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 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731a8b444a67868b159b0cb2edbe47e857b02b5c4bf264c73657ec92a8f2f5e6
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1022020ac14eaf0a9e5bc9d718931cc3e39959c76ef771785070d1dfc1f61428
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a3ce0a7953805a740782fa662ad1cfc52f991ff8549d177fd4033bfffc63f0
+size 16090217224

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069a21fb89e9cdd912b5dc454d58844eeb9e7af136215bc79c9a32dc0f860079
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1933ef234c6d1950447450676fa465319c6dfea13fd8f45a8b587983e4707aa2
+size 15920

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860ac45307c7a18d297d614ddaf15e44b83fa85a059ef5f3094bd2e3dba2c36b
+size 15920

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0ffbf272e35be211cf29563fafba476c8e4b4f5a9a051cb183c83cd7a9207c
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c2a0fdfe8d5d0e5249a4016327271562f035b0aa16e43e03eae55f889c6a90
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5223fcf1a77743cc1dddc34ea56384e61c0597f22375eb02b7051f644628dd04
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a690fe8858c599f911541e1927330a04ebb2ed4c99a33896ff51998825d351a
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2bdf42e2e9e14cb079536cdc422e6dfe602793fda2e855a66fd2903edad8e2
+size 15920

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d85e8888f64de356995cd02981ee52b52226141b982fbd59dd28f331e6c872
+size 1064

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 sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
+size 11422821

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 405,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.028125,
+      "completions/max_length": 2620.6,
+      "completions/max_terminated_length": 2367.6,
+      "completions/mean_length": 883.478125,
+      "completions/mean_terminated_length": 807.5466979980469,
+      "completions/min_length": 197.9,
+      "completions/min_terminated_length": 197.9,
+      "entropy": 0.23559987246990205,
+      "epoch": 0.07407407407407407,
+      "frac_reward_zero_std": 0.525,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 0.024,
+      "num_tokens": 1074521.0,
+      "reward": 0.55625,
+      "reward_std": 0.19937496185302733,
+      "rewards/qwen_accuracy_reward/mean": 0.55625,
+      "rewards/qwen_accuracy_reward/std": 0.4109149545431137,
+      "step": 10,
+      "step_time": 88.14663478741423
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1834.7,
+      "completions/max_terminated_length": 1834.7,
+      "completions/mean_length": 585.428125,
+      "completions/mean_terminated_length": 585.428125,
+      "completions/min_length": 182.1,
+      "completions/min_terminated_length": 182.1,
+      "entropy": 0.2393606960773468,
+      "epoch": 0.14814814814814814,
+      "frac_reward_zero_std": 0.675,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.530864197530865e-06,
+      "loss": 0.0006,
+      "num_tokens": 2260202.0,
+      "reward": 0.34375,
+      "reward_std": 0.13309670016169547,
+      "rewards/qwen_accuracy_reward/mean": 0.34375,
+      "rewards/qwen_accuracy_reward/std": 0.43564632534980774,
+      "step": 20,
+      "step_time": 68.61595703456551
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1243.6,
+      "completions/max_terminated_length": 1243.6,
+      "completions/mean_length": 450.828125,
+      "completions/mean_terminated_length": 450.828125,
+      "completions/min_length": 166.3,
+      "completions/min_terminated_length": 166.3,
+      "entropy": 0.20521417111158372,
+      "epoch": 0.2222222222222222,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.28395061728395e-06,
+      "loss": -0.0119,
+      "num_tokens": 3563603.0,
+      "reward": 0.45,
+      "reward_std": 0.161917694658041,
+      "rewards/qwen_accuracy_reward/mean": 0.45,
+      "rewards/qwen_accuracy_reward/std": 0.4305156499147415,
+      "step": 30,
+      "step_time": 54.05118924472481
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 1784.0,
+      "completions/max_terminated_length": 1784.0,
+      "completions/mean_length": 641.815625,
+      "completions/mean_terminated_length": 641.815625,
+      "completions/min_length": 201.1,
+      "completions/min_terminated_length": 201.1,
+      "entropy": 0.24612632393836975,
+      "epoch": 0.2962962962962963,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.037037037037037e-06,
+      "loss": -0.0269,
+      "num_tokens": 4556680.0,
+      "reward": 0.4125,
+      "reward_std": 0.10794617459177971,
+      "rewards/qwen_accuracy_reward/mean": 0.4125,
+      "rewards/qwen_accuracy_reward/std": 0.4408176690340042,
+      "step": 40,
+      "step_time": 62.3625052860938
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 2380.8,
+      "completions/max_terminated_length": 2099.1,
+      "completions/mean_length": 739.5,
+      "completions/mean_terminated_length": 684.6817810058594,
+      "completions/min_length": 199.8,
+      "completions/min_terminated_length": 199.8,
+      "entropy": 0.2352774903178215,
+      "epoch": 0.37037037037037035,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.0,
+      "learning_rate": 8.790123456790124e-06,
+      "loss": 0.0811,
+      "num_tokens": 5832520.0,
+      "reward": 0.578125,
+      "reward_std": 0.17328082770109177,
+      "rewards/qwen_accuracy_reward/mean": 0.578125,
+      "rewards/qwen_accuracy_reward/std": 0.46805118918418886,
+      "step": 50,
+      "step_time": 85.62781593985855
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 2675.6,
+      "completions/max_terminated_length": 2675.6,
+      "completions/mean_length": 883.246875,
+      "completions/mean_terminated_length": 883.246875,
+      "completions/min_length": 186.3,
+      "completions/min_terminated_length": 186.3,
+      "entropy": 0.2517232894897461,
+      "epoch": 0.4444444444444444,
+      "frac_reward_zero_std": 0.575,
+      "grad_norm": 0.82421875,
+      "learning_rate": 8.54320987654321e-06,
+      "loss": -0.0098,
+      "num_tokens": 7189655.0,
+      "reward": 0.475,
+      "reward_std": 0.19032337367534638,
+      "rewards/qwen_accuracy_reward/mean": 0.475,
+      "rewards/qwen_accuracy_reward/std": 0.4926638722419739,
+      "step": 60,
+      "step_time": 92.28469488024712
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.021875,
+      "completions/max_length": 2552.0,
+      "completions/max_terminated_length": 2446.1,
+      "completions/mean_length": 883.15,
+      "completions/mean_terminated_length": 819.4166320800781,
+      "completions/min_length": 228.0,
+      "completions/min_terminated_length": 228.0,
+      "entropy": 0.2566807523369789,
+      "epoch": 0.5185185185185185,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.68359375,
+      "learning_rate": 8.296296296296297e-06,
+      "loss": -0.005,
+      "num_tokens": 8291047.0,
+      "reward": 0.59375,
+      "reward_std": 0.14424002543091774,
+      "rewards/qwen_accuracy_reward/mean": 0.59375,
+      "rewards/qwen_accuracy_reward/std": 0.44616653919219973,
+      "step": 70,
+      "step_time": 84.87951188636944
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.021875,
+      "completions/max_length": 2260.4,
+      "completions/max_terminated_length": 2111.1,
+      "completions/mean_length": 764.521875,
+      "completions/mean_terminated_length": 696.4317199707032,
+      "completions/min_length": 211.0,
+      "completions/min_terminated_length": 211.0,
+      "entropy": 0.23985399603843688,
+      "epoch": 0.5925925925925926,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.049382716049384e-06,
+      "loss": 0.0083,
+      "num_tokens": 9351534.0,
+      "reward": 0.609375,
+      "reward_std": 0.08373925313353539,
+      "rewards/qwen_accuracy_reward/mean": 0.609375,
+      "rewards/qwen_accuracy_reward/std": 0.4246617123484612,
+      "step": 80,
+      "step_time": 72.22795200794936
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 3024.8,
+      "completions/max_terminated_length": 2973.5,
+      "completions/mean_length": 921.46875,
+      "completions/mean_terminated_length": 875.6511962890625,
+      "completions/min_length": 188.1,
+      "completions/min_terminated_length": 188.1,
+      "entropy": 0.2663497790694237,
+      "epoch": 0.6666666666666666,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.5859375,
+      "learning_rate": 7.80246913580247e-06,
+      "loss": 0.0353,
+      "num_tokens": 10367988.0,
+      "reward": 0.653125,
+      "reward_std": 0.17917103096842765,
+      "rewards/qwen_accuracy_reward/mean": 0.653125,
+      "rewards/qwen_accuracy_reward/std": 0.4230299547314644,
+      "step": 90,
+      "step_time": 99.58555124951526
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 2742.8,
+      "completions/max_terminated_length": 2697.5,
+      "completions/mean_length": 973.35625,
+      "completions/mean_terminated_length": 942.023486328125,
+      "completions/min_length": 211.5,
+      "completions/min_terminated_length": 211.5,
+      "entropy": 0.28204803764820097,
+      "epoch": 0.7407407407407407,
+      "frac_reward_zero_std": 0.525,
+      "grad_norm": 1.5078125,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.0189,
+      "num_tokens": 11643438.0,
+      "reward": 0.584375,
+      "reward_std": 0.2061118684709072,
+      "rewards/qwen_accuracy_reward/mean": 0.584375,
+      "rewards/qwen_accuracy_reward/std": 0.446831539273262,
+      "step": 100,
+      "step_time": 102.57813223907723
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.021875,
+      "completions/max_length": 2316.0,
+      "completions/max_terminated_length": 2139.6,
+      "completions/mean_length": 738.425,
+      "completions/mean_terminated_length": 670.76943359375,
+      "completions/min_length": 176.9,
+      "completions/min_terminated_length": 176.9,
+      "entropy": 0.22543054223060607,
+      "epoch": 0.8148148148148148,
+      "frac_reward_zero_std": 0.525,
+      "grad_norm": 1.1015625,
+      "learning_rate": 7.308641975308642e-06,
+      "loss": 0.0297,
+      "num_tokens": 12699542.0,
+      "reward": 0.6125,
+      "reward_std": 0.22020382136106492,
+      "rewards/qwen_accuracy_reward/mean": 0.6125,
+      "rewards/qwen_accuracy_reward/std": 0.39834206998348237,
+      "step": 110,
+      "step_time": 76.58990271799266
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2589.8,
+      "completions/max_terminated_length": 2478.6,
+      "completions/mean_length": 781.328125,
+      "completions/mean_terminated_length": 760.4564636230468,
+      "completions/min_length": 195.2,
+      "completions/min_terminated_length": 195.2,
+      "entropy": 0.2283908247947693,
+      "epoch": 0.8888888888888888,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 1.3984375,
+      "learning_rate": 7.061728395061729e-06,
+      "loss": -0.0513,
+      "num_tokens": 13937615.0,
+      "reward": 0.575,
+      "reward_std": 0.16234711930155754,
+      "rewards/qwen_accuracy_reward/mean": 0.575,
+      "rewards/qwen_accuracy_reward/std": 0.4618679523468018,
+      "step": 120,
+      "step_time": 87.97343005295843
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.009375,
+      "completions/max_length": 3062.2,
+      "completions/max_terminated_length": 2905.6,
+      "completions/mean_length": 934.53125,
+      "completions/mean_terminated_length": 907.7045288085938,
+      "completions/min_length": 204.6,
+      "completions/min_terminated_length": 204.6,
+      "entropy": 0.26524889916181565,
+      "epoch": 0.9629629629629629,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.390625,
+      "learning_rate": 6.814814814814815e-06,
+      "loss": -0.0358,
+      "num_tokens": 14956009.0,
+      "reward": 0.559375,
+      "reward_std": 0.19821664243936538,
+      "rewards/qwen_accuracy_reward/mean": 0.559375,
+      "rewards/qwen_accuracy_reward/std": 0.4717142373323441,
+      "step": 130,
+      "step_time": 94.2147848018445
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 2597.6,
+      "completions/max_terminated_length": 2383.1,
+      "completions/mean_length": 869.10625,
+      "completions/mean_terminated_length": 820.9176330566406,
+      "completions/min_length": 188.5,
+      "completions/min_terminated_length": 188.5,
+      "entropy": 0.24891505092382432,
+      "epoch": 1.037037037037037,
+      "frac_reward_zero_std": 0.475,
+      "grad_norm": 1.703125,
+      "learning_rate": 6.567901234567902e-06,
+      "loss": 0.0034,
+      "num_tokens": 15982347.0,
+      "reward": 0.6,
+      "reward_std": 0.2333553045988083,
+      "rewards/qwen_accuracy_reward/mean": 0.6,
+      "rewards/qwen_accuracy_reward/std": 0.4240004062652588,
+      "step": 140,
+      "step_time": 81.38715343279765
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 2014.9,
+      "completions/max_terminated_length": 2014.9,
+      "completions/mean_length": 690.875,
+      "completions/mean_terminated_length": 690.875,
+      "completions/min_length": 183.7,
+      "completions/min_terminated_length": 183.7,
+      "entropy": 0.24473001956939697,
+      "epoch": 1.1111111111111112,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.0,
+      "learning_rate": 6.320987654320988e-06,
+      "loss": -0.0187,
+      "num_tokens": 17167291.0,
+      "reward": 0.56875,
+      "reward_std": 0.06849093958735467,
+      "rewards/qwen_accuracy_reward/mean": 0.56875,
+      "rewards/qwen_accuracy_reward/std": 0.4323489248752594,
+      "step": 150,
+      "step_time": 70.79571634447203
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2118.0,
+      "completions/max_terminated_length": 1952.7,
+      "completions/mean_length": 782.18125,
+      "completions/mean_terminated_length": 762.3953552246094,
+      "completions/min_length": 195.0,
+      "completions/min_terminated_length": 195.0,
+      "entropy": 0.2831777364015579,
+      "epoch": 1.1851851851851851,
+      "frac_reward_zero_std": 0.625,
+      "grad_norm": 1.203125,
+      "learning_rate": 6.0740740740740745e-06,
+      "loss": -0.006,
+      "num_tokens": 18437597.0,
+      "reward": 0.584375,
+      "reward_std": 0.16034405902028084,
+      "rewards/qwen_accuracy_reward/mean": 0.584375,
+      "rewards/qwen_accuracy_reward/std": 0.4593903660774231,
+      "step": 160,
+      "step_time": 82.42543985564262
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 2807.9,
+      "completions/max_terminated_length": 2465.3,
+      "completions/mean_length": 846.784375,
+      "completions/mean_terminated_length": 768.7292907714843,
+      "completions/min_length": 191.4,
+      "completions/min_terminated_length": 191.4,
+      "entropy": 0.29504771530628204,
+      "epoch": 1.2592592592592593,
+      "frac_reward_zero_std": 0.575,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.827160493827161e-06,
+      "loss": 0.0493,
+      "num_tokens": 19576592.0,
+      "reward": 0.646875,
+      "reward_std": 0.1770761601626873,
+      "rewards/qwen_accuracy_reward/mean": 0.646875,
+      "rewards/qwen_accuracy_reward/std": 0.4303886190056801,
+      "step": 170,
+      "step_time": 92.26987883467227
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 2465.0,
+      "completions/max_terminated_length": 2418.4,
+      "completions/mean_length": 787.653125,
+      "completions/mean_terminated_length": 704.81298828125,
+      "completions/min_length": 179.5,
+      "completions/min_terminated_length": 179.5,
+      "entropy": 0.26591353863477707,
+      "epoch": 1.3333333333333333,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.0859375,
+      "learning_rate": 5.580246913580247e-06,
+      "loss": -0.0034,
+      "num_tokens": 20843313.0,
+      "reward": 0.64375,
+      "reward_std": 0.10615586340427399,
+      "rewards/qwen_accuracy_reward/mean": 0.64375,
+      "rewards/qwen_accuracy_reward/std": 0.4466709479689598,
+      "step": 180,
+      "step_time": 88.50245857564732
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.003125,
+      "completions/max_length": 2406.1,
+      "completions/max_terminated_length": 2396.1,
+      "completions/mean_length": 782.7625,
+      "completions/mean_terminated_length": 772.6895141601562,
+      "completions/min_length": 194.8,
+      "completions/min_terminated_length": 194.8,
+      "entropy": 0.2830284103751183,
+      "epoch": 1.4074074074074074,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.859375,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": -0.0002,
+      "num_tokens": 21942557.0,
+      "reward": 0.65,
+      "reward_std": 0.17233722135424615,
+      "rewards/qwen_accuracy_reward/mean": 0.65,
+      "rewards/qwen_accuracy_reward/std": 0.4606447845697403,
+      "step": 190,
+      "step_time": 79.6569756497629
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.003125,
+      "completions/max_length": 2617.1,
+      "completions/max_terminated_length": 2592.9,
+      "completions/mean_length": 752.6375,
+      "completions/mean_terminated_length": 745.0163208007813,
+      "completions/min_length": 180.0,
+      "completions/min_terminated_length": 180.0,
+      "entropy": 0.2685975283384323,
+      "epoch": 1.4814814814814814,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 1.28125,
+      "learning_rate": 5.08641975308642e-06,
+      "loss": -0.0354,
+      "num_tokens": 23169865.0,
+      "reward": 0.64375,
+      "reward_std": 0.12130923345685005,
+      "rewards/qwen_accuracy_reward/mean": 0.64375,
+      "rewards/qwen_accuracy_reward/std": 0.3130414053797722,
+      "step": 200,
+      "step_time": 100.35109018562362
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2467.5,
+      "completions/max_terminated_length": 2375.0,
+      "completions/mean_length": 731.296875,
+      "completions/mean_terminated_length": 710.1114624023437,
+      "completions/min_length": 187.4,
+      "completions/min_terminated_length": 187.4,
+      "entropy": 0.28902816474437715,
+      "epoch": 1.5555555555555556,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 0.9453125,
+      "learning_rate": 4.839506172839506e-06,
+      "loss": -0.0082,
+      "num_tokens": 24149336.0,
+      "reward": 0.703125,
+      "reward_std": 0.1222528412938118,
+      "rewards/qwen_accuracy_reward/mean": 0.703125,
+      "rewards/qwen_accuracy_reward/std": 0.4237747400999069,
+      "step": 210,
+      "step_time": 78.0917964133434
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 2886.6,
+      "completions/max_terminated_length": 2886.6,
+      "completions/mean_length": 897.096875,
+      "completions/mean_terminated_length": 897.096875,
+      "completions/min_length": 191.6,
+      "completions/min_terminated_length": 191.6,
+      "entropy": 0.31183156073093415,
+      "epoch": 1.6296296296296298,
+      "frac_reward_zero_std": 0.55,
+      "grad_norm": 1.0703125,
+      "learning_rate": 4.592592592592593e-06,
+      "loss": -0.0243,
+      "num_tokens": 25347711.0,
+      "reward": 0.65625,
+      "reward_std": 0.20462808087468148,
+      "rewards/qwen_accuracy_reward/mean": 0.65625,
+      "rewards/qwen_accuracy_reward/std": 0.4532728582620621,
+      "step": 220,
+      "step_time": 93.06012930087745
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.04375,
+      "completions/max_length": 2465.6,
+      "completions/max_terminated_length": 2255.0,
+      "completions/mean_length": 999.33125,
+      "completions/mean_terminated_length": 878.30361328125,
+      "completions/min_length": 232.3,
+      "completions/min_terminated_length": 232.3,
+      "entropy": 0.3391134202480316,
+      "epoch": 1.7037037037037037,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 0.96875,
+      "learning_rate": 4.3456790123456795e-06,
+      "loss": -0.0001,
+      "num_tokens": 26642217.0,
+      "reward": 0.678125,
+      "reward_std": 0.12720139995217322,
+      "rewards/qwen_accuracy_reward/mean": 0.678125,
+      "rewards/qwen_accuracy_reward/std": 0.4184228301048279,
+      "step": 230,
+      "step_time": 88.6226040866226
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2785.9,
+      "completions/max_terminated_length": 2730.1,
+      "completions/mean_length": 909.590625,
+      "completions/mean_terminated_length": 891.3462585449219,
+      "completions/min_length": 190.4,
+      "completions/min_terminated_length": 190.4,
+      "entropy": 0.32510876506567,
+      "epoch": 1.7777777777777777,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.0078125,
+      "learning_rate": 4.098765432098766e-06,
+      "loss": -0.0166,
+      "num_tokens": 27687190.0,
+      "reward": 0.50625,
+      "reward_std": 0.09932401403784752,
+      "rewards/qwen_accuracy_reward/mean": 0.50625,
+      "rewards/qwen_accuracy_reward/std": 0.48888437151908876,
+      "step": 240,
+      "step_time": 88.031781095732
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 3251.9,
+      "completions/max_terminated_length": 3199.1,
+      "completions/mean_length": 1043.075,
+      "completions/mean_terminated_length": 965.6980834960938,
+      "completions/min_length": 220.2,
+      "completions/min_terminated_length": 220.2,
+      "entropy": 0.3173308566212654,
+      "epoch": 1.8518518518518519,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 1.078125,
+      "learning_rate": 3.851851851851852e-06,
+      "loss": 0.0025,
+      "num_tokens": 28924038.0,
+      "reward": 0.615625,
+      "reward_std": 0.13382559418678283,
+      "rewards/qwen_accuracy_reward/mean": 0.615625,
+      "rewards/qwen_accuracy_reward/std": 0.4652743384242058,
+      "step": 250,
+      "step_time": 106.19994000922888
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.021875,
+      "completions/max_length": 2887.5,
+      "completions/max_terminated_length": 2873.7,
+      "completions/mean_length": 1157.359375,
+      "completions/mean_terminated_length": 1113.9273681640625,
+      "completions/min_length": 301.1,
+      "completions/min_terminated_length": 301.1,
+      "entropy": 0.3402048021554947,
+      "epoch": 1.925925925925926,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.69921875,
+      "learning_rate": 3.6049382716049387e-06,
+      "loss": 0.052,
+      "num_tokens": 30091337.0,
+      "reward": 0.715625,
+      "reward_std": 0.0889025278389454,
+      "rewards/qwen_accuracy_reward/mean": 0.715625,
+      "rewards/qwen_accuracy_reward/std": 0.32325668483972547,
+      "step": 260,
+      "step_time": 91.37333038905635
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.021875,
+      "completions/max_length": 2470.1,
+      "completions/max_terminated_length": 2292.8,
+      "completions/mean_length": 843.490625,
+      "completions/mean_terminated_length": 775.8818176269531,
+      "completions/min_length": 177.1,
+      "completions/min_terminated_length": 177.1,
+      "entropy": 0.2989307105541229,
+      "epoch": 2.0,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.358024691358025e-06,
+      "loss": 0.0466,
+      "num_tokens": 31255966.0,
+      "reward": 0.603125,
+      "reward_std": 0.07963935881853104,
+      "rewards/qwen_accuracy_reward/mean": 0.603125,
+      "rewards/qwen_accuracy_reward/std": 0.42693530917167666,
+      "step": 270,
+      "step_time": 89.96300350194797
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.009375,
+      "completions/max_length": 2517.0,
+      "completions/max_terminated_length": 2420.1,
+      "completions/mean_length": 888.171875,
+      "completions/mean_terminated_length": 862.066357421875,
+      "completions/min_length": 248.3,
+      "completions/min_terminated_length": 248.3,
+      "entropy": 0.31943089663982394,
+      "epoch": 2.074074074074074,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.0098,
+      "num_tokens": 32377037.0,
+      "reward": 0.690625,
+      "reward_std": 0.08301232233643532,
+      "rewards/qwen_accuracy_reward/mean": 0.690625,
+      "rewards/qwen_accuracy_reward/std": 0.41344006955623624,
+      "step": 280,
+      "step_time": 89.49578351443634
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.01875,
+      "completions/max_length": 2672.4,
+      "completions/max_terminated_length": 2588.6,
+      "completions/mean_length": 996.834375,
+      "completions/mean_terminated_length": 938.0544189453125,
+      "completions/min_length": 215.1,
+      "completions/min_terminated_length": 215.1,
+      "entropy": 0.32308214008808134,
+      "epoch": 2.148148148148148,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 0.0,
+      "learning_rate": 2.864197530864198e-06,
+      "loss": 0.0158,
+      "num_tokens": 33522664.0,
+      "reward": 0.69375,
+      "reward_std": 0.1285673774778843,
+      "rewards/qwen_accuracy_reward/mean": 0.69375,
+      "rewards/qwen_accuracy_reward/std": 0.37902161926031114,
+      "step": 290,
+      "step_time": 86.68293683826923
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2608.0,
+      "completions/max_terminated_length": 2520.2,
+      "completions/mean_length": 946.959375,
+      "completions/mean_terminated_length": 928.6271118164062,
+      "completions/min_length": 270.5,
+      "completions/min_terminated_length": 270.5,
+      "entropy": 0.3524158984422684,
+      "epoch": 2.2222222222222223,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 0.7890625,
+      "learning_rate": 2.617283950617284e-06,
+      "loss": -0.0148,
+      "num_tokens": 34700627.0,
+      "reward": 0.65625,
+      "reward_std": 0.11973364129662514,
+      "rewards/qwen_accuracy_reward/mean": 0.65625,
+      "rewards/qwen_accuracy_reward/std": 0.41356782615184784,
+      "step": 300,
+      "step_time": 87.42863798243926
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0125,
+      "completions/max_length": 2972.9,
+      "completions/max_terminated_length": 2897.5,
+      "completions/mean_length": 988.09375,
+      "completions/mean_terminated_length": 950.5379272460938,
+      "completions/min_length": 178.1,
+      "completions/min_terminated_length": 178.1,
+      "entropy": 0.35300183594226836,
+      "epoch": 2.2962962962962963,
+      "frac_reward_zero_std": 0.675,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3703703703703707e-06,
+      "loss": 0.0343,
+      "num_tokens": 35737041.0,
+      "reward": 0.696875,
+      "reward_std": 0.13173072263598443,
+      "rewards/qwen_accuracy_reward/mean": 0.696875,
+      "rewards/qwen_accuracy_reward/std": 0.3739522725343704,
+      "step": 310,
+      "step_time": 91.70364078907296
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 3188.5,
+      "completions/max_terminated_length": 3128.3,
+      "completions/mean_length": 1083.1125,
+      "completions/mean_terminated_length": 1040.7671630859375,
+      "completions/min_length": 210.6,
+      "completions/min_terminated_length": 210.6,
+      "entropy": 0.3282592862844467,
+      "epoch": 2.3703703703703702,
+      "frac_reward_zero_std": 0.675,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2.123456790123457e-06,
+      "loss": -0.0189,
+      "num_tokens": 37111573.0,
+      "reward": 0.55625,
+      "reward_std": 0.13625495061278342,
+      "rewards/qwen_accuracy_reward/mean": 0.55625,
+      "rewards/qwen_accuracy_reward/std": 0.44359574764966964,
+      "step": 320,
+      "step_time": 111.29351590340957
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 2530.0,
+      "completions/max_terminated_length": 2530.0,
+      "completions/mean_length": 861.1625,
+      "completions/mean_terminated_length": 861.1625,
+      "completions/min_length": 237.2,
+      "completions/min_terminated_length": 237.2,
+      "entropy": 0.33077896386384964,
+      "epoch": 2.4444444444444446,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.8765432098765435e-06,
+      "loss": -0.0035,
+      "num_tokens": 38235497.0,
+      "reward": 0.753125,
+      "reward_std": 0.06712496280670166,
+      "rewards/qwen_accuracy_reward/mean": 0.753125,
+      "rewards/qwen_accuracy_reward/std": 0.3345354929566383,
+      "step": 330,
+      "step_time": 85.06333898054436
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 2847.5,
+      "completions/max_terminated_length": 2795.2,
+      "completions/mean_length": 959.253125,
+      "completions/mean_terminated_length": 913.3017211914063,
+      "completions/min_length": 206.6,
+      "completions/min_terminated_length": 206.6,
+      "entropy": 0.31485441625118255,
+      "epoch": 2.5185185185185186,
+      "frac_reward_zero_std": 0.725,
+      "grad_norm": 0.97265625,
+      "learning_rate": 1.62962962962963e-06,
+      "loss": -0.0131,
+      "num_tokens": 39410138.0,
+      "reward": 0.703125,
+      "reward_std": 0.11089480444788932,
+      "rewards/qwen_accuracy_reward/mean": 0.703125,
+      "rewards/qwen_accuracy_reward/std": 0.40059446543455124,
+      "step": 340,
+      "step_time": 96.2432292709127
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.01875,
+      "completions/max_length": 2841.1,
+      "completions/max_terminated_length": 2761.6,
+      "completions/mean_length": 977.59375,
+      "completions/mean_terminated_length": 932.3578735351563,
+      "completions/min_length": 218.1,
+      "completions/min_terminated_length": 218.1,
+      "entropy": 0.32475618124008176,
+      "epoch": 2.5925925925925926,
+      "frac_reward_zero_std": 0.675,
+      "grad_norm": 0.703125,
+      "learning_rate": 1.382716049382716e-06,
+      "loss": -0.0032,
+      "num_tokens": 40474160.0,
+      "reward": 0.596875,
+      "reward_std": 0.1422400951385498,
+      "rewards/qwen_accuracy_reward/mean": 0.596875,
+      "rewards/qwen_accuracy_reward/std": 0.44790197908878326,
+      "step": 350,
+      "step_time": 94.29619938712567
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0375,
+      "completions/max_length": 2836.5,
+      "completions/max_terminated_length": 2630.0,
+      "completions/mean_length": 953.403125,
+      "completions/mean_terminated_length": 836.7918395996094,
+      "completions/min_length": 182.6,
+      "completions/min_terminated_length": 182.6,
+      "entropy": 0.29742794930934907,
+      "epoch": 2.6666666666666665,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.1358024691358026e-06,
+      "loss": 0.0334,
+      "num_tokens": 41924201.0,
+      "reward": 0.540625,
+      "reward_std": 0.13288394510746002,
+      "rewards/qwen_accuracy_reward/mean": 0.540625,
+      "rewards/qwen_accuracy_reward/std": 0.4684432566165924,
+      "step": 360,
+      "step_time": 92.4419061298482
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.009375,
+      "completions/max_length": 2586.9,
+      "completions/max_terminated_length": 2387.2,
+      "completions/mean_length": 884.53125,
+      "completions/mean_terminated_length": 859.0074462890625,
+      "completions/min_length": 216.4,
+      "completions/min_terminated_length": 216.4,
+      "entropy": 0.3111660867929459,
+      "epoch": 2.7407407407407405,
+      "frac_reward_zero_std": 0.65,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 0.0232,
+      "num_tokens": 43079411.0,
+      "reward": 0.678125,
+      "reward_std": 0.15970305502414703,
+      "rewards/qwen_accuracy_reward/mean": 0.678125,
+      "rewards/qwen_accuracy_reward/std": 0.44499066174030305,
+      "step": 370,
+      "step_time": 87.8870439321734
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.015625,
+      "completions/max_length": 2993.8,
+      "completions/max_terminated_length": 2757.8,
+      "completions/mean_length": 884.4375,
+      "completions/mean_terminated_length": 836.5636779785157,
+      "completions/min_length": 203.2,
+      "completions/min_terminated_length": 203.2,
+      "entropy": 0.3149792984127998,
+      "epoch": 2.814814814814815,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 1.109375,
+      "learning_rate": 6.419753086419754e-07,
+      "loss": 0.0361,
+      "num_tokens": 44174927.0,
+      "reward": 0.64375,
+      "reward_std": 0.10931411162018775,
+      "rewards/qwen_accuracy_reward/mean": 0.64375,
+      "rewards/qwen_accuracy_reward/std": 0.4142391666769981,
+      "step": 380,
+      "step_time": 102.23014580868184
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00625,
+      "completions/max_length": 2648.8,
+      "completions/max_terminated_length": 2561.9,
+      "completions/mean_length": 792.796875,
+      "completions/mean_terminated_length": 774.4787231445313,
+      "completions/min_length": 213.6,
+      "completions/min_terminated_length": 213.6,
+      "entropy": 0.3075984627008438,
+      "epoch": 2.888888888888889,
+      "frac_reward_zero_std": 0.775,
+      "grad_norm": 0.7890625,
+      "learning_rate": 3.9506172839506174e-07,
+      "loss": 0.0105,
+      "num_tokens": 45515390.0,
+      "reward": 0.625,
+      "reward_std": 0.09910930022597313,
+      "rewards/qwen_accuracy_reward/mean": 0.625,
+      "rewards/qwen_accuracy_reward/std": 0.4127164900302887,
+      "step": 390,
+      "step_time": 94.27956027435138
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 2960.8,
+      "completions/max_terminated_length": 2754.7,
+      "completions/mean_length": 1044.615625,
+      "completions/mean_terminated_length": 961.3511047363281,
+      "completions/min_length": 202.3,
+      "completions/min_terminated_length": 202.3,
+      "entropy": 0.3200776308774948,
+      "epoch": 2.962962962962963,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4814814814814817e-07,
+      "loss": 0.0416,
+      "num_tokens": 46797883.0,
+      "reward": 0.690625,
+      "reward_std": 0.18148061260581017,
+      "rewards/qwen_accuracy_reward/mean": 0.690625,
+      "rewards/qwen_accuracy_reward/std": 0.4207667887210846,
+      "step": 400,
+      "step_time": 98.57531574275345
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 405,
+  "num_input_tokens_seen": 47401625,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f568df06f3257638cc297d2262f06ad97dd20fe58e0663dc4e613dd621cb36
+size 7096