Upload 10 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/wangbenyou/models/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.45.0"
+}

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-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.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.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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1774 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997792494481236,
+  "eval_steps": 50,
+  "global_step": 2037,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014716703458425313,
+      "grad_norm": 3.226644655877531,
+      "learning_rate": 4.901960784313725e-07,
+      "loss": 0.4182,
+      "step": 10
+    },
+    {
+      "epoch": 0.029433406916850625,
+      "grad_norm": 2.129692195859408,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.389,
+      "step": 20
+    },
+    {
+      "epoch": 0.04415011037527594,
+      "grad_norm": 1.5861033073146842,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 0.2876,
+      "step": 30
+    },
+    {
+      "epoch": 0.05886681383370125,
+      "grad_norm": 0.9864226661653924,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.1933,
+      "step": 40
+    },
+    {
+      "epoch": 0.07358351729212656,
+      "grad_norm": 0.8851816239940652,
+      "learning_rate": 2.450980392156863e-06,
+      "loss": 0.166,
+      "step": 50
+    },
+    {
+      "epoch": 0.07358351729212656,
+      "eval_loss": 0.1525491625070572,
+      "eval_runtime": 216.1194,
+      "eval_samples_per_second": 5.59,
+      "eval_steps_per_second": 0.699,
+      "step": 50
+    },
+    {
+      "epoch": 0.08830022075055188,
+      "grad_norm": 0.8806004863473016,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.1491,
+      "step": 60
+    },
+    {
+      "epoch": 0.10301692420897719,
+      "grad_norm": 1.0095005155732772,
+      "learning_rate": 3.431372549019608e-06,
+      "loss": 0.1444,
+      "step": 70
+    },
+    {
+      "epoch": 0.1177336276674025,
+      "grad_norm": 0.8222552861447616,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.1325,
+      "step": 80
+    },
+    {
+      "epoch": 0.13245033112582782,
+      "grad_norm": 0.8482175166475515,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.1249,
+      "step": 90
+    },
+    {
+      "epoch": 0.14716703458425312,
+      "grad_norm": 0.8916707135250133,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.1267,
+      "step": 100
+    },
+    {
+      "epoch": 0.14716703458425312,
+      "eval_loss": 0.12268291413784027,
+      "eval_runtime": 206.0326,
+      "eval_samples_per_second": 5.863,
+      "eval_steps_per_second": 0.733,
+      "step": 100
+    },
+    {
+      "epoch": 0.16188373804267844,
+      "grad_norm": 0.8391480398866726,
+      "learning_rate": 5.392156862745098e-06,
+      "loss": 0.1261,
+      "step": 110
+    },
+    {
+      "epoch": 0.17660044150110377,
+      "grad_norm": 0.8543855316305797,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.1239,
+      "step": 120
+    },
+    {
+      "epoch": 0.19131714495952906,
+      "grad_norm": 1.0426618599860231,
+      "learning_rate": 6.372549019607843e-06,
+      "loss": 0.1249,
+      "step": 130
+    },
+    {
+      "epoch": 0.20603384841795438,
+      "grad_norm": 0.7381326766253737,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.1161,
+      "step": 140
+    },
+    {
+      "epoch": 0.22075055187637968,
+      "grad_norm": 0.7710809135546592,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 0.1171,
+      "step": 150
+    },
+    {
+      "epoch": 0.22075055187637968,
+      "eval_loss": 0.11395128816366196,
+      "eval_runtime": 173.8286,
+      "eval_samples_per_second": 6.949,
+      "eval_steps_per_second": 0.869,
+      "step": 150
+    },
+    {
+      "epoch": 0.235467255334805,
+      "grad_norm": 0.6891100266664143,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.1156,
+      "step": 160
+    },
+    {
+      "epoch": 0.2501839587932303,
+      "grad_norm": 0.8566371646933698,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.1123,
+      "step": 170
+    },
+    {
+      "epoch": 0.26490066225165565,
+      "grad_norm": 0.678987575471473,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.114,
+      "step": 180
+    },
+    {
+      "epoch": 0.27961736571008095,
+      "grad_norm": 0.7177541472393981,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 0.1144,
+      "step": 190
+    },
+    {
+      "epoch": 0.29433406916850624,
+      "grad_norm": 0.6069002401700933,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.1117,
+      "step": 200
+    },
+    {
+      "epoch": 0.29433406916850624,
+      "eval_loss": 0.1121131181716919,
+      "eval_runtime": 204.0232,
+      "eval_samples_per_second": 5.921,
+      "eval_steps_per_second": 0.74,
+      "step": 200
+    },
+    {
+      "epoch": 0.3090507726269316,
+      "grad_norm": 0.6658587363100609,
+      "learning_rate": 9.999735629192408e-06,
+      "loss": 0.1207,
+      "step": 210
+    },
+    {
+      "epoch": 0.3237674760853569,
+      "grad_norm": 0.6216355033039211,
+      "learning_rate": 9.99812013105419e-06,
+      "loss": 0.1099,
+      "step": 220
+    },
+    {
+      "epoch": 0.3384841795437822,
+      "grad_norm": 0.6191227561051886,
+      "learning_rate": 9.995036481411005e-06,
+      "loss": 0.1099,
+      "step": 230
+    },
+    {
+      "epoch": 0.35320088300220753,
+      "grad_norm": 1.8888088694270877,
+      "learning_rate": 9.990485586056381e-06,
+      "loss": 0.1091,
+      "step": 240
+    },
+    {
+      "epoch": 0.36791758646063283,
+      "grad_norm": 0.6030722360970995,
+      "learning_rate": 9.984468781773688e-06,
+      "loss": 0.1089,
+      "step": 250
+    },
+    {
+      "epoch": 0.36791758646063283,
+      "eval_loss": 0.10794272273778915,
+      "eval_runtime": 192.1395,
+      "eval_samples_per_second": 6.287,
+      "eval_steps_per_second": 0.786,
+      "step": 250
+    },
+    {
+      "epoch": 0.3826342899190581,
+      "grad_norm": 0.595437994630761,
+      "learning_rate": 9.976987835943465e-06,
+      "loss": 0.1059,
+      "step": 260
+    },
+    {
+      "epoch": 0.3973509933774834,
+      "grad_norm": 0.6619589566630248,
+      "learning_rate": 9.968044946024277e-06,
+      "loss": 0.113,
+      "step": 270
+    },
+    {
+      "epoch": 0.41206769683590877,
+      "grad_norm": 0.5476231049438186,
+      "learning_rate": 9.957642738907226e-06,
+      "loss": 0.1143,
+      "step": 280
+    },
+    {
+      "epoch": 0.42678440029433407,
+      "grad_norm": 0.5802953355038116,
+      "learning_rate": 9.945784270144321e-06,
+      "loss": 0.11,
+      "step": 290
+    },
+    {
+      "epoch": 0.44150110375275936,
+      "grad_norm": 0.5847953307046128,
+      "learning_rate": 9.932473023050954e-06,
+      "loss": 0.1048,
+      "step": 300
+    },
+    {
+      "epoch": 0.44150110375275936,
+      "eval_loss": 0.10326112061738968,
+      "eval_runtime": 179.9326,
+      "eval_samples_per_second": 6.714,
+      "eval_steps_per_second": 0.839,
+      "step": 300
+    },
+    {
+      "epoch": 0.4562178072111847,
+      "grad_norm": 0.6275753190574224,
+      "learning_rate": 9.917712907682694e-06,
+      "loss": 0.1013,
+      "step": 310
+    },
+    {
+      "epoch": 0.47093451066961,
+      "grad_norm": 0.6431980899061217,
+      "learning_rate": 9.901508259686746e-06,
+      "loss": 0.1017,
+      "step": 320
+    },
+    {
+      "epoch": 0.4856512141280353,
+      "grad_norm": 0.5721037703631747,
+      "learning_rate": 9.883863839028402e-06,
+      "loss": 0.1099,
+      "step": 330
+    },
+    {
+      "epoch": 0.5003679175864606,
+      "grad_norm": 0.5487439214439007,
+      "learning_rate": 9.864784828592842e-06,
+      "loss": 0.0969,
+      "step": 340
+    },
+    {
+      "epoch": 0.515084621044886,
+      "grad_norm": 0.5817005922601163,
+      "learning_rate": 9.844276832662704e-06,
+      "loss": 0.0976,
+      "step": 350
+    },
+    {
+      "epoch": 0.515084621044886,
+      "eval_loss": 0.09972475469112396,
+      "eval_runtime": 193.3575,
+      "eval_samples_per_second": 6.247,
+      "eval_steps_per_second": 0.781,
+      "step": 350
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 0.7409277848217514,
+      "learning_rate": 9.822345875271884e-06,
+      "loss": 0.1053,
+      "step": 360
+    },
+    {
+      "epoch": 0.5445180279617365,
+      "grad_norm": 0.6141304848014978,
+      "learning_rate": 9.798998398436031e-06,
+      "loss": 0.1028,
+      "step": 370
+    },
+    {
+      "epoch": 0.5592347314201619,
+      "grad_norm": 0.5607954946605025,
+      "learning_rate": 9.774241260260266e-06,
+      "loss": 0.1033,
+      "step": 380
+    },
+    {
+      "epoch": 0.5739514348785872,
+      "grad_norm": 0.5542868417397482,
+      "learning_rate": 9.74808173292467e-06,
+      "loss": 0.1037,
+      "step": 390
+    },
+    {
+      "epoch": 0.5886681383370125,
+      "grad_norm": 0.6069603969724401,
+      "learning_rate": 9.720527500548155e-06,
+      "loss": 0.0972,
+      "step": 400
+    },
+    {
+      "epoch": 0.5886681383370125,
+      "eval_loss": 0.09853184223175049,
+      "eval_runtime": 199.2969,
+      "eval_samples_per_second": 6.061,
+      "eval_steps_per_second": 0.758,
+      "step": 400
+    },
+    {
+      "epoch": 0.6033848417954378,
+      "grad_norm": 0.5133322169553051,
+      "learning_rate": 9.691586656931326e-06,
+      "loss": 0.1024,
+      "step": 410
+    },
+    {
+      "epoch": 0.6181015452538632,
+      "grad_norm": 0.5357388008964457,
+      "learning_rate": 9.661267703178999e-06,
+      "loss": 0.1033,
+      "step": 420
+    },
+    {
+      "epoch": 0.6328182487122884,
+      "grad_norm": 0.5215856861597291,
+      "learning_rate": 9.629579545203076e-06,
+      "loss": 0.0994,
+      "step": 430
+    },
+    {
+      "epoch": 0.6475349521707138,
+      "grad_norm": 0.5969857087876467,
+      "learning_rate": 9.596531491106528e-06,
+      "loss": 0.1019,
+      "step": 440
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "grad_norm": 0.5231050382062306,
+      "learning_rate": 9.56213324844921e-06,
+      "loss": 0.0968,
+      "step": 450
+    },
+    {
+      "epoch": 0.6622516556291391,
+      "eval_loss": 0.09699959307909012,
+      "eval_runtime": 190.5546,
+      "eval_samples_per_second": 6.339,
+      "eval_steps_per_second": 0.792,
+      "step": 450
+    },
+    {
+      "epoch": 0.6769683590875644,
+      "grad_norm": 0.5546434863895826,
+      "learning_rate": 9.526394921396373e-06,
+      "loss": 0.1026,
+      "step": 460
+    },
+    {
+      "epoch": 0.6916850625459897,
+      "grad_norm": 0.5168914632751676,
+      "learning_rate": 9.489327007750644e-06,
+      "loss": 0.1012,
+      "step": 470
+    },
+    {
+      "epoch": 0.7064017660044151,
+      "grad_norm": 0.5152122638926383,
+      "learning_rate": 9.450940395868397e-06,
+      "loss": 0.1013,
+      "step": 480
+    },
+    {
+      "epoch": 0.7211184694628403,
+      "grad_norm": 0.5104516201207467,
+      "learning_rate": 9.41124636146141e-06,
+      "loss": 0.0945,
+      "step": 490
+    },
+    {
+      "epoch": 0.7358351729212657,
+      "grad_norm": 0.5202984287068582,
+      "learning_rate": 9.370256564284713e-06,
+      "loss": 0.0967,
+      "step": 500
+    },
+    {
+      "epoch": 0.7358351729212657,
+      "eval_loss": 0.09431542456150055,
+      "eval_runtime": 184.4167,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 0.819,
+      "step": 500
+    },
+    {
+      "epoch": 0.7505518763796909,
+      "grad_norm": 0.5032141555673829,
+      "learning_rate": 9.327983044711655e-06,
+      "loss": 0.0935,
+      "step": 510
+    },
+    {
+      "epoch": 0.7652685798381162,
+      "grad_norm": 0.5167615309062046,
+      "learning_rate": 9.28443822019715e-06,
+      "loss": 0.0981,
+      "step": 520
+    },
+    {
+      "epoch": 0.7799852832965416,
+      "grad_norm": 0.48598303739277543,
+      "learning_rate": 9.239634881630162e-06,
+      "loss": 0.0897,
+      "step": 530
+    },
+    {
+      "epoch": 0.7947019867549668,
+      "grad_norm": 0.53876383666863,
+      "learning_rate": 9.19358618957651e-06,
+      "loss": 0.0986,
+      "step": 540
+    },
+    {
+      "epoch": 0.8094186902133922,
+      "grad_norm": 0.49526243406348325,
+      "learning_rate": 9.146305670413069e-06,
+      "loss": 0.0879,
+      "step": 550
+    },
+    {
+      "epoch": 0.8094186902133922,
+      "eval_loss": 0.09373725950717926,
+      "eval_runtime": 203.9941,
+      "eval_samples_per_second": 5.922,
+      "eval_steps_per_second": 0.74,
+      "step": 550
+    },
+    {
+      "epoch": 0.8241353936718175,
+      "grad_norm": 0.5723604640533689,
+      "learning_rate": 9.097807212354513e-06,
+      "loss": 0.0915,
+      "step": 560
+    },
+    {
+      "epoch": 0.8388520971302428,
+      "grad_norm": 0.567543105501399,
+      "learning_rate": 9.048105061373793e-06,
+      "loss": 0.0947,
+      "step": 570
+    },
+    {
+      "epoch": 0.8535688005886681,
+      "grad_norm": 0.5181347389812981,
+      "learning_rate": 8.997213817017508e-06,
+      "loss": 0.095,
+      "step": 580
+    },
+    {
+      "epoch": 0.8682855040470935,
+      "grad_norm": 0.4258862103531478,
+      "learning_rate": 8.945148428117423e-06,
+      "loss": 0.0917,
+      "step": 590
+    },
+    {
+      "epoch": 0.8830022075055187,
+      "grad_norm": 0.5739504951081847,
+      "learning_rate": 8.891924188399395e-06,
+      "loss": 0.1014,
+      "step": 600
+    },
+    {
+      "epoch": 0.8830022075055187,
+      "eval_loss": 0.09279368817806244,
+      "eval_runtime": 174.7309,
+      "eval_samples_per_second": 6.913,
+      "eval_steps_per_second": 0.864,
+      "step": 600
+    },
+    {
+      "epoch": 0.8977189109639441,
+      "grad_norm": 0.5023401278687947,
+      "learning_rate": 8.837556731990973e-06,
+      "loss": 0.0977,
+      "step": 610
+    },
+    {
+      "epoch": 0.9124356144223694,
+      "grad_norm": 0.4472157776860558,
+      "learning_rate": 8.782062028829028e-06,
+      "loss": 0.0944,
+      "step": 620
+    },
+    {
+      "epoch": 0.9271523178807947,
+      "grad_norm": 0.5229751477277164,
+      "learning_rate": 8.725456379968717e-06,
+      "loss": 0.0894,
+      "step": 630
+    },
+    {
+      "epoch": 0.94186902133922,
+      "grad_norm": 0.540335952099867,
+      "learning_rate": 8.667756412795217e-06,
+      "loss": 0.0914,
+      "step": 640
+    },
+    {
+      "epoch": 0.9565857247976454,
+      "grad_norm": 0.5214096611567617,
+      "learning_rate": 8.608979076139572e-06,
+      "loss": 0.1026,
+      "step": 650
+    },
+    {
+      "epoch": 0.9565857247976454,
+      "eval_loss": 0.09049851447343826,
+      "eval_runtime": 191.9453,
+      "eval_samples_per_second": 6.293,
+      "eval_steps_per_second": 0.787,
+      "step": 650
+    },
+    {
+      "epoch": 0.9713024282560706,
+      "grad_norm": 0.47553610942736374,
+      "learning_rate": 8.549141635300135e-06,
+      "loss": 0.0906,
+      "step": 660
+    },
+    {
+      "epoch": 0.986019131714496,
+      "grad_norm": 0.5432074308037707,
+      "learning_rate": 8.488261666971047e-06,
+      "loss": 0.0854,
+      "step": 670
+    },
+    {
+      "epoch": 1.0007358351729212,
+      "grad_norm": 0.5579816589630594,
+      "learning_rate": 8.426357054079244e-06,
+      "loss": 0.0923,
+      "step": 680
+    },
+    {
+      "epoch": 1.0154525386313467,
+      "grad_norm": 0.5140159523753607,
+      "learning_rate": 8.363445980531515e-06,
+      "loss": 0.0683,
+      "step": 690
+    },
+    {
+      "epoch": 1.030169242089772,
+      "grad_norm": 0.49111266471989273,
+      "learning_rate": 8.299546925873148e-06,
+      "loss": 0.0635,
+      "step": 700
+    },
+    {
+      "epoch": 1.030169242089772,
+      "eval_loss": 0.09157832711935043,
+      "eval_runtime": 185.5584,
+      "eval_samples_per_second": 6.51,
+      "eval_steps_per_second": 0.814,
+      "step": 700
+    },
+    {
+      "epoch": 1.0448859455481971,
+      "grad_norm": 0.4650423339954392,
+      "learning_rate": 8.234678659859729e-06,
+      "loss": 0.0667,
+      "step": 710
+    },
+    {
+      "epoch": 1.0596026490066226,
+      "grad_norm": 0.5350038624215137,
+      "learning_rate": 8.168860236943709e-06,
+      "loss": 0.0692,
+      "step": 720
+    },
+    {
+      "epoch": 1.0743193524650478,
+      "grad_norm": 0.4137475767583062,
+      "learning_rate": 8.102110990677328e-06,
+      "loss": 0.0723,
+      "step": 730
+    },
+    {
+      "epoch": 1.089036055923473,
+      "grad_norm": 0.42028700866957225,
+      "learning_rate": 8.034450528033565e-06,
+      "loss": 0.066,
+      "step": 740
+    },
+    {
+      "epoch": 1.1037527593818985,
+      "grad_norm": 0.5321405562977654,
+      "learning_rate": 7.965898723646777e-06,
+      "loss": 0.0703,
+      "step": 750
+    },
+    {
+      "epoch": 1.1037527593818985,
+      "eval_loss": 0.08948411047458649,
+      "eval_runtime": 184.8668,
+      "eval_samples_per_second": 6.534,
+      "eval_steps_per_second": 0.817,
+      "step": 750
+    },
+    {
+      "epoch": 1.1184694628403238,
+      "grad_norm": 0.4973824096134147,
+      "learning_rate": 7.896475713974696e-06,
+      "loss": 0.0667,
+      "step": 760
+    },
+    {
+      "epoch": 1.133186166298749,
+      "grad_norm": 0.5184687953265169,
+      "learning_rate": 7.826201891383542e-06,
+      "loss": 0.0721,
+      "step": 770
+    },
+    {
+      "epoch": 1.1479028697571745,
+      "grad_norm": 0.4182786077759931,
+      "learning_rate": 7.755097898157957e-06,
+      "loss": 0.0652,
+      "step": 780
+    },
+    {
+      "epoch": 1.1626195732155997,
+      "grad_norm": 0.5162298391916976,
+      "learning_rate": 7.683184620437511e-06,
+      "loss": 0.0715,
+      "step": 790
+    },
+    {
+      "epoch": 1.177336276674025,
+      "grad_norm": 0.41958696094652936,
+      "learning_rate": 7.610483182081607e-06,
+      "loss": 0.0699,
+      "step": 800
+    },
+    {
+      "epoch": 1.177336276674025,
+      "eval_loss": 0.08885398507118225,
+      "eval_runtime": 198.9152,
+      "eval_samples_per_second": 6.073,
+      "eval_steps_per_second": 0.759,
+      "step": 800
+    },
+    {
+      "epoch": 1.1920529801324504,
+      "grad_norm": 0.4131639402362476,
+      "learning_rate": 7.537014938464529e-06,
+      "loss": 0.0679,
+      "step": 810
+    },
+    {
+      "epoch": 1.2067696835908757,
+      "grad_norm": 0.48371552023497083,
+      "learning_rate": 7.462801470202513e-06,
+      "loss": 0.0724,
+      "step": 820
+    },
+    {
+      "epoch": 1.221486387049301,
+      "grad_norm": 0.5028126635648151,
+      "learning_rate": 7.387864576814628e-06,
+      "loss": 0.065,
+      "step": 830
+    },
+    {
+      "epoch": 1.2362030905077264,
+      "grad_norm": 0.46008897965297035,
+      "learning_rate": 7.31222627031938e-06,
+      "loss": 0.0672,
+      "step": 840
+    },
+    {
+      "epoch": 1.2509197939661516,
+      "grad_norm": 0.3995351586970657,
+      "learning_rate": 7.235908768768875e-06,
+      "loss": 0.0655,
+      "step": 850
+    },
+    {
+      "epoch": 1.2509197939661516,
+      "eval_loss": 0.0898497924208641,
+      "eval_runtime": 190.9254,
+      "eval_samples_per_second": 6.327,
+      "eval_steps_per_second": 0.791,
+      "step": 850
+    },
+    {
+      "epoch": 1.2656364974245768,
+      "grad_norm": 0.37529528925372135,
+      "learning_rate": 7.1589344897224795e-06,
+      "loss": 0.0696,
+      "step": 860
+    },
+    {
+      "epoch": 1.280353200883002,
+      "grad_norm": 0.5211153879452506,
+      "learning_rate": 7.081326043661867e-06,
+      "loss": 0.0671,
+      "step": 870
+    },
+    {
+      "epoch": 1.2950699043414275,
+      "grad_norm": 0.46585166367095826,
+      "learning_rate": 7.003106227349399e-06,
+      "loss": 0.0673,
+      "step": 880
+    },
+    {
+      "epoch": 1.3097866077998528,
+      "grad_norm": 0.49300557145854806,
+      "learning_rate": 6.924298017131786e-06,
+      "loss": 0.0664,
+      "step": 890
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "grad_norm": 0.480260675255211,
+      "learning_rate": 6.844924562191003e-06,
+      "loss": 0.065,
+      "step": 900
+    },
+    {
+      "epoch": 1.3245033112582782,
+      "eval_loss": 0.08873660862445831,
+      "eval_runtime": 206.5717,
+      "eval_samples_per_second": 5.848,
+      "eval_steps_per_second": 0.731,
+      "step": 900
+    },
+    {
+      "epoch": 1.3392200147167035,
+      "grad_norm": 0.4824688537300334,
+      "learning_rate": 6.765009177744425e-06,
+      "loss": 0.0704,
+      "step": 910
+    },
+    {
+      "epoch": 1.3539367181751287,
+      "grad_norm": 0.4415786568127757,
+      "learning_rate": 6.6845753381961995e-06,
+      "loss": 0.0654,
+      "step": 920
+    },
+    {
+      "epoch": 1.368653421633554,
+      "grad_norm": 0.5631526023299833,
+      "learning_rate": 6.603646670241863e-06,
+      "loss": 0.0663,
+      "step": 930
+    },
+    {
+      "epoch": 1.3833701250919794,
+      "grad_norm": 0.46084364060561317,
+      "learning_rate": 6.522246945928214e-06,
+      "loss": 0.0692,
+      "step": 940
+    },
+    {
+      "epoch": 1.3980868285504047,
+      "grad_norm": 0.5348577097898968,
+      "learning_rate": 6.440400075670491e-06,
+      "loss": 0.069,
+      "step": 950
+    },
+    {
+      "epoch": 1.3980868285504047,
+      "eval_loss": 0.08685711026191711,
+      "eval_runtime": 177.7464,
+      "eval_samples_per_second": 6.796,
+      "eval_steps_per_second": 0.85,
+      "step": 950
+    },
+    {
+      "epoch": 1.4128035320088301,
+      "grad_norm": 0.5250790642687054,
+      "learning_rate": 6.358130101228914e-06,
+      "loss": 0.0702,
+      "step": 960
+    },
+    {
+      "epoch": 1.4275202354672554,
+      "grad_norm": 0.5047393202253249,
+      "learning_rate": 6.275461188646641e-06,
+      "loss": 0.0699,
+      "step": 970
+    },
+    {
+      "epoch": 1.4422369389256806,
+      "grad_norm": 0.48776704190164294,
+      "learning_rate": 6.1924176211512145e-06,
+      "loss": 0.0634,
+      "step": 980
+    },
+    {
+      "epoch": 1.4569536423841059,
+      "grad_norm": 0.49529594396564186,
+      "learning_rate": 6.109023792021586e-06,
+      "loss": 0.0667,
+      "step": 990
+    },
+    {
+      "epoch": 1.4716703458425313,
+      "grad_norm": 0.47438683295737333,
+      "learning_rate": 6.025304197422819e-06,
+      "loss": 0.0693,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4716703458425313,
+      "eval_loss": 0.08619654178619385,
+      "eval_runtime": 181.9786,
+      "eval_samples_per_second": 6.638,
+      "eval_steps_per_second": 0.83,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4863870493009566,
+      "grad_norm": 0.47483465689550636,
+      "learning_rate": 5.941283429210568e-06,
+      "loss": 0.0659,
+      "step": 1010
+    },
+    {
+      "epoch": 1.501103752759382,
+      "grad_norm": 0.4446944338196383,
+      "learning_rate": 5.856986167707448e-06,
+      "loss": 0.0638,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5158204562178073,
+      "grad_norm": 0.47714369154377795,
+      "learning_rate": 5.772437174453418e-06,
+      "loss": 0.0646,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5305371596762325,
+      "grad_norm": 0.4489337679674589,
+      "learning_rate": 5.687661284932306e-06,
+      "loss": 0.0644,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5452538631346577,
+      "grad_norm": 0.5494239982767725,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.0648,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5452538631346577,
+      "eval_loss": 0.08584881573915482,
+      "eval_runtime": 196.0939,
+      "eval_samples_per_second": 6.16,
+      "eval_steps_per_second": 0.77,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5599705665930832,
+      "grad_norm": 0.4324026964232888,
+      "learning_rate": 5.5175284849527635e-06,
+      "loss": 0.0662,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5746872700515084,
+      "grad_norm": 0.43771048938211576,
+      "learning_rate": 5.432221549428867e-06,
+      "loss": 0.0646,
+      "step": 1070
+    },
+    {
+      "epoch": 1.589403973509934,
+      "grad_norm": 0.40653033653295745,
+      "learning_rate": 5.346787652827279e-06,
+      "loss": 0.0673,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6041206769683591,
+      "grad_norm": 0.4218995885501481,
+      "learning_rate": 5.26125189056399e-06,
+      "loss": 0.0652,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6188373804267844,
+      "grad_norm": 0.42589283927464555,
+      "learning_rate": 5.175639387977091e-06,
+      "loss": 0.067,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6188373804267844,
+      "eval_loss": 0.08547249436378479,
+      "eval_runtime": 188.3934,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 0.802,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6335540838852096,
+      "grad_norm": 0.4607522386339002,
+      "learning_rate": 5.089975292946427e-06,
+      "loss": 0.0677,
+      "step": 1110
+    },
+    {
+      "epoch": 1.648270787343635,
+      "grad_norm": 0.41120752213023654,
+      "learning_rate": 5.00428476850665e-06,
+      "loss": 0.0633,
+      "step": 1120
+    },
+    {
+      "epoch": 1.6629874908020603,
+      "grad_norm": 0.5477912053365783,
+      "learning_rate": 4.918592985455799e-06,
+      "loss": 0.0648,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6777041942604858,
+      "grad_norm": 0.47503483012059583,
+      "learning_rate": 4.832925114961629e-06,
+      "loss": 0.0618,
+      "step": 1140
+    },
+    {
+      "epoch": 1.692420897718911,
+      "grad_norm": 0.45774600350002437,
+      "learning_rate": 4.747306321167791e-06,
+      "loss": 0.0617,
+      "step": 1150
+    },
+    {
+      "epoch": 1.692420897718911,
+      "eval_loss": 0.08534925431013107,
+      "eval_runtime": 204.7242,
+      "eval_samples_per_second": 5.901,
+      "eval_steps_per_second": 0.738,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7071376011773363,
+      "grad_norm": 0.45847738919073283,
+      "learning_rate": 4.66176175380212e-06,
+      "loss": 0.0658,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7218543046357615,
+      "grad_norm": 0.44501034067234635,
+      "learning_rate": 4.576316540789122e-06,
+      "loss": 0.0649,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7365710080941867,
+      "grad_norm": 0.4832020901371425,
+      "learning_rate": 4.4909957808688765e-06,
+      "loss": 0.0663,
+      "step": 1180
+    },
+    {
+      "epoch": 1.7512877115526122,
+      "grad_norm": 0.5231088503027554,
+      "learning_rate": 4.4058245362245276e-06,
+      "loss": 0.0617,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7660044150110377,
+      "grad_norm": 0.5011172484501668,
+      "learning_rate": 4.320827825120485e-06,
+      "loss": 0.0639,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7660044150110377,
+      "eval_loss": 0.08313070237636566,
+      "eval_runtime": 199.3984,
+      "eval_samples_per_second": 6.058,
+      "eval_steps_per_second": 0.757,
+      "step": 1200
+    },
+    {
+      "epoch": 1.780721118469463,
+      "grad_norm": 0.5345442409242496,
+      "learning_rate": 4.236030614553552e-06,
+      "loss": 0.0606,
+      "step": 1210
+    },
+    {
+      "epoch": 1.7954378219278881,
+      "grad_norm": 0.512563715796756,
+      "learning_rate": 4.151457812919094e-06,
+      "loss": 0.0603,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8101545253863134,
+      "grad_norm": 0.44851621254213614,
+      "learning_rate": 4.067134262694431e-06,
+      "loss": 0.0645,
+      "step": 1230
+    },
+    {
+      "epoch": 1.8248712288447386,
+      "grad_norm": 0.5248672860684085,
+      "learning_rate": 3.983084733141588e-06,
+      "loss": 0.0623,
+      "step": 1240
+    },
+    {
+      "epoch": 1.839587932303164,
+      "grad_norm": 0.5498054945628633,
+      "learning_rate": 3.899333913031561e-06,
+      "loss": 0.0668,
+      "step": 1250
+    },
+    {
+      "epoch": 1.839587932303164,
+      "eval_loss": 0.0824863463640213,
+      "eval_runtime": 186.253,
+      "eval_samples_per_second": 6.486,
+      "eval_steps_per_second": 0.811,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8543046357615895,
+      "grad_norm": 0.42853375775393104,
+      "learning_rate": 3.815906403392203e-06,
+      "loss": 0.0593,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8690213392200148,
+      "grad_norm": 0.45809760814838824,
+      "learning_rate": 3.732826710281923e-06,
+      "loss": 0.0635,
+      "step": 1270
+    },
+    {
+      "epoch": 1.88373804267844,
+      "grad_norm": 0.41621812440438655,
+      "learning_rate": 3.650119237591232e-06,
+      "loss": 0.0585,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8984547461368653,
+      "grad_norm": 0.47534317303862195,
+      "learning_rate": 3.5678082798743498e-06,
+      "loss": 0.0595,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9131714495952905,
+      "grad_norm": 0.41752392992965454,
+      "learning_rate": 3.485918015212891e-06,
+      "loss": 0.0643,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9131714495952905,
+      "eval_loss": 0.08134686201810837,
+      "eval_runtime": 180.7959,
+      "eval_samples_per_second": 6.682,
+      "eval_steps_per_second": 0.835,
+      "step": 1300
+    },
+    {
+      "epoch": 1.927888153053716,
+      "grad_norm": 0.4388803040345972,
+      "learning_rate": 3.4044724981137787e-06,
+      "loss": 0.0609,
+      "step": 1310
+    },
+    {
+      "epoch": 1.9426048565121414,
+      "grad_norm": 0.4342058670787917,
+      "learning_rate": 3.3234956524434615e-06,
+      "loss": 0.062,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9573215599705667,
+      "grad_norm": 0.40894625830036435,
+      "learning_rate": 3.243011264400494e-06,
+      "loss": 0.0606,
+      "step": 1330
+    },
+    {
+      "epoch": 1.972038263428992,
+      "grad_norm": 0.4587254776423067,
+      "learning_rate": 3.1630429755285623e-06,
+      "loss": 0.0639,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "grad_norm": 0.5863720947155439,
+      "learning_rate": 3.0836142757720034e-06,
+      "loss": 0.0601,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9867549668874172,
+      "eval_loss": 0.08116251230239868,
+      "eval_runtime": 214.6117,
+      "eval_samples_per_second": 5.629,
+      "eval_steps_per_second": 0.704,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0014716703458424,
+      "grad_norm": 0.3180683055717724,
+      "learning_rate": 3.004748496575842e-06,
+      "loss": 0.0571,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0161883738042676,
+      "grad_norm": 0.37920317857819413,
+      "learning_rate": 2.9264688040324098e-06,
+      "loss": 0.0418,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0309050772626933,
+      "grad_norm": 0.43496386857367136,
+      "learning_rate": 2.8487981920765044e-06,
+      "loss": 0.0412,
+      "step": 1380
+    },
+    {
+      "epoch": 2.0456217807211186,
+      "grad_norm": 0.454994148288807,
+      "learning_rate": 2.7717594757311435e-06,
+      "loss": 0.0386,
+      "step": 1390
+    },
+    {
+      "epoch": 2.060338484179544,
+      "grad_norm": 0.4879169888697804,
+      "learning_rate": 2.69537528440586e-06,
+      "loss": 0.0391,
+      "step": 1400
+    },
+    {
+      "epoch": 2.060338484179544,
+      "eval_loss": 0.08909143507480621,
+      "eval_runtime": 197.7898,
+      "eval_samples_per_second": 6.107,
+      "eval_steps_per_second": 0.763,
+      "step": 1400
+    },
+    {
+      "epoch": 2.075055187637969,
+      "grad_norm": 0.44447001392962837,
+      "learning_rate": 2.619668055249527e-06,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 2.0897718910963943,
+      "grad_norm": 0.40740917793748654,
+      "learning_rate": 2.544660026559639e-06,
+      "loss": 0.0367,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1044885945548195,
+      "grad_norm": 0.399633409974892,
+      "learning_rate": 2.4703732312500438e-06,
+      "loss": 0.0382,
+      "step": 1430
+    },
+    {
+      "epoch": 2.119205298013245,
+      "grad_norm": 0.43107632751069047,
+      "learning_rate": 2.3968294903789474e-06,
+      "loss": 0.0398,
+      "step": 1440
+    },
+    {
+      "epoch": 2.1339220014716704,
+      "grad_norm": 0.43610535435590353,
+      "learning_rate": 2.324050406739205e-06,
+      "loss": 0.0411,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1339220014716704,
+      "eval_loss": 0.08864710479974747,
+      "eval_runtime": 185.9081,
+      "eval_samples_per_second": 6.498,
+      "eval_steps_per_second": 0.812,
+      "step": 1450
+    },
+    {
+      "epoch": 2.1486387049300957,
+      "grad_norm": 0.3969874821725999,
+      "learning_rate": 2.2520573585126863e-06,
+      "loss": 0.0407,
+      "step": 1460
+    },
+    {
+      "epoch": 2.163355408388521,
+      "grad_norm": 0.44469487818286946,
+      "learning_rate": 2.1808714929906394e-06,
+      "loss": 0.037,
+      "step": 1470
+    },
+    {
+      "epoch": 2.178072111846946,
+      "grad_norm": 0.4933403170140201,
+      "learning_rate": 2.110513720361869e-06,
+      "loss": 0.0385,
+      "step": 1480
+    },
+    {
+      "epoch": 2.1927888153053714,
+      "grad_norm": 0.40970411491367764,
+      "learning_rate": 2.041004707570555e-06,
+      "loss": 0.0362,
+      "step": 1490
+    },
+    {
+      "epoch": 2.207505518763797,
+      "grad_norm": 0.47294108634743565,
+      "learning_rate": 1.972364872245539e-06,
+      "loss": 0.0376,
+      "step": 1500
+    },
+    {
+      "epoch": 2.207505518763797,
+      "eval_loss": 0.09001829475164413,
+      "eval_runtime": 203.7053,
+      "eval_samples_per_second": 5.93,
+      "eval_steps_per_second": 0.741,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.4013296778951186,
+      "learning_rate": 1.9046143767028309e-06,
+      "loss": 0.0359,
+      "step": 1510
+    },
+    {
+      "epoch": 2.2369389256806476,
+      "grad_norm": 0.41616621605630383,
+      "learning_rate": 1.8377731220231144e-06,
+      "loss": 0.0373,
+      "step": 1520
+    },
+    {
+      "epoch": 2.251655629139073,
+      "grad_norm": 0.4858320948580327,
+      "learning_rate": 1.771860742205988e-06,
+      "loss": 0.0355,
+      "step": 1530
+    },
+    {
+      "epoch": 2.266372332597498,
+      "grad_norm": 0.4284960397863766,
+      "learning_rate": 1.706896598402663e-06,
+      "loss": 0.0379,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2810890360559233,
+      "grad_norm": 0.41264671002453457,
+      "learning_rate": 1.642899773228801e-06,
+      "loss": 0.0372,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2810890360559233,
+      "eval_loss": 0.08930070698261261,
+      "eval_runtime": 216.4439,
+      "eval_samples_per_second": 5.581,
+      "eval_steps_per_second": 0.698,
+      "step": 1550
+    },
+    {
+      "epoch": 2.295805739514349,
+      "grad_norm": 0.4348744731420184,
+      "learning_rate": 1.5798890651591759e-06,
+      "loss": 0.0375,
+      "step": 1560
+    },
+    {
+      "epoch": 2.310522442972774,
+      "grad_norm": 0.4350319794815005,
+      "learning_rate": 1.5178829830057883e-06,
+      "loss": 0.0353,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3252391464311994,
+      "grad_norm": 0.397696827791832,
+      "learning_rate": 1.4568997404810858e-06,
+      "loss": 0.0369,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3399558498896247,
+      "grad_norm": 0.44249359787198733,
+      "learning_rate": 1.3969572508478424e-06,
+      "loss": 0.0365,
+      "step": 1590
+    },
+    {
+      "epoch": 2.35467255334805,
+      "grad_norm": 0.3999504032855848,
+      "learning_rate": 1.33807312165731e-06,
+      "loss": 0.0391,
+      "step": 1600
+    },
+    {
+      "epoch": 2.35467255334805,
+      "eval_loss": 0.08941526710987091,
+      "eval_runtime": 201.599,
+      "eval_samples_per_second": 5.992,
+      "eval_steps_per_second": 0.749,
+      "step": 1600
+    },
+    {
+      "epoch": 2.369389256806475,
+      "grad_norm": 0.47235025180203943,
+      "learning_rate": 1.2802646495771592e-06,
+      "loss": 0.0374,
+      "step": 1610
+    },
+    {
+      "epoch": 2.384105960264901,
+      "grad_norm": 0.4505178794969632,
+      "learning_rate": 1.2235488153107488e-06,
+      "loss": 0.0386,
+      "step": 1620
+    },
+    {
+      "epoch": 2.398822663723326,
+      "grad_norm": 0.4515169168194488,
+      "learning_rate": 1.1679422786091909e-06,
+      "loss": 0.0355,
+      "step": 1630
+    },
+    {
+      "epoch": 2.4135393671817513,
+      "grad_norm": 0.4486232416834487,
+      "learning_rate": 1.1134613733777195e-06,
+      "loss": 0.0353,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4282560706401766,
+      "grad_norm": 0.45969446958453936,
+      "learning_rate": 1.060122102877739e-06,
+      "loss": 0.0369,
+      "step": 1650
+    },
+    {
+      "epoch": 2.4282560706401766,
+      "eval_loss": 0.08896949887275696,
+      "eval_runtime": 190.8926,
+      "eval_samples_per_second": 6.328,
+      "eval_steps_per_second": 0.791,
+      "step": 1650
+    },
+    {
+      "epoch": 2.442972774098602,
+      "grad_norm": 0.4795593227430335,
+      "learning_rate": 1.0079401350260288e-06,
+      "loss": 0.0365,
+      "step": 1660
+    },
+    {
+      "epoch": 2.457689477557027,
+      "grad_norm": 0.4364131921904563,
+      "learning_rate": 9.569307977924304e-07,
+      "loss": 0.0374,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4724061810154527,
+      "grad_norm": 0.39082384348290283,
+      "learning_rate": 9.071090746973999e-07,
+      "loss": 0.0367,
+      "step": 1680
+    },
+    {
+      "epoch": 2.487122884473878,
+      "grad_norm": 0.4316116220500935,
+      "learning_rate": 8.584896004107379e-07,
+      "loss": 0.0357,
+      "step": 1690
+    },
+    {
+      "epoch": 2.501839587932303,
+      "grad_norm": 0.4639023437586311,
+      "learning_rate": 8.110866564527925e-07,
+      "loss": 0.0362,
+      "step": 1700
+    },
+    {
+      "epoch": 2.501839587932303,
+      "eval_loss": 0.08904436975717545,
+      "eval_runtime": 192.3246,
+      "eval_samples_per_second": 6.281,
+      "eval_steps_per_second": 0.785,
+      "step": 1700
+    },
+    {
+      "epoch": 2.5165562913907285,
+      "grad_norm": 0.44077589190339306,
+      "learning_rate": 7.649141669993881e-07,
+      "loss": 0.0342,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5312729948491537,
+      "grad_norm": 0.4866710092763864,
+      "learning_rate": 7.199856947917372e-07,
+      "loss": 0.0355,
+      "step": 1720
+    },
+    {
+      "epoch": 2.5459896983075794,
+      "grad_norm": 0.5558412036138655,
+      "learning_rate": 6.763144371525048e-07,
+      "loss": 0.0362,
+      "step": 1730
+    },
+    {
+      "epoch": 2.560706401766004,
+      "grad_norm": 0.5242729609693463,
+      "learning_rate": 6.339132221092181e-07,
+      "loss": 0.0346,
+      "step": 1740
+    },
+    {
+      "epoch": 2.57542310522443,
+      "grad_norm": 0.43612087623478013,
+      "learning_rate": 5.927945046261541e-07,
+      "loss": 0.0351,
+      "step": 1750
+    },
+    {
+      "epoch": 2.57542310522443,
+      "eval_loss": 0.08865496516227722,
+      "eval_runtime": 189.4933,
+      "eval_samples_per_second": 6.375,
+      "eval_steps_per_second": 0.797,
+      "step": 1750
+    },
+    {
+      "epoch": 2.590139808682855,
+      "grad_norm": 0.4402357233053372,
+      "learning_rate": 5.529703629458027e-07,
+      "loss": 0.0351,
+      "step": 1760
+    },
+    {
+      "epoch": 2.6048565121412803,
+      "grad_norm": 0.4547936707636127,
+      "learning_rate": 5.144524950410074e-07,
+      "loss": 0.0353,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6195732155997056,
+      "grad_norm": 0.46968163264663654,
+      "learning_rate": 4.772522151787822e-07,
+      "loss": 0.0335,
+      "step": 1780
+    },
+    {
+      "epoch": 2.634289919058131,
+      "grad_norm": 0.5323493186585175,
+      "learning_rate": 4.413804505968533e-07,
+      "loss": 0.0381,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6490066225165565,
+      "grad_norm": 0.44646022512750955,
+      "learning_rate": 4.0684773829388737e-07,
+      "loss": 0.0365,
+      "step": 1800
+    },
+    {
+      "epoch": 2.6490066225165565,
+      "eval_loss": 0.08848826587200165,
+      "eval_runtime": 144.7247,
+      "eval_samples_per_second": 8.347,
+      "eval_steps_per_second": 1.043,
+      "step": 1800
+    },
+    {
+      "epoch": 2.6637233259749817,
+      "grad_norm": 0.48313861824298177,
+      "learning_rate": 3.736642219343456e-07,
+      "loss": 0.0341,
+      "step": 1810
+    },
+    {
+      "epoch": 2.678440029433407,
+      "grad_norm": 0.46254464308741905,
+      "learning_rate": 3.4183964886887135e-07,
+      "loss": 0.035,
+      "step": 1820
+    },
+    {
+      "epoch": 2.693156732891832,
+      "grad_norm": 0.44252007786800557,
+      "learning_rate": 3.1138336727110307e-07,
+      "loss": 0.0349,
+      "step": 1830
+    },
+    {
+      "epoch": 2.7078734363502575,
+      "grad_norm": 0.4843414570638625,
+      "learning_rate": 2.823043233917272e-07,
+      "loss": 0.0315,
+      "step": 1840
+    },
+    {
+      "epoch": 2.7225901398086827,
+      "grad_norm": 0.4233437476360991,
+      "learning_rate": 2.5461105893060667e-07,
+      "loss": 0.0336,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7225901398086827,
+      "eval_loss": 0.0889279693365097,
+      "eval_runtime": 148.3,
+      "eval_samples_per_second": 8.146,
+      "eval_steps_per_second": 1.018,
+      "step": 1850
+    },
+    {
+      "epoch": 2.737306843267108,
+      "grad_norm": 0.43298766819944895,
+      "learning_rate": 2.2831170852773198e-07,
+      "loss": 0.0327,
+      "step": 1860
+    },
+    {
+      "epoch": 2.7520235467255336,
+      "grad_norm": 0.5107092795769058,
+      "learning_rate": 2.03413997373747e-07,
+      "loss": 0.035,
+      "step": 1870
+    },
+    {
+      "epoch": 2.766740250183959,
+      "grad_norm": 0.42425673512298995,
+      "learning_rate": 1.7992523894074688e-07,
+      "loss": 0.0356,
+      "step": 1880
+    },
+    {
+      "epoch": 2.781456953642384,
+      "grad_norm": 0.4354877107084126,
+      "learning_rate": 1.578523328340087e-07,
+      "loss": 0.0351,
+      "step": 1890
+    },
+    {
+      "epoch": 2.7961736571008093,
+      "grad_norm": 0.409569927662352,
+      "learning_rate": 1.372017627653044e-07,
+      "loss": 0.0328,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7961736571008093,
+      "eval_loss": 0.08891716599464417,
+      "eval_runtime": 150.1495,
+      "eval_samples_per_second": 8.045,
+      "eval_steps_per_second": 1.006,
+      "step": 1900
+    },
+    {
+      "epoch": 2.8108903605592346,
+      "grad_norm": 0.505372980725658,
+      "learning_rate": 1.179795946483625e-07,
+      "loss": 0.0359,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8256070640176603,
+      "grad_norm": 0.4789426274321432,
+      "learning_rate": 1.0019147481706626e-07,
+      "loss": 0.034,
+      "step": 1920
+    },
+    {
+      "epoch": 2.8403237674760855,
+      "grad_norm": 0.4326698452169212,
+      "learning_rate": 8.384262836689472e-08,
+      "loss": 0.0359,
+      "step": 1930
+    },
+    {
+      "epoch": 2.8550404709345107,
+      "grad_norm": 0.4504134801165135,
+      "learning_rate": 6.893785762009942e-08,
+      "loss": 0.033,
+      "step": 1940
+    },
+    {
+      "epoch": 2.869757174392936,
+      "grad_norm": 0.4418357481535817,
+      "learning_rate": 5.5481540715066616e-08,
+      "loss": 0.031,
+      "step": 1950
+    },
+    {
+      "epoch": 2.869757174392936,
+      "eval_loss": 0.08881029486656189,
+      "eval_runtime": 160.2824,
+      "eval_samples_per_second": 7.537,
+      "eval_steps_per_second": 0.942,
+      "step": 1950
+    },
+    {
+      "epoch": 2.8844738778513612,
+      "grad_norm": 0.39177398397892965,
+      "learning_rate": 4.3477630320279405e-08,
+      "loss": 0.0341,
+      "step": 1960
+    },
+    {
+      "epoch": 2.8991905813097865,
+      "grad_norm": 0.4264281839143634,
+      "learning_rate": 3.292965247325641e-08,
+      "loss": 0.0327,
+      "step": 1970
+    },
+    {
+      "epoch": 2.9139072847682117,
+      "grad_norm": 0.4458194572989954,
+      "learning_rate": 2.3840705544815324e-08,
+      "loss": 0.037,
+      "step": 1980
+    },
+    {
+      "epoch": 2.9286239882266374,
+      "grad_norm": 0.4161959002875069,
+      "learning_rate": 1.6213459328950355e-08,
+      "loss": 0.0336,
+      "step": 1990
+    },
+    {
+      "epoch": 2.9433406916850626,
+      "grad_norm": 0.4581647348930819,
+      "learning_rate": 1.0050154258607336e-08,
+      "loss": 0.0361,
+      "step": 2000
+    },
+    {
+      "epoch": 2.9433406916850626,
+      "eval_loss": 0.08885689079761505,
+      "eval_runtime": 115.9736,
+      "eval_samples_per_second": 10.416,
+      "eval_steps_per_second": 1.302,
+      "step": 2000
+    },
+    {
+      "epoch": 2.958057395143488,
+      "grad_norm": 0.4098910931260614,
+      "learning_rate": 5.352600747577929e-09,
+      "loss": 0.0323,
+      "step": 2010
+    },
+    {
+      "epoch": 2.972774098601913,
+      "grad_norm": 0.4203250122459563,
+      "learning_rate": 2.12217865870612e-09,
+      "loss": 0.0337,
+      "step": 2020
+    },
+    {
+      "epoch": 2.9874908020603383,
+      "grad_norm": 0.4851341052865305,
+      "learning_rate": 3.5983689856522453e-10,
+      "loss": 0.0343,
+      "step": 2030
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2037,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 31897094414336.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}