Upload folder using huggingface_hub

.gitattributes

@@ -53,3 +53,4 @@ Qwen3-8B-huatuo_o1-SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen3-8B-m23k-SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen3-8B-medreason-SFT/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 Qwen2.5-7B-Instruct-Self-Distillation-medreason/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/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
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "4.57.0"
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49935fbf288d9ccf046e70f4ac9ff463b7a72bec92007a04fca76f36ca55f63e
+size 4976687216

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414e096ad736706f8b6d3e0d7674ac570ed6d38d35dfa0c55bd4393b2792f8f6
+size 4778622352

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80b4f855d8bb13ca600c557b8d3ec39b00e24f34acc44071fedadf48b4d1d79
+size 4932743960

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b5a4db1658f93172cb07e38d92ba8b81caa2948e2fe7bc894be5452098daee
+size 4932743992

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79fb4e5847c198632a61bf7578092c9d684ef8332ae10b8df4c9cc144654b74
+size 4998852296

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d60d75d0a8ac3ec241e873364f035264512525e60a2de7ccfa63915382962b3
+size 3662865184

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103592c4469ac604bdcacbbc9189620b1c5375d06de34b2bc4461e0b7ae8bd82
+size 2179989632

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 7615616512,
+    "total_size": 30462466048
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/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
+  }
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/tokenizer.json

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

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/trainer_state.json

@@ -0,0 +1,3730 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 462,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006496142915144133,
+      "grad_norm": 17.562747955322266,
+      "learning_rate": 0.0,
+      "loss": 1.9689,
+      "num_tokens": 84465.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.012992285830288266,
+      "grad_norm": 17.362287521362305,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 1.9322,
+      "num_tokens": 167285.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.0194884287454324,
+      "grad_norm": 16.845909118652344,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.9738,
+      "num_tokens": 252091.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.025984571660576532,
+      "grad_norm": 16.620525360107422,
+      "learning_rate": 1.25e-06,
+      "loss": 1.9506,
+      "num_tokens": 336897.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.032480714575720666,
+      "grad_norm": 14.639083862304688,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.8916,
+      "num_tokens": 419333.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0389768574908648,
+      "grad_norm": 11.3887357711792,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.7946,
+      "num_tokens": 502202.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.045473000406008934,
+      "grad_norm": 10.162360191345215,
+      "learning_rate": 2.5e-06,
+      "loss": 1.7546,
+      "num_tokens": 587493.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.051969143321153065,
+      "grad_norm": 7.007160186767578,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 1.5643,
+      "num_tokens": 674054.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.058465286236297195,
+      "grad_norm": 4.717799186706543,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.5774,
+      "num_tokens": 759259.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.06496142915144133,
+      "grad_norm": 4.105033874511719,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.5696,
+      "num_tokens": 843679.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07145757206658547,
+      "grad_norm": 7.028597354888916,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.5605,
+      "num_tokens": 927331.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0779537149817296,
+      "grad_norm": 5.529964447021484,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 1.4963,
+      "num_tokens": 1011605.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.08444985789687373,
+      "grad_norm": 5.247542858123779,
+      "learning_rate": 5e-06,
+      "loss": 1.4857,
+      "num_tokens": 1093778.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.09094600081201787,
+      "grad_norm": 4.490520477294922,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 1.4377,
+      "num_tokens": 1175346.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.09744214372716199,
+      "grad_norm": 4.15904426574707,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 1.4478,
+      "num_tokens": 1259612.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.10393828664230613,
+      "grad_norm": 3.1510307788848877,
+      "learning_rate": 6.25e-06,
+      "loss": 1.3909,
+      "num_tokens": 1344522.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.11043442955745027,
+      "grad_norm": 2.5599446296691895,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.4011,
+      "num_tokens": 1426767.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.11693057247259439,
+      "grad_norm": 2.3610329627990723,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 1.437,
+      "num_tokens": 1510757.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.12342671538773853,
+      "grad_norm": 2.6431725025177,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.4101,
+      "num_tokens": 1591051.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.12992285830288267,
+      "grad_norm": 2.6624433994293213,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 1.3884,
+      "num_tokens": 1675073.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.1364190012180268,
+      "grad_norm": 2.451549530029297,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.3812,
+      "num_tokens": 1760097.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.14291514413317094,
+      "grad_norm": 2.6071887016296387,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.3534,
+      "num_tokens": 1841556.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.14941128704831505,
+      "grad_norm": 2.1755149364471436,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 1.3768,
+      "num_tokens": 1926237.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.1559074299634592,
+      "grad_norm": 2.017758369445801,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 1.342,
+      "num_tokens": 2010610.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.16240357287860333,
+      "grad_norm": 1.908360481262207,
+      "learning_rate": 1e-05,
+      "loss": 1.3626,
+      "num_tokens": 2095115.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.16889971579374746,
+      "grad_norm": 2.0104880332946777,
+      "learning_rate": 9.999871385577756e-06,
+      "loss": 1.346,
+      "num_tokens": 2175836.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.1753958587088916,
+      "grad_norm": 2.00000262260437,
+      "learning_rate": 9.999485548927686e-06,
+      "loss": 1.3705,
+      "num_tokens": 2259622.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.18189200162403574,
+      "grad_norm": 1.710154414176941,
+      "learning_rate": 9.998842509899456e-06,
+      "loss": 1.343,
+      "num_tokens": 2343207.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.18838814453917987,
+      "grad_norm": 1.665773630142212,
+      "learning_rate": 9.997942301574701e-06,
+      "loss": 1.3338,
+      "num_tokens": 2425528.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.19488428745432398,
+      "grad_norm": 1.4821083545684814,
+      "learning_rate": 9.996784970265335e-06,
+      "loss": 1.3611,
+      "num_tokens": 2510459.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.20138043036946812,
+      "grad_norm": 1.459311604499817,
+      "learning_rate": 9.995370575511151e-06,
+      "loss": 1.2883,
+      "num_tokens": 2592168.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.20787657328461226,
+      "grad_norm": 1.4694446325302124,
+      "learning_rate": 9.993699190076778e-06,
+      "loss": 1.3356,
+      "num_tokens": 2671235.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.2143727161997564,
+      "grad_norm": 1.427956461906433,
+      "learning_rate": 9.991770899947925e-06,
+      "loss": 1.3473,
+      "num_tokens": 2757240.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.22086885911490053,
+      "grad_norm": 1.5773028135299683,
+      "learning_rate": 9.989585804326963e-06,
+      "loss": 1.3681,
+      "num_tokens": 2840374.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.22736500203004467,
+      "grad_norm": 1.3972843885421753,
+      "learning_rate": 9.98714401562781e-06,
+      "loss": 1.3324,
+      "num_tokens": 2922365.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.23386114494518878,
+      "grad_norm": 1.3473612070083618,
+      "learning_rate": 9.984445659470166e-06,
+      "loss": 1.276,
+      "num_tokens": 3007512.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.24035728786033292,
+      "grad_norm": 1.2357933521270752,
+      "learning_rate": 9.98149087467304e-06,
+      "loss": 1.3101,
+      "num_tokens": 3089879.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.24685343077547706,
+      "grad_norm": 1.3232909440994263,
+      "learning_rate": 9.978279813247605e-06,
+      "loss": 1.3357,
+      "num_tokens": 3173269.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.25334957369062117,
+      "grad_norm": 1.3534554243087769,
+      "learning_rate": 9.97481264038939e-06,
+      "loss": 1.2894,
+      "num_tokens": 3256390.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.25984571660576533,
+      "grad_norm": 1.4550755023956299,
+      "learning_rate": 9.97108953446976e-06,
+      "loss": 1.3341,
+      "num_tokens": 3340467.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.26634185952090944,
+      "grad_norm": 1.2924156188964844,
+      "learning_rate": 9.967110687026769e-06,
+      "loss": 1.3119,
+      "num_tokens": 3425507.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.2728380024360536,
+      "grad_norm": 1.2923297882080078,
+      "learning_rate": 9.962876302755283e-06,
+      "loss": 1.3086,
+      "num_tokens": 3507521.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.2793341453511977,
+      "grad_norm": 1.5484058856964111,
+      "learning_rate": 9.95838659949645e-06,
+      "loss": 1.306,
+      "num_tokens": 3590255.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.2858302882663419,
+      "grad_norm": 1.3221476078033447,
+      "learning_rate": 9.953641808226513e-06,
+      "loss": 1.3093,
+      "num_tokens": 3674326.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.292326431181486,
+      "grad_norm": 1.2185076475143433,
+      "learning_rate": 9.948642173044906e-06,
+      "loss": 1.3416,
+      "num_tokens": 3758664.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2988225740966301,
+      "grad_norm": 1.2500603199005127,
+      "learning_rate": 9.943387951161702e-06,
+      "loss": 1.3146,
+      "num_tokens": 3841911.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.30531871701177427,
+      "grad_norm": 1.4542837142944336,
+      "learning_rate": 9.93787941288439e-06,
+      "loss": 1.2806,
+      "num_tokens": 3923028.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.3118148599269184,
+      "grad_norm": 1.2518470287322998,
+      "learning_rate": 9.932116841603954e-06,
+      "loss": 1.2829,
+      "num_tokens": 4006087.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.31831100284206254,
+      "grad_norm": 1.2868304252624512,
+      "learning_rate": 9.926100533780304e-06,
+      "loss": 1.3192,
+      "num_tokens": 4090847.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.32480714575720665,
+      "grad_norm": 1.369153380393982,
+      "learning_rate": 9.919830798927024e-06,
+      "loss": 1.2882,
+      "num_tokens": 4173684.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3313032886723508,
+      "grad_norm": 1.401447057723999,
+      "learning_rate": 9.913307959595443e-06,
+      "loss": 1.3006,
+      "num_tokens": 4254811.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.3377994315874949,
+      "grad_norm": 1.5202405452728271,
+      "learning_rate": 9.906532351358047e-06,
+      "loss": 1.3351,
+      "num_tokens": 4339851.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.34429557450263903,
+      "grad_norm": 1.3173249959945679,
+      "learning_rate": 9.899504322791212e-06,
+      "loss": 1.2866,
+      "num_tokens": 4424766.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.3507917174177832,
+      "grad_norm": 1.3548083305358887,
+      "learning_rate": 9.892224235457269e-06,
+      "loss": 1.3078,
+      "num_tokens": 4508789.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.3572878603329273,
+      "grad_norm": 1.351115345954895,
+      "learning_rate": 9.88469246388591e-06,
+      "loss": 1.3166,
+      "num_tokens": 4590337.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.3637840032480715,
+      "grad_norm": 1.3130844831466675,
+      "learning_rate": 9.876909395554915e-06,
+      "loss": 1.2914,
+      "num_tokens": 4671150.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.3702801461632156,
+      "grad_norm": 1.330084204673767,
+      "learning_rate": 9.868875430870217e-06,
+      "loss": 1.2773,
+      "num_tokens": 4754488.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.37677628907835975,
+      "grad_norm": 1.361896276473999,
+      "learning_rate": 9.860590983145307e-06,
+      "loss": 1.31,
+      "num_tokens": 4836526.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.38327243199350386,
+      "grad_norm": 1.1739567518234253,
+      "learning_rate": 9.85205647857997e-06,
+      "loss": 1.2989,
+      "num_tokens": 4921708.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.38976857490864797,
+      "grad_norm": 1.1971162557601929,
+      "learning_rate": 9.843272356238355e-06,
+      "loss": 1.304,
+      "num_tokens": 5005581.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.39626471782379213,
+      "grad_norm": 1.508194088935852,
+      "learning_rate": 9.834239068026388e-06,
+      "loss": 1.3087,
+      "num_tokens": 5089533.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.40276086073893624,
+      "grad_norm": 1.3696171045303345,
+      "learning_rate": 9.82495707866853e-06,
+      "loss": 1.2733,
+      "num_tokens": 5172689.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.4092570036540804,
+      "grad_norm": 1.2612931728363037,
+      "learning_rate": 9.815426865683858e-06,
+      "loss": 1.3032,
+      "num_tokens": 5257501.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.4157531465692245,
+      "grad_norm": 1.3167438507080078,
+      "learning_rate": 9.805648919361505e-06,
+      "loss": 1.3155,
+      "num_tokens": 5341549.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.42224928948436863,
+      "grad_norm": 1.374207615852356,
+      "learning_rate": 9.79562374273544e-06,
+      "loss": 1.2731,
+      "num_tokens": 5426855.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.4287454323995128,
+      "grad_norm": 1.384965419769287,
+      "learning_rate": 9.785351851558585e-06,
+      "loss": 1.3152,
+      "num_tokens": 5508073.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.4352415753146569,
+      "grad_norm": 1.2849382162094116,
+      "learning_rate": 9.774833774276278e-06,
+      "loss": 1.3124,
+      "num_tokens": 5589292.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.44173771822980107,
+      "grad_norm": 1.2917120456695557,
+      "learning_rate": 9.76407005199909e-06,
+      "loss": 1.3001,
+      "num_tokens": 5670587.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.4482338611449452,
+      "grad_norm": 1.2769274711608887,
+      "learning_rate": 9.75306123847499e-06,
+      "loss": 1.2648,
+      "num_tokens": 5753432.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.45473000406008934,
+      "grad_norm": 1.4168981313705444,
+      "learning_rate": 9.741807900060858e-06,
+      "loss": 1.2815,
+      "num_tokens": 5835935.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.46122614697523345,
+      "grad_norm": 1.38175630569458,
+      "learning_rate": 9.73031061569334e-06,
+      "loss": 1.3248,
+      "num_tokens": 5918426.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.46772228989037756,
+      "grad_norm": 1.428305983543396,
+      "learning_rate": 9.718569976859068e-06,
+      "loss": 1.3151,
+      "num_tokens": 6000808.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.47421843280552173,
+      "grad_norm": 1.3129373788833618,
+      "learning_rate": 9.706586587564236e-06,
+      "loss": 1.2962,
+      "num_tokens": 6086626.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.48071457572066584,
+      "grad_norm": 1.384333610534668,
+      "learning_rate": 9.69436106430352e-06,
+      "loss": 1.289,
+      "num_tokens": 6167279.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.48721071863581,
+      "grad_norm": 1.487824559211731,
+      "learning_rate": 9.681894036028365e-06,
+      "loss": 1.2632,
+      "num_tokens": 6249658.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.4937068615509541,
+      "grad_norm": 1.6289348602294922,
+      "learning_rate": 9.669186144114627e-06,
+      "loss": 1.2906,
+      "num_tokens": 6334332.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.5002030044660982,
+      "grad_norm": 1.3658896684646606,
+      "learning_rate": 9.656238042329575e-06,
+      "loss": 1.3,
+      "num_tokens": 6417653.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.5066991473812423,
+      "grad_norm": 1.3326728343963623,
+      "learning_rate": 9.643050396798262e-06,
+      "loss": 1.3011,
+      "num_tokens": 6499822.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.5131952902963866,
+      "grad_norm": 1.4987390041351318,
+      "learning_rate": 9.62962388596925e-06,
+      "loss": 1.2534,
+      "num_tokens": 6581617.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.5196914332115307,
+      "grad_norm": 1.2615147829055786,
+      "learning_rate": 9.615959200579716e-06,
+      "loss": 1.2973,
+      "num_tokens": 6667168.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.5261875761266748,
+      "grad_norm": 1.2144757509231567,
+      "learning_rate": 9.602057043619903e-06,
+      "loss": 1.2725,
+      "num_tokens": 6750919.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.5326837190418189,
+      "grad_norm": 1.232978105545044,
+      "learning_rate": 9.587918130296969e-06,
+      "loss": 1.3138,
+      "num_tokens": 6835934.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.5391798619569631,
+      "grad_norm": 1.1847156286239624,
+      "learning_rate": 9.57354318799818e-06,
+      "loss": 1.2847,
+      "num_tokens": 6918758.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.5456760048721072,
+      "grad_norm": 1.2400496006011963,
+      "learning_rate": 9.558932956253492e-06,
+      "loss": 1.2978,
+      "num_tokens": 7001640.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.5521721477872513,
+      "grad_norm": 1.283271312713623,
+      "learning_rate": 9.544088186697515e-06,
+      "loss": 1.2971,
+      "num_tokens": 7084558.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.5586682907023954,
+      "grad_norm": 1.319679617881775,
+      "learning_rate": 9.529009643030831e-06,
+      "loss": 1.2687,
+      "num_tokens": 7167781.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.5651644336175395,
+      "grad_norm": 1.1831490993499756,
+      "learning_rate": 9.513698100980715e-06,
+      "loss": 1.2688,
+      "num_tokens": 7249572.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.5716605765326838,
+      "grad_norm": 1.2290761470794678,
+      "learning_rate": 9.498154348261217e-06,
+      "loss": 1.2984,
+      "num_tokens": 7334219.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.5781567194478279,
+      "grad_norm": 1.4779788255691528,
+      "learning_rate": 9.482379184532652e-06,
+      "loss": 1.2891,
+      "num_tokens": 7415086.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.584652862362972,
+      "grad_norm": 1.4846903085708618,
+      "learning_rate": 9.466373421360442e-06,
+      "loss": 1.3119,
+      "num_tokens": 7498494.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5911490052781161,
+      "grad_norm": 1.3375158309936523,
+      "learning_rate": 9.450137882173385e-06,
+      "loss": 1.2904,
+      "num_tokens": 7580337.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.5976451481932602,
+      "grad_norm": 1.30452299118042,
+      "learning_rate": 9.433673402221275e-06,
+      "loss": 1.2902,
+      "num_tokens": 7663543.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.6041412911084044,
+      "grad_norm": 1.2734310626983643,
+      "learning_rate": 9.416980828531944e-06,
+      "loss": 1.315,
+      "num_tokens": 7748168.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.6106374340235485,
+      "grad_norm": 1.4652938842773438,
+      "learning_rate": 9.40006101986768e-06,
+      "loss": 1.3199,
+      "num_tokens": 7832940.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.6171335769386926,
+      "grad_norm": 1.2219370603561401,
+      "learning_rate": 9.382914846681049e-06,
+      "loss": 1.2905,
+      "num_tokens": 7916166.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.6236297198538368,
+      "grad_norm": 1.2579518556594849,
+      "learning_rate": 9.365543191070114e-06,
+      "loss": 1.2966,
+      "num_tokens": 7998640.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.630125862768981,
+      "grad_norm": 1.211687445640564,
+      "learning_rate": 9.347946946733055e-06,
+      "loss": 1.266,
+      "num_tokens": 8081281.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.6366220056841251,
+      "grad_norm": 1.336165189743042,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.2879,
+      "num_tokens": 8166111.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.6431181485992692,
+      "grad_norm": 1.1750496625900269,
+      "learning_rate": 9.312084324397416e-06,
+      "loss": 1.2741,
+      "num_tokens": 8250173.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.6496142915144133,
+      "grad_norm": 1.3167986869812012,
+      "learning_rate": 9.293819791379016e-06,
+      "loss": 1.3011,
+      "num_tokens": 8333829.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6561104344295574,
+      "grad_norm": 1.4260773658752441,
+      "learning_rate": 9.275334359499936e-06,
+      "loss": 1.2792,
+      "num_tokens": 8417492.0,
+      "step": 101
+    },
+    {
+      "epoch": 0.6626065773447016,
+      "grad_norm": 1.239101529121399,
+      "learning_rate": 9.256628979757435e-06,
+      "loss": 1.2847,
+      "num_tokens": 8501328.0,
+      "step": 102
+    },
+    {
+      "epoch": 0.6691027202598457,
+      "grad_norm": 1.2062146663665771,
+      "learning_rate": 9.237704614464157e-06,
+      "loss": 1.273,
+      "num_tokens": 8583413.0,
+      "step": 103
+    },
+    {
+      "epoch": 0.6755988631749898,
+      "grad_norm": 1.317754864692688,
+      "learning_rate": 9.218562237198624e-06,
+      "loss": 1.2632,
+      "num_tokens": 8667080.0,
+      "step": 104
+    },
+    {
+      "epoch": 0.682095006090134,
+      "grad_norm": 1.481912612915039,
+      "learning_rate": 9.19920283275515e-06,
+      "loss": 1.3208,
+      "num_tokens": 8749839.0,
+      "step": 105
+    },
+    {
+      "epoch": 0.6885911490052781,
+      "grad_norm": 1.3733457326889038,
+      "learning_rate": 9.179627397093184e-06,
+      "loss": 1.2741,
+      "num_tokens": 8834596.0,
+      "step": 106
+    },
+    {
+      "epoch": 0.6950872919204223,
+      "grad_norm": 1.2260396480560303,
+      "learning_rate": 9.15983693728607e-06,
+      "loss": 1.2678,
+      "num_tokens": 8917338.0,
+      "step": 107
+    },
+    {
+      "epoch": 0.7015834348355664,
+      "grad_norm": 1.3256531953811646,
+      "learning_rate": 9.139832471469224e-06,
+      "loss": 1.2586,
+      "num_tokens": 8997499.0,
+      "step": 108
+    },
+    {
+      "epoch": 0.7080795777507105,
+      "grad_norm": 1.322245717048645,
+      "learning_rate": 9.119615028787771e-06,
+      "loss": 1.2949,
+      "num_tokens": 9080253.0,
+      "step": 109
+    },
+    {
+      "epoch": 0.7145757206658546,
+      "grad_norm": 1.4608854055404663,
+      "learning_rate": 9.0991856493436e-06,
+      "loss": 1.2954,
+      "num_tokens": 9162573.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.7210718635809987,
+      "grad_norm": 1.3021233081817627,
+      "learning_rate": 9.07854538414184e-06,
+      "loss": 1.2985,
+      "num_tokens": 9246477.0,
+      "step": 111
+    },
+    {
+      "epoch": 0.727568006496143,
+      "grad_norm": 1.1615984439849854,
+      "learning_rate": 9.057695295036806e-06,
+      "loss": 1.2697,
+      "num_tokens": 9331753.0,
+      "step": 112
+    },
+    {
+      "epoch": 0.7340641494112871,
+      "grad_norm": 1.2004354000091553,
+      "learning_rate": 9.036636454677363e-06,
+      "loss": 1.274,
+      "num_tokens": 9413069.0,
+      "step": 113
+    },
+    {
+      "epoch": 0.7405602923264312,
+      "grad_norm": 1.273322343826294,
+      "learning_rate": 9.015369946451749e-06,
+      "loss": 1.2872,
+      "num_tokens": 9494242.0,
+      "step": 114
+    },
+    {
+      "epoch": 0.7470564352415753,
+      "grad_norm": 1.2161086797714233,
+      "learning_rate": 8.993896864431825e-06,
+      "loss": 1.2789,
+      "num_tokens": 9575566.0,
+      "step": 115
+    },
+    {
+      "epoch": 0.7535525781567195,
+      "grad_norm": 1.415924310684204,
+      "learning_rate": 8.972218313316812e-06,
+      "loss": 1.2809,
+      "num_tokens": 9658911.0,
+      "step": 116
+    },
+    {
+      "epoch": 0.7600487210718636,
+      "grad_norm": 1.200283408164978,
+      "learning_rate": 8.950335408376438e-06,
+      "loss": 1.2465,
+      "num_tokens": 9742973.0,
+      "step": 117
+    },
+    {
+      "epoch": 0.7665448639870077,
+      "grad_norm": 1.210262417793274,
+      "learning_rate": 8.928249275393572e-06,
+      "loss": 1.2777,
+      "num_tokens": 9829225.0,
+      "step": 118
+    },
+    {
+      "epoch": 0.7730410069021518,
+      "grad_norm": 1.2613799571990967,
+      "learning_rate": 8.905961050606311e-06,
+      "loss": 1.292,
+      "num_tokens": 9909455.0,
+      "step": 119
+    },
+    {
+      "epoch": 0.7795371498172959,
+      "grad_norm": 1.2984654903411865,
+      "learning_rate": 8.883471880649514e-06,
+      "loss": 1.3049,
+      "num_tokens": 9989604.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.7860332927324402,
+      "grad_norm": 1.2884876728057861,
+      "learning_rate": 8.860782922495821e-06,
+      "loss": 1.2728,
+      "num_tokens": 10071926.0,
+      "step": 121
+    },
+    {
+      "epoch": 0.7925294356475843,
+      "grad_norm": 1.4020085334777832,
+      "learning_rate": 8.837895343396132e-06,
+      "loss": 1.2526,
+      "num_tokens": 10155567.0,
+      "step": 122
+    },
+    {
+      "epoch": 0.7990255785627284,
+      "grad_norm": 1.5161283016204834,
+      "learning_rate": 8.814810320819551e-06,
+      "loss": 1.2837,
+      "num_tokens": 10239100.0,
+      "step": 123
+    },
+    {
+      "epoch": 0.8055217214778725,
+      "grad_norm": 1.2875089645385742,
+      "learning_rate": 8.791529042392813e-06,
+      "loss": 1.2902,
+      "num_tokens": 10322977.0,
+      "step": 124
+    },
+    {
+      "epoch": 0.8120178643930166,
+      "grad_norm": 1.5158648490905762,
+      "learning_rate": 8.76805270583919e-06,
+      "loss": 1.3148,
+      "num_tokens": 10406981.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.8185140073081608,
+      "grad_norm": 1.421493649482727,
+      "learning_rate": 8.744382518916866e-06,
+      "loss": 1.2646,
+      "num_tokens": 10491399.0,
+      "step": 126
+    },
+    {
+      "epoch": 0.8250101502233049,
+      "grad_norm": 1.4433742761611938,
+      "learning_rate": 8.720519699356804e-06,
+      "loss": 1.2917,
+      "num_tokens": 10574537.0,
+      "step": 127
+    },
+    {
+      "epoch": 0.831506293138449,
+      "grad_norm": 1.519897222518921,
+      "learning_rate": 8.696465474800109e-06,
+      "loss": 1.2841,
+      "num_tokens": 10657893.0,
+      "step": 128
+    },
+    {
+      "epoch": 0.8380024360535931,
+      "grad_norm": 1.3815525770187378,
+      "learning_rate": 8.672221082734857e-06,
+      "loss": 1.2873,
+      "num_tokens": 10738401.0,
+      "step": 129
+    },
+    {
+      "epoch": 0.8444985789687373,
+      "grad_norm": 1.4318150281906128,
+      "learning_rate": 8.647787770432439e-06,
+      "loss": 1.284,
+      "num_tokens": 10821154.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.8509947218838815,
+      "grad_norm": 1.5661940574645996,
+      "learning_rate": 8.623166794883393e-06,
+      "loss": 1.3119,
+      "num_tokens": 10906871.0,
+      "step": 131
+    },
+    {
+      "epoch": 0.8574908647990256,
+      "grad_norm": 1.2105814218521118,
+      "learning_rate": 8.598359422732736e-06,
+      "loss": 1.2735,
+      "num_tokens": 10991331.0,
+      "step": 132
+    },
+    {
+      "epoch": 0.8639870077141697,
+      "grad_norm": 1.2898861169815063,
+      "learning_rate": 8.573366930214807e-06,
+      "loss": 1.3051,
+      "num_tokens": 11075270.0,
+      "step": 133
+    },
+    {
+      "epoch": 0.8704831506293138,
+      "grad_norm": 1.1356163024902344,
+      "learning_rate": 8.548190603087594e-06,
+      "loss": 1.2911,
+      "num_tokens": 11159143.0,
+      "step": 134
+    },
+    {
+      "epoch": 0.876979293544458,
+      "grad_norm": 1.258713722229004,
+      "learning_rate": 8.522831736566607e-06,
+      "loss": 1.2499,
+      "num_tokens": 11246243.0,
+      "step": 135
+    },
+    {
+      "epoch": 0.8834754364596021,
+      "grad_norm": 1.406661868095398,
+      "learning_rate": 8.497291635258235e-06,
+      "loss": 1.2722,
+      "num_tokens": 11329266.0,
+      "step": 136
+    },
+    {
+      "epoch": 0.8899715793747462,
+      "grad_norm": 1.169723629951477,
+      "learning_rate": 8.471571613092626e-06,
+      "loss": 1.2766,
+      "num_tokens": 11412418.0,
+      "step": 137
+    },
+    {
+      "epoch": 0.8964677222898904,
+      "grad_norm": 1.1368649005889893,
+      "learning_rate": 8.445672993256095e-06,
+      "loss": 1.2558,
+      "num_tokens": 11497555.0,
+      "step": 138
+    },
+    {
+      "epoch": 0.9029638652050345,
+      "grad_norm": 1.413297176361084,
+      "learning_rate": 8.419597108123054e-06,
+      "loss": 1.3049,
+      "num_tokens": 11582839.0,
+      "step": 139
+    },
+    {
+      "epoch": 0.9094600081201787,
+      "grad_norm": 1.3231922388076782,
+      "learning_rate": 8.393345299187463e-06,
+      "loss": 1.2891,
+      "num_tokens": 11664935.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.9159561510353228,
+      "grad_norm": 1.2128703594207764,
+      "learning_rate": 8.366918916993817e-06,
+      "loss": 1.2862,
+      "num_tokens": 11749695.0,
+      "step": 141
+    },
+    {
+      "epoch": 0.9224522939504669,
+      "grad_norm": 1.153149962425232,
+      "learning_rate": 8.340319321067668e-06,
+      "loss": 1.2766,
+      "num_tokens": 11831884.0,
+      "step": 142
+    },
+    {
+      "epoch": 0.928948436865611,
+      "grad_norm": 1.3276317119598389,
+      "learning_rate": 8.313547879845682e-06,
+      "loss": 1.2792,
+      "num_tokens": 11915694.0,
+      "step": 143
+    },
+    {
+      "epoch": 0.9354445797807551,
+      "grad_norm": 1.1659517288208008,
+      "learning_rate": 8.286605970605234e-06,
+      "loss": 1.2704,
+      "num_tokens": 11999924.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.9419407226958993,
+      "grad_norm": 1.1881825923919678,
+      "learning_rate": 8.259494979393563e-06,
+      "loss": 1.2591,
+      "num_tokens": 12082707.0,
+      "step": 145
+    },
+    {
+      "epoch": 0.9484368656110435,
+      "grad_norm": 1.1128777265548706,
+      "learning_rate": 8.232216300956457e-06,
+      "loss": 1.2718,
+      "num_tokens": 12167643.0,
+      "step": 146
+    },
+    {
+      "epoch": 0.9549330085261876,
+      "grad_norm": 1.1774969100952148,
+      "learning_rate": 8.204771338666504e-06,
+      "loss": 1.3006,
+      "num_tokens": 12251422.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.9614291514413317,
+      "grad_norm": 1.396966814994812,
+      "learning_rate": 8.177161504450887e-06,
+      "loss": 1.3026,
+      "num_tokens": 12333912.0,
+      "step": 148
+    },
+    {
+      "epoch": 0.9679252943564759,
+      "grad_norm": 1.1824673414230347,
+      "learning_rate": 8.149388218718763e-06,
+      "loss": 1.2819,
+      "num_tokens": 12415656.0,
+      "step": 149
+    },
+    {
+      "epoch": 0.97442143727162,
+      "grad_norm": 1.241964340209961,
+      "learning_rate": 8.121452910288164e-06,
+      "loss": 1.267,
+      "num_tokens": 12498747.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.9809175801867641,
+      "grad_norm": 1.1436463594436646,
+      "learning_rate": 8.093357016312518e-06,
+      "loss": 1.2716,
+      "num_tokens": 12581234.0,
+      "step": 151
+    },
+    {
+      "epoch": 0.9874137231019082,
+      "grad_norm": 1.1730459928512573,
+      "learning_rate": 8.06510198220669e-06,
+      "loss": 1.2304,
+      "num_tokens": 12664152.0,
+      "step": 152
+    },
+    {
+      "epoch": 0.9939098660170523,
+      "grad_norm": 1.1741156578063965,
+      "learning_rate": 8.036689261572636e-06,
+      "loss": 1.2218,
+      "num_tokens": 12747151.0,
+      "step": 153
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.325751543045044,
+      "learning_rate": 8.008120316124612e-06,
+      "loss": 1.2784,
+      "num_tokens": 12824843.0,
+      "step": 154
+    },
+    {
+      "epoch": 1.0064961429151442,
+      "grad_norm": 1.4416372776031494,
+      "learning_rate": 7.97939661561399e-06,
+      "loss": 1.1371,
+      "num_tokens": 12911467.0,
+      "step": 155
+    },
+    {
+      "epoch": 1.0129922858302882,
+      "grad_norm": 1.2547346353530884,
+      "learning_rate": 7.950519637753623e-06,
+      "loss": 1.074,
+      "num_tokens": 12996579.0,
+      "step": 156
+    },
+    {
+      "epoch": 1.0194884287454324,
+      "grad_norm": 1.1656826734542847,
+      "learning_rate": 7.921490868141843e-06,
+      "loss": 1.1514,
+      "num_tokens": 13080544.0,
+      "step": 157
+    },
+    {
+      "epoch": 1.0259845716605764,
+      "grad_norm": 1.2442162036895752,
+      "learning_rate": 7.89231180018602e-06,
+      "loss": 1.1561,
+      "num_tokens": 13166500.0,
+      "step": 158
+    },
+    {
+      "epoch": 1.0324807145757207,
+      "grad_norm": 1.1605167388916016,
+      "learning_rate": 7.862983935025745e-06,
+      "loss": 1.1223,
+      "num_tokens": 13250137.0,
+      "step": 159
+    },
+    {
+      "epoch": 1.0389768574908649,
+      "grad_norm": 1.3069239854812622,
+      "learning_rate": 7.83350878145559e-06,
+      "loss": 1.1639,
+      "num_tokens": 13332500.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.0454730004060089,
+      "grad_norm": 1.2415261268615723,
+      "learning_rate": 7.80388785584749e-06,
+      "loss": 1.148,
+      "num_tokens": 13415140.0,
+      "step": 161
+    },
+    {
+      "epoch": 1.051969143321153,
+      "grad_norm": 1.1572989225387573,
+      "learning_rate": 7.774122682072743e-06,
+      "loss": 1.1022,
+      "num_tokens": 13498236.0,
+      "step": 162
+    },
+    {
+      "epoch": 1.058465286236297,
+      "grad_norm": 1.2552450895309448,
+      "learning_rate": 7.744214791423597e-06,
+      "loss": 1.1117,
+      "num_tokens": 13581262.0,
+      "step": 163
+    },
+    {
+      "epoch": 1.0649614291514413,
+      "grad_norm": 1.2701185941696167,
+      "learning_rate": 7.714165722534485e-06,
+      "loss": 1.1257,
+      "num_tokens": 13663813.0,
+      "step": 164
+    },
+    {
+      "epoch": 1.0714575720665855,
+      "grad_norm": 1.323929786682129,
+      "learning_rate": 7.68397702130286e-06,
+      "loss": 1.1253,
+      "num_tokens": 13749320.0,
+      "step": 165
+    },
+    {
+      "epoch": 1.0779537149817295,
+      "grad_norm": 1.4088057279586792,
+      "learning_rate": 7.653650240809667e-06,
+      "loss": 1.1112,
+      "num_tokens": 13833738.0,
+      "step": 166
+    },
+    {
+      "epoch": 1.0844498578968738,
+      "grad_norm": 1.2743468284606934,
+      "learning_rate": 7.6231869412394495e-06,
+      "loss": 1.1386,
+      "num_tokens": 13915970.0,
+      "step": 167
+    },
+    {
+      "epoch": 1.0909460008120178,
+      "grad_norm": 1.1729387044906616,
+      "learning_rate": 7.592588689800077e-06,
+      "loss": 1.1349,
+      "num_tokens": 14001783.0,
+      "step": 168
+    },
+    {
+      "epoch": 1.097442143727162,
+      "grad_norm": 1.2223827838897705,
+      "learning_rate": 7.56185706064212e-06,
+      "loss": 1.1562,
+      "num_tokens": 14083133.0,
+      "step": 169
+    },
+    {
+      "epoch": 1.1039382866423062,
+      "grad_norm": 1.267095923423767,
+      "learning_rate": 7.530993634777868e-06,
+      "loss": 1.1162,
+      "num_tokens": 14167205.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.1104344295574502,
+      "grad_norm": 1.277076005935669,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.1068,
+      "num_tokens": 14248583.0,
+      "step": 171
+    },
+    {
+      "epoch": 1.1169305724725944,
+      "grad_norm": 1.193051815032959,
+      "learning_rate": 7.468877750799887e-06,
+      "loss": 1.1076,
+      "num_tokens": 14331532.0,
+      "step": 172
+    },
+    {
+      "epoch": 1.1234267153877386,
+      "grad_norm": 1.1778908967971802,
+      "learning_rate": 7.437628488285568e-06,
+      "loss": 1.1167,
+      "num_tokens": 14417742.0,
+      "step": 173
+    },
+    {
+      "epoch": 1.1299228583028826,
+      "grad_norm": 1.1709506511688232,
+      "learning_rate": 7.40625382009938e-06,
+      "loss": 1.1471,
+      "num_tokens": 14498868.0,
+      "step": 174
+    },
+    {
+      "epoch": 1.1364190012180269,
+      "grad_norm": 1.267059326171875,
+      "learning_rate": 7.374755360335253e-06,
+      "loss": 1.129,
+      "num_tokens": 14579992.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.1429151441331709,
+      "grad_norm": 1.2610149383544922,
+      "learning_rate": 7.343134729455667e-06,
+      "loss": 1.1357,
+      "num_tokens": 14664246.0,
+      "step": 176
+    },
+    {
+      "epoch": 1.149411287048315,
+      "grad_norm": 1.0788607597351074,
+      "learning_rate": 7.311393554208292e-06,
+      "loss": 1.1575,
+      "num_tokens": 14748831.0,
+      "step": 177
+    },
+    {
+      "epoch": 1.155907429963459,
+      "grad_norm": 1.1409209966659546,
+      "learning_rate": 7.279533467542295e-06,
+      "loss": 1.103,
+      "num_tokens": 14829749.0,
+      "step": 178
+    },
+    {
+      "epoch": 1.1624035728786033,
+      "grad_norm": 1.2172008752822876,
+      "learning_rate": 7.24755610852433e-06,
+      "loss": 1.1398,
+      "num_tokens": 14913033.0,
+      "step": 179
+    },
+    {
+      "epoch": 1.1688997157937475,
+      "grad_norm": 1.2029918432235718,
+      "learning_rate": 7.2154631222542205e-06,
+      "loss": 1.1145,
+      "num_tokens": 14994745.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.1753958587088915,
+      "grad_norm": 1.1301356554031372,
+      "learning_rate": 7.183256159780321e-06,
+      "loss": 1.1375,
+      "num_tokens": 15080251.0,
+      "step": 181
+    },
+    {
+      "epoch": 1.1818920016240357,
+      "grad_norm": 1.216943621635437,
+      "learning_rate": 7.150936878014578e-06,
+      "loss": 1.1152,
+      "num_tokens": 15163893.0,
+      "step": 182
+    },
+    {
+      "epoch": 1.18838814453918,
+      "grad_norm": 1.2363911867141724,
+      "learning_rate": 7.118506939647295e-06,
+      "loss": 1.1484,
+      "num_tokens": 15248020.0,
+      "step": 183
+    },
+    {
+      "epoch": 1.194884287454324,
+      "grad_norm": 1.1245181560516357,
+      "learning_rate": 7.085968013061585e-06,
+      "loss": 1.111,
+      "num_tokens": 15330841.0,
+      "step": 184
+    },
+    {
+      "epoch": 1.2013804303694682,
+      "grad_norm": 1.1434259414672852,
+      "learning_rate": 7.053321772247546e-06,
+      "loss": 1.1396,
+      "num_tokens": 15414533.0,
+      "step": 185
+    },
+    {
+      "epoch": 1.2078765732846122,
+      "grad_norm": 1.1437957286834717,
+      "learning_rate": 7.020569896716137e-06,
+      "loss": 1.1178,
+      "num_tokens": 15495990.0,
+      "step": 186
+    },
+    {
+      "epoch": 1.2143727161997564,
+      "grad_norm": 1.179869294166565,
+      "learning_rate": 6.987714071412781e-06,
+      "loss": 1.1187,
+      "num_tokens": 15576404.0,
+      "step": 187
+    },
+    {
+      "epoch": 1.2208688591149006,
+      "grad_norm": 1.1332143545150757,
+      "learning_rate": 6.9547559866306695e-06,
+      "loss": 1.143,
+      "num_tokens": 15661163.0,
+      "step": 188
+    },
+    {
+      "epoch": 1.2273650020300446,
+      "grad_norm": 1.194716215133667,
+      "learning_rate": 6.9216973379238175e-06,
+      "loss": 1.1271,
+      "num_tokens": 15746597.0,
+      "step": 189
+    },
+    {
+      "epoch": 1.2338611449451888,
+      "grad_norm": 1.1721012592315674,
+      "learning_rate": 6.888539826019824e-06,
+      "loss": 1.1471,
+      "num_tokens": 15832449.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.2403572878603328,
+      "grad_norm": 1.134859323501587,
+      "learning_rate": 6.855285156732389e-06,
+      "loss": 1.1208,
+      "num_tokens": 15915582.0,
+      "step": 191
+    },
+    {
+      "epoch": 1.246853430775477,
+      "grad_norm": 1.2513058185577393,
+      "learning_rate": 6.821935040873538e-06,
+      "loss": 1.1166,
+      "num_tokens": 15999150.0,
+      "step": 192
+    },
+    {
+      "epoch": 1.2533495736906213,
+      "grad_norm": 1.1668031215667725,
+      "learning_rate": 6.788491194165629e-06,
+      "loss": 1.1347,
+      "num_tokens": 16081498.0,
+      "step": 193
+    },
+    {
+      "epoch": 1.2598457166057653,
+      "grad_norm": 1.1581473350524902,
+      "learning_rate": 6.754955337153066e-06,
+      "loss": 1.1034,
+      "num_tokens": 16165782.0,
+      "step": 194
+    },
+    {
+      "epoch": 1.2663418595209095,
+      "grad_norm": 1.2343841791152954,
+      "learning_rate": 6.721329195113802e-06,
+      "loss": 1.1942,
+      "num_tokens": 16250012.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.2728380024360537,
+      "grad_norm": 1.252421259880066,
+      "learning_rate": 6.687614497970567e-06,
+      "loss": 1.1446,
+      "num_tokens": 16331957.0,
+      "step": 196
+    },
+    {
+      "epoch": 1.2793341453511977,
+      "grad_norm": 1.074736475944519,
+      "learning_rate": 6.653812980201882e-06,
+      "loss": 1.16,
+      "num_tokens": 16418009.0,
+      "step": 197
+    },
+    {
+      "epoch": 1.285830288266342,
+      "grad_norm": 1.1678014993667603,
+      "learning_rate": 6.6199263807528136e-06,
+      "loss": 1.1553,
+      "num_tokens": 16501118.0,
+      "step": 198
+    },
+    {
+      "epoch": 1.292326431181486,
+      "grad_norm": 1.3026130199432373,
+      "learning_rate": 6.585956442945531e-06,
+      "loss": 1.1549,
+      "num_tokens": 16585198.0,
+      "step": 199
+    },
+    {
+      "epoch": 1.2988225740966302,
+      "grad_norm": 1.093330979347229,
+      "learning_rate": 6.551904914389601e-06,
+      "loss": 1.1174,
+      "num_tokens": 16666955.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.3053187170117742,
+      "grad_norm": 1.146944284439087,
+      "learning_rate": 6.5177735468920935e-06,
+      "loss": 1.1284,
+      "num_tokens": 16750912.0,
+      "step": 201
+    },
+    {
+      "epoch": 1.3118148599269184,
+      "grad_norm": 1.3015366792678833,
+      "learning_rate": 6.483564096367452e-06,
+      "loss": 1.1086,
+      "num_tokens": 16835020.0,
+      "step": 202
+    },
+    {
+      "epoch": 1.3183110028420626,
+      "grad_norm": 1.1633856296539307,
+      "learning_rate": 6.449278322747164e-06,
+      "loss": 1.0864,
+      "num_tokens": 16919121.0,
+      "step": 203
+    },
+    {
+      "epoch": 1.3248071457572066,
+      "grad_norm": 1.1894924640655518,
+      "learning_rate": 6.414917989889212e-06,
+      "loss": 1.1851,
+      "num_tokens": 17003653.0,
+      "step": 204
+    },
+    {
+      "epoch": 1.3313032886723508,
+      "grad_norm": 1.156470775604248,
+      "learning_rate": 6.380484865487346e-06,
+      "loss": 1.1124,
+      "num_tokens": 17085957.0,
+      "step": 205
+    },
+    {
+      "epoch": 1.337799431587495,
+      "grad_norm": 1.092347502708435,
+      "learning_rate": 6.345980720980119e-06,
+      "loss": 1.1446,
+      "num_tokens": 17168752.0,
+      "step": 206
+    },
+    {
+      "epoch": 1.344295574502639,
+      "grad_norm": 1.17254638671875,
+      "learning_rate": 6.311407331459781e-06,
+      "loss": 1.1441,
+      "num_tokens": 17253659.0,
+      "step": 207
+    },
+    {
+      "epoch": 1.3507917174177833,
+      "grad_norm": 1.3522309064865112,
+      "learning_rate": 6.276766475580935e-06,
+      "loss": 1.1459,
+      "num_tokens": 17335250.0,
+      "step": 208
+    },
+    {
+      "epoch": 1.3572878603329273,
+      "grad_norm": 1.1459577083587646,
+      "learning_rate": 6.242059935469051e-06,
+      "loss": 1.1304,
+      "num_tokens": 17419362.0,
+      "step": 209
+    },
+    {
+      "epoch": 1.3637840032480715,
+      "grad_norm": 1.1647331714630127,
+      "learning_rate": 6.207289496628768e-06,
+      "loss": 1.1105,
+      "num_tokens": 17503007.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.3702801461632155,
+      "grad_norm": 1.1486610174179077,
+      "learning_rate": 6.1724569478520495e-06,
+      "loss": 1.136,
+      "num_tokens": 17585984.0,
+      "step": 211
+    },
+    {
+      "epoch": 1.3767762890783597,
+      "grad_norm": 1.1860041618347168,
+      "learning_rate": 6.1375640811261486e-06,
+      "loss": 1.1681,
+      "num_tokens": 17669363.0,
+      "step": 212
+    },
+    {
+      "epoch": 1.383272431993504,
+      "grad_norm": 1.1668682098388672,
+      "learning_rate": 6.102612691541422e-06,
+      "loss": 1.1051,
+      "num_tokens": 17750953.0,
+      "step": 213
+    },
+    {
+      "epoch": 1.389768574908648,
+      "grad_norm": 1.0861740112304688,
+      "learning_rate": 6.067604577198981e-06,
+      "loss": 1.1032,
+      "num_tokens": 17832985.0,
+      "step": 214
+    },
+    {
+      "epoch": 1.3962647178237921,
+      "grad_norm": 1.135737419128418,
+      "learning_rate": 6.032541539118188e-06,
+      "loss": 1.1397,
+      "num_tokens": 17918648.0,
+      "step": 215
+    },
+    {
+      "epoch": 1.4027608607389364,
+      "grad_norm": 1.144451379776001,
+      "learning_rate": 5.997425381143994e-06,
+      "loss": 1.139,
+      "num_tokens": 18001661.0,
+      "step": 216
+    },
+    {
+      "epoch": 1.4092570036540804,
+      "grad_norm": 1.0454533100128174,
+      "learning_rate": 5.96225790985415e-06,
+      "loss": 1.1219,
+      "num_tokens": 18084376.0,
+      "step": 217
+    },
+    {
+      "epoch": 1.4157531465692246,
+      "grad_norm": 1.1287851333618164,
+      "learning_rate": 5.927040934466255e-06,
+      "loss": 1.167,
+      "num_tokens": 18166920.0,
+      "step": 218
+    },
+    {
+      "epoch": 1.4222492894843686,
+      "grad_norm": 1.1230182647705078,
+      "learning_rate": 5.891776266744686e-06,
+      "loss": 1.1336,
+      "num_tokens": 18253867.0,
+      "step": 219
+    },
+    {
+      "epoch": 1.4287454323995128,
+      "grad_norm": 1.1605838537216187,
+      "learning_rate": 5.856465720907388e-06,
+      "loss": 1.1149,
+      "num_tokens": 18338029.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.4352415753146568,
+      "grad_norm": 1.1887422800064087,
+      "learning_rate": 5.821111113532545e-06,
+      "loss": 1.1071,
+      "num_tokens": 18418849.0,
+      "step": 221
+    },
+    {
+      "epoch": 1.441737718229801,
+      "grad_norm": 1.1023333072662354,
+      "learning_rate": 5.7857142634651135e-06,
+      "loss": 1.1427,
+      "num_tokens": 18501911.0,
+      "step": 222
+    },
+    {
+      "epoch": 1.4482338611449452,
+      "grad_norm": 1.192810297012329,
+      "learning_rate": 5.7502769917232635e-06,
+      "loss": 1.1167,
+      "num_tokens": 18585572.0,
+      "step": 223
+    },
+    {
+      "epoch": 1.4547300040600892,
+      "grad_norm": 1.1409016847610474,
+      "learning_rate": 5.7148011214046895e-06,
+      "loss": 1.1977,
+      "num_tokens": 18667480.0,
+      "step": 224
+    },
+    {
+      "epoch": 1.4612261469752335,
+      "grad_norm": 1.0730053186416626,
+      "learning_rate": 5.679288477592815e-06,
+      "loss": 1.1379,
+      "num_tokens": 18751874.0,
+      "step": 225
+    },
+    {
+      "epoch": 1.4677222898903777,
+      "grad_norm": 1.1611896753311157,
+      "learning_rate": 5.643740887262905e-06,
+      "loss": 1.1143,
+      "num_tokens": 18834464.0,
+      "step": 226
+    },
+    {
+      "epoch": 1.4742184328055217,
+      "grad_norm": 1.1547163724899292,
+      "learning_rate": 5.608160179188079e-06,
+      "loss": 1.1261,
+      "num_tokens": 18915392.0,
+      "step": 227
+    },
+    {
+      "epoch": 1.480714575720666,
+      "grad_norm": 1.227557897567749,
+      "learning_rate": 5.572548183845222e-06,
+      "loss": 1.1,
+      "num_tokens": 18996650.0,
+      "step": 228
+    },
+    {
+      "epoch": 1.4872107186358101,
+      "grad_norm": 1.2479780912399292,
+      "learning_rate": 5.536906733320816e-06,
+      "loss": 1.1197,
+      "num_tokens": 19079293.0,
+      "step": 229
+    },
+    {
+      "epoch": 1.4937068615509541,
+      "grad_norm": 1.1428312063217163,
+      "learning_rate": 5.501237661216687e-06,
+      "loss": 1.1444,
+      "num_tokens": 19160274.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.5002030044660981,
+      "grad_norm": 1.1627033948898315,
+      "learning_rate": 5.465542802555677e-06,
+      "loss": 1.1218,
+      "num_tokens": 19242419.0,
+      "step": 231
+    },
+    {
+      "epoch": 1.5066991473812423,
+      "grad_norm": 1.1563552618026733,
+      "learning_rate": 5.429823993687234e-06,
+      "loss": 1.1502,
+      "num_tokens": 19327651.0,
+      "step": 232
+    },
+    {
+      "epoch": 1.5131952902963866,
+      "grad_norm": 1.3349025249481201,
+      "learning_rate": 5.394083072192944e-06,
+      "loss": 1.1212,
+      "num_tokens": 19407472.0,
+      "step": 233
+    },
+    {
+      "epoch": 1.5196914332115306,
+      "grad_norm": 1.2745858430862427,
+      "learning_rate": 5.358321876791995e-06,
+      "loss": 1.1387,
+      "num_tokens": 19489167.0,
+      "step": 234
+    },
+    {
+      "epoch": 1.5261875761266748,
+      "grad_norm": 1.0928750038146973,
+      "learning_rate": 5.322542247246583e-06,
+      "loss": 1.1475,
+      "num_tokens": 19573981.0,
+      "step": 235
+    },
+    {
+      "epoch": 1.532683719041819,
+      "grad_norm": 1.191294550895691,
+      "learning_rate": 5.286746024267257e-06,
+      "loss": 1.1309,
+      "num_tokens": 19657385.0,
+      "step": 236
+    },
+    {
+      "epoch": 1.539179861956963,
+      "grad_norm": 1.1260490417480469,
+      "learning_rate": 5.2509350494182365e-06,
+      "loss": 1.0823,
+      "num_tokens": 19742329.0,
+      "step": 237
+    },
+    {
+      "epoch": 1.5456760048721072,
+      "grad_norm": 1.2375948429107666,
+      "learning_rate": 5.215111165022653e-06,
+      "loss": 1.124,
+      "num_tokens": 19826610.0,
+      "step": 238
+    },
+    {
+      "epoch": 1.5521721477872514,
+      "grad_norm": 1.1782491207122803,
+      "learning_rate": 5.179276214067788e-06,
+      "loss": 1.1118,
+      "num_tokens": 19910142.0,
+      "step": 239
+    },
+    {
+      "epoch": 1.5586682907023954,
+      "grad_norm": 1.2461634874343872,
+      "learning_rate": 5.143432040110243e-06,
+      "loss": 1.128,
+      "num_tokens": 19995534.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.5651644336175394,
+      "grad_norm": 1.112359642982483,
+      "learning_rate": 5.107580487181112e-06,
+      "loss": 1.1175,
+      "num_tokens": 20078744.0,
+      "step": 241
+    },
+    {
+      "epoch": 1.5716605765326839,
+      "grad_norm": 1.0535489320755005,
+      "learning_rate": 5.071723399691098e-06,
+      "loss": 1.1216,
+      "num_tokens": 20161258.0,
+      "step": 242
+    },
+    {
+      "epoch": 1.5781567194478279,
+      "grad_norm": 1.242282509803772,
+      "learning_rate": 5.035862622335641e-06,
+      "loss": 1.0893,
+      "num_tokens": 20241604.0,
+      "step": 243
+    },
+    {
+      "epoch": 1.5846528623629719,
+      "grad_norm": 1.2262176275253296,
+      "learning_rate": 5e-06,
+      "loss": 1.1672,
+      "num_tokens": 20326714.0,
+      "step": 244
+    },
+    {
+      "epoch": 1.591149005278116,
+      "grad_norm": 1.0598175525665283,
+      "learning_rate": 4.964137377664362e-06,
+      "loss": 1.1248,
+      "num_tokens": 20408893.0,
+      "step": 245
+    },
+    {
+      "epoch": 1.5976451481932603,
+      "grad_norm": 1.0841113328933716,
+      "learning_rate": 4.9282766003089025e-06,
+      "loss": 1.1471,
+      "num_tokens": 20491450.0,
+      "step": 246
+    },
+    {
+      "epoch": 1.6041412911084043,
+      "grad_norm": 1.1693425178527832,
+      "learning_rate": 4.89241951281889e-06,
+      "loss": 1.1617,
+      "num_tokens": 20575795.0,
+      "step": 247
+    },
+    {
+      "epoch": 1.6106374340235485,
+      "grad_norm": 1.071923851966858,
+      "learning_rate": 4.856567959889758e-06,
+      "loss": 1.1039,
+      "num_tokens": 20659186.0,
+      "step": 248
+    },
+    {
+      "epoch": 1.6171335769386928,
+      "grad_norm": 1.107526421546936,
+      "learning_rate": 4.8207237859322144e-06,
+      "loss": 1.1221,
+      "num_tokens": 20742663.0,
+      "step": 249
+    },
+    {
+      "epoch": 1.6236297198538368,
+      "grad_norm": 1.1305243968963623,
+      "learning_rate": 4.784888834977347e-06,
+      "loss": 1.1116,
+      "num_tokens": 20826017.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.630125862768981,
+      "grad_norm": 1.1435154676437378,
+      "learning_rate": 4.749064950581765e-06,
+      "loss": 1.1413,
+      "num_tokens": 20908095.0,
+      "step": 251
+    },
+    {
+      "epoch": 1.6366220056841252,
+      "grad_norm": 1.1344348192214966,
+      "learning_rate": 4.7132539757327435e-06,
+      "loss": 1.1005,
+      "num_tokens": 20989481.0,
+      "step": 252
+    },
+    {
+      "epoch": 1.6431181485992692,
+      "grad_norm": 1.1638672351837158,
+      "learning_rate": 4.6774577527534195e-06,
+      "loss": 1.1718,
+      "num_tokens": 21075797.0,
+      "step": 253
+    },
+    {
+      "epoch": 1.6496142915144132,
+      "grad_norm": 1.1063148975372314,
+      "learning_rate": 4.641678123208005e-06,
+      "loss": 1.1149,
+      "num_tokens": 21159597.0,
+      "step": 254
+    },
+    {
+      "epoch": 1.6561104344295574,
+      "grad_norm": 1.1222566366195679,
+      "learning_rate": 4.6059169278070576e-06,
+      "loss": 1.1319,
+      "num_tokens": 21241765.0,
+      "step": 255
+    },
+    {
+      "epoch": 1.6626065773447016,
+      "grad_norm": 1.0895583629608154,
+      "learning_rate": 4.570176006312769e-06,
+      "loss": 1.1134,
+      "num_tokens": 21327660.0,
+      "step": 256
+    },
+    {
+      "epoch": 1.6691027202598456,
+      "grad_norm": 1.0752440690994263,
+      "learning_rate": 4.5344571974443255e-06,
+      "loss": 1.1215,
+      "num_tokens": 21412084.0,
+      "step": 257
+    },
+    {
+      "epoch": 1.6755988631749898,
+      "grad_norm": 1.1699520349502563,
+      "learning_rate": 4.498762338783314e-06,
+      "loss": 1.1256,
+      "num_tokens": 21496205.0,
+      "step": 258
+    },
+    {
+      "epoch": 1.682095006090134,
+      "grad_norm": 1.1109583377838135,
+      "learning_rate": 4.463093266679185e-06,
+      "loss": 1.1295,
+      "num_tokens": 21577143.0,
+      "step": 259
+    },
+    {
+      "epoch": 1.688591149005278,
+      "grad_norm": 1.0834985971450806,
+      "learning_rate": 4.42745181615478e-06,
+      "loss": 1.1284,
+      "num_tokens": 21660099.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.6950872919204223,
+      "grad_norm": 1.0798195600509644,
+      "learning_rate": 4.391839820811923e-06,
+      "loss": 1.118,
+      "num_tokens": 21742313.0,
+      "step": 261
+    },
+    {
+      "epoch": 1.7015834348355665,
+      "grad_norm": 1.0989066362380981,
+      "learning_rate": 4.356259112737096e-06,
+      "loss": 1.121,
+      "num_tokens": 21825731.0,
+      "step": 262
+    },
+    {
+      "epoch": 1.7080795777507105,
+      "grad_norm": 1.2065327167510986,
+      "learning_rate": 4.3207115224071874e-06,
+      "loss": 1.1624,
+      "num_tokens": 21908635.0,
+      "step": 263
+    },
+    {
+      "epoch": 1.7145757206658545,
+      "grad_norm": 1.1532487869262695,
+      "learning_rate": 4.285198878595312e-06,
+      "loss": 1.1215,
+      "num_tokens": 21990863.0,
+      "step": 264
+    },
+    {
+      "epoch": 1.7210718635809987,
+      "grad_norm": 1.2180917263031006,
+      "learning_rate": 4.249723008276737e-06,
+      "loss": 1.1527,
+      "num_tokens": 22072989.0,
+      "step": 265
+    },
+    {
+      "epoch": 1.727568006496143,
+      "grad_norm": 1.1133525371551514,
+      "learning_rate": 4.214285736534887e-06,
+      "loss": 1.1212,
+      "num_tokens": 22156603.0,
+      "step": 266
+    },
+    {
+      "epoch": 1.734064149411287,
+      "grad_norm": 1.1373378038406372,
+      "learning_rate": 4.178888886467457e-06,
+      "loss": 1.1163,
+      "num_tokens": 22238996.0,
+      "step": 267
+    },
+    {
+      "epoch": 1.7405602923264312,
+      "grad_norm": 1.1160866022109985,
+      "learning_rate": 4.143534279092613e-06,
+      "loss": 1.1213,
+      "num_tokens": 22322792.0,
+      "step": 268
+    },
+    {
+      "epoch": 1.7470564352415754,
+      "grad_norm": 1.0862774848937988,
+      "learning_rate": 4.108223733255316e-06,
+      "loss": 1.1373,
+      "num_tokens": 22404999.0,
+      "step": 269
+    },
+    {
+      "epoch": 1.7535525781567194,
+      "grad_norm": 1.168677806854248,
+      "learning_rate": 4.072959065533745e-06,
+      "loss": 1.1225,
+      "num_tokens": 22487451.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.7600487210718636,
+      "grad_norm": 1.1960335969924927,
+      "learning_rate": 4.037742090145851e-06,
+      "loss": 1.1229,
+      "num_tokens": 22572339.0,
+      "step": 271
+    },
+    {
+      "epoch": 1.7665448639870078,
+      "grad_norm": 1.0907739400863647,
+      "learning_rate": 4.002574618856007e-06,
+      "loss": 1.1047,
+      "num_tokens": 22652887.0,
+      "step": 272
+    },
+    {
+      "epoch": 1.7730410069021518,
+      "grad_norm": 1.0913026332855225,
+      "learning_rate": 3.967458460881815e-06,
+      "loss": 1.113,
+      "num_tokens": 22735054.0,
+      "step": 273
+    },
+    {
+      "epoch": 1.7795371498172958,
+      "grad_norm": 1.151492714881897,
+      "learning_rate": 3.93239542280102e-06,
+      "loss": 1.133,
+      "num_tokens": 22818806.0,
+      "step": 274
+    },
+    {
+      "epoch": 1.7860332927324403,
+      "grad_norm": 1.1062548160552979,
+      "learning_rate": 3.89738730845858e-06,
+      "loss": 1.1346,
+      "num_tokens": 22904737.0,
+      "step": 275
+    },
+    {
+      "epoch": 1.7925294356475843,
+      "grad_norm": 1.2805333137512207,
+      "learning_rate": 3.862435918873854e-06,
+      "loss": 1.1636,
+      "num_tokens": 22989906.0,
+      "step": 276
+    },
+    {
+      "epoch": 1.7990255785627283,
+      "grad_norm": 1.1878929138183594,
+      "learning_rate": 3.827543052147952e-06,
+      "loss": 1.1136,
+      "num_tokens": 23072677.0,
+      "step": 277
+    },
+    {
+      "epoch": 1.8055217214778725,
+      "grad_norm": 1.0575178861618042,
+      "learning_rate": 3.792710503371232e-06,
+      "loss": 1.107,
+      "num_tokens": 23158061.0,
+      "step": 278
+    },
+    {
+      "epoch": 1.8120178643930167,
+      "grad_norm": 1.1051832437515259,
+      "learning_rate": 3.75794006453095e-06,
+      "loss": 1.1081,
+      "num_tokens": 23240847.0,
+      "step": 279
+    },
+    {
+      "epoch": 1.8185140073081607,
+      "grad_norm": 1.065326452255249,
+      "learning_rate": 3.7232335244190656e-06,
+      "loss": 1.1424,
+      "num_tokens": 23323072.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.825010150223305,
+      "grad_norm": 1.292227864265442,
+      "learning_rate": 3.6885926685402213e-06,
+      "loss": 1.1093,
+      "num_tokens": 23406862.0,
+      "step": 281
+    },
+    {
+      "epoch": 1.8315062931384491,
+      "grad_norm": 1.1526057720184326,
+      "learning_rate": 3.654019279019881e-06,
+      "loss": 1.1122,
+      "num_tokens": 23490846.0,
+      "step": 282
+    },
+    {
+      "epoch": 1.8380024360535931,
+      "grad_norm": 1.0824768543243408,
+      "learning_rate": 3.6195151345126556e-06,
+      "loss": 1.1126,
+      "num_tokens": 23571243.0,
+      "step": 283
+    },
+    {
+      "epoch": 1.8444985789687371,
+      "grad_norm": 1.0672643184661865,
+      "learning_rate": 3.5850820101107885e-06,
+      "loss": 1.1401,
+      "num_tokens": 23656706.0,
+      "step": 284
+    },
+    {
+      "epoch": 1.8509947218838816,
+      "grad_norm": 1.0917854309082031,
+      "learning_rate": 3.5507216772528392e-06,
+      "loss": 1.1345,
+      "num_tokens": 23739113.0,
+      "step": 285
+    },
+    {
+      "epoch": 1.8574908647990256,
+      "grad_norm": 1.073060154914856,
+      "learning_rate": 3.5164359036325483e-06,
+      "loss": 1.1244,
+      "num_tokens": 23824332.0,
+      "step": 286
+    },
+    {
+      "epoch": 1.8639870077141696,
+      "grad_norm": 1.1292610168457031,
+      "learning_rate": 3.4822264531079074e-06,
+      "loss": 1.1242,
+      "num_tokens": 23907727.0,
+      "step": 287
+    },
+    {
+      "epoch": 1.8704831506293138,
+      "grad_norm": 1.1766952276229858,
+      "learning_rate": 3.4480950856104002e-06,
+      "loss": 1.1343,
+      "num_tokens": 23990564.0,
+      "step": 288
+    },
+    {
+      "epoch": 1.876979293544458,
+      "grad_norm": 1.1008917093276978,
+      "learning_rate": 3.4140435570544708e-06,
+      "loss": 1.1349,
+      "num_tokens": 24076318.0,
+      "step": 289
+    },
+    {
+      "epoch": 1.883475436459602,
+      "grad_norm": 1.2433549165725708,
+      "learning_rate": 3.380073619247187e-06,
+      "loss": 1.125,
+      "num_tokens": 24158443.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.8899715793747462,
+      "grad_norm": 1.1355684995651245,
+      "learning_rate": 3.3461870197981205e-06,
+      "loss": 1.1211,
+      "num_tokens": 24242990.0,
+      "step": 291
+    },
+    {
+      "epoch": 1.8964677222898905,
+      "grad_norm": 1.080373764038086,
+      "learning_rate": 3.3123855020294344e-06,
+      "loss": 1.1186,
+      "num_tokens": 24326344.0,
+      "step": 292
+    },
+    {
+      "epoch": 1.9029638652050345,
+      "grad_norm": 1.0541375875473022,
+      "learning_rate": 3.2786708048862e-06,
+      "loss": 1.1374,
+      "num_tokens": 24410900.0,
+      "step": 293
+    },
+    {
+      "epoch": 1.9094600081201787,
+      "grad_norm": 1.1492620706558228,
+      "learning_rate": 3.2450446628469346e-06,
+      "loss": 1.1482,
+      "num_tokens": 24493611.0,
+      "step": 294
+    },
+    {
+      "epoch": 1.915956151035323,
+      "grad_norm": 1.2003000974655151,
+      "learning_rate": 3.2115088058343725e-06,
+      "loss": 1.0959,
+      "num_tokens": 24576250.0,
+      "step": 295
+    },
+    {
+      "epoch": 1.922452293950467,
+      "grad_norm": 1.141201376914978,
+      "learning_rate": 3.1780649591264635e-06,
+      "loss": 1.1316,
+      "num_tokens": 24657175.0,
+      "step": 296
+    },
+    {
+      "epoch": 1.928948436865611,
+      "grad_norm": 1.1175236701965332,
+      "learning_rate": 3.144714843267613e-06,
+      "loss": 1.0968,
+      "num_tokens": 24740718.0,
+      "step": 297
+    },
+    {
+      "epoch": 1.9354445797807551,
+      "grad_norm": 1.131095290184021,
+      "learning_rate": 3.111460173980175e-06,
+      "loss": 1.1215,
+      "num_tokens": 24825120.0,
+      "step": 298
+    },
+    {
+      "epoch": 1.9419407226958993,
+      "grad_norm": 1.0876582860946655,
+      "learning_rate": 3.0783026620761846e-06,
+      "loss": 1.1281,
+      "num_tokens": 24908431.0,
+      "step": 299
+    },
+    {
+      "epoch": 1.9484368656110433,
+      "grad_norm": 1.1105399131774902,
+      "learning_rate": 3.045244013369333e-06,
+      "loss": 1.1189,
+      "num_tokens": 24992664.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.9549330085261876,
+      "grad_norm": 1.101572871208191,
+      "learning_rate": 3.0122859285872214e-06,
+      "loss": 1.1105,
+      "num_tokens": 25074941.0,
+      "step": 301
+    },
+    {
+      "epoch": 1.9614291514413318,
+      "grad_norm": 1.0596871376037598,
+      "learning_rate": 2.9794301032838634e-06,
+      "loss": 1.1114,
+      "num_tokens": 25160481.0,
+      "step": 302
+    },
+    {
+      "epoch": 1.9679252943564758,
+      "grad_norm": 1.137643814086914,
+      "learning_rate": 2.9466782277524554e-06,
+      "loss": 1.0986,
+      "num_tokens": 25243458.0,
+      "step": 303
+    },
+    {
+      "epoch": 1.97442143727162,
+      "grad_norm": 1.1811145544052124,
+      "learning_rate": 2.914031986938417e-06,
+      "loss": 1.1154,
+      "num_tokens": 25323934.0,
+      "step": 304
+    },
+    {
+      "epoch": 1.9809175801867642,
+      "grad_norm": 1.1021146774291992,
+      "learning_rate": 2.8814930603527067e-06,
+      "loss": 1.1382,
+      "num_tokens": 25407804.0,
+      "step": 305
+    },
+    {
+      "epoch": 1.9874137231019082,
+      "grad_norm": 1.0973855257034302,
+      "learning_rate": 2.8490631219854224e-06,
+      "loss": 1.1416,
+      "num_tokens": 25492742.0,
+      "step": 306
+    },
+    {
+      "epoch": 1.9939098660170522,
+      "grad_norm": 1.1048208475112915,
+      "learning_rate": 2.816743840219681e-06,
+      "loss": 1.1108,
+      "num_tokens": 25573950.0,
+      "step": 307
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.154869556427002,
+      "learning_rate": 2.7845368777457803e-06,
+      "loss": 1.123,
+      "num_tokens": 25649686.0,
+      "step": 308
+    },
+    {
+      "epoch": 2.006496142915144,
+      "grad_norm": 1.1224220991134644,
+      "learning_rate": 2.7524438914756714e-06,
+      "loss": 0.9791,
+      "num_tokens": 25732699.0,
+      "step": 309
+    },
+    {
+      "epoch": 2.0129922858302884,
+      "grad_norm": 1.1351141929626465,
+      "learning_rate": 2.720466532457707e-06,
+      "loss": 0.9837,
+      "num_tokens": 25816961.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.0194884287454324,
+      "grad_norm": 1.1491280794143677,
+      "learning_rate": 2.6886064457917094e-06,
+      "loss": 1.0178,
+      "num_tokens": 25899397.0,
+      "step": 311
+    },
+    {
+      "epoch": 2.0259845716605764,
+      "grad_norm": 1.0822738409042358,
+      "learning_rate": 2.6568652705443355e-06,
+      "loss": 1.005,
+      "num_tokens": 25987091.0,
+      "step": 312
+    },
+    {
+      "epoch": 2.032480714575721,
+      "grad_norm": 1.065159797668457,
+      "learning_rate": 2.6252446396647503e-06,
+      "loss": 1.0093,
+      "num_tokens": 26068693.0,
+      "step": 313
+    },
+    {
+      "epoch": 2.038976857490865,
+      "grad_norm": 1.0333430767059326,
+      "learning_rate": 2.5937461799006215e-06,
+      "loss": 1.0059,
+      "num_tokens": 26152552.0,
+      "step": 314
+    },
+    {
+      "epoch": 2.045473000406009,
+      "grad_norm": 1.1080933809280396,
+      "learning_rate": 2.5623715117144337e-06,
+      "loss": 1.0022,
+      "num_tokens": 26236258.0,
+      "step": 315
+    },
+    {
+      "epoch": 2.051969143321153,
+      "grad_norm": 1.256309986114502,
+      "learning_rate": 2.531122249200114e-06,
+      "loss": 0.9787,
+      "num_tokens": 26316946.0,
+      "step": 316
+    },
+    {
+      "epoch": 2.0584652862362973,
+      "grad_norm": 1.1670758724212646,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.9837,
+      "num_tokens": 26399196.0,
+      "step": 317
+    },
+    {
+      "epoch": 2.0649614291514413,
+      "grad_norm": 1.0930993556976318,
+      "learning_rate": 2.469006365222132e-06,
+      "loss": 1.002,
+      "num_tokens": 26483273.0,
+      "step": 318
+    },
+    {
+      "epoch": 2.0714575720665853,
+      "grad_norm": 1.1212270259857178,
+      "learning_rate": 2.438142939357882e-06,
+      "loss": 1.0183,
+      "num_tokens": 26569447.0,
+      "step": 319
+    },
+    {
+      "epoch": 2.0779537149817298,
+      "grad_norm": 1.1512538194656372,
+      "learning_rate": 2.4074113101999245e-06,
+      "loss": 1.0263,
+      "num_tokens": 26652073.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.0844498578968738,
+      "grad_norm": 1.1119822263717651,
+      "learning_rate": 2.3768130587605513e-06,
+      "loss": 1.0347,
+      "num_tokens": 26737261.0,
+      "step": 321
+    },
+    {
+      "epoch": 2.0909460008120178,
+      "grad_norm": 1.1659584045410156,
+      "learning_rate": 2.346349759190332e-06,
+      "loss": 0.9898,
+      "num_tokens": 26820816.0,
+      "step": 322
+    },
+    {
+      "epoch": 2.097442143727162,
+      "grad_norm": 1.089632511138916,
+      "learning_rate": 2.316022978697143e-06,
+      "loss": 0.9786,
+      "num_tokens": 26901795.0,
+      "step": 323
+    },
+    {
+      "epoch": 2.103938286642306,
+      "grad_norm": 1.1519066095352173,
+      "learning_rate": 2.2858342774655174e-06,
+      "loss": 1.0492,
+      "num_tokens": 26985009.0,
+      "step": 324
+    },
+    {
+      "epoch": 2.11043442955745,
+      "grad_norm": 1.1025583744049072,
+      "learning_rate": 2.2557852085764053e-06,
+      "loss": 0.9919,
+      "num_tokens": 27067220.0,
+      "step": 325
+    },
+    {
+      "epoch": 2.116930572472594,
+      "grad_norm": 1.0912355184555054,
+      "learning_rate": 2.2258773179272588e-06,
+      "loss": 1.0507,
+      "num_tokens": 27152292.0,
+      "step": 326
+    },
+    {
+      "epoch": 2.1234267153877386,
+      "grad_norm": 1.1049952507019043,
+      "learning_rate": 2.1961121441525113e-06,
+      "loss": 1.0116,
+      "num_tokens": 27234350.0,
+      "step": 327
+    },
+    {
+      "epoch": 2.1299228583028826,
+      "grad_norm": 1.0956944227218628,
+      "learning_rate": 2.1664912185444127e-06,
+      "loss": 0.9713,
+      "num_tokens": 27317954.0,
+      "step": 328
+    },
+    {
+      "epoch": 2.1364190012180266,
+      "grad_norm": 1.1260950565338135,
+      "learning_rate": 2.137016064974256e-06,
+      "loss": 0.9836,
+      "num_tokens": 27402042.0,
+      "step": 329
+    },
+    {
+      "epoch": 2.142915144133171,
+      "grad_norm": 1.1343945264816284,
+      "learning_rate": 2.1076881998139794e-06,
+      "loss": 0.9977,
+      "num_tokens": 27485176.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.149411287048315,
+      "grad_norm": 1.2157853841781616,
+      "learning_rate": 2.0785091318581577e-06,
+      "loss": 0.9866,
+      "num_tokens": 27568047.0,
+      "step": 331
+    },
+    {
+      "epoch": 2.155907429963459,
+      "grad_norm": 1.0874643325805664,
+      "learning_rate": 2.049480362246378e-06,
+      "loss": 0.9952,
+      "num_tokens": 27649834.0,
+      "step": 332
+    },
+    {
+      "epoch": 2.1624035728786035,
+      "grad_norm": 1.1243056058883667,
+      "learning_rate": 2.0206033843860113e-06,
+      "loss": 0.9969,
+      "num_tokens": 27732541.0,
+      "step": 333
+    },
+    {
+      "epoch": 2.1688997157937475,
+      "grad_norm": 1.139676570892334,
+      "learning_rate": 1.991879683875386e-06,
+      "loss": 1.0149,
+      "num_tokens": 27817492.0,
+      "step": 334
+    },
+    {
+      "epoch": 2.1753958587088915,
+      "grad_norm": 1.1310027837753296,
+      "learning_rate": 1.9633107384273668e-06,
+      "loss": 1.0203,
+      "num_tokens": 27900990.0,
+      "step": 335
+    },
+    {
+      "epoch": 2.1818920016240355,
+      "grad_norm": 1.0737470388412476,
+      "learning_rate": 1.9348980177933126e-06,
+      "loss": 1.0139,
+      "num_tokens": 27989578.0,
+      "step": 336
+    },
+    {
+      "epoch": 2.18838814453918,
+      "grad_norm": 1.124861240386963,
+      "learning_rate": 1.9066429836874844e-06,
+      "loss": 1.0147,
+      "num_tokens": 28073778.0,
+      "step": 337
+    },
+    {
+      "epoch": 2.194884287454324,
+      "grad_norm": 1.061835765838623,
+      "learning_rate": 1.8785470897118362e-06,
+      "loss": 0.9827,
+      "num_tokens": 28155732.0,
+      "step": 338
+    },
+    {
+      "epoch": 2.201380430369468,
+      "grad_norm": 1.035414695739746,
+      "learning_rate": 1.850611781281239e-06,
+      "loss": 0.9612,
+      "num_tokens": 28240092.0,
+      "step": 339
+    },
+    {
+      "epoch": 2.2078765732846124,
+      "grad_norm": 1.0432775020599365,
+      "learning_rate": 1.8228384955491136e-06,
+      "loss": 0.9973,
+      "num_tokens": 28322607.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.2143727161997564,
+      "grad_norm": 1.1318039894104004,
+      "learning_rate": 1.7952286613334986e-06,
+      "loss": 1.0242,
+      "num_tokens": 28403996.0,
+      "step": 341
+    },
+    {
+      "epoch": 2.2208688591149004,
+      "grad_norm": 1.009614109992981,
+      "learning_rate": 1.7677836990435427e-06,
+      "loss": 0.9778,
+      "num_tokens": 28486865.0,
+      "step": 342
+    },
+    {
+      "epoch": 2.227365002030045,
+      "grad_norm": 1.0884579420089722,
+      "learning_rate": 1.7405050206064372e-06,
+      "loss": 1.0022,
+      "num_tokens": 28567098.0,
+      "step": 343
+    },
+    {
+      "epoch": 2.233861144945189,
+      "grad_norm": 1.0507434606552124,
+      "learning_rate": 1.7133940293947671e-06,
+      "loss": 0.9703,
+      "num_tokens": 28649662.0,
+      "step": 344
+    },
+    {
+      "epoch": 2.240357287860333,
+      "grad_norm": 1.0619853734970093,
+      "learning_rate": 1.68645212015432e-06,
+      "loss": 0.982,
+      "num_tokens": 28732559.0,
+      "step": 345
+    },
+    {
+      "epoch": 2.2468534307754773,
+      "grad_norm": 1.0535067319869995,
+      "learning_rate": 1.6596806789323317e-06,
+      "loss": 1.0012,
+      "num_tokens": 28816658.0,
+      "step": 346
+    },
+    {
+      "epoch": 2.2533495736906213,
+      "grad_norm": 1.078536868095398,
+      "learning_rate": 1.6330810830061833e-06,
+      "loss": 0.9932,
+      "num_tokens": 28902558.0,
+      "step": 347
+    },
+    {
+      "epoch": 2.2598457166057653,
+      "grad_norm": 1.1850616931915283,
+      "learning_rate": 1.6066547008125399e-06,
+      "loss": 1.0389,
+      "num_tokens": 28985289.0,
+      "step": 348
+    },
+    {
+      "epoch": 2.2663418595209093,
+      "grad_norm": 1.0730029344558716,
+      "learning_rate": 1.5804028918769488e-06,
+      "loss": 0.9847,
+      "num_tokens": 29068481.0,
+      "step": 349
+    },
+    {
+      "epoch": 2.2728380024360537,
+      "grad_norm": 1.0403430461883545,
+      "learning_rate": 1.5543270067439059e-06,
+      "loss": 0.9995,
+      "num_tokens": 29152891.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.2793341453511977,
+      "grad_norm": 1.0579943656921387,
+      "learning_rate": 1.5284283869073753e-06,
+      "loss": 1.0213,
+      "num_tokens": 29235697.0,
+      "step": 351
+    },
+    {
+      "epoch": 2.2858302882663417,
+      "grad_norm": 1.0701862573623657,
+      "learning_rate": 1.5027083647417657e-06,
+      "loss": 0.9844,
+      "num_tokens": 29318647.0,
+      "step": 352
+    },
+    {
+      "epoch": 2.292326431181486,
+      "grad_norm": 1.081486463546753,
+      "learning_rate": 1.4771682634333933e-06,
+      "loss": 0.9945,
+      "num_tokens": 29402484.0,
+      "step": 353
+    },
+    {
+      "epoch": 2.29882257409663,
+      "grad_norm": 1.0865415334701538,
+      "learning_rate": 1.4518093969124063e-06,
+      "loss": 0.9846,
+      "num_tokens": 29487845.0,
+      "step": 354
+    },
+    {
+      "epoch": 2.305318717011774,
+      "grad_norm": 1.129677653312683,
+      "learning_rate": 1.4266330697851955e-06,
+      "loss": 1.0252,
+      "num_tokens": 29569756.0,
+      "step": 355
+    },
+    {
+      "epoch": 2.311814859926918,
+      "grad_norm": 1.0224719047546387,
+      "learning_rate": 1.4016405772672647e-06,
+      "loss": 0.9956,
+      "num_tokens": 29655666.0,
+      "step": 356
+    },
+    {
+      "epoch": 2.3183110028420626,
+      "grad_norm": 1.0721043348312378,
+      "learning_rate": 1.3768332051166089e-06,
+      "loss": 0.9618,
+      "num_tokens": 29737987.0,
+      "step": 357
+    },
+    {
+      "epoch": 2.3248071457572066,
+      "grad_norm": 1.1139700412750244,
+      "learning_rate": 1.3522122295675616e-06,
+      "loss": 1.0095,
+      "num_tokens": 29821566.0,
+      "step": 358
+    },
+    {
+      "epoch": 2.331303288672351,
+      "grad_norm": 1.0636839866638184,
+      "learning_rate": 1.327778917265144e-06,
+      "loss": 0.9875,
+      "num_tokens": 29903286.0,
+      "step": 359
+    },
+    {
+      "epoch": 2.337799431587495,
+      "grad_norm": 1.0611505508422852,
+      "learning_rate": 1.3035345251998933e-06,
+      "loss": 1.0283,
+      "num_tokens": 29987454.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.344295574502639,
+      "grad_norm": 1.058504581451416,
+      "learning_rate": 1.2794803006431984e-06,
+      "loss": 0.9952,
+      "num_tokens": 30069242.0,
+      "step": 361
+    },
+    {
+      "epoch": 2.350791717417783,
+      "grad_norm": 1.054958462715149,
+      "learning_rate": 1.2556174810831368e-06,
+      "loss": 1.0233,
+      "num_tokens": 30151697.0,
+      "step": 362
+    },
+    {
+      "epoch": 2.3572878603329275,
+      "grad_norm": 1.1081610918045044,
+      "learning_rate": 1.2319472941608118e-06,
+      "loss": 1.0723,
+      "num_tokens": 30234040.0,
+      "step": 363
+    },
+    {
+      "epoch": 2.3637840032480715,
+      "grad_norm": 1.0654082298278809,
+      "learning_rate": 1.2084709576071885e-06,
+      "loss": 1.015,
+      "num_tokens": 30316313.0,
+      "step": 364
+    },
+    {
+      "epoch": 2.3702801461632155,
+      "grad_norm": 1.1052758693695068,
+      "learning_rate": 1.1851896791804507e-06,
+      "loss": 0.9713,
+      "num_tokens": 30400189.0,
+      "step": 365
+    },
+    {
+      "epoch": 2.37677628907836,
+      "grad_norm": 1.0523080825805664,
+      "learning_rate": 1.162104656603868e-06,
+      "loss": 1.0268,
+      "num_tokens": 30483250.0,
+      "step": 366
+    },
+    {
+      "epoch": 2.383272431993504,
+      "grad_norm": 1.040045142173767,
+      "learning_rate": 1.1392170775041788e-06,
+      "loss": 0.9949,
+      "num_tokens": 30565145.0,
+      "step": 367
+    },
+    {
+      "epoch": 2.389768574908648,
+      "grad_norm": 1.0308566093444824,
+      "learning_rate": 1.1165281193504873e-06,
+      "loss": 0.9998,
+      "num_tokens": 30647390.0,
+      "step": 368
+    },
+    {
+      "epoch": 2.396264717823792,
+      "grad_norm": 1.0677629709243774,
+      "learning_rate": 1.0940389493936903e-06,
+      "loss": 1.0242,
+      "num_tokens": 30730569.0,
+      "step": 369
+    },
+    {
+      "epoch": 2.4027608607389364,
+      "grad_norm": 1.0684865713119507,
+      "learning_rate": 1.0717507246064273e-06,
+      "loss": 1.0079,
+      "num_tokens": 30814390.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.4092570036540804,
+      "grad_norm": 1.031925916671753,
+      "learning_rate": 1.049664591623563e-06,
+      "loss": 1.0121,
+      "num_tokens": 30900238.0,
+      "step": 371
+    },
+    {
+      "epoch": 2.4157531465692244,
+      "grad_norm": 1.0733017921447754,
+      "learning_rate": 1.027781686683189e-06,
+      "loss": 0.9778,
+      "num_tokens": 30982621.0,
+      "step": 372
+    },
+    {
+      "epoch": 2.422249289484369,
+      "grad_norm": 1.0866520404815674,
+      "learning_rate": 1.0061031355681766e-06,
+      "loss": 1.0235,
+      "num_tokens": 31065699.0,
+      "step": 373
+    },
+    {
+      "epoch": 2.428745432399513,
+      "grad_norm": 1.0389002561569214,
+      "learning_rate": 9.846300535482534e-07,
+      "loss": 0.9996,
+      "num_tokens": 31149574.0,
+      "step": 374
+    },
+    {
+      "epoch": 2.435241575314657,
+      "grad_norm": 1.0431241989135742,
+      "learning_rate": 9.633635453226376e-07,
+      "loss": 0.9956,
+      "num_tokens": 31232487.0,
+      "step": 375
+    },
+    {
+      "epoch": 2.4417377182298012,
+      "grad_norm": 1.0718599557876587,
+      "learning_rate": 9.423047049631956e-07,
+      "loss": 1.0072,
+      "num_tokens": 31316301.0,
+      "step": 376
+    },
+    {
+      "epoch": 2.4482338611449452,
+      "grad_norm": 1.0717698335647583,
+      "learning_rate": 9.214546158581622e-07,
+      "loss": 0.9969,
+      "num_tokens": 31399173.0,
+      "step": 377
+    },
+    {
+      "epoch": 2.4547300040600892,
+      "grad_norm": 1.051547884941101,
+      "learning_rate": 9.00814350656401e-07,
+      "loss": 1.0151,
+      "num_tokens": 31483315.0,
+      "step": 378
+    },
+    {
+      "epoch": 2.4612261469752337,
+      "grad_norm": 1.0786367654800415,
+      "learning_rate": 8.803849712122292e-07,
+      "loss": 1.0076,
+      "num_tokens": 31565993.0,
+      "step": 379
+    },
+    {
+      "epoch": 2.4677222898903777,
+      "grad_norm": 1.0435740947723389,
+      "learning_rate": 8.601675285307781e-07,
+      "loss": 0.9912,
+      "num_tokens": 31648324.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.4742184328055217,
+      "grad_norm": 1.0448262691497803,
+      "learning_rate": 8.401630627139317e-07,
+      "loss": 1.0484,
+      "num_tokens": 31732928.0,
+      "step": 381
+    },
+    {
+      "epoch": 2.4807145757206657,
+      "grad_norm": 1.1241081953048706,
+      "learning_rate": 8.203726029068149e-07,
+      "loss": 1.0345,
+      "num_tokens": 31814680.0,
+      "step": 382
+    },
+    {
+      "epoch": 2.48721071863581,
+      "grad_norm": 1.1598526239395142,
+      "learning_rate": 8.007971672448511e-07,
+      "loss": 0.9765,
+      "num_tokens": 31897993.0,
+      "step": 383
+    },
+    {
+      "epoch": 2.493706861550954,
+      "grad_norm": 1.0971860885620117,
+      "learning_rate": 7.814377628013786e-07,
+      "loss": 0.9819,
+      "num_tokens": 31980547.0,
+      "step": 384
+    },
+    {
+      "epoch": 2.500203004466098,
+      "grad_norm": 1.100080966949463,
+      "learning_rate": 7.622953855358456e-07,
+      "loss": 0.9859,
+      "num_tokens": 32061493.0,
+      "step": 385
+    },
+    {
+      "epoch": 2.5066991473812426,
+      "grad_norm": 1.0546306371688843,
+      "learning_rate": 7.433710202425653e-07,
+      "loss": 1.0103,
+      "num_tokens": 32145626.0,
+      "step": 386
+    },
+    {
+      "epoch": 2.5131952902963866,
+      "grad_norm": 1.0321263074874878,
+      "learning_rate": 7.246656405000646e-07,
+      "loss": 0.9759,
+      "num_tokens": 32228149.0,
+      "step": 387
+    },
+    {
+      "epoch": 2.5196914332115306,
+      "grad_norm": 1.0437856912612915,
+      "learning_rate": 7.061802086209857e-07,
+      "loss": 0.9875,
+      "num_tokens": 32311504.0,
+      "step": 388
+    },
+    {
+      "epoch": 2.5261875761266745,
+      "grad_norm": 1.0462093353271484,
+      "learning_rate": 6.879156756025851e-07,
+      "loss": 0.9658,
+      "num_tokens": 32393882.0,
+      "step": 389
+    },
+    {
+      "epoch": 2.532683719041819,
+      "grad_norm": 1.0680969953536987,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 1.0093,
+      "num_tokens": 32476257.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.539179861956963,
+      "grad_norm": 1.153793454170227,
+      "learning_rate": 6.52053053266945e-07,
+      "loss": 1.0075,
+      "num_tokens": 32560641.0,
+      "step": 391
+    },
+    {
+      "epoch": 2.5456760048721074,
+      "grad_norm": 1.0823545455932617,
+      "learning_rate": 6.344568089298875e-07,
+      "loss": 1.0112,
+      "num_tokens": 32644014.0,
+      "step": 392
+    },
+    {
+      "epoch": 2.5521721477872514,
+      "grad_norm": 1.0579285621643066,
+      "learning_rate": 6.170851533189537e-07,
+      "loss": 1.024,
+      "num_tokens": 32726496.0,
+      "step": 393
+    },
+    {
+      "epoch": 2.5586682907023954,
+      "grad_norm": 1.0545684099197388,
+      "learning_rate": 5.999389801323219e-07,
+      "loss": 0.9834,
+      "num_tokens": 32808916.0,
+      "step": 394
+    },
+    {
+      "epoch": 2.5651644336175394,
+      "grad_norm": 1.0284395217895508,
+      "learning_rate": 5.830191714680578e-07,
+      "loss": 1.0047,
+      "num_tokens": 32890500.0,
+      "step": 395
+    },
+    {
+      "epoch": 2.571660576532684,
+      "grad_norm": 1.090678334236145,
+      "learning_rate": 5.663265977787263e-07,
+      "loss": 0.9771,
+      "num_tokens": 32973400.0,
+      "step": 396
+    },
+    {
+      "epoch": 2.578156719447828,
+      "grad_norm": 1.1110414266586304,
+      "learning_rate": 5.498621178266167e-07,
+      "loss": 1.0092,
+      "num_tokens": 33059134.0,
+      "step": 397
+    },
+    {
+      "epoch": 2.584652862362972,
+      "grad_norm": 0.9998200535774231,
+      "learning_rate": 5.336265786395589e-07,
+      "loss": 0.9979,
+      "num_tokens": 33145337.0,
+      "step": 398
+    },
+    {
+      "epoch": 2.5911490052781163,
+      "grad_norm": 1.11801278591156,
+      "learning_rate": 5.176208154673502e-07,
+      "loss": 1.018,
+      "num_tokens": 33229101.0,
+      "step": 399
+    },
+    {
+      "epoch": 2.5976451481932603,
+      "grad_norm": 1.0278111696243286,
+      "learning_rate": 5.018456517387837e-07,
+      "loss": 0.9961,
+      "num_tokens": 33315106.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.6041412911084043,
+      "grad_norm": 1.0382176637649536,
+      "learning_rate": 4.86301899019287e-07,
+      "loss": 0.9995,
+      "num_tokens": 33397275.0,
+      "step": 401
+    },
+    {
+      "epoch": 2.6106374340235483,
+      "grad_norm": 1.0294314622879028,
+      "learning_rate": 4.709903569691687e-07,
+      "loss": 1.0019,
+      "num_tokens": 33479736.0,
+      "step": 402
+    },
+    {
+      "epoch": 2.6171335769386928,
+      "grad_norm": 1.0874602794647217,
+      "learning_rate": 4.5591181330248534e-07,
+      "loss": 1.0489,
+      "num_tokens": 33565192.0,
+      "step": 403
+    },
+    {
+      "epoch": 2.6236297198538368,
+      "grad_norm": 1.0460293292999268,
+      "learning_rate": 4.4106704374650865e-07,
+      "loss": 1.0131,
+      "num_tokens": 33647121.0,
+      "step": 404
+    },
+    {
+      "epoch": 2.630125862768981,
+      "grad_norm": 1.0692638158798218,
+      "learning_rate": 4.2645681200182197e-07,
+      "loss": 1.0058,
+      "num_tokens": 33729512.0,
+      "step": 405
+    },
+    {
+      "epoch": 2.636622005684125,
+      "grad_norm": 1.1397271156311035,
+      "learning_rate": 4.1208186970303097e-07,
+      "loss": 1.0358,
+      "num_tokens": 33811632.0,
+      "step": 406
+    },
+    {
+      "epoch": 2.643118148599269,
+      "grad_norm": 1.038702368736267,
+      "learning_rate": 3.9794295638009683e-07,
+      "loss": 0.9887,
+      "num_tokens": 33894556.0,
+      "step": 407
+    },
+    {
+      "epoch": 2.649614291514413,
+      "grad_norm": 1.0522540807724,
+      "learning_rate": 3.840407994202849e-07,
+      "loss": 1.0451,
+      "num_tokens": 33976713.0,
+      "step": 408
+    },
+    {
+      "epoch": 2.656110434429557,
+      "grad_norm": 1.0562784671783447,
+      "learning_rate": 3.70376114030751e-07,
+      "loss": 0.9683,
+      "num_tokens": 34060720.0,
+      "step": 409
+    },
+    {
+      "epoch": 2.6626065773447016,
+      "grad_norm": 1.047566533088684,
+      "learning_rate": 3.5694960320174056e-07,
+      "loss": 1.0128,
+      "num_tokens": 34143137.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.6691027202598456,
+      "grad_norm": 1.0189069509506226,
+      "learning_rate": 3.4376195767042706e-07,
+      "loss": 1.0104,
+      "num_tokens": 34226356.0,
+      "step": 411
+    },
+    {
+      "epoch": 2.67559886317499,
+      "grad_norm": 1.0227577686309814,
+      "learning_rate": 3.308138558853746e-07,
+      "loss": 0.9804,
+      "num_tokens": 34307953.0,
+      "step": 412
+    },
+    {
+      "epoch": 2.682095006090134,
+      "grad_norm": 1.0241705179214478,
+      "learning_rate": 3.181059639716355e-07,
+      "loss": 0.9452,
+      "num_tokens": 34391342.0,
+      "step": 413
+    },
+    {
+      "epoch": 2.688591149005278,
+      "grad_norm": 1.0222891569137573,
+      "learning_rate": 3.0563893569648007e-07,
+      "loss": 1.005,
+      "num_tokens": 34477659.0,
+      "step": 414
+    },
+    {
+      "epoch": 2.695087291920422,
+      "grad_norm": 1.0145410299301147,
+      "learning_rate": 2.934134124357646e-07,
+      "loss": 0.9835,
+      "num_tokens": 34559084.0,
+      "step": 415
+    },
+    {
+      "epoch": 2.7015834348355665,
+      "grad_norm": 1.0440430641174316,
+      "learning_rate": 2.814300231409334e-07,
+      "loss": 0.9885,
+      "num_tokens": 34642185.0,
+      "step": 416
+    },
+    {
+      "epoch": 2.7080795777507105,
+      "grad_norm": 1.0567108392715454,
+      "learning_rate": 2.696893843066617e-07,
+      "loss": 0.9822,
+      "num_tokens": 34726160.0,
+      "step": 417
+    },
+    {
+      "epoch": 2.7145757206658545,
+      "grad_norm": 1.0289652347564697,
+      "learning_rate": 2.5819209993914185e-07,
+      "loss": 1.0051,
+      "num_tokens": 34808233.0,
+      "step": 418
+    },
+    {
+      "epoch": 2.721071863580999,
+      "grad_norm": 0.9950981736183167,
+      "learning_rate": 2.469387615250096e-07,
+      "loss": 0.9804,
+      "num_tokens": 34894645.0,
+      "step": 419
+    },
+    {
+      "epoch": 2.727568006496143,
+      "grad_norm": 1.007178544998169,
+      "learning_rate": 2.359299480009114e-07,
+      "loss": 0.9918,
+      "num_tokens": 34979800.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.734064149411287,
+      "grad_norm": 1.060936450958252,
+      "learning_rate": 2.2516622572372416e-07,
+      "loss": 1.0059,
+      "num_tokens": 35063916.0,
+      "step": 421
+    },
+    {
+      "epoch": 2.740560292326431,
+      "grad_norm": 1.058678150177002,
+      "learning_rate": 2.146481484414159e-07,
+      "loss": 0.9738,
+      "num_tokens": 35146672.0,
+      "step": 422
+    },
+    {
+      "epoch": 2.7470564352415754,
+      "grad_norm": 1.0162526369094849,
+      "learning_rate": 2.0437625726456024e-07,
+      "loss": 1.0059,
+      "num_tokens": 35230319.0,
+      "step": 423
+    },
+    {
+      "epoch": 2.7535525781567194,
+      "grad_norm": 1.035975694656372,
+      "learning_rate": 1.9435108063849684e-07,
+      "loss": 0.9996,
+      "num_tokens": 35315742.0,
+      "step": 424
+    },
+    {
+      "epoch": 2.760048721071864,
+      "grad_norm": 1.0511385202407837,
+      "learning_rate": 1.84573134316145e-07,
+      "loss": 0.9887,
+      "num_tokens": 35396028.0,
+      "step": 425
+    },
+    {
+      "epoch": 2.766544863987008,
+      "grad_norm": 0.9890627264976501,
+      "learning_rate": 1.7504292133147194e-07,
+      "loss": 0.9991,
+      "num_tokens": 35481635.0,
+      "step": 426
+    },
+    {
+      "epoch": 2.773041006902152,
+      "grad_norm": 1.0321937799453735,
+      "learning_rate": 1.6576093197361253e-07,
+      "loss": 1.029,
+      "num_tokens": 35564666.0,
+      "step": 427
+    },
+    {
+      "epoch": 2.779537149817296,
+      "grad_norm": 1.0288523435592651,
+      "learning_rate": 1.5672764376164607e-07,
+      "loss": 1.0409,
+      "num_tokens": 35647570.0,
+      "step": 428
+    },
+    {
+      "epoch": 2.7860332927324403,
+      "grad_norm": 1.0310142040252686,
+      "learning_rate": 1.4794352142003088e-07,
+      "loss": 1.0185,
+      "num_tokens": 35732010.0,
+      "step": 429
+    },
+    {
+      "epoch": 2.7925294356475843,
+      "grad_norm": 1.0283852815628052,
+      "learning_rate": 1.39409016854693e-07,
+      "loss": 1.0342,
+      "num_tokens": 35815364.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.7990255785627283,
+      "grad_norm": 1.0819894075393677,
+      "learning_rate": 1.3112456912978467e-07,
+      "loss": 0.9719,
+      "num_tokens": 35898164.0,
+      "step": 431
+    },
+    {
+      "epoch": 2.8055217214778727,
+      "grad_norm": 1.0560641288757324,
+      "learning_rate": 1.2309060444508746e-07,
+      "loss": 1.0421,
+      "num_tokens": 35986280.0,
+      "step": 432
+    },
+    {
+      "epoch": 2.8120178643930167,
+      "grad_norm": 1.065772533416748,
+      "learning_rate": 1.1530753611409151e-07,
+      "loss": 1.0111,
+      "num_tokens": 36069345.0,
+      "step": 433
+    },
+    {
+      "epoch": 2.8185140073081607,
+      "grad_norm": 1.0099737644195557,
+      "learning_rate": 1.0777576454273242e-07,
+      "loss": 1.0222,
+      "num_tokens": 36154510.0,
+      "step": 434
+    },
+    {
+      "epoch": 2.8250101502233047,
+      "grad_norm": 1.1104416847229004,
+      "learning_rate": 1.004956772087895e-07,
+      "loss": 1.0286,
+      "num_tokens": 36240352.0,
+      "step": 435
+    },
+    {
+      "epoch": 2.831506293138449,
+      "grad_norm": 1.0606105327606201,
+      "learning_rate": 9.346764864195335e-08,
+      "loss": 0.9926,
+      "num_tokens": 36322268.0,
+      "step": 436
+    },
+    {
+      "epoch": 2.838002436053593,
+      "grad_norm": 1.0643787384033203,
+      "learning_rate": 8.669204040455737e-08,
+      "loss": 1.0098,
+      "num_tokens": 36403758.0,
+      "step": 437
+    },
+    {
+      "epoch": 2.844498578968737,
+      "grad_norm": 1.086890459060669,
+      "learning_rate": 8.016920107297654e-08,
+      "loss": 0.9824,
+      "num_tokens": 36484614.0,
+      "step": 438
+    },
+    {
+      "epoch": 2.8509947218838816,
+      "grad_norm": 1.0153158903121948,
+      "learning_rate": 7.389946621969679e-08,
+      "loss": 0.9894,
+      "num_tokens": 36569246.0,
+      "step": 439
+    },
+    {
+      "epoch": 2.8574908647990256,
+      "grad_norm": 1.0508722066879272,
+      "learning_rate": 6.788315839604765e-08,
+      "loss": 1.0031,
+      "num_tokens": 36653430.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.8639870077141696,
+      "grad_norm": 1.0280561447143555,
+      "learning_rate": 6.212058711561165e-08,
+      "loss": 0.9871,
+      "num_tokens": 36736431.0,
+      "step": 441
+    },
+    {
+      "epoch": 2.8704831506293136,
+      "grad_norm": 1.0388000011444092,
+      "learning_rate": 5.661204883829763e-08,
+      "loss": 0.9951,
+      "num_tokens": 36819100.0,
+      "step": 442
+    },
+    {
+      "epoch": 2.876979293544458,
+      "grad_norm": 1.0347610712051392,
+      "learning_rate": 5.135782695509461e-08,
+      "loss": 0.9877,
+      "num_tokens": 36902324.0,
+      "step": 443
+    },
+    {
+      "epoch": 2.883475436459602,
+      "grad_norm": 1.053459882736206,
+      "learning_rate": 4.635819177348677e-08,
+      "loss": 0.9992,
+      "num_tokens": 36986509.0,
+      "step": 444
+    },
+    {
+      "epoch": 2.8899715793747465,
+      "grad_norm": 1.1181039810180664,
+      "learning_rate": 4.1613400503550114e-08,
+      "loss": 1.0213,
+      "num_tokens": 37067699.0,
+      "step": 445
+    },
+    {
+      "epoch": 2.8964677222898905,
+      "grad_norm": 1.0160572528839111,
+      "learning_rate": 3.71236972447192e-08,
+      "loss": 1.0266,
+      "num_tokens": 37153469.0,
+      "step": 446
+    },
+    {
+      "epoch": 2.9029638652050345,
+      "grad_norm": 1.048988938331604,
+      "learning_rate": 3.2889312973231616e-08,
+      "loss": 1.0107,
+      "num_tokens": 37238201.0,
+      "step": 447
+    },
+    {
+      "epoch": 2.9094600081201785,
+      "grad_norm": 1.0428284406661987,
+      "learning_rate": 2.8910465530240793e-08,
+      "loss": 0.9793,
+      "num_tokens": 37322184.0,
+      "step": 448
+    },
+    {
+      "epoch": 2.915956151035323,
+      "grad_norm": 1.1448193788528442,
+      "learning_rate": 2.5187359610612805e-08,
+      "loss": 1.0031,
+      "num_tokens": 37406320.0,
+      "step": 449
+    },
+    {
+      "epoch": 2.922452293950467,
+      "grad_norm": 1.088547945022583,
+      "learning_rate": 2.1720186752395288e-08,
+      "loss": 1.0082,
+      "num_tokens": 37487061.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.928948436865611,
+      "grad_norm": 1.0607171058654785,
+      "learning_rate": 1.850912532696092e-08,
+      "loss": 1.0056,
+      "num_tokens": 37568119.0,
+      "step": 451
+    },
+    {
+      "epoch": 2.9354445797807553,
+      "grad_norm": 1.0544319152832031,
+      "learning_rate": 1.5554340529834733e-08,
+      "loss": 0.9787,
+      "num_tokens": 37649082.0,
+      "step": 452
+    },
+    {
+      "epoch": 2.9419407226958993,
+      "grad_norm": 1.0804128646850586,
+      "learning_rate": 1.2855984372191488e-08,
+      "loss": 0.9928,
+      "num_tokens": 37732113.0,
+      "step": 453
+    },
+    {
+      "epoch": 2.9484368656110433,
+      "grad_norm": 1.0458853244781494,
+      "learning_rate": 1.041419567303914e-08,
+      "loss": 1.0196,
+      "num_tokens": 37813828.0,
+      "step": 454
+    },
+    {
+      "epoch": 2.9549330085261873,
+      "grad_norm": 1.030555009841919,
+      "learning_rate": 8.229100052074557e-09,
+      "loss": 0.9954,
+      "num_tokens": 37898084.0,
+      "step": 455
+    },
+    {
+      "epoch": 2.961429151441332,
+      "grad_norm": 1.0712569952011108,
+      "learning_rate": 6.300809923222017e-09,
+      "loss": 1.0126,
+      "num_tokens": 37978305.0,
+      "step": 456
+    },
+    {
+      "epoch": 2.967925294356476,
+      "grad_norm": 1.0257033109664917,
+      "learning_rate": 4.629424488850065e-09,
+      "loss": 1.0202,
+      "num_tokens": 38064281.0,
+      "step": 457
+    },
+    {
+      "epoch": 2.9744214372716202,
+      "grad_norm": 1.0383819341659546,
+      "learning_rate": 3.215029734667252e-09,
+      "loss": 1.0291,
+      "num_tokens": 38148969.0,
+      "step": 458
+    },
+    {
+      "epoch": 2.9809175801867642,
+      "grad_norm": 1.0436694622039795,
+      "learning_rate": 2.05769842529957e-09,
+      "loss": 0.9998,
+      "num_tokens": 38234154.0,
+      "step": 459
+    },
+    {
+      "epoch": 2.9874137231019082,
+      "grad_norm": 1.0255451202392578,
+      "learning_rate": 1.1574901005456662e-09,
+      "loss": 1.0029,
+      "num_tokens": 38314776.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.9939098660170522,
+      "grad_norm": 1.0773762464523315,
+      "learning_rate": 5.144510723154028e-10,
+      "loss": 1.0352,
+      "num_tokens": 38397163.0,
+      "step": 461
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0865943431854248,
+      "learning_rate": 1.2861442224565423e-10,
+      "loss": 0.9824,
+      "num_tokens": 38474529.0,
+      "step": 462
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 462,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1890772626141348e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen2.5-7B-Instruct-huatuo-o1-lr1e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf96d56ba2f3076a6c9b570e8c398310bb31554cf9951da4c267127f196e73e
+size 6353