Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

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 %}

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ed5a1688386771c40f47f6a01574b68e5b3c4c1cbcff3a8c42c17889d045db
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa910751ec2c12d3b4d5d059e36e74743c2cbac15d9c1d72d09a2b52cfb94ece
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c866dd5dbf2b7b0474fbef3d7271460e9a9847655950a224886ec565d8c045c
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4092b47849a6d76efe436ddcac3a22380a5229ebc96ea500f413cc28b369016
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+}

trainer_state.json

@@ -0,0 +1,1276 @@
+{
+  "best_global_step": 626,
+  "best_metric": 0.90001261,
+  "best_model_checkpoint": "/proj/checkpoints/zhangchen/tool-rl-dev/sft_models/Qwen2.5-7B-Instruct-MIX-KimiK2-DD3-LR2.0e-5-EPOCHS2/v1-20250919-024521/checkpoint-626",
+  "epoch": 2.0,
+  "eval_steps": 16,
+  "global_step": 626,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032025620496397116,
+      "grad_norm": 12.095559524428625,
+      "learning_rate": 1.9999874072618805e-05,
+      "loss": 1.7495059967041016,
+      "step": 1
+    },
+    {
+      "epoch": 0.016012810248198558,
+      "grad_norm": 2.4446721027205087,
+      "learning_rate": 1.999685197404432e-05,
+      "loss": 1.3246392011642456,
+      "step": 5
+    },
+    {
+      "epoch": 0.032025620496397116,
+      "grad_norm": 0.8674719311080642,
+      "learning_rate": 1.9987409878190752e-05,
+      "loss": 1.1605964660644532,
+      "step": 10
+    },
+    {
+      "epoch": 0.04803843074459568,
+      "grad_norm": 0.8078480489924645,
+      "learning_rate": 1.9971679657231874e-05,
+      "loss": 1.1610276222229003,
+      "step": 15
+    },
+    {
+      "epoch": 0.051240992794235385,
+      "eval_loss": 1.051803469657898,
+      "eval_runtime": 14.5335,
+      "eval_samples_per_second": 7.293,
+      "eval_steps_per_second": 0.963,
+      "eval_token_acc": 0.7288482137333997,
+      "step": 16
+    },
+    {
+      "epoch": 0.06405124099279423,
+      "grad_norm": 0.7441419049827398,
+      "learning_rate": 1.9949671214996448e-05,
+      "loss": 1.1230401992797852,
+      "step": 20
+    },
+    {
+      "epoch": 0.08006405124099279,
+      "grad_norm": 0.66006524950857,
+      "learning_rate": 1.9921398408113955e-05,
+      "loss": 1.088608741760254,
+      "step": 25
+    },
+    {
+      "epoch": 0.09607686148919135,
+      "grad_norm": 0.5824061800332928,
+      "learning_rate": 1.9886879037290385e-05,
+      "loss": 1.0843761444091797,
+      "step": 30
+    },
+    {
+      "epoch": 0.10248198558847077,
+      "eval_loss": 1.0146167278289795,
+      "eval_runtime": 14.4953,
+      "eval_samples_per_second": 7.313,
+      "eval_steps_per_second": 0.966,
+      "eval_token_acc": 0.7360955106479266,
+      "step": 32
+    },
+    {
+      "epoch": 0.11208967173738991,
+      "grad_norm": 0.6124558915875796,
+      "learning_rate": 1.9846134836100797e-05,
+      "loss": 1.0593854904174804,
+      "step": 35
+    },
+    {
+      "epoch": 0.12810248198558846,
+      "grad_norm": 0.6688978350600125,
+      "learning_rate": 1.9799191457305767e-05,
+      "loss": 1.042323684692383,
+      "step": 40
+    },
+    {
+      "epoch": 0.14411529223378702,
+      "grad_norm": 0.583235840286963,
+      "learning_rate": 1.974607845670028e-05,
+      "loss": 1.0665904998779296,
+      "step": 45
+    },
+    {
+      "epoch": 0.15372297838270615,
+      "eval_loss": 0.9931923151016235,
+      "eval_runtime": 14.3487,
+      "eval_samples_per_second": 7.387,
+      "eval_steps_per_second": 0.976,
+      "eval_token_acc": 0.740839136705638,
+      "step": 48
+    },
+    {
+      "epoch": 0.16012810248198558,
+      "grad_norm": 0.6834039523199339,
+      "learning_rate": 1.968682927450523e-05,
+      "loss": 1.0202735900878905,
+      "step": 50
+    },
+    {
+      "epoch": 0.17614091273018415,
+      "grad_norm": 0.7236032273618205,
+      "learning_rate": 1.9621481214313295e-05,
+      "loss": 1.048078727722168,
+      "step": 55
+    },
+    {
+      "epoch": 0.1921537229783827,
+      "grad_norm": 0.6147507739334064,
+      "learning_rate": 1.955007541960241e-05,
+      "loss": 1.0933009147644044,
+      "step": 60
+    },
+    {
+      "epoch": 0.20496397117694154,
+      "eval_loss": 0.980483889579773,
+      "eval_runtime": 14.5799,
+      "eval_samples_per_second": 7.27,
+      "eval_steps_per_second": 0.96,
+      "eval_token_acc": 0.7434513325237371,
+      "step": 64
+    },
+    {
+      "epoch": 0.20816653322658127,
+      "grad_norm": 0.5981978572505926,
+      "learning_rate": 1.9472656847831595e-05,
+      "loss": 1.0627766609191895,
+      "step": 65
+    },
+    {
+      "epoch": 0.22417934347477983,
+      "grad_norm": 0.5944938726625539,
+      "learning_rate": 1.9389274242135528e-05,
+      "loss": 1.0284326553344727,
+      "step": 70
+    },
+    {
+      "epoch": 0.2401921537229784,
+      "grad_norm": 0.5690809156814671,
+      "learning_rate": 1.9299980100635612e-05,
+      "loss": 0.9859808921813965,
+      "step": 75
+    },
+    {
+      "epoch": 0.2562049639711769,
+      "grad_norm": 0.5905137235030116,
+      "learning_rate": 1.920483064338687e-05,
+      "loss": 1.0671635627746583,
+      "step": 80
+    },
+    {
+      "epoch": 0.2562049639711769,
+      "eval_loss": 0.9712809324264526,
+      "eval_runtime": 14.4122,
+      "eval_samples_per_second": 7.355,
+      "eval_steps_per_second": 0.971,
+      "eval_token_acc": 0.7450575019507362,
+      "step": 80
+    },
+    {
+      "epoch": 0.2722177742193755,
+      "grad_norm": 0.5816842433518039,
+      "learning_rate": 1.9103885776981517e-05,
+      "loss": 0.9951675415039063,
+      "step": 85
+    },
+    {
+      "epoch": 0.28823058446757405,
+      "grad_norm": 0.5787862483192674,
+      "learning_rate": 1.8997209056831462e-05,
+      "loss": 1.049220657348633,
+      "step": 90
+    },
+    {
+      "epoch": 0.3042433947157726,
+      "grad_norm": 0.6164119168224672,
+      "learning_rate": 1.8884867647153483e-05,
+      "loss": 1.0655245780944824,
+      "step": 95
+    },
+    {
+      "epoch": 0.3074459567654123,
+      "eval_loss": 0.9638978838920593,
+      "eval_runtime": 14.4222,
+      "eval_samples_per_second": 7.35,
+      "eval_steps_per_second": 0.971,
+      "eval_token_acc": 0.7468503343111432,
+      "step": 96
+    },
+    {
+      "epoch": 0.32025620496397117,
+      "grad_norm": 0.5809223505771192,
+      "learning_rate": 1.87669322786823e-05,
+      "loss": 1.0123931884765625,
+      "step": 100
+    },
+    {
+      "epoch": 0.33626901521216973,
+      "grad_norm": 0.5370286998411188,
+      "learning_rate": 1.8643477204138114e-05,
+      "loss": 0.9670543670654297,
+      "step": 105
+    },
+    {
+      "epoch": 0.3522818254603683,
+      "grad_norm": 0.5969517267654925,
+      "learning_rate": 1.851458015147673e-05,
+      "loss": 1.0549612045288086,
+      "step": 110
+    },
+    {
+      "epoch": 0.3586869495596477,
+      "eval_loss": 0.9577141404151917,
+      "eval_runtime": 14.3804,
+      "eval_samples_per_second": 7.371,
+      "eval_steps_per_second": 0.974,
+      "eval_token_acc": 0.7479301576759162,
+      "step": 112
+    },
+    {
+      "epoch": 0.36829463570856685,
+      "grad_norm": 0.5551260620868368,
+      "learning_rate": 1.838032227495163e-05,
+      "loss": 0.9998938560485839,
+      "step": 115
+    },
+    {
+      "epoch": 0.3843074459567654,
+      "grad_norm": 0.5943112601394075,
+      "learning_rate": 1.8240788104018824e-05,
+      "loss": 0.9902477264404297,
+      "step": 120
+    },
+    {
+      "epoch": 0.400320256204964,
+      "grad_norm": 0.5771043855645519,
+      "learning_rate": 1.809606549011667e-05,
+      "loss": 1.0216222763061524,
+      "step": 125
+    },
+    {
+      "epoch": 0.4099279423538831,
+      "eval_loss": 0.9509572386741638,
+      "eval_runtime": 14.4968,
+      "eval_samples_per_second": 7.312,
+      "eval_steps_per_second": 0.966,
+      "eval_token_acc": 0.7491141650035217,
+      "step": 128
+    },
+    {
+      "epoch": 0.41633306645316254,
+      "grad_norm": 0.5544818028626222,
+      "learning_rate": 1.7946245551354156e-05,
+      "loss": 0.9958406448364258,
+      "step": 130
+    },
+    {
+      "epoch": 0.4323458767013611,
+      "grad_norm": 0.5968141913341887,
+      "learning_rate": 1.779142261514247e-05,
+      "loss": 0.9774517059326172,
+      "step": 135
+    },
+    {
+      "epoch": 0.44835868694955966,
+      "grad_norm": 0.5850121301746795,
+      "learning_rate": 1.7631694158805945e-05,
+      "loss": 1.0328359603881836,
+      "step": 140
+    },
+    {
+      "epoch": 0.4611689351481185,
+      "eval_loss": 0.9461285471916199,
+      "eval_runtime": 14.5166,
+      "eval_samples_per_second": 7.302,
+      "eval_steps_per_second": 0.964,
+      "eval_token_acc": 0.750104997900042,
+      "step": 144
+    },
+    {
+      "epoch": 0.4643714971977582,
+      "grad_norm": 0.5752900237956412,
+      "learning_rate": 1.7467160748209872e-05,
+      "loss": 1.0004414558410644,
+      "step": 145
+    },
+    {
+      "epoch": 0.4803843074459568,
+      "grad_norm": 0.603759980991957,
+      "learning_rate": 1.7297925974443675e-05,
+      "loss": 0.9869029998779297,
+      "step": 150
+    },
+    {
+      "epoch": 0.49639711769415534,
+      "grad_norm": 0.5943556191906708,
+      "learning_rate": 1.7124096388599438e-05,
+      "loss": 0.9789384841918946,
+      "step": 155
+    },
+    {
+      "epoch": 0.5124099279423538,
+      "grad_norm": 0.534895902584602,
+      "learning_rate": 1.6945781434686783e-05,
+      "loss": 0.9825244903564453,
+      "step": 160
+    },
+    {
+      "epoch": 0.5124099279423538,
+      "eval_loss": 0.9406914710998535,
+      "eval_runtime": 14.543,
+      "eval_samples_per_second": 7.289,
+      "eval_steps_per_second": 0.963,
+      "eval_token_acc": 0.7515060551502148,
+      "step": 160
+    },
+    {
+      "epoch": 0.5284227381905524,
+      "grad_norm": 0.570687760675595,
+      "learning_rate": 1.6763093380726347e-05,
+      "loss": 0.9817087173461914,
+      "step": 165
+    },
+    {
+      "epoch": 0.544435548438751,
+      "grad_norm": 0.538629612243421,
+      "learning_rate": 1.6576147248065268e-05,
+      "loss": 0.9138102531433105,
+      "step": 170
+    },
+    {
+      "epoch": 0.5604483586869495,
+      "grad_norm": 0.5367674967998894,
+      "learning_rate": 1.6385060738959123e-05,
+      "loss": 1.0132644653320313,
+      "step": 175
+    },
+    {
+      "epoch": 0.5636509207365893,
+      "eval_loss": 0.9347953796386719,
+      "eval_runtime": 14.5385,
+      "eval_samples_per_second": 7.291,
+      "eval_steps_per_second": 0.963,
+      "eval_token_acc": 0.7528409121740046,
+      "step": 176
+    },
+    {
+      "epoch": 0.5764611689351481,
+      "grad_norm": 0.5505130343882023,
+      "learning_rate": 1.618995416246601e-05,
+      "loss": 0.992160701751709,
+      "step": 180
+    },
+    {
+      "epoch": 0.5924739791833467,
+      "grad_norm": 0.5177676977332548,
+      "learning_rate": 1.5990950358699313e-05,
+      "loss": 0.9666297912597657,
+      "step": 185
+    },
+    {
+      "epoch": 0.6084867894315452,
+      "grad_norm": 0.5115335805994138,
+      "learning_rate": 1.5788174621486936e-05,
+      "loss": 1.0041114807128906,
+      "step": 190
+    },
+    {
+      "epoch": 0.6148919135308246,
+      "eval_loss": 0.93098384141922,
+      "eval_runtime": 14.3902,
+      "eval_samples_per_second": 7.366,
+      "eval_steps_per_second": 0.973,
+      "eval_token_acc": 0.7536678723789866,
+      "step": 192
+    },
+    {
+      "epoch": 0.6244995996797438,
+      "grad_norm": 0.5250074708052181,
+      "learning_rate": 1.5581754619485665e-05,
+      "loss": 0.9529659271240234,
+      "step": 195
+    },
+    {
+      "epoch": 0.6405124099279423,
+      "grad_norm": 0.5229963755514054,
+      "learning_rate": 1.5371820315800316e-05,
+      "loss": 0.9871055603027343,
+      "step": 200
+    },
+    {
+      "epoch": 0.6565252201761409,
+      "grad_norm": 0.5619728554930467,
+      "learning_rate": 1.515850388615829e-05,
+      "loss": 0.9758607864379882,
+      "step": 205
+    },
+    {
+      "epoch": 0.6661329063250601,
+      "eval_loss": 0.9274569749832153,
+      "eval_runtime": 14.4012,
+      "eval_samples_per_second": 7.36,
+      "eval_steps_per_second": 0.972,
+      "eval_token_acc": 0.7543787108753949,
+      "step": 208
+    },
+    {
+      "epoch": 0.6725380304243395,
+      "grad_norm": 0.5225355460662542,
+      "learning_rate": 1.4941939635691036e-05,
+      "loss": 0.9769810676574707,
+      "step": 210
+    },
+    {
+      "epoch": 0.688550840672538,
+      "grad_norm": 0.568577150338433,
+      "learning_rate": 1.472226391437487e-05,
+      "loss": 0.9766319274902344,
+      "step": 215
+    },
+    {
+      "epoch": 0.7045636509207366,
+      "grad_norm": 0.5082957989681854,
+      "learning_rate": 1.4499615031184297e-05,
+      "loss": 1.0206737518310547,
+      "step": 220
+    },
+    {
+      "epoch": 0.7173738991192954,
+      "eval_loss": 0.9242973327636719,
+      "eval_runtime": 14.3413,
+      "eval_samples_per_second": 7.391,
+      "eval_steps_per_second": 0.976,
+      "eval_token_acc": 0.7550070704012276,
+      "step": 224
+    },
+    {
+      "epoch": 0.7205764611689351,
+      "grad_norm": 0.5358194740461656,
+      "learning_rate": 1.4274133167011974e-05,
+      "loss": 0.9878074645996093,
+      "step": 225
+    },
+    {
+      "epoch": 0.7365892714171337,
+      "grad_norm": 0.5339305541304005,
+      "learning_rate": 1.4045960286410093e-05,
+      "loss": 0.9679292678833008,
+      "step": 230
+    },
+    {
+      "epoch": 0.7526020816653323,
+      "grad_norm": 0.5593865586297648,
+      "learning_rate": 1.3815240048208754e-05,
+      "loss": 1.0053502082824708,
+      "step": 235
+    },
+    {
+      "epoch": 0.7686148919135308,
+      "grad_norm": 0.5401750319818177,
+      "learning_rate": 1.3582117715067628e-05,
+      "loss": 0.9748393058776855,
+      "step": 240
+    },
+    {
+      "epoch": 0.7686148919135308,
+      "eval_loss": 0.9197457432746887,
+      "eval_runtime": 14.3833,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 0.973,
+      "eval_token_acc": 0.7559349588202035,
+      "step": 240
+    },
+    {
+      "epoch": 0.7846277021617294,
+      "grad_norm": 0.5111792950923116,
+      "learning_rate": 1.3346740062017838e-05,
+      "loss": 0.9668654441833496,
+      "step": 245
+    },
+    {
+      "epoch": 0.800640512409928,
+      "grad_norm": 0.4908084859303256,
+      "learning_rate": 1.3109255284051615e-05,
+      "loss": 0.9447157859802247,
+      "step": 250
+    },
+    {
+      "epoch": 0.8166533226581265,
+      "grad_norm": 0.562628279362229,
+      "learning_rate": 1.2869812902817983e-05,
+      "loss": 1.0060791969299316,
+      "step": 255
+    },
+    {
+      "epoch": 0.8198558847077662,
+      "eval_loss": 0.9148392081260681,
+      "eval_runtime": 14.5143,
+      "eval_samples_per_second": 7.303,
+      "eval_steps_per_second": 0.965,
+      "eval_token_acc": 0.7570961759059393,
+      "step": 256
+    },
+    {
+      "epoch": 0.8326661329063251,
+      "grad_norm": 0.5551169665873459,
+      "learning_rate": 1.2628563672483147e-05,
+      "loss": 0.9434755325317383,
+      "step": 260
+    },
+    {
+      "epoch": 0.8486789431545236,
+      "grad_norm": 0.5384977105444301,
+      "learning_rate": 1.2385659484814884e-05,
+      "loss": 0.9425140380859375,
+      "step": 265
+    },
+    {
+      "epoch": 0.8646917534027222,
+      "grad_norm": 0.5558312305489408,
+      "learning_rate": 1.2141253273550698e-05,
+      "loss": 0.9308363914489746,
+      "step": 270
+    },
+    {
+      "epoch": 0.8710968775020016,
+      "eval_loss": 0.9132360816001892,
+      "eval_runtime": 14.3299,
+      "eval_samples_per_second": 7.397,
+      "eval_steps_per_second": 0.977,
+      "eval_token_acc": 0.756837886498084,
+      "step": 272
+    },
+    {
+      "epoch": 0.8807045636509208,
+      "grad_norm": 0.5408069248699333,
+      "learning_rate": 1.1895498918109944e-05,
+      "loss": 0.9968246459960938,
+      "step": 275
+    },
+    {
+      "epoch": 0.8967173738991193,
+      "grad_norm": 0.5610077458655038,
+      "learning_rate": 1.1648551146710557e-05,
+      "loss": 0.9824394226074219,
+      "step": 280
+    },
+    {
+      "epoch": 0.9127301841473179,
+      "grad_norm": 0.5255605897633258,
+      "learning_rate": 1.1400565438951343e-05,
+      "loss": 0.9811803817749023,
+      "step": 285
+    },
+    {
+      "epoch": 0.922337870296237,
+      "eval_loss": 0.9093953371047974,
+      "eval_runtime": 14.6394,
+      "eval_samples_per_second": 7.241,
+      "eval_steps_per_second": 0.956,
+      "eval_token_acc": 0.7579763133419503,
+      "step": 288
+    },
+    {
+      "epoch": 0.9287429943955164,
+      "grad_norm": 0.5221824598602125,
+      "learning_rate": 1.1151697927921242e-05,
+      "loss": 0.9672993659973145,
+      "step": 290
+    },
+    {
+      "epoch": 0.944755804643715,
+      "grad_norm": 0.5526116046751202,
+      "learning_rate": 1.0902105301897098e-05,
+      "loss": 0.9626201629638672,
+      "step": 295
+    },
+    {
+      "epoch": 0.9607686148919136,
+      "grad_norm": 0.5572541912245995,
+      "learning_rate": 1.065194470569193e-05,
+      "loss": 0.9313549041748047,
+      "step": 300
+    },
+    {
+      "epoch": 0.9735788630904724,
+      "eval_loss": 0.9058682322502136,
+      "eval_runtime": 14.643,
+      "eval_samples_per_second": 7.239,
+      "eval_steps_per_second": 0.956,
+      "eval_token_acc": 0.7587338175717105,
+      "step": 304
+    },
+    {
+      "epoch": 0.9767814251401121,
+      "grad_norm": 0.5274146008466054,
+      "learning_rate": 1.0401373641715725e-05,
+      "loss": 0.9810738563537598,
+      "step": 305
+    },
+    {
+      "epoch": 0.9927942353883107,
+      "grad_norm": 0.524106900784095,
+      "learning_rate": 1.0150549870811108e-05,
+      "loss": 1.0075571060180664,
+      "step": 310
+    },
+    {
+      "epoch": 1.0064051240992795,
+      "grad_norm": 0.6435736665358253,
+      "learning_rate": 9.899631312926303e-06,
+      "loss": 0.911602783203125,
+      "step": 315
+    },
+    {
+      "epoch": 1.022417934347478,
+      "grad_norm": 0.5331283028468047,
+      "learning_rate": 9.648775947687914e-06,
+      "loss": 0.8135837554931641,
+      "step": 320
+    },
+    {
+      "epoch": 1.022417934347478,
+      "eval_loss": 0.9115325212478638,
+      "eval_runtime": 14.6079,
+      "eval_samples_per_second": 7.256,
+      "eval_steps_per_second": 0.958,
+      "eval_token_acc": 0.7582769274847061,
+      "step": 320
+    },
+    {
+      "epoch": 1.0384307445956766,
+      "grad_norm": 0.5591218522147324,
+      "learning_rate": 9.398141714936104e-06,
+      "loss": 0.8059094429016114,
+      "step": 325
+    },
+    {
+      "epoch": 1.054443554843875,
+      "grad_norm": 0.4934373856607571,
+      "learning_rate": 9.147886415284903e-06,
+      "loss": 0.7668675422668457,
+      "step": 330
+    },
+    {
+      "epoch": 1.0704563650920738,
+      "grad_norm": 0.5225315577164972,
+      "learning_rate": 8.898167610770075e-06,
+      "loss": 0.8142057418823242,
+      "step": 335
+    },
+    {
+      "epoch": 1.0736589271417134,
+      "eval_loss": 0.9149956107139587,
+      "eval_runtime": 14.4577,
+      "eval_samples_per_second": 7.332,
+      "eval_steps_per_second": 0.968,
+      "eval_token_acc": 0.7586025023685573,
+      "step": 336
+    },
+    {
+      "epoch": 1.0864691753402722,
+      "grad_norm": 0.5505230936617594,
+      "learning_rate": 8.649142525647271e-06,
+      "loss": 0.7990794658660889,
+      "step": 340
+    },
+    {
+      "epoch": 1.1024819855884709,
+      "grad_norm": 0.5093097727784036,
+      "learning_rate": 8.400967947402802e-06,
+      "loss": 0.8117720603942871,
+      "step": 345
+    },
+    {
+      "epoch": 1.1184947958366693,
+      "grad_norm": 0.5036948822528423,
+      "learning_rate": 8.153800128039441e-06,
+      "loss": 0.7948765754699707,
+      "step": 350
+    },
+    {
+      "epoch": 1.1248999199359488,
+      "eval_loss": 0.9154974818229675,
+      "eval_runtime": 14.5423,
+      "eval_samples_per_second": 7.289,
+      "eval_steps_per_second": 0.963,
+      "eval_token_acc": 0.7590235792183381,
+      "step": 352
+    },
+    {
+      "epoch": 1.1345076060848678,
+      "grad_norm": 0.4769674515169561,
+      "learning_rate": 7.907794685699347e-06,
+      "loss": 0.7767979621887207,
+      "step": 355
+    },
+    {
+      "epoch": 1.1505204163330665,
+      "grad_norm": 0.46860511663718424,
+      "learning_rate": 7.663106506686057e-06,
+      "loss": 0.8007712364196777,
+      "step": 360
+    },
+    {
+      "epoch": 1.1665332265812651,
+      "grad_norm": 0.5257245232743394,
+      "learning_rate": 7.419889647947294e-06,
+      "loss": 0.7960629463195801,
+      "step": 365
+    },
+    {
+      "epoch": 1.176140912730184,
+      "eval_loss": 0.9117251038551331,
+      "eval_runtime": 14.5432,
+      "eval_samples_per_second": 7.289,
+      "eval_steps_per_second": 0.963,
+      "eval_token_acc": 0.7595477547813385,
+      "step": 368
+    },
+    {
+      "epoch": 1.1825460368294636,
+      "grad_norm": 0.4875981050318745,
+      "learning_rate": 7.1782972400798825e-06,
+      "loss": 0.8045159339904785,
+      "step": 370
+    },
+    {
+      "epoch": 1.198558847077662,
+      "grad_norm": 0.49641916149081433,
+      "learning_rate": 6.938481390917966e-06,
+      "loss": 0.7951483726501465,
+      "step": 375
+    },
+    {
+      "epoch": 1.2145716573258607,
+      "grad_norm": 0.5035877161539227,
+      "learning_rate": 6.700593089765086e-06,
+      "loss": 0.7760053634643554,
+      "step": 380
+    },
+    {
+      "epoch": 1.2273819055244195,
+      "eval_loss": 0.9107971787452698,
+      "eval_runtime": 14.5702,
+      "eval_samples_per_second": 7.275,
+      "eval_steps_per_second": 0.961,
+      "eval_token_acc": 0.76016417656143,
+      "step": 384
+    },
+    {
+      "epoch": 1.2305844675740594,
+      "grad_norm": 0.5325891391407898,
+      "learning_rate": 6.4647821123305595e-06,
+      "loss": 0.8205606460571289,
+      "step": 385
+    },
+    {
+      "epoch": 1.2465972778222578,
+      "grad_norm": 0.5135559248558815,
+      "learning_rate": 6.231196926429913e-06,
+      "loss": 0.7906920909881592,
+      "step": 390
+    },
+    {
+      "epoch": 1.2626100880704563,
+      "grad_norm": 0.5335030354283354,
+      "learning_rate": 5.9999845985087555e-06,
+      "loss": 0.7642984867095948,
+      "step": 395
+    },
+    {
+      "epoch": 1.278622898318655,
+      "grad_norm": 0.48895214640029644,
+      "learning_rate": 5.7712907010490036e-06,
+      "loss": 0.7710936069488525,
+      "step": 400
+    },
+    {
+      "epoch": 1.278622898318655,
+      "eval_loss": 0.9103301167488098,
+      "eval_runtime": 14.5639,
+      "eval_samples_per_second": 7.278,
+      "eval_steps_per_second": 0.961,
+      "eval_token_acc": 0.7599558086357653,
+      "step": 400
+    },
+    {
+      "epoch": 1.2946357085668536,
+      "grad_norm": 0.48139293101652547,
+      "learning_rate": 5.54525922091568e-06,
+      "loss": 0.7966293811798095,
+      "step": 405
+    },
+    {
+      "epoch": 1.310648518815052,
+      "grad_norm": 0.49809536135629684,
+      "learning_rate": 5.322032468702037e-06,
+      "loss": 0.7998294830322266,
+      "step": 410
+    },
+    {
+      "epoch": 1.3266613290632505,
+      "grad_norm": 0.4763833723377931,
+      "learning_rate": 5.101750989130061e-06,
+      "loss": 0.7967349529266358,
+      "step": 415
+    },
+    {
+      "epoch": 1.3298638911128904,
+      "eval_loss": 0.9072456955909729,
+      "eval_runtime": 14.9836,
+      "eval_samples_per_second": 7.074,
+      "eval_steps_per_second": 0.934,
+      "eval_token_acc": 0.7605136269367636,
+      "step": 416
+    },
+    {
+      "epoch": 1.3426741393114492,
+      "grad_norm": 0.47173729117652685,
+      "learning_rate": 4.884553472562809e-06,
+      "loss": 0.7906300544738769,
+      "step": 420
+    },
+    {
+      "epoch": 1.3586869495596476,
+      "grad_norm": 0.48564485172021316,
+      "learning_rate": 4.670576667684217e-06,
+      "loss": 0.8035748481750489,
+      "step": 425
+    },
+    {
+      "epoch": 1.3746997598078463,
+      "grad_norm": 0.4915778703667535,
+      "learning_rate": 4.459955295401415e-06,
+      "loss": 0.7896071434020996,
+      "step": 430
+    },
+    {
+      "epoch": 1.3811048839071258,
+      "eval_loss": 0.9058337807655334,
+      "eval_runtime": 15.1686,
+      "eval_samples_per_second": 6.988,
+      "eval_steps_per_second": 0.923,
+      "eval_token_acc": 0.7609249365400289,
+      "step": 432
+    },
+    {
+      "epoch": 1.3907125700560448,
+      "grad_norm": 0.5001513581944296,
+      "learning_rate": 4.2528219640237565e-06,
+      "loss": 0.771601390838623,
+      "step": 435
+    },
+    {
+      "epoch": 1.4067253803042434,
+      "grad_norm": 0.5015899348463313,
+      "learning_rate": 4.0493070857719305e-06,
+      "loss": 0.8050725936889649,
+      "step": 440
+    },
+    {
+      "epoch": 1.4227381905524419,
+      "grad_norm": 0.4385885001536844,
+      "learning_rate": 3.849538794669767e-06,
+      "loss": 0.7711515903472901,
+      "step": 445
+    },
+    {
+      "epoch": 1.432345876701361,
+      "eval_loss": 0.9053142666816711,
+      "eval_runtime": 14.9957,
+      "eval_samples_per_second": 7.069,
+      "eval_steps_per_second": 0.934,
+      "eval_token_acc": 0.7611723734517558,
+      "step": 448
+    },
+    {
+      "epoch": 1.4387510008006406,
+      "grad_norm": 0.4923484323839949,
+      "learning_rate": 3.6536428658703594e-06,
+      "loss": 0.8126641273498535,
+      "step": 450
+    },
+    {
+      "epoch": 1.454763811048839,
+      "grad_norm": 0.4696764489825615,
+      "learning_rate": 3.4617426364674088e-06,
+      "loss": 0.8082319259643554,
+      "step": 455
+    },
+    {
+      "epoch": 1.4707766212970377,
+      "grad_norm": 0.49222563172262457,
+      "learning_rate": 3.2739589278415252e-06,
+      "loss": 0.7895666122436523,
+      "step": 460
+    },
+    {
+      "epoch": 1.4835868694955965,
+      "eval_loss": 0.9038885831832886,
+      "eval_runtime": 15.1795,
+      "eval_samples_per_second": 6.983,
+      "eval_steps_per_second": 0.922,
+      "eval_token_acc": 0.7614545383510934,
+      "step": 464
+    },
+    {
+      "epoch": 1.4867894315452361,
+      "grad_norm": 0.49886868372218357,
+      "learning_rate": 3.0904099695904677e-06,
+      "loss": 0.7927409172058105,
+      "step": 465
+    },
+    {
+      "epoch": 1.5028022417934348,
+      "grad_norm": 0.4598131832969276,
+      "learning_rate": 2.9112113250911844e-06,
+      "loss": 0.7818885803222656,
+      "step": 470
+    },
+    {
+      "epoch": 1.5188150520416333,
+      "grad_norm": 0.5625875539857127,
+      "learning_rate": 2.7364758187404895e-06,
+      "loss": 0.7819410800933838,
+      "step": 475
+    },
+    {
+      "epoch": 1.534827862289832,
+      "grad_norm": 0.5114133442743116,
+      "learning_rate": 2.566313464920265e-06,
+      "loss": 0.7769948959350585,
+      "step": 480
+    },
+    {
+      "epoch": 1.534827862289832,
+      "eval_loss": 0.902407705783844,
+      "eval_runtime": 15.1633,
+      "eval_samples_per_second": 6.991,
+      "eval_steps_per_second": 0.923,
+      "eval_token_acc": 0.7618387167140378,
+      "step": 480
+    },
+    {
+      "epoch": 1.5508406725380304,
+      "grad_norm": 0.4441806210622428,
+      "learning_rate": 2.4008313987318057e-06,
+      "loss": 0.771674919128418,
+      "step": 485
+    },
+    {
+      "epoch": 1.5668534827862288,
+      "grad_norm": 0.49075637368256414,
+      "learning_rate": 2.2401338085430326e-06,
+      "loss": 0.7837276935577393,
+      "step": 490
+    },
+    {
+      "epoch": 1.5828662930344275,
+      "grad_norm": 0.4597708187505928,
+      "learning_rate": 2.0843218703909197e-06,
+      "loss": 0.8008305549621582,
+      "step": 495
+    },
+    {
+      "epoch": 1.5860688550840671,
+      "eval_loss": 0.901805579662323,
+      "eval_runtime": 14.941,
+      "eval_samples_per_second": 7.095,
+      "eval_steps_per_second": 0.937,
+      "eval_token_acc": 0.7620666191327337,
+      "step": 496
+    },
+    {
+      "epoch": 1.5988791032826262,
+      "grad_norm": 0.4720072570006326,
+      "learning_rate": 1.933493684280574e-06,
+      "loss": 0.7590449333190918,
+      "step": 500
+    },
+    {
+      "epoch": 1.6148919135308246,
+      "grad_norm": 0.4681413165579918,
+      "learning_rate": 1.7877442124209454e-06,
+      "loss": 0.7496448516845703,
+      "step": 505
+    },
+    {
+      "epoch": 1.630904723779023,
+      "grad_norm": 0.512917797281379,
+      "learning_rate": 1.6471652194361131e-06,
+      "loss": 0.8017988204956055,
+      "step": 510
+    },
+    {
+      "epoch": 1.6373098478783028,
+      "eval_loss": 0.9010795950889587,
+      "eval_runtime": 14.9598,
+      "eval_samples_per_second": 7.086,
+      "eval_steps_per_second": 0.936,
+      "eval_token_acc": 0.762230491824272,
+      "step": 512
+    },
+    {
+      "epoch": 1.6469175340272217,
+      "grad_norm": 0.47200391166538574,
+      "learning_rate": 1.5118452145898333e-06,
+      "loss": 0.7879790782928466,
+      "step": 515
+    },
+    {
+      "epoch": 1.6629303442754204,
+      "grad_norm": 0.46302656170029055,
+      "learning_rate": 1.3818693960596186e-06,
+      "loss": 0.8126321792602539,
+      "step": 520
+    },
+    {
+      "epoch": 1.6789431545236189,
+      "grad_norm": 0.47488283670703535,
+      "learning_rate": 1.2573195972955366e-06,
+      "loss": 0.7743080139160157,
+      "step": 525
+    },
+    {
+      "epoch": 1.688550840672538,
+      "eval_loss": 0.9008040428161621,
+      "eval_runtime": 15.0798,
+      "eval_samples_per_second": 7.029,
+      "eval_steps_per_second": 0.928,
+      "eval_token_acc": 0.7623943645158104,
+      "step": 528
+    },
+    {
+      "epoch": 1.6949559647718173,
+      "grad_norm": 0.4692191060367917,
+      "learning_rate": 1.138274235497443e-06,
+      "loss": 0.7871302604675293,
+      "step": 530
+    },
+    {
+      "epoch": 1.710968775020016,
+      "grad_norm": 0.4643020032036482,
+      "learning_rate": 1.0248082622431089e-06,
+      "loss": 0.8171819686889649,
+      "step": 535
+    },
+    {
+      "epoch": 1.7269815852682147,
+      "grad_norm": 0.4858630939402049,
+      "learning_rate": 9.169931162983137e-07,
+      "loss": 0.799337911605835,
+      "step": 540
+    },
+    {
+      "epoch": 1.7397918334667735,
+      "eval_loss": 0.900395929813385,
+      "eval_runtime": 15.0673,
+      "eval_samples_per_second": 7.035,
+      "eval_steps_per_second": 0.929,
+      "eval_token_acc": 0.7622619640630444,
+      "step": 544
+    },
+    {
+      "epoch": 1.742994395516413,
+      "grad_norm": 0.4799218615796674,
+      "learning_rate": 8.14896678638627e-07,
+      "loss": 0.7801701068878174,
+      "step": 545
+    },
+    {
+      "epoch": 1.7590072057646116,
+      "grad_norm": 0.4601161306972559,
+      "learning_rate": 7.185832297111939e-07,
+      "loss": 0.7815041065216064,
+      "step": 550
+    },
+    {
+      "epoch": 1.7750200160128102,
+      "grad_norm": 0.49546298524642746,
+      "learning_rate": 6.281134089634344e-07,
+      "loss": 0.7939868927001953,
+      "step": 555
+    },
+    {
+      "epoch": 1.791032826261009,
+      "grad_norm": 0.450946115728095,
+      "learning_rate": 5.43544176664137e-07,
+      "loss": 0.7616684913635254,
+      "step": 560
+    },
+    {
+      "epoch": 1.791032826261009,
+      "eval_loss": 0.9009150862693787,
+      "eval_runtime": 15.0544,
+      "eval_samples_per_second": 7.041,
+      "eval_steps_per_second": 0.93,
+      "eval_token_acc": 0.7623921940165848,
+      "step": 560
+    },
+    {
+      "epoch": 1.8070456365092074,
+      "grad_norm": 0.47911563419797926,
+      "learning_rate": 4.649287780409639e-07,
+      "loss": 0.7857556343078613,
+      "step": 565
+    },
+    {
+      "epoch": 1.8230584467574058,
+      "grad_norm": 0.46252106401819404,
+      "learning_rate": 3.9231670975699354e-07,
+      "loss": 0.7810296535491943,
+      "step": 570
+    },
+    {
+      "epoch": 1.8390712570056045,
+      "grad_norm": 0.4694570979755398,
+      "learning_rate": 3.257536887473545e-07,
+      "loss": 0.7967131614685059,
+      "step": 575
+    },
+    {
+      "epoch": 1.8422738190552441,
+      "eval_loss": 0.9001392722129822,
+      "eval_runtime": 14.9754,
+      "eval_samples_per_second": 7.078,
+      "eval_steps_per_second": 0.935,
+      "eval_token_acc": 0.7625387027143178,
+      "step": 576
+    },
+    {
+      "epoch": 1.8550840672538031,
+      "grad_norm": 0.4661576925242358,
+      "learning_rate": 2.6528162343561593e-07,
+      "loss": 0.7634014129638672,
+      "step": 580
+    },
+    {
+      "epoch": 1.8710968775020016,
+      "grad_norm": 0.4606424682139549,
+      "learning_rate": 2.109385873480141e-07,
+      "loss": 0.803773021697998,
+      "step": 585
+    },
+    {
+      "epoch": 1.8871096877502,
+      "grad_norm": 0.45627441448144695,
+      "learning_rate": 1.6275879514217052e-07,
+      "loss": 0.8115141868591309,
+      "step": 590
+    },
+    {
+      "epoch": 1.8935148118494796,
+      "eval_loss": 0.9000989198684692,
+      "eval_runtime": 15.3159,
+      "eval_samples_per_second": 6.921,
+      "eval_steps_per_second": 0.914,
+      "eval_token_acc": 0.7625256797189638,
+      "step": 592
+    },
+    {
+      "epoch": 1.9031224979983987,
+      "grad_norm": 0.46130608210077223,
+      "learning_rate": 1.2077258106536927e-07,
+      "loss": 0.8369948387145996,
+      "step": 595
+    },
+    {
+      "epoch": 1.9191353082465974,
+      "grad_norm": 0.4743433129321771,
+      "learning_rate": 8.50063798559475e-08,
+      "loss": 0.7816999912261963,
+      "step": 600
+    },
+    {
+      "epoch": 1.9351481184947958,
+      "grad_norm": 0.4716524325522153,
+      "learning_rate": 5.54827100998534e-08,
+      "loss": 0.7883635520935058,
+      "step": 605
+    },
+    {
+      "epoch": 1.944755804643715,
+      "eval_loss": 0.90007084608078,
+      "eval_runtime": 15.3084,
+      "eval_samples_per_second": 6.924,
+      "eval_steps_per_second": 0.915,
+      "eval_token_acc": 0.7624746729871604,
+      "step": 608
+    },
+    {
+      "epoch": 1.9511609287429943,
+      "grad_norm": 0.44797137033963047,
+      "learning_rate": 3.2220160052828245e-08,
+      "loss": 0.7870570182800293,
+      "step": 610
+    },
+    {
+      "epoch": 1.967173738991193,
+      "grad_norm": 0.45207745564951624,
+      "learning_rate": 1.523337593714036e-08,
+      "loss": 0.8020266532897949,
+      "step": 615
+    },
+    {
+      "epoch": 1.9831865492393916,
+      "grad_norm": 0.46560058211157906,
+      "learning_rate": 4.5330527202480656e-09,
+      "loss": 0.8163101196289062,
+      "step": 620
+    },
+    {
+      "epoch": 1.9959967974379502,
+      "eval_loss": 0.9000772833824158,
+      "eval_runtime": 14.9354,
+      "eval_samples_per_second": 7.097,
+      "eval_steps_per_second": 0.937,
+      "eval_token_acc": 0.762490951731353,
+      "step": 624
+    },
+    {
+      "epoch": 1.99919935948759,
+      "grad_norm": 0.49036708117796896,
+      "learning_rate": 1.2592738119709957e-10,
+      "loss": 0.8205068588256836,
+      "step": 625
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9000126123428345,
+      "eval_runtime": 15.1395,
+      "eval_samples_per_second": 7.002,
+      "eval_steps_per_second": 0.925,
+      "eval_token_acc": 0.7625473847112205,
+      "step": 626
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 626,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6044514006305341e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:742f6bdf30a8e3cd827f7e6c9ce0588fdb84db960590f099246ae1e02327dd45
+size 9233