e-06,
+      "loss": 0.7773,
+      "step": 1015
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.0429385720996782,
+      "learning_rate": 7.230752739573398e-06,
+      "loss": 0.7959,
+      "step": 1020
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.0525788357504489,
+      "learning_rate": 7.205694911803019e-06,
+      "loss": 0.7962,
+      "step": 1025
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.986228023483833,
+      "learning_rate": 7.18056811079932e-06,
+      "loss": 0.79,
+      "step": 1030
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.031179895714868,
+      "learning_rate": 7.155373122290508e-06,
+      "loss": 0.8101,
+      "step": 1035
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.0379629517770603,
+      "learning_rate": 7.13011073413705e-06,
+      "loss": 0.781,
+      "step": 1040
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.033153108919124,
+      "learning_rate": 7.1047817363070325e-06,
+      "loss": 0.8418,
+      "step": 1045
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 1.0357203376239867,
+      "learning_rate": 7.079386920851466e-06,
+      "loss": 0.8065,
+      "step": 1050
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 1.0540192082846203,
+      "learning_rate": 7.053927081879505e-06,
+      "loss": 0.7956,
+      "step": 1055
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.0552828635725824,
+      "learning_rate": 7.0284030155336315e-06,
+      "loss": 0.7945,
+      "step": 1060
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.9810627289945896,
+      "learning_rate": 7.002815519964745e-06,
+      "loss": 0.7965,
+      "step": 1065
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 1.0916102744452092,
+      "learning_rate": 6.977165395307215e-06,
+      "loss": 0.7991,
+      "step": 1070
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.1543690326062077,
+      "learning_rate": 6.951453443653852e-06,
+      "loss": 0.7896,
+      "step": 1075
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.1170103600405488,
+      "learning_rate": 6.9256804690308276e-06,
+      "loss": 0.7828,
+      "step": 1080
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.0526733296614392,
+      "learning_rate": 6.899847277372538e-06,
+      "loss": 0.7923,
+      "step": 1085
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 1.0770254342023697,
+      "learning_rate": 6.873954676496395e-06,
+      "loss": 0.8128,
+      "step": 1090
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.037705594081886,
+      "learning_rate": 6.848003476077567e-06,
+      "loss": 0.7856,
+      "step": 1095
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.0319807068181204,
+      "learning_rate": 6.8219944876236645e-06,
+      "loss": 0.7949,
+      "step": 1100
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 1.0927555007584646,
+      "learning_rate": 6.795928524449354e-06,
+      "loss": 0.7941,
+      "step": 1105
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9869897993273156,
+      "learning_rate": 6.769806401650936e-06,
+      "loss": 0.7667,
+      "step": 1110
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0055956062759406,
+      "learning_rate": 6.743628936080852e-06,
+      "loss": 0.7855,
+      "step": 1115
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0283367881989096,
+      "learning_rate": 6.717396946322137e-06,
+      "loss": 0.7745,
+      "step": 1120
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.0345829389670045,
+      "learning_rate": 6.6911112526628295e-06,
+      "loss": 0.7842,
+      "step": 1125
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.0711135328845822,
+      "learning_rate": 6.664772677070316e-06,
+      "loss": 0.7558,
+      "step": 1130
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.9877769296594265,
+      "learning_rate": 6.638382043165628e-06,
+      "loss": 0.7788,
+      "step": 1135
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.131836138091609,
+      "learning_rate": 6.611940176197688e-06,
+      "loss": 0.7901,
+      "step": 1140
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.058249641590972,
+      "learning_rate": 6.585447903017506e-06,
+      "loss": 0.7936,
+      "step": 1145
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 1.073971008814511,
+      "learning_rate": 6.558906052052314e-06,
+      "loss": 0.7835,
+      "step": 1150
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 1.0491301969369466,
+      "learning_rate": 6.532315453279673e-06,
+      "loss": 0.7902,
+      "step": 1155
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.046297097483487,
+      "learning_rate": 6.505676938201512e-06,
+      "loss": 0.7767,
+      "step": 1160
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 1.046022517875942,
+      "learning_rate": 6.478991339818128e-06,
+      "loss": 0.8091,
+      "step": 1165
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.0086633248074561,
+      "learning_rate": 6.4522594926021355e-06,
+      "loss": 0.7797,
+      "step": 1170
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.0965955454651117,
+      "learning_rate": 6.425482232472377e-06,
+      "loss": 0.7702,
+      "step": 1175
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0362189192150881,
+      "learning_rate": 6.3986603967677805e-06,
+      "loss": 0.7931,
+      "step": 1180
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.110468197330772,
+      "learning_rate": 6.371794824221173e-06,
+      "loss": 0.7917,
+      "step": 1185
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.0163659020071605,
+      "learning_rate": 6.344886354933058e-06,
+      "loss": 0.7886,
+      "step": 1190
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.0115549227695064,
+      "learning_rate": 6.3179358303453386e-06,
+      "loss": 0.7511,
+      "step": 1195
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 1.0872016119161863,
+      "learning_rate": 6.290944093215016e-06,
+      "loss": 0.8036,
+      "step": 1200
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 1.0553500518484338,
+      "learning_rate": 6.263911987587822e-06,
+      "loss": 0.7938,
+      "step": 1205
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.993815270148442,
+      "learning_rate": 6.236840358771837e-06,
+      "loss": 0.7788,
+      "step": 1210
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.0605675582324252,
+      "learning_rate": 6.20973005331105e-06,
+      "loss": 0.7781,
+      "step": 1215
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.0965085071552372,
+      "learning_rate": 6.1825819189588885e-06,
+      "loss": 0.7872,
+      "step": 1220
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.040866195350916,
+      "learning_rate": 6.155396804651714e-06,
+      "loss": 0.7966,
+      "step": 1225
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.0593376609536802,
+      "learning_rate": 6.128175560482264e-06,
+      "loss": 0.7832,
+      "step": 1230
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.0081718313330637,
+      "learning_rate": 6.1009190376730785e-06,
+      "loss": 0.7772,
+      "step": 1235
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.9892554397828908,
+      "learning_rate": 6.07362808854988e-06,
+      "loss": 0.7856,
+      "step": 1240
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.0515874983049542,
+      "learning_rate": 6.046303566514919e-06,
+      "loss": 0.7812,
+      "step": 1245
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.01738547568124,
+      "learning_rate": 6.018946326020287e-06,
+      "loss": 0.7824,
+      "step": 1250
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.992994982201507,
+      "learning_rate": 5.991557222541201e-06,
+      "loss": 0.7842,
+      "step": 1255
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.9928822859609259,
+      "learning_rate": 5.964137112549251e-06,
+      "loss": 0.7906,
+      "step": 1260
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.0673862770846931,
+      "learning_rate": 5.9366868534856115e-06,
+      "loss": 0.7896,
+      "step": 1265
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.0627251705995355,
+      "learning_rate": 5.909207303734241e-06,
+      "loss": 0.7965,
+      "step": 1270
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.0050051635503012,
+      "learning_rate": 5.881699322595031e-06,
+      "loss": 0.7775,
+      "step": 1275
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.0049258262531797,
+      "learning_rate": 5.854163770256934e-06,
+      "loss": 0.7659,
+      "step": 1280
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.1097225296353777,
+      "learning_rate": 5.826601507771073e-06,
+      "loss": 0.7699,
+      "step": 1285
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.0610730723756006,
+      "learning_rate": 5.799013397023806e-06,
+      "loss": 0.7996,
+      "step": 1290
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.0285633823079718,
+      "learning_rate": 5.771400300709785e-06,
+      "loss": 0.7829,
+      "step": 1295
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.0484599021027985,
+      "learning_rate": 5.743763082304973e-06,
+      "loss": 0.7619,
+      "step": 1300
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.0137701786577156,
+      "learning_rate": 5.7161026060396375e-06,
+      "loss": 0.798,
+      "step": 1305
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.0289414598602742,
+      "learning_rate": 5.688419736871341e-06,
+      "loss": 0.7827,
+      "step": 1310
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.058376335913828,
+      "learning_rate": 5.660715340457874e-06,
+      "loss": 0.7921,
+      "step": 1315
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.0011219088912342,
+      "learning_rate": 5.632990283130204e-06,
+      "loss": 0.781,
+      "step": 1320
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.984264955084216,
+      "learning_rate": 5.605245431865368e-06,
+      "loss": 0.7772,
+      "step": 1325
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.0151072044919451,
+      "learning_rate": 5.577481654259377e-06,
+      "loss": 0.7735,
+      "step": 1330
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.063533843295668,
+      "learning_rate": 5.549699818500074e-06,
+      "loss": 0.7682,
+      "step": 1335
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.0434635789190496,
+      "learning_rate": 5.521900793339989e-06,
+      "loss": 0.7915,
+      "step": 1340
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.0587561050751115,
+      "learning_rate": 5.494085448069181e-06,
+      "loss": 0.7997,
+      "step": 1345
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.0758864296233028,
+      "learning_rate": 5.466254652488036e-06,
+      "loss": 0.7964,
+      "step": 1350
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.0556751372323996,
+      "learning_rate": 5.438409276880089e-06,
+      "loss": 0.8062,
+      "step": 1355
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.9792859835280993,
+      "learning_rate": 5.410550191984798e-06,
+      "loss": 0.787,
+      "step": 1360
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0231438624972786,
+      "learning_rate": 5.3826782689703115e-06,
+      "loss": 0.7803,
+      "step": 1365
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 1.0660534726358564,
+      "learning_rate": 5.354794379406242e-06,
+      "loss": 0.78,
+      "step": 1370
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.9527414539128428,
+      "learning_rate": 5.3268993952363936e-06,
+      "loss": 0.796,
+      "step": 1375
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.9870931434726852,
+      "learning_rate": 5.29899418875151e-06,
+      "loss": 0.7652,
+      "step": 1380
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.0537299945885146,
+      "learning_rate": 5.271079632561992e-06,
+      "loss": 0.7854,
+      "step": 1385
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.1396368040574916,
+      "learning_rate": 5.243156599570606e-06,
+      "loss": 0.7617,
+      "step": 1390
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 1.0924704024745873,
+      "learning_rate": 5.2152259629451986e-06,
+      "loss": 0.7713,
+      "step": 1395
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.021493417245078,
+      "learning_rate": 5.18728859609138e-06,
+      "loss": 0.7609,
+      "step": 1400
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.0148194958691719,
+      "learning_rate": 5.159345372625223e-06,
+      "loss": 0.7788,
+      "step": 1405
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.0402765811164951,
+      "learning_rate": 5.131397166345938e-06,
+      "loss": 0.7599,
+      "step": 1410
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.9966250584272072,
+      "learning_rate": 5.103444851208549e-06,
+      "loss": 0.7874,
+      "step": 1415
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.9871275158697829,
+      "learning_rate": 5.075489301296567e-06,
+      "loss": 0.7566,
+      "step": 1420
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.0896451679213162,
+      "learning_rate": 5.047531390794661e-06,
+      "loss": 0.7699,
+      "step": 1425
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.1203863877988638,
+      "learning_rate": 5.019571993961307e-06,
+      "loss": 0.8088,
+      "step": 1430
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.03311513179617,
+      "learning_rate": 4.9916119851014664e-06,
+      "loss": 0.7739,
+      "step": 1435
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.0389351009988612,
+      "learning_rate": 4.96365223853924e-06,
+      "loss": 0.7816,
+      "step": 1440
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.9960641498632878,
+      "learning_rate": 4.93569362859052e-06,
+      "loss": 0.775,
+      "step": 1445
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.9388823495229471,
+      "learning_rate": 4.907737029535664e-06,
+      "loss": 0.756,
+      "step": 1450
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.0662538022442485,
+      "learning_rate": 4.8797833155921396e-06,
+      "loss": 0.7992,
+      "step": 1455
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.0350212904727674,
+      "learning_rate": 4.8518333608872015e-06,
+      "loss": 0.7595,
+      "step": 1460
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.9967538128228846,
+      "learning_rate": 4.823888039430551e-06,
+      "loss": 0.7582,
+      "step": 1465
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.0139079612075497,
+      "learning_rate": 4.795948225087001e-06,
+      "loss": 0.7709,
+      "step": 1470
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.0510044388149635,
+      "learning_rate": 4.7680147915491585e-06,
+      "loss": 0.7692,
+      "step": 1475
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 1.0641353890612333,
+      "learning_rate": 4.740088612310096e-06,
+      "loss": 0.7847,
+      "step": 1480
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.0192435995305715,
+      "learning_rate": 4.7121705606360424e-06,
+      "loss": 0.7732,
+      "step": 1485
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.0076325415256413,
+      "learning_rate": 4.684261509539072e-06,
+      "loss": 0.7701,
+      "step": 1490
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.9707102286396411,
+      "learning_rate": 4.65636233174981e-06,
+      "loss": 0.77,
+      "step": 1495
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.0835636202474823,
+      "learning_rate": 4.628473899690133e-06,
+      "loss": 0.7849,
+      "step": 1500
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.0157410126136626,
+      "learning_rate": 4.600597085445894e-06,
+      "loss": 0.784,
+      "step": 1505
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.0616186913926178,
+      "learning_rate": 4.572732760739653e-06,
+      "loss": 0.7785,
+      "step": 1510
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.006516145178769,
+      "learning_rate": 4.5448817969034165e-06,
+      "loss": 0.7753,
+      "step": 1515
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.0480529823653495,
+      "learning_rate": 4.517045064851386e-06,
+      "loss": 0.7989,
+      "step": 1520
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.0432567441250045,
+      "learning_rate": 4.489223435052732e-06,
+      "loss": 0.7946,
+      "step": 1525
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.0461342178531015,
+      "learning_rate": 4.461417777504363e-06,
+      "loss": 0.7676,
+      "step": 1530
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.0045382622138492,
+      "learning_rate": 4.433628961703733e-06,
+      "loss": 0.7651,
+      "step": 1535
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.9890094489435823,
+      "learning_rate": 4.405857856621644e-06,
+      "loss": 0.7943,
+      "step": 1540
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 1.0127639919495397,
+      "learning_rate": 4.378105330675074e-06,
+      "loss": 0.7895,
+      "step": 1545
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.0398544121817734,
+      "learning_rate": 4.350372251700025e-06,
+      "loss": 0.8004,
+      "step": 1550
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.037857459368961,
+      "learning_rate": 4.322659486924373e-06,
+      "loss": 0.7963,
+      "step": 1555
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.106103919813531,
+      "learning_rate": 4.294967902940768e-06,
+      "loss": 0.787,
+      "step": 1560
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 1.0865617469424886,
+      "learning_rate": 4.267298365679522e-06,
+      "loss": 0.788,
+      "step": 1565
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.0303226290700802,
+      "learning_rate": 4.239651740381534e-06,
+      "loss": 0.7642,
+      "step": 1570
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.0512505166055992,
+      "learning_rate": 4.212028891571237e-06,
+      "loss": 0.7832,
+      "step": 1575
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 1.0750316874597787,
+      "learning_rate": 4.184430683029552e-06,
+      "loss": 0.7599,
+      "step": 1580
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.0622608820174235,
+      "learning_rate": 4.156857977766896e-06,
+      "loss": 0.7841,
+      "step": 1585
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.0023528643121005,
+      "learning_rate": 4.129311637996182e-06,
+      "loss": 0.7845,
+      "step": 1590
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.0597451506484419,
+      "learning_rate": 4.101792525105857e-06,
+      "loss": 0.7802,
+      "step": 1595
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.9622973096022323,
+      "learning_rate": 4.0743014996329764e-06,
+      "loss": 0.7678,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.051095411122212,
+      "learning_rate": 4.046839421236276e-06,
+      "loss": 0.7972,
+      "step": 1605
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.0082128589578265,
+      "learning_rate": 4.019407148669312e-06,
+      "loss": 0.7948,
+      "step": 1610
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.0901759578931909,
+      "learning_rate": 3.992005539753592e-06,
+      "loss": 0.7914,
+      "step": 1615
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.0584302499373435,
+      "learning_rate": 3.964635451351758e-06,
+      "loss": 0.7821,
+      "step": 1620
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.043189384648134,
+      "learning_rate": 3.937297739340783e-06,
+      "loss": 0.778,
+      "step": 1625
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 1.0245392793145456,
+      "learning_rate": 3.909993258585219e-06,
+      "loss": 0.7908,
+      "step": 1630
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.0082519645854728,
+      "learning_rate": 3.882722862910458e-06,
+      "loss": 0.7793,
+      "step": 1635
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.0211341337802105,
+      "learning_rate": 3.8554874050760345e-06,
+      "loss": 0.8042,
+      "step": 1640
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.9920127978660441,
+      "learning_rate": 3.828287736748957e-06,
+      "loss": 0.758,
+      "step": 1645
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 1.0187229111502758,
+      "learning_rate": 3.8011247084770754e-06,
+      "loss": 0.7986,
+      "step": 1650
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.9982295207578855,
+      "learning_rate": 3.773999169662489e-06,
+      "loss": 0.7623,
+      "step": 1655
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.025180441312379,
+      "learning_rate": 3.746911968534982e-06,
+      "loss": 0.7454,
+      "step": 1660
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.9884338430346545,
+      "learning_rate": 3.7198639521254988e-06,
+      "loss": 0.7671,
+      "step": 1665
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.9685352318412103,
+      "learning_rate": 3.6928559662396574e-06,
+      "loss": 0.7583,
+      "step": 1670
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.029404957630594,
+      "learning_rate": 3.6658888554312967e-06,
+      "loss": 0.7868,
+      "step": 1675
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.9921023940146521,
+      "learning_rate": 3.6389634629760763e-06,
+      "loss": 0.7555,
+      "step": 1680
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.017350986680598,
+      "learning_rate": 3.612080630845096e-06,
+      "loss": 0.7905,
+      "step": 1685
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.0430603602540587,
+      "learning_rate": 3.5852411996785776e-06,
+      "loss": 0.7947,
+      "step": 1690
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.9737056004061376,
+      "learning_rate": 3.558446008759569e-06,
+      "loss": 0.7789,
+      "step": 1695
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0212119960635129,
+      "learning_rate": 3.5316958959876985e-06,
+      "loss": 0.7671,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0072141418910243,
+      "learning_rate": 3.504991697852983e-06,
+      "loss": 0.7844,
+      "step": 1705
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.059809521658242,
+      "learning_rate": 3.4783342494096627e-06,
+      "loss": 0.7845,
+      "step": 1710
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.032182317108509,
+      "learning_rate": 3.451724384250091e-06,
+      "loss": 0.7792,
+      "step": 1715
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.9779053888998924,
+      "learning_rate": 3.4251629344786675e-06,
+      "loss": 0.7591,
+      "step": 1720
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0116163318504925,
+      "learning_rate": 3.398650730685813e-06,
+      "loss": 0.7556,
+      "step": 1725
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.0511489470052602,
+      "learning_rate": 3.372188601922006e-06,
+      "loss": 0.7637,
+      "step": 1730
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.0172930500825146,
+      "learning_rate": 3.3457773756718513e-06,
+      "loss": 0.7696,
+      "step": 1735
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.039493994412079,
+      "learning_rate": 3.3194178778282046e-06,
+      "loss": 0.7931,
+      "step": 1740
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 1.033662637919394,
+      "learning_rate": 3.293110932666349e-06,
+      "loss": 0.7692,
+      "step": 1745
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.0584694868797393,
+      "learning_rate": 3.2668573628182145e-06,
+      "loss": 0.7792,
+      "step": 1750
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.994626270021195,
+      "learning_rate": 3.2406579892466582e-06,
+      "loss": 0.7682,
+      "step": 1755
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.9270237802993908,
+      "learning_rate": 3.2145136312197943e-06,
+      "loss": 0.7552,
+      "step": 1760
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 2.0595234604236357,
+      "learning_rate": 3.18842510628537e-06,
+      "loss": 0.7749,
+      "step": 1765
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.0396319816767299,
+      "learning_rate": 3.162393230245203e-06,
+      "loss": 0.804,
+      "step": 1770
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.0214462086054552,
+      "learning_rate": 3.1364188171296677e-06,
+      "loss": 0.7744,
+      "step": 1775
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 1.0145502545771508,
+      "learning_rate": 3.110502679172246e-06,
+      "loss": 0.7824,
+      "step": 1780
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.0196641711891408,
+      "learning_rate": 3.084645626784124e-06,
+      "loss": 0.7745,
+      "step": 1785
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.0197064636159427,
+      "learning_rate": 3.058848468528852e-06,
+      "loss": 0.8031,
+      "step": 1790
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.9907125667454302,
+      "learning_rate": 3.03311201109706e-06,
+      "loss": 0.7919,
+      "step": 1795
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.017942513059757,
+      "learning_rate": 3.0074370592812286e-06,
+      "loss": 0.7907,
+      "step": 1800
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.0821499695866912,
+      "learning_rate": 2.9818244159505265e-06,
+      "loss": 0.7901,
+      "step": 1805
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.9934394662674368,
+      "learning_rate": 2.956274882025706e-06,
+      "loss": 0.7638,
+      "step": 1810
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.0313411208961847,
+      "learning_rate": 2.930789256454052e-06,
+      "loss": 0.7553,
+      "step": 1815
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.9950833531614097,
+      "learning_rate": 2.905368336184406e-06,
+      "loss": 0.7576,
+      "step": 1820
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.9936896686220547,
+      "learning_rate": 2.8800129161422365e-06,
+      "loss": 0.7671,
+      "step": 1825
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.9909860465997411,
+      "learning_rate": 2.8547237892047852e-06,
+      "loss": 0.74,
+      "step": 1830
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.9788752840880554,
+      "learning_rate": 2.8295017461762806e-06,
+      "loss": 0.767,
+      "step": 1835
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.9764110020200104,
+      "learning_rate": 2.804347575763193e-06,
+      "loss": 0.7668,
+      "step": 1840
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.9772254707929505,
+      "learning_rate": 2.7792620645495917e-06,
+      "loss": 0.7425,
+      "step": 1845
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.0000854462976456,
+      "learning_rate": 2.7542459969725215e-06,
+      "loss": 0.7466,
+      "step": 1850
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.0352323998365711,
+      "learning_rate": 2.729300155297504e-06,
+      "loss": 0.771,
+      "step": 1855
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.9811051893834364,
+      "learning_rate": 2.704425319594049e-06,
+      "loss": 0.7778,
+      "step": 1860
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.0284677234046133,
+      "learning_rate": 2.6796222677112825e-06,
+      "loss": 0.7796,
+      "step": 1865
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.9664217044137716,
+      "learning_rate": 2.6548917752535997e-06,
+      "loss": 0.771,
+      "step": 1870
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.0008524753186703,
+      "learning_rate": 2.6302346155564385e-06,
+      "loss": 0.7963,
+      "step": 1875
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.0088045948631796,
+      "learning_rate": 2.6056515596620715e-06,
+      "loss": 0.7571,
+      "step": 1880
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.9727997698934588,
+      "learning_rate": 2.581143376295516e-06,
+      "loss": 0.7968,
+      "step": 1885
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9760428822299934,
+      "learning_rate": 2.556710831840481e-06,
+      "loss": 0.7829,
+      "step": 1890
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1893585643467264,
+      "learning_rate": 2.5323546903154074e-06,
+      "loss": 0.7363,
+      "step": 1895
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.0408498899558132,
+      "learning_rate": 2.508075713349575e-06,
+      "loss": 0.683,
+      "step": 1900
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 1.0852218097728863,
+      "learning_rate": 2.483874660159294e-06,
+      "loss": 0.6388,
+      "step": 1905
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.0636193658435114,
+      "learning_rate": 2.45975228752415e-06,
+      "loss": 0.6785,
+      "step": 1910
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.05164052954354,
+      "learning_rate": 2.435709349763354e-06,
+      "loss": 0.7024,
+      "step": 1915
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.0744751292672923,
+      "learning_rate": 2.4117465987121357e-06,
+      "loss": 0.6714,
+      "step": 1920
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 1.0221167769747221,
+      "learning_rate": 2.387864783698258e-06,
+      "loss": 0.6441,
+      "step": 1925
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.0453109653021675,
+      "learning_rate": 2.3640646515185596e-06,
+      "loss": 0.6668,
+      "step": 1930
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 1.0035196656143317,
+      "learning_rate": 2.3403469464156235e-06,
+      "loss": 0.6711,
+      "step": 1935
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 1.0614923887712562,
+      "learning_rate": 2.31671241005449e-06,
+      "loss": 0.6801,
+      "step": 1940
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.0457688195463548,
+      "learning_rate": 2.2931617814994704e-06,
+      "loss": 0.6676,
+      "step": 1945
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 1.094973586743587,
+      "learning_rate": 2.269695797191032e-06,
+      "loss": 0.6467,
+      "step": 1950
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.0312304548353073,
+      "learning_rate": 2.2463151909227804e-06,
+      "loss": 0.6626,
+      "step": 1955
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.0435526510546405,
+      "learning_rate": 2.223020693818495e-06,
+      "loss": 0.6565,
+      "step": 1960
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.0361388218534178,
+      "learning_rate": 2.1998130343092866e-06,
+      "loss": 0.655,
+      "step": 1965
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.071971382261616,
+      "learning_rate": 2.176692938110801e-06,
+      "loss": 0.6628,
+      "step": 1970
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.0449189624346316,
+      "learning_rate": 2.1536611282005374e-06,
+      "loss": 0.6742,
+      "step": 1975
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.0076278447431801,
+      "learning_rate": 2.130718324795234e-06,
+      "loss": 0.6615,
+      "step": 1980
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.044357139317297,
+      "learning_rate": 2.107865245328354e-06,
+      "loss": 0.6707,
+      "step": 1985
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 1.0155250644507565,
+      "learning_rate": 2.0851026044276405e-06,
+      "loss": 0.6701,
+      "step": 1990
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.012020172763002,
+      "learning_rate": 2.0624311138927795e-06,
+      "loss": 0.6531,
+      "step": 1995
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 1.0209851165233697,
+      "learning_rate": 2.0398514826731326e-06,
+      "loss": 0.6685,
+      "step": 2000
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.0147123852944229,
+      "learning_rate": 2.017364416845579e-06,
+      "loss": 0.6506,
+      "step": 2005
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 1.06994559921509,
+      "learning_rate": 1.9949706195924235e-06,
+      "loss": 0.6743,
+      "step": 2010
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.9930487524595831,
+      "learning_rate": 1.97267079117942e-06,
+      "loss": 0.6596,
+      "step": 2015
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.0334858708046972,
+      "learning_rate": 1.950465628933863e-06,
+      "loss": 0.6679,
+      "step": 2020
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 1.060064879245556,
+      "learning_rate": 1.9283558272227866e-06,
+      "loss": 0.6749,
+      "step": 2025
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.0171368650427,
+      "learning_rate": 1.9063420774312509e-06,
+      "loss": 0.6703,
+      "step": 2030
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.9646165360014197,
+      "learning_rate": 1.8844250679407272e-06,
+      "loss": 0.6878,
+      "step": 2035
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0209055430674492,
+      "learning_rate": 1.862605484107562e-06,
+      "loss": 0.7052,
+      "step": 2040
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0216869737250995,
+      "learning_rate": 1.840884008241549e-06,
+      "loss": 0.6778,
+      "step": 2045
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.990030094537176,
+      "learning_rate": 1.819261319584602e-06,
+      "loss": 0.675,
+      "step": 2050
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.9972968188321764,
+      "learning_rate": 1.7977380942895007e-06,
+      "loss": 0.6832,
+      "step": 2055
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.002919858574642,
+      "learning_rate": 1.7763150053987532e-06,
+      "loss": 0.6669,
+      "step": 2060
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.040641077805689,
+      "learning_rate": 1.7549927228235547e-06,
+      "loss": 0.6874,
+      "step": 2065
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.0136593089712416,
+      "learning_rate": 1.7337719133228308e-06,
+      "loss": 0.6662,
+      "step": 2070
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.0032381970613455,
+      "learning_rate": 1.7126532404823898e-06,
+      "loss": 0.657,
+      "step": 2075
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.0107311218156156,
+      "learning_rate": 1.6916373646941774e-06,
+      "loss": 0.6706,
+      "step": 2080
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.0313882769598175,
+      "learning_rate": 1.6707249431356188e-06,
+      "loss": 0.6803,
+      "step": 2085
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 1.0013867402651844,
+      "learning_rate": 1.6499166297490716e-06,
+      "loss": 0.6896,
+      "step": 2090
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.9974367112606389,
+      "learning_rate": 1.6292130752213747e-06,
+      "loss": 0.6773,
+      "step": 2095
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.0457782650116,
+      "learning_rate": 1.6086149269635081e-06,
+      "loss": 0.668,
+      "step": 2100
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.9930241935385495,
+      "learning_rate": 1.5881228290903367e-06,
+      "loss": 0.6508,
+      "step": 2105
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 1.0059354322817335,
+      "learning_rate": 1.5677374224004793e-06,
+      "loss": 0.6529,
+      "step": 2110
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.0338579100235163,
+      "learning_rate": 1.547459344356262e-06,
+      "loss": 0.6614,
+      "step": 2115
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.0203126239591027,
+      "learning_rate": 1.5272892290637892e-06,
+      "loss": 0.6749,
+      "step": 2120
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.983643586611109,
+      "learning_rate": 1.5072277072531127e-06,
+      "loss": 0.6517,
+      "step": 2125
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.0203957676102433,
+      "learning_rate": 1.4872754062585126e-06,
+      "loss": 0.6716,
+      "step": 2130
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.036201909144992,
+      "learning_rate": 1.4674329499988737e-06,
+      "loss": 0.6574,
+      "step": 2135
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 1.0277085537623492,
+      "learning_rate": 1.4477009589581787e-06,
+      "loss": 0.6593,
+      "step": 2140
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.9713425669443266,
+      "learning_rate": 1.4280800501661057e-06,
+      "loss": 0.6621,
+      "step": 2145
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 1.028497947768737,
+      "learning_rate": 1.408570837178735e-06,
+      "loss": 0.6656,
+      "step": 2150
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.0565632370972053,
+      "learning_rate": 1.3891739300593559e-06,
+      "loss": 0.6644,
+      "step": 2155
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.0043346444991121,
+      "learning_rate": 1.369889935359402e-06,
+      "loss": 0.6539,
+      "step": 2160
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.0294689299797029,
+      "learning_rate": 1.3507194560994657e-06,
+      "loss": 0.6666,
+      "step": 2165
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 1.0123495429792864,
+      "learning_rate": 1.331663091750463e-06,
+      "loss": 0.6928,
+      "step": 2170
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.9951164224382856,
+      "learning_rate": 1.312721438214869e-06,
+      "loss": 0.6501,
+      "step": 2175
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.025832661356824,
+      "learning_rate": 1.293895087808098e-06,
+      "loss": 0.6658,
+      "step": 2180
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.9888366700648139,
+      "learning_rate": 1.2751846292399705e-06,
+      "loss": 0.6592,
+      "step": 2185
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 1.0208359350524125,
+      "learning_rate": 1.2565906475963102e-06,
+      "loss": 0.6483,
+      "step": 2190
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.0568986951058392,
+      "learning_rate": 1.2381137243206455e-06,
+      "loss": 0.6557,
+      "step": 2195
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.9849389521844061,
+      "learning_rate": 1.2197544371960317e-06,
+      "loss": 0.6488,
+      "step": 2200
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 1.0466426799607875,
+      "learning_rate": 1.2015133603269753e-06,
+      "loss": 0.6596,
+      "step": 2205
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.9985742048846067,
+      "learning_rate": 1.183391064121493e-06,
+      "loss": 0.6572,
+      "step": 2210
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.9661312369342807,
+      "learning_rate": 1.1653881152732582e-06,
+      "loss": 0.6439,
+      "step": 2215
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.0327058718249167,
+      "learning_rate": 1.1475050767439e-06,
+      "loss": 0.6811,
+      "step": 2220
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.0365200638536969,
+      "learning_rate": 1.129742507745382e-06,
+      "loss": 0.6588,
+      "step": 2225
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.9804079029045045,
+      "learning_rate": 1.1121009637225283e-06,
+      "loss": 0.6783,
+      "step": 2230
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.0326866018136251,
+      "learning_rate": 1.0945809963356442e-06,
+      "loss": 0.6705,
+      "step": 2235
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 1.0314679157662048,
+      "learning_rate": 1.0771831534432714e-06,
+      "loss": 0.6353,
+      "step": 2240
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.9589889108924486,
+      "learning_rate": 1.0599079790850542e-06,
+      "loss": 0.655,
+      "step": 2245
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.9894914192305704,
+      "learning_rate": 1.0427560134647308e-06,
+      "loss": 0.643,
+      "step": 2250
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.0693419775513076,
+      "learning_rate": 1.0257277929332332e-06,
+      "loss": 0.6611,
+      "step": 2255
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.9951590219864285,
+      "learning_rate": 1.0088238499719254e-06,
+      "loss": 0.6403,
+      "step": 2260
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 1.0105626202971048,
+      "learning_rate": 9.920447131759392e-07,
+      "loss": 0.6707,
+      "step": 2265
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.0186289750333066,
+      "learning_rate": 9.753909072376594e-07,
+      "loss": 0.6809,
+      "step": 2270
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.0267980845318398,
+      "learning_rate": 9.58862952930304e-07,
+      "loss": 0.6642,
+      "step": 2275
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 1.0314667402705489,
+      "learning_rate": 9.424613670916499e-07,
+      "loss": 0.6815,
+      "step": 2280
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.9818510396592551,
+      "learning_rate": 9.261866626078625e-07,
+      "loss": 0.6579,
+      "step": 2285
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.998040916561116,
+      "learning_rate": 9.100393483974612e-07,
+      "loss": 0.6815,
+      "step": 2290
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.007529165875462,
+      "learning_rate": 8.940199293954033e-07,
+      "loss": 0.6609,
+      "step": 2295
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 1.0489165413908048,
+      "learning_rate": 8.781289065373016e-07,
+      "loss": 0.6661,
+      "step": 2300
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 1.0586483881635766,
+      "learning_rate": 8.623667767437483e-07,
+      "loss": 0.6494,
+      "step": 2305
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.970861929985865,
+      "learning_rate": 8.467340329047874e-07,
+      "loss": 0.6403,
+      "step": 2310
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 1.0315170437890622,
+      "learning_rate": 8.312311638644888e-07,
+      "loss": 0.6802,
+      "step": 2315
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 1.018615901485097,
+      "learning_rate": 8.158586544056791e-07,
+      "loss": 0.6813,
+      "step": 2320
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.9991739019084611,
+      "learning_rate": 8.00616985234764e-07,
+      "loss": 0.6757,
+      "step": 2325
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 1.039226698329409,
+      "learning_rate": 7.855066329667121e-07,
+      "loss": 0.6421,
+      "step": 2330
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.0505394427255816,
+      "learning_rate": 7.705280701101392e-07,
+      "loss": 0.6655,
+      "step": 2335
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.9750027460632938,
+      "learning_rate": 7.556817650525383e-07,
+      "loss": 0.6526,
+      "step": 2340
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.989246982143368,
+      "learning_rate": 7.409681820456315e-07,
+      "loss": 0.667,
+      "step": 2345
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.9977414734019189,
+      "learning_rate": 7.263877811908553e-07,
+      "loss": 0.6647,
+      "step": 2350
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.9875292562685886,
+      "learning_rate": 7.11941018424967e-07,
+      "loss": 0.667,
+      "step": 2355
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.9932801930288735,
+      "learning_rate": 6.97628345505797e-07,
+      "loss": 0.6511,
+      "step": 2360
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0199295886729471,
+      "learning_rate": 6.83450209998106e-07,
+      "loss": 0.6556,
+      "step": 2365
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0279710885988984,
+      "learning_rate": 6.694070552596105e-07,
+      "loss": 0.6676,
+      "step": 2370
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.0221845787587531,
+      "learning_rate": 6.554993204270993e-07,
+      "loss": 0.6512,
+      "step": 2375
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.9597530531552908,
+      "learning_rate": 6.417274404027163e-07,
+      "loss": 0.6482,
+      "step": 2380
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 1.0201542647464452,
+      "learning_rate": 6.280918458403506e-07,
+      "loss": 0.6623,
+      "step": 2385
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.9818765108255797,
+      "learning_rate": 6.14592963132174e-07,
+      "loss": 0.6599,
+      "step": 2390
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.0020031777534095,
+      "learning_rate": 6.012312143953075e-07,
+      "loss": 0.6818,
+      "step": 2395
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 1.020601700800406,
+      "learning_rate": 5.880070174586228e-07,
+      "loss": 0.6794,
+      "step": 2400
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.9781529112263975,
+      "learning_rate": 5.74920785849673e-07,
+      "loss": 0.6612,
+      "step": 2405
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.020456830272749,
+      "learning_rate": 5.619729287817621e-07,
+      "loss": 0.6638,
+      "step": 2410
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 1.0134058298180835,
+      "learning_rate": 5.49163851141154e-07,
+      "loss": 0.6468,
+      "step": 2415
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.0051724307379968,
+      "learning_rate": 5.36493953474404e-07,
+      "loss": 0.6411,
+      "step": 2420
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.9963926377815217,
+      "learning_rate": 5.239636319758356e-07,
+      "loss": 0.668,
+      "step": 2425
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.9731428272925532,
+      "learning_rate": 5.115732784751576e-07,
+      "loss": 0.6444,
+      "step": 2430
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 1.0185774017291327,
+      "learning_rate": 4.993232804252018e-07,
+      "loss": 0.6529,
+      "step": 2435
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 1.00711656230006,
+      "learning_rate": 4.872140208898118e-07,
+      "loss": 0.6539,
+      "step": 2440
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 1.0045164786035452,
+      "learning_rate": 4.7524587853186866e-07,
+      "loss": 0.6629,
+      "step": 2445
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.9961645157673277,
+      "learning_rate": 4.634192276014399e-07,
+      "loss": 0.6738,
+      "step": 2450
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 1.0214318273829783,
+      "learning_rate": 4.5173443792408625e-07,
+      "loss": 0.6552,
+      "step": 2455
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.0163355618069994,
+      "learning_rate": 4.4019187488928914e-07,
+      "loss": 0.6638,
+      "step": 2460
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 1.032574771687925,
+      "learning_rate": 4.2879189943903335e-07,
+      "loss": 0.6877,
+      "step": 2465
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.9930486578442914,
+      "learning_rate": 4.1753486805651e-07,
+      "loss": 0.6832,
+      "step": 2470
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.969259241462703,
+      "learning_rate": 4.064211327549794e-07,
+      "loss": 0.6738,
+      "step": 2475
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 1.018380412495952,
+      "learning_rate": 3.95451041066755e-07,
+      "loss": 0.671,
+      "step": 2480
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.9735720562840744,
+      "learning_rate": 3.8462493603234064e-07,
+      "loss": 0.6433,
+      "step": 2485
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 1.023935871901339,
+      "learning_rate": 3.739431561897011e-07,
+      "loss": 0.6593,
+      "step": 2490
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.9931869209408388,
+      "learning_rate": 3.634060355636798e-07,
+      "loss": 0.6647,
+      "step": 2495
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.0007736035504975,
+      "learning_rate": 3.53013903655548e-07,
+      "loss": 0.6683,
+      "step": 2500
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.9926593135266999,
+      "learning_rate": 3.427670854327042e-07,
+      "loss": 0.6668,
+      "step": 2505
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.9870259704326787,
+      "learning_rate": 3.3266590131851296e-07,
+      "loss": 0.6583,
+      "step": 2510
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 1.0298553599069395,
+      "learning_rate": 3.227106671822849e-07,
+      "loss": 0.6835,
+      "step": 2515
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.9915918166378904,
+      "learning_rate": 3.1290169432939556e-07,
+      "loss": 0.6428,
+      "step": 2520
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.060474012796049,
+      "learning_rate": 3.03239289491557e-07,
+      "loss": 0.6571,
+      "step": 2525
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 1.0203183687136719,
+      "learning_rate": 2.937237548172206e-07,
+      "loss": 0.6511,
+      "step": 2530
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.989507237700814,
+      "learning_rate": 2.8435538786213134e-07,
+      "loss": 0.6746,
+      "step": 2535
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.9853274639882493,
+      "learning_rate": 2.7513448158002334e-07,
+      "loss": 0.6657,
+      "step": 2540
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.9957797339050202,
+      "learning_rate": 2.66061324313458e-07,
+      "loss": 0.6496,
+      "step": 2545
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 1.0073836211394178,
+      "learning_rate": 2.5713619978480653e-07,
+      "loss": 0.6596,
+      "step": 2550
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.9798969178233458,
+      "learning_rate": 2.483593870873829e-07,
+      "loss": 0.654,
+      "step": 2555
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.9936847658098146,
+      "learning_rate": 2.3973116067670665e-07,
+      "loss": 0.6457,
+      "step": 2560
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 1.0224466038654803,
+      "learning_rate": 2.3125179036193214e-07,
+      "loss": 0.6572,
+      "step": 2565
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 1.0378183041017084,
+      "learning_rate": 2.2292154129740117e-07,
+      "loss": 0.6554,
+      "step": 2570
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.9787357607930246,
+      "learning_rate": 2.147406739743596e-07,
+      "loss": 0.6689,
+      "step": 2575
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.003947207260689,
+      "learning_rate": 2.0670944421280646e-07,
+      "loss": 0.6458,
+      "step": 2580
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 1.0063190015667964,
+      "learning_rate": 1.9882810315349554e-07,
+      "loss": 0.6648,
+      "step": 2585
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.0148103533053272,
+      "learning_rate": 1.9109689725008317e-07,
+      "loss": 0.6738,
+      "step": 2590
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 1.0122729219524842,
+      "learning_rate": 1.8351606826142176e-07,
+      "loss": 0.6796,
+      "step": 2595
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.0170129872933447,
+      "learning_rate": 1.7608585324399684e-07,
+      "loss": 0.6798,
+      "step": 2600
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.992464215850126,
+      "learning_rate": 1.688064845445192e-07,
+      "loss": 0.6695,
+      "step": 2605
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.9778375876093532,
+      "learning_rate": 1.6167818979265282e-07,
+      "loss": 0.6563,
+      "step": 2610
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.0165595693382412,
+      "learning_rate": 1.5470119189390342e-07,
+      "loss": 0.6709,
+      "step": 2615
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.9846854115443192,
+      "learning_rate": 1.4787570902264293e-07,
+      "loss": 0.6468,
+      "step": 2620
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.0226129803358943,
+      "learning_rate": 1.4120195461529097e-07,
+      "loss": 0.6699,
+      "step": 2625
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.0082916511837874,
+      "learning_rate": 1.3468013736363694e-07,
+      "loss": 0.6516,
+      "step": 2630
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.0086534086914538,
+      "learning_rate": 1.2831046120831692e-07,
+      "loss": 0.6483,
+      "step": 2635
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.9957571698657345,
+      "learning_rate": 1.2209312533243535e-07,
+      "loss": 0.6632,
+      "step": 2640
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.0298383480420663,
+      "learning_rate": 1.1602832415533616e-07,
+      "loss": 0.6645,
+      "step": 2645
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.0188314052602203,
+      "learning_rate": 1.1011624732652437e-07,
+      "loss": 0.6752,
+      "step": 2650
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 1.0019681746822835,
+      "learning_rate": 1.0435707971973297e-07,
+      "loss": 0.6573,
+      "step": 2655
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.9926022445477827,
+      "learning_rate": 9.875100142714478e-08,
+      "loss": 0.6396,
+      "step": 2660
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.9847567872289796,
+      "learning_rate": 9.329818775376088e-08,
+      "loss": 0.672,
+      "step": 2665
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 1.0103069579844817,
+      "learning_rate": 8.79988092119144e-08,
+      "loss": 0.678,
+      "step": 2670
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.0092463732513441,
+      "learning_rate": 8.285303151594537e-08,
+      "loss": 0.6837,
+      "step": 2675
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 1.0032753352403014,
+      "learning_rate": 7.786101557701209e-08,
+      "loss": 0.6494,
+      "step": 2680
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 1.0278927407365124,
+      "learning_rate": 7.302291749806345e-08,
+      "loss": 0.6597,
+      "step": 2685
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.9985234255556347,
+      "learning_rate": 6.833888856895676e-08,
+      "loss": 0.6672,
+      "step": 2690
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 1.0086435046290338,
+      "learning_rate": 6.380907526172597e-08,
+      "loss": 0.6768,
+      "step": 2695
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.9639413787477988,
+      "learning_rate": 5.943361922600255e-08,
+      "loss": 0.6346,
+      "step": 2700
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.9898392259409212,
+      "learning_rate": 5.521265728458347e-08,
+      "loss": 0.6655,
+      "step": 2705
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.0000733408715612,
+      "learning_rate": 5.114632142915687e-08,
+      "loss": 0.638,
+      "step": 2710
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.990452054352071,
+      "learning_rate": 4.723473881617147e-08,
+      "loss": 0.6583,
+      "step": 2715
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.988717000145255,
+      "learning_rate": 4.347803176286025e-08,
+      "loss": 0.6708,
+      "step": 2720
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.9868081897157113,
+      "learning_rate": 3.98763177434186e-08,
+      "loss": 0.6583,
+      "step": 2725
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.001603936622736,
+      "learning_rate": 3.642970938532553e-08,
+      "loss": 0.6754,
+      "step": 2730
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 1.0028854813842756,
+      "learning_rate": 3.313831446582816e-08,
+      "loss": 0.6784,
+      "step": 2735
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.9840591494137083,
+      "learning_rate": 3.000223590856666e-08,
+      "loss": 0.6651,
+      "step": 2740
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 1.0425902900408417,
+      "learning_rate": 2.7021571780356804e-08,
+      "loss": 0.6489,
+      "step": 2745
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 1.0016271763738829,
+      "learning_rate": 2.419641528812522e-08,
+      "loss": 0.6501,
+      "step": 2750
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.9875844742537229,
+      "learning_rate": 2.1526854775992255e-08,
+      "loss": 0.667,
+      "step": 2755
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.9909068409835267,
+      "learning_rate": 1.901297372251143e-08,
+      "loss": 0.6649,
+      "step": 2760
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 1.0200770120528766,
+      "learning_rate": 1.665485073805817e-08,
+      "loss": 0.6542,
+      "step": 2765
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.9699214260408161,
+      "learning_rate": 1.4452559562370683e-08,
+      "loss": 0.6644,
+      "step": 2770
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.9962874170809767,
+      "learning_rate": 1.2406169062246232e-08,
+      "loss": 0.6502,
+      "step": 2775
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.0264867036759864,
+      "learning_rate": 1.0515743229385645e-08,
+      "loss": 0.6698,
+      "step": 2780
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 1.0133222133442825,
+      "learning_rate": 8.781341178393244e-09,
+      "loss": 0.6723,
+      "step": 2785
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.0159129157737807,
+      "learning_rate": 7.203017144927771e-09,
+      "loss": 0.6561,
+      "step": 2790
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.9931795490054022,
+      "learning_rate": 5.780820484007632e-09,
+      "loss": 0.6563,
+      "step": 2795
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.0195254872888724,
+      "learning_rate": 4.514795668466576e-09,
+      "loss": 0.6808,
+      "step": 2800
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.0210108366337896,
+      "learning_rate": 3.4049822875614757e-09,
+      "loss": 0.6723,
+      "step": 2805
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.9891130306027911,
+      "learning_rate": 2.4514150457377594e-09,
+      "loss": 0.6763,
+      "step": 2810
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.9876265686294937,
+      "learning_rate": 1.654123761541393e-09,
+      "loss": 0.6652,
+      "step": 2815
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.9719073327336301,
+      "learning_rate": 1.0131333666885124e-09,
+      "loss": 0.6793,
+      "step": 2820
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.004648101535836,
+      "learning_rate": 5.284639052832718e-10,
+      "loss": 0.6643,
+      "step": 2825
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.0172517540637482,
+      "learning_rate": 2.0013053319334341e-10,
+      "loss": 0.6768,
+      "step": 2830
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9650966122076953,
+      "learning_rate": 2.814351757529643e-11,
+      "loss": 0.6356,
+      "step": 2835
+    },
+    {
+      "epoch": 3.0,
+      "step": 2838,
+      "total_flos": 1471706245890048.0,
+      "train_loss": 0.8058284866381398,
+      "train_runtime": 31310.8966,
+      "train_samples_per_second": 5.802,
+      "train_steps_per_second": 0.091
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2838,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1471706245890048.0,
+  "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:b23d858201c4f90b917709f51f6f4ed0cb0e4b8c2a89f05e310280aa3f3798c8
+size 6072