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 sha256:2560d39ca86873138060108722789ef6673658ae16517a6ac6361b0b7e9f1641
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2224d33ed62c4adfe2c4d44a79c96e84479847194b9a39743a0803904dbe12a2
+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:fdb8671399ec4c5bca33ea643e05e16db6cc2b414116b1d89f263d3d6a8ca3da
+size 16090217224

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3adcc012f6add74231d9adbee53311e577ad2cfdeddb826c1ce561df868ea5
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa32417f440cbd114483de7bfea8d3b13b43ac2e11e3d2a7a039f1441d9680a9
+size 15920

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350b02fb5c703db39010addbd874720a46539b020cc7f33df71064feef7d28cb
+size 15920

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82431ef0900cff5c350d673d7a3338290eba668499d3bf1841bb53f02a2d8617
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a9c5ccacb211611d1713e6c963ce6b861b9d8aeb1850ac07e1792bcad967a4
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ac5c0158090ef9f2a1778afbfec05b2e967555bfb8d0fa7a77e88b900092ba
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe1558e78f9a8dc088b61327a14cf41bfc3019206fa065f125447ec46fa6e67
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fad2b308941f76425e71264dbf8a5a206d5df40f14b824a8ad3432bb3e33bc8
+size 15920

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d749dec336a7eed1620833d398ef1809f14d63c6180401c86817ba2671f5fd8a
+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 +1,2518 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 921,
+  "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": 0.034375,
+      "completions/max_length": 2677.6,
+      "completions/max_terminated_length": 2598.3,
+      "completions/mean_length": 1001.065625,
+      "completions/mean_terminated_length": 917.1349365234375,
+      "completions/min_length": 241.5,
+      "completions/min_terminated_length": 241.5,
+      "entropy": 0.333204485476017,
+      "epoch": 0.03257328990228013,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.65234375,
+      "learning_rate": 9.90228013029316e-06,
+      "loss": 0.0174,
+      "num_tokens": 439045.0,
+      "reward": 0.43125,
+      "reward_std": 0.09436839669942856,
+      "rewards/qwen_accuracy_reward/mean": 0.43125,
+      "rewards/qwen_accuracy_reward/std": 0.37916621267795564,
+      "step": 10,
+      "step_time": 71.61828093789518
+    },
+    {
+      "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": 3279.5,
+      "completions/max_terminated_length": 3047.0,
+      "completions/mean_length": 1331.078125,
+      "completions/mean_terminated_length": 1259.9069458007812,
+      "completions/min_length": 249.8,
+      "completions/min_terminated_length": 249.8,
+      "entropy": 0.4010499566793442,
+      "epoch": 0.06514657980456026,
+      "frac_reward_zero_std": 0.6,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.79370249728556e-06,
+      "loss": 0.0164,
+      "num_tokens": 963294.0,
+      "reward": 0.484375,
+      "reward_std": 0.18727783858776093,
+      "rewards/qwen_accuracy_reward/mean": 0.484375,
+      "rewards/qwen_accuracy_reward/std": 0.4520114839076996,
+      "step": 20,
+      "step_time": 87.72073962157592
+    },
+    {
+      "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": 2875.3,
+      "completions/max_terminated_length": 2534.2,
+      "completions/mean_length": 1027.8875,
+      "completions/mean_terminated_length": 924.80517578125,
+      "completions/min_length": 219.2,
+      "completions/min_terminated_length": 219.2,
+      "entropy": 0.3684565082192421,
+      "epoch": 0.09771986970684039,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.84375,
+      "learning_rate": 9.68512486427796e-06,
+      "loss": -0.0268,
+      "num_tokens": 1391226.0,
+      "reward": 0.60625,
+      "reward_std": 0.08984613344073296,
+      "rewards/qwen_accuracy_reward/mean": 0.60625,
+      "rewards/qwen_accuracy_reward/std": 0.47234617471694945,
+      "step": 30,
+      "step_time": 76.90530362166464
+    },
+    {
+      "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": 2603.9,
+      "completions/max_terminated_length": 2559.9,
+      "completions/mean_length": 906.215625,
+      "completions/mean_terminated_length": 888.0654052734375,
+      "completions/min_length": 230.5,
+      "completions/min_terminated_length": 230.5,
+      "entropy": 0.350618913769722,
+      "epoch": 0.13029315960912052,
+      "frac_reward_zero_std": 0.8,
+      "grad_norm": 0.0,
+      "learning_rate": 9.576547231270358e-06,
+      "loss": 0.0068,
+      "num_tokens": 1789591.0,
+      "reward": 0.71875,
+      "reward_std": 0.08206871449947357,
+      "rewards/qwen_accuracy_reward/mean": 0.71875,
+      "rewards/qwen_accuracy_reward/std": 0.4095485180616379,
+      "step": 40,
+      "step_time": 69.04101052414626
+    },
+    {
+      "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": 0.03125,
+      "completions/max_length": 2860.0,
+      "completions/max_terminated_length": 2853.8,
+      "completions/mean_length": 1064.771875,
+      "completions/mean_terminated_length": 990.3612426757812,
+      "completions/min_length": 282.9,
+      "completions/min_terminated_length": 282.9,
+      "entropy": 0.36633683890104296,
+      "epoch": 0.16286644951140064,
+      "frac_reward_zero_std": 0.7,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.467969598262759e-06,
+      "loss": -0.0447,
+      "num_tokens": 2257246.0,
+      "reward": 0.753125,
+      "reward_std": 0.12656745240092276,
+      "rewards/qwen_accuracy_reward/mean": 0.753125,
+      "rewards/qwen_accuracy_reward/std": 0.34750270247459414,
+      "step": 50,
+      "step_time": 75.63329665400087
+    },
+    {
+      "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": 3409.6,
+      "completions/max_terminated_length": 3273.6,
+      "completions/mean_length": 1275.78125,
+      "completions/mean_terminated_length": 1222.5706176757812,
+      "completions/min_length": 266.0,
+      "completions/min_terminated_length": 266.0,
+      "entropy": 0.3917502075433731,
+      "epoch": 0.19543973941368079,
+      "frac_reward_zero_std": 0.625,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.359391965255158e-06,
+      "loss": 0.0374,
+      "num_tokens": 2777864.0,
+      "reward": 0.721875,
+      "reward_std": 0.17485642284154893,
+      "rewards/qwen_accuracy_reward/mean": 0.721875,
+      "rewards/qwen_accuracy_reward/std": 0.4061304032802582,
+      "step": 60,
+      "step_time": 88.08973164549097
+    },
+    {
+      "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": 3239.4,
+      "completions/max_terminated_length": 3136.2,
+      "completions/mean_length": 1192.175,
+      "completions/mean_terminated_length": 1105.1968688964844,
+      "completions/min_length": 274.1,
+      "completions/min_terminated_length": 274.1,
+      "entropy": 0.3692863553762436,
+      "epoch": 0.2280130293159609,
+      "frac_reward_zero_std": 0.675,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.250814332247557e-06,
+      "loss": 0.0222,
+      "num_tokens": 3293904.0,
+      "reward": 0.71875,
+      "reward_std": 0.1526545248925686,
+      "rewards/qwen_accuracy_reward/mean": 0.71875,
+      "rewards/qwen_accuracy_reward/std": 0.4149239182472229,
+      "step": 70,
+      "step_time": 86.97396173980087
+    },
+    {
+      "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": 0.078125,
+      "completions/max_length": 3480.3,
+      "completions/max_terminated_length": 3033.2,
+      "completions/mean_length": 1291.58125,
+      "completions/mean_terminated_length": 1050.9552062988282,
+      "completions/min_length": 258.4,
+      "completions/min_terminated_length": 258.4,
+      "entropy": 0.36572070717811583,
+      "epoch": 0.26058631921824105,
+      "frac_reward_zero_std": 0.775,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.142236699239957e-06,
+      "loss": 0.0703,
+      "num_tokens": 3843402.0,
+      "reward": 0.8,
+      "reward_std": 0.10005094558000564,
+      "rewards/qwen_accuracy_reward/mean": 0.8,
+      "rewards/qwen_accuracy_reward/std": 0.30182539820671084,
+      "step": 80,
+      "step_time": 95.39563230751082
+    },
+    {
+      "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": 3299.5,
+      "completions/max_terminated_length": 3093.0,
+      "completions/mean_length": 1185.8125,
+      "completions/mean_terminated_length": 1162.4843627929688,
+      "completions/min_length": 290.0,
+      "completions/min_terminated_length": 290.0,
+      "entropy": 0.3959953486919403,
+      "epoch": 0.2931596091205212,
+      "frac_reward_zero_std": 0.775,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.033659066232356e-06,
+      "loss": 0.0449,
+      "num_tokens": 4335982.0,
+      "reward": 0.809375,
+      "reward_std": 0.0945850744843483,
+      "rewards/qwen_accuracy_reward/mean": 0.809375,
+      "rewards/qwen_accuracy_reward/std": 0.31030095368623734,
+      "step": 90,
+      "step_time": 88.77400590376928
+    },
+    {
+      "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": 0.05,
+      "completions/max_length": 3318.0,
+      "completions/max_terminated_length": 2993.6,
+      "completions/mean_length": 1281.775,
+      "completions/mean_terminated_length": 1150.3262939453125,
+      "completions/min_length": 289.3,
+      "completions/min_terminated_length": 289.3,
+      "entropy": 0.3654392659664154,
+      "epoch": 0.3257328990228013,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.486328125,
+      "learning_rate": 8.925081433224755e-06,
+      "loss": 0.051,
+      "num_tokens": 4886374.0,
+      "reward": 0.8125,
+      "reward_std": 0.06849094033241272,
+      "rewards/qwen_accuracy_reward/mean": 0.8125,
+      "rewards/qwen_accuracy_reward/std": 0.2677406892180443,
+      "step": 100,
+      "step_time": 92.20114967450499
+    },
+    {
+      "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": 3308.2,
+      "completions/max_terminated_length": 2944.0,
+      "completions/mean_length": 1175.375,
+      "completions/mean_terminated_length": 1139.4002807617187,
+      "completions/min_length": 267.7,
+      "completions/min_terminated_length": 267.7,
+      "entropy": 0.3834399998188019,
+      "epoch": 0.3583061889250814,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.734375,
+      "learning_rate": 8.816503800217156e-06,
+      "loss": 0.0177,
+      "num_tokens": 5404430.0,
+      "reward": 0.7875,
+      "reward_std": 0.06870565414428711,
+      "rewards/qwen_accuracy_reward/mean": 0.7875,
+      "rewards/qwen_accuracy_reward/std": 0.2738855093717575,
+      "step": 110,
+      "step_time": 88.0384052307345
+    },
+    {
+      "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": 0.078125,
+      "completions/max_length": 3146.0,
+      "completions/max_terminated_length": 2604.6,
+      "completions/mean_length": 1137.178125,
+      "completions/mean_terminated_length": 888.4818664550781,
+      "completions/min_length": 235.5,
+      "completions/min_terminated_length": 235.5,
+      "entropy": 0.3079161733388901,
+      "epoch": 0.39087947882736157,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.707926167209557e-06,
+      "loss": 0.0605,
+      "num_tokens": 5908263.0,
+      "reward": 0.875,
+      "reward_std": 0.04692808985710144,
+      "rewards/qwen_accuracy_reward/mean": 0.875,
+      "rewards/qwen_accuracy_reward/std": 0.2187224417924881,
+      "step": 120,
+      "step_time": 86.96171942604705
+    },
+    {
+      "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": 2680.8,
+      "completions/max_terminated_length": 2673.8,
+      "completions/mean_length": 1002.196875,
+      "completions/mean_terminated_length": 993.0019165039063,
+      "completions/min_length": 270.1,
+      "completions/min_terminated_length": 270.1,
+      "entropy": 0.34904909133911133,
+      "epoch": 0.4234527687296417,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 0.81640625,
+      "learning_rate": 8.599348534201956e-06,
+      "loss": 0.0263,
+      "num_tokens": 6346214.0,
+      "reward": 0.903125,
+      "reward_std": 0.06533465310931205,
+      "rewards/qwen_accuracy_reward/mean": 0.903125,
+      "rewards/qwen_accuracy_reward/std": 0.19970145374536513,
+      "step": 130,
+      "step_time": 71.75175027744845
+    },
+    {
+      "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": 2802.7,
+      "completions/max_terminated_length": 2403.3,
+      "completions/mean_length": 861.221875,
+      "completions/mean_terminated_length": 840.4104766845703,
+      "completions/min_length": 236.7,
+      "completions/min_terminated_length": 236.7,
+      "entropy": 0.3106671258807182,
+      "epoch": 0.4560260586319218,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.59765625,
+      "learning_rate": 8.490770901194355e-06,
+      "loss": 0.0721,
+      "num_tokens": 6753109.0,
+      "reward": 0.8875,
+      "reward_std": 0.07827338129281998,
+      "rewards/qwen_accuracy_reward/mean": 0.8875,
+      "rewards/qwen_accuracy_reward/std": 0.2551010876893997,
+      "step": 140,
+      "step_time": 77.07738372143358
+    },
+    {
+      "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": 2352.7,
+      "completions/max_terminated_length": 2317.1,
+      "completions/mean_length": 829.49375,
+      "completions/mean_terminated_length": 811.7066772460937,
+      "completions/min_length": 222.1,
+      "completions/min_terminated_length": 222.1,
+      "entropy": 0.2921102657914162,
+      "epoch": 0.48859934853420195,
+      "frac_reward_zero_std": 0.775,
+      "grad_norm": 0.8125,
+      "learning_rate": 8.382193268186755e-06,
+      "loss": 0.0156,
+      "num_tokens": 7138907.0,
+      "reward": 0.8875,
+      "reward_std": 0.09679971560835839,
+      "rewards/qwen_accuracy_reward/mean": 0.8875,
+      "rewards/qwen_accuracy_reward/std": 0.2569649308919907,
+      "step": 150,
+      "step_time": 64.74061961406842
+    },
+    {
+      "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": 2155.2,
+      "completions/max_terminated_length": 2155.2,
+      "completions/mean_length": 743.490625,
+      "completions/mean_terminated_length": 743.490625,
+      "completions/min_length": 204.6,
+      "completions/min_terminated_length": 204.6,
+      "entropy": 0.29313592314720155,
+      "epoch": 0.5211726384364821,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 8.273615635179154e-06,
+      "loss": 0.0272,
+      "num_tokens": 7488424.0,
+      "reward": 0.8875,
+      "reward_std": 0.02177756354212761,
+      "rewards/qwen_accuracy_reward/mean": 0.8875,
+      "rewards/qwen_accuracy_reward/std": 0.18192448019981383,
+      "step": 160,
+      "step_time": 56.19097121860832
+    },
+    {
+      "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": 2440.0,
+      "completions/max_terminated_length": 2440.0,
+      "completions/mean_length": 844.440625,
+      "completions/mean_terminated_length": 844.440625,
+      "completions/min_length": 251.0,
+      "completions/min_terminated_length": 251.0,
+      "entropy": 0.29565098136663437,
+      "epoch": 0.5537459283387622,
+      "frac_reward_zero_std": 0.825,
+      "grad_norm": 0.0,
+      "learning_rate": 8.165038002171553e-06,
+      "loss": -0.0086,
+      "num_tokens": 7878501.0,
+      "reward": 0.93125,
+      "reward_std": 0.0800636924803257,
+      "rewards/qwen_accuracy_reward/mean": 0.93125,
+      "rewards/qwen_accuracy_reward/std": 0.16346374601125718,
+      "step": 170,
+      "step_time": 66.09473502421751
+    },
+    {
+      "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": 2379.1,
+      "completions/max_terminated_length": 2154.0,
+      "completions/mean_length": 784.996875,
+      "completions/mean_terminated_length": 766.0695556640625,
+      "completions/min_length": 255.2,
+      "completions/min_terminated_length": 255.2,
+      "entropy": 0.2795317336916924,
+      "epoch": 0.5863192182410424,
+      "frac_reward_zero_std": 0.85,
+      "grad_norm": 1.140625,
+      "learning_rate": 8.056460369163954e-06,
+      "loss": 0.0167,
+      "num_tokens": 8256812.0,
+      "reward": 0.9125,
+      "reward_std": 0.05850084200501442,
+      "rewards/qwen_accuracy_reward/mean": 0.9125,
+      "rewards/qwen_accuracy_reward/std": 0.16458767354488374,
+      "step": 180,
+      "step_time": 65.01561901448295
+    },
+    {
+      "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": 2328.6,
+      "completions/max_terminated_length": 2320.4,
+      "completions/mean_length": 850.88125,
+      "completions/mean_terminated_length": 841.9321533203125,
+      "completions/min_length": 216.4,
+      "completions/min_terminated_length": 216.4,
+      "entropy": 0.27169933915138245,
+      "epoch": 0.6188925081433225,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 7.947882736156353e-06,
+      "loss": 0.0007,
+      "num_tokens": 8652902.0,
+      "reward": 0.921875,
+      "reward_std": 0.03377464786171913,
+      "rewards/qwen_accuracy_reward/mean": 0.921875,
+      "rewards/qwen_accuracy_reward/std": 0.15925233066082,
+      "step": 190,
+      "step_time": 64.30843478655443
+    },
+    {
+      "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": 1819.1,
+      "completions/max_terminated_length": 1723.5,
+      "completions/mean_length": 664.359375,
+      "completions/mean_terminated_length": 614.3344909667969,
+      "completions/min_length": 223.3,
+      "completions/min_terminated_length": 223.3,
+      "entropy": 0.2222038835287094,
+      "epoch": 0.6514657980456026,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 7.839305103148752e-06,
+      "loss": 0.0265,
+      "num_tokens": 9018561.0,
+      "reward": 0.921875,
+      "reward_std": 0.036084231734275815,
+      "rewards/qwen_accuracy_reward/mean": 0.921875,
+      "rewards/qwen_accuracy_reward/std": 0.1368771880865097,
+      "step": 200,
+      "step_time": 50.43694004062563
+    },
+    {
+      "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": 2158.4,
+      "completions/max_terminated_length": 2132.2,
+      "completions/mean_length": 757.484375,
+      "completions/mean_terminated_length": 726.5084045410156,
+      "completions/min_length": 216.3,
+      "completions/min_terminated_length": 216.3,
+      "entropy": 0.253067896515131,
+      "epoch": 0.6840390879478827,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.85546875,
+      "learning_rate": 7.730727470141152e-06,
+      "loss": 0.0208,
+      "num_tokens": 9369284.0,
+      "reward": 0.934375,
+      "reward_std": 0.04807935431599617,
+      "rewards/qwen_accuracy_reward/mean": 0.934375,
+      "rewards/qwen_accuracy_reward/std": 0.1333692654967308,
+      "step": 210,
+      "step_time": 58.671303189732136
+    },
+    {
+      "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": 1711.7,
+      "completions/max_terminated_length": 1711.7,
+      "completions/mean_length": 662.759375,
+      "completions/mean_terminated_length": 662.759375,
+      "completions/min_length": 224.6,
+      "completions/min_terminated_length": 224.6,
+      "entropy": 0.2540799155831337,
+      "epoch": 0.7166123778501629,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 7.622149837133551e-06,
+      "loss": 0.0035,
+      "num_tokens": 9696887.0,
+      "reward": 0.9625,
+      "reward_std": 0.013363061845302582,
+      "rewards/qwen_accuracy_reward/mean": 0.9625,
+      "rewards/qwen_accuracy_reward/std": 0.07759521007537842,
+      "step": 220,
+      "step_time": 45.685889296606184
+    },
+    {
+      "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": 2240.7,
+      "completions/max_terminated_length": 2240.7,
+      "completions/mean_length": 768.94375,
+      "completions/mean_terminated_length": 768.94375,
+      "completions/min_length": 243.2,
+      "completions/min_terminated_length": 243.2,
+      "entropy": 0.2813176602125168,
+      "epoch": 0.749185667752443,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 1.2890625,
+      "learning_rate": 7.51357220412595e-06,
+      "loss": 0.0152,
+      "num_tokens": 10058373.0,
+      "reward": 0.9375,
+      "reward_std": 0.04492306634783745,
+      "rewards/qwen_accuracy_reward/mean": 0.9375,
+      "rewards/qwen_accuracy_reward/std": 0.12228720486164094,
+      "step": 230,
+      "step_time": 61.028474612068386
+    },
+    {
+      "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": 2169.4,
+      "completions/max_terminated_length": 2132.5,
+      "completions/mean_length": 739.503125,
+      "completions/mean_terminated_length": 698.6049133300781,
+      "completions/min_length": 218.8,
+      "completions/min_terminated_length": 218.8,
+      "entropy": 0.2684470996260643,
+      "epoch": 0.7817589576547231,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 7.40499457111835e-06,
+      "loss": 0.0125,
+      "num_tokens": 10432006.0,
+      "reward": 0.9875,
+      "reward_std": 0.013363061845302582,
+      "rewards/qwen_accuracy_reward/mean": 0.9875,
+      "rewards/qwen_accuracy_reward/std": 0.033601075410842896,
+      "step": 240,
+      "step_time": 59.92722728513181
+    },
+    {
+      "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": 2439.9,
+      "completions/max_terminated_length": 2386.6,
+      "completions/mean_length": 835.70625,
+      "completions/mean_terminated_length": 818.9010498046875,
+      "completions/min_length": 245.0,
+      "completions/min_terminated_length": 245.0,
+      "entropy": 0.2859576910734177,
+      "epoch": 0.8143322475570033,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 7.29641693811075e-06,
+      "loss": -0.0021,
+      "num_tokens": 10838408.0,
+      "reward": 0.959375,
+      "reward_std": 0.0245114803314209,
+      "rewards/qwen_accuracy_reward/mean": 0.959375,
+      "rewards/qwen_accuracy_reward/std": 0.09820206016302109,
+      "step": 250,
+      "step_time": 67.63989680018275
+    },
+    {
+      "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": 2440.0,
+      "completions/max_terminated_length": 2378.2,
+      "completions/mean_length": 839.625,
+      "completions/mean_terminated_length": 821.0300048828125,
+      "completions/min_length": 248.6,
+      "completions/min_terminated_length": 248.6,
+      "entropy": 0.28902051597833633,
+      "epoch": 0.8469055374592834,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.84765625,
+      "learning_rate": 7.187839305103149e-06,
+      "loss": 0.0337,
+      "num_tokens": 11218088.0,
+      "reward": 0.9625,
+      "reward_std": 0.02925042062997818,
+      "rewards/qwen_accuracy_reward/mean": 0.9625,
+      "rewards/qwen_accuracy_reward/std": 0.08795147836208343,
+      "step": 260,
+      "step_time": 63.1799141773954
+    },
+    {
+      "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": 2544.2,
+      "completions/max_terminated_length": 2490.8,
+      "completions/mean_length": 1000.415625,
+      "completions/mean_terminated_length": 918.9749755859375,
+      "completions/min_length": 284.6,
+      "completions/min_terminated_length": 284.6,
+      "entropy": 0.29957995414733884,
+      "epoch": 0.8794788273615635,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.079261672095549e-06,
+      "loss": 0.0121,
+      "num_tokens": 11668661.0,
+      "reward": 0.934375,
+      "reward_std": 0.03061639815568924,
+      "rewards/qwen_accuracy_reward/mean": 0.934375,
+      "rewards/qwen_accuracy_reward/std": 0.10957810133695603,
+      "step": 270,
+      "step_time": 69.61986783705652
+    },
+    {
+      "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": 2133.8,
+      "completions/max_terminated_length": 2133.8,
+      "completions/mean_length": 713.509375,
+      "completions/mean_terminated_length": 713.509375,
+      "completions/min_length": 233.5,
+      "completions/min_terminated_length": 233.5,
+      "entropy": 0.2510858058929443,
+      "epoch": 0.9120521172638436,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 6.9706840390879485e-06,
+      "loss": 0.0135,
+      "num_tokens": 12023072.0,
+      "reward": 0.996875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.996875,
+      "rewards/qwen_accuracy_reward/std": 0.01767766922712326,
+      "step": 280,
+      "step_time": 58.07799549689516
+    },
+    {
+      "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": 2090.7,
+      "completions/max_terminated_length": 2090.7,
+      "completions/mean_length": 697.66875,
+      "completions/mean_terminated_length": 697.66875,
+      "completions/min_length": 241.0,
+      "completions/min_terminated_length": 241.0,
+      "entropy": 0.2558185949921608,
+      "epoch": 0.9446254071661238,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.0,
+      "learning_rate": 6.8621064060803475e-06,
+      "loss": 0.0112,
+      "num_tokens": 12353414.0,
+      "reward": 0.925,
+      "reward_std": 0.051027984172105786,
+      "rewards/qwen_accuracy_reward/mean": 0.925,
+      "rewards/qwen_accuracy_reward/std": 0.16133979260921477,
+      "step": 290,
+      "step_time": 56.3230952934362
+    },
+    {
+      "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": 1713.9,
+      "completions/max_terminated_length": 1713.9,
+      "completions/mean_length": 610.203125,
+      "completions/mean_terminated_length": 610.203125,
+      "completions/min_length": 240.8,
+      "completions/min_terminated_length": 240.8,
+      "entropy": 0.24070774465799333,
+      "epoch": 0.9771986970684039,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 6.753528773072747e-06,
+      "loss": 0.0173,
+      "num_tokens": 12681759.0,
+      "reward": 0.965625,
+      "reward_std": 0.02041158601641655,
+      "rewards/qwen_accuracy_reward/mean": 0.965625,
+      "rewards/qwen_accuracy_reward/std": 0.08626527190208436,
+      "step": 300,
+      "step_time": 47.36222105557099
+    },
+    {
+      "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": 2020.4,
+      "completions/max_terminated_length": 2020.4,
+      "completions/mean_length": 677.00625,
+      "completions/mean_terminated_length": 677.00625,
+      "completions/min_length": 225.1,
+      "completions/min_terminated_length": 225.1,
+      "entropy": 0.2349437654018402,
+      "epoch": 1.009771986970684,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.0,
+      "learning_rate": 6.644951140065147e-06,
+      "loss": -0.0031,
+      "num_tokens": 13024209.0,
+      "reward": 0.925,
+      "reward_std": 0.05828612819314003,
+      "rewards/qwen_accuracy_reward/mean": 0.925,
+      "rewards/qwen_accuracy_reward/std": 0.18913658261299132,
+      "step": 310,
+      "step_time": 52.18600384155288
+    },
+    {
+      "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": 2016.0,
+      "completions/max_terminated_length": 2016.0,
+      "completions/mean_length": 739.634375,
+      "completions/mean_terminated_length": 739.634375,
+      "completions/min_length": 227.1,
+      "completions/min_terminated_length": 227.1,
+      "entropy": 0.2607535943388939,
+      "epoch": 1.0423452768729642,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 6.536373507057546e-06,
+      "loss": 0.0144,
+      "num_tokens": 13373220.0,
+      "reward": 0.996875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.996875,
+      "rewards/qwen_accuracy_reward/std": 0.01767766922712326,
+      "step": 320,
+      "step_time": 56.04217133913189
+    },
+    {
+      "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": 1912.8,
+      "completions/max_terminated_length": 1912.8,
+      "completions/mean_length": 675.971875,
+      "completions/mean_terminated_length": 675.971875,
+      "completions/min_length": 248.4,
+      "completions/min_terminated_length": 248.4,
+      "entropy": 0.22910359650850295,
+      "epoch": 1.0749185667752443,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 6.427795874049946e-06,
+      "loss": 0.0149,
+      "num_tokens": 13720035.0,
+      "reward": 0.99375,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.024593468010425567,
+      "step": 330,
+      "step_time": 52.62400772022083
+    },
+    {
+      "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": 1872.4,
+      "completions/max_terminated_length": 1872.4,
+      "completions/mean_length": 671.859375,
+      "completions/mean_terminated_length": 671.859375,
+      "completions/min_length": 244.0,
+      "completions/min_terminated_length": 244.0,
+      "entropy": 0.2325178161263466,
+      "epoch": 1.1074918566775245,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 6.319218241042345e-06,
+      "loss": -0.0041,
+      "num_tokens": 14055878.0,
+      "reward": 0.996875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.996875,
+      "rewards/qwen_accuracy_reward/std": 0.01767766922712326,
+      "step": 340,
+      "step_time": 51.82339646322653
+    },
+    {
+      "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": 2325.1,
+      "completions/max_terminated_length": 2325.1,
+      "completions/mean_length": 858.025,
+      "completions/mean_terminated_length": 858.025,
+      "completions/min_length": 219.4,
+      "completions/min_terminated_length": 219.4,
+      "entropy": 0.2665655896067619,
+      "epoch": 1.1400651465798046,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.91015625,
+      "learning_rate": 6.2106406080347455e-06,
+      "loss": 0.005,
+      "num_tokens": 14447758.0,
+      "reward": 0.93125,
+      "reward_std": 0.0408231720328331,
+      "rewards/qwen_accuracy_reward/mean": 0.93125,
+      "rewards/qwen_accuracy_reward/std": 0.1350443869829178,
+      "step": 350,
+      "step_time": 64.82575829299167
+    },
+    {
+      "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": 1837.9,
+      "completions/max_terminated_length": 1837.9,
+      "completions/mean_length": 684.38125,
+      "completions/mean_terminated_length": 684.38125,
+      "completions/min_length": 237.7,
+      "completions/min_terminated_length": 237.7,
+      "entropy": 0.24428945928812026,
+      "epoch": 1.1726384364820848,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.61328125,
+      "learning_rate": 6.102062975027145e-06,
+      "loss": -0.0047,
+      "num_tokens": 14782216.0,
+      "reward": 0.953125,
+      "reward_std": 0.02651650384068489,
+      "rewards/qwen_accuracy_reward/mean": 0.953125,
+      "rewards/qwen_accuracy_reward/std": 0.10168035477399825,
+      "step": 360,
+      "step_time": 46.66475373953581
+    },
+    {
+      "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": 1696.2,
+      "completions/max_terminated_length": 1696.2,
+      "completions/mean_length": 668.06875,
+      "completions/mean_terminated_length": 668.06875,
+      "completions/min_length": 227.5,
+      "completions/min_terminated_length": 227.5,
+      "entropy": 0.23859673142433166,
+      "epoch": 1.205211726384365,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 5.993485342019545e-06,
+      "loss": 0.0012,
+      "num_tokens": 15108926.0,
+      "reward": 0.903125,
+      "reward_std": 0.03787454068660736,
+      "rewards/qwen_accuracy_reward/mean": 0.903125,
+      "rewards/qwen_accuracy_reward/std": 0.17332438826560975,
+      "step": 370,
+      "step_time": 46.88851107805967
+    },
+    {
+      "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": 2117.2,
+      "completions/max_terminated_length": 2041.7,
+      "completions/mean_length": 779.765625,
+      "completions/mean_terminated_length": 759.7556274414062,
+      "completions/min_length": 242.8,
+      "completions/min_terminated_length": 242.8,
+      "entropy": 0.25157202035188675,
+      "epoch": 1.237785016286645,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 5.884907709011944e-06,
+      "loss": 0.0203,
+      "num_tokens": 15488027.0,
+      "reward": 0.959375,
+      "reward_std": 0.022201895713806152,
+      "rewards/qwen_accuracy_reward/mean": 0.959375,
+      "rewards/qwen_accuracy_reward/std": 0.08088433742523193,
+      "step": 380,
+      "step_time": 59.138066929019985
+    },
+    {
+      "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": 1781.4,
+      "completions/max_terminated_length": 1781.4,
+      "completions/mean_length": 700.425,
+      "completions/mean_terminated_length": 700.425,
+      "completions/min_length": 235.0,
+      "completions/min_terminated_length": 235.0,
+      "entropy": 0.23496372401714324,
+      "epoch": 1.2703583061889252,
+      "frac_reward_zero_std": 0.9,
+      "grad_norm": 0.0,
+      "learning_rate": 5.776330076004344e-06,
+      "loss": 0.0176,
+      "num_tokens": 15855563.0,
+      "reward": 0.915625,
+      "reward_std": 0.03808925524353981,
+      "rewards/qwen_accuracy_reward/mean": 0.915625,
+      "rewards/qwen_accuracy_reward/std": 0.15826207846403123,
+      "step": 390,
+      "step_time": 50.060482597071676
+    },
+    {
+      "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": 2096.2,
+      "completions/max_terminated_length": 2096.2,
+      "completions/mean_length": 812.94375,
+      "completions/mean_terminated_length": 812.94375,
+      "completions/min_length": 237.0,
+      "completions/min_terminated_length": 237.0,
+      "entropy": 0.25660712122917173,
+      "epoch": 1.3029315960912053,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 5.667752442996744e-06,
+      "loss": 0.0008,
+      "num_tokens": 16248769.0,
+      "reward": 0.971875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.971875,
+      "rewards/qwen_accuracy_reward/std": 0.061671803891658786,
+      "step": 400,
+      "step_time": 57.74213280631229
+    },
+    {
+      "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": 2004.3,
+      "completions/max_terminated_length": 2004.3,
+      "completions/mean_length": 783.475,
+      "completions/mean_terminated_length": 783.475,
+      "completions/min_length": 247.3,
+      "completions/min_terminated_length": 247.3,
+      "entropy": 0.2624002441763878,
+      "epoch": 1.3355048859934853,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 5.559174809989143e-06,
+      "loss": -0.0023,
+      "num_tokens": 16618217.0,
+      "reward": 0.978125,
+      "reward_std": 0.020411586761474608,
+      "rewards/qwen_accuracy_reward/mean": 0.978125,
+      "rewards/qwen_accuracy_reward/std": 0.0420013427734375,
+      "step": 410,
+      "step_time": 55.04804942021146
+    },
+    {
+      "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": 2008.8,
+      "completions/max_terminated_length": 2008.8,
+      "completions/mean_length": 738.990625,
+      "completions/mean_terminated_length": 738.990625,
+      "completions/min_length": 235.2,
+      "completions/min_terminated_length": 235.2,
+      "entropy": 0.23914156556129457,
+      "epoch": 1.3680781758957654,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 5.4505971769815425e-06,
+      "loss": -0.0033,
+      "num_tokens": 16982726.0,
+      "reward": 0.96875,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.96875,
+      "rewards/qwen_accuracy_reward/std": 0.06858760267496108,
+      "step": 420,
+      "step_time": 55.440987238287924
+    },
+    {
+      "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": 1761.0,
+      "completions/max_terminated_length": 1761.0,
+      "completions/mean_length": 693.9375,
+      "completions/mean_terminated_length": 693.9375,
+      "completions/min_length": 229.9,
+      "completions/min_terminated_length": 229.9,
+      "entropy": 0.2197161704301834,
+      "epoch": 1.4006514657980456,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.342019543973942e-06,
+      "loss": 0.0221,
+      "num_tokens": 17349890.0,
+      "reward": 0.98125,
+      "reward_std": 0.03104073032736778,
+      "rewards/qwen_accuracy_reward/mean": 0.98125,
+      "rewards/qwen_accuracy_reward/std": 0.05456787198781967,
+      "step": 430,
+      "step_time": 48.33475280003622
+    },
+    {
+      "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": 2297.5,
+      "completions/max_terminated_length": 2297.5,
+      "completions/mean_length": 739.340625,
+      "completions/mean_terminated_length": 739.340625,
+      "completions/min_length": 219.5,
+      "completions/min_terminated_length": 219.5,
+      "entropy": 0.25024042576551436,
+      "epoch": 1.4332247557003257,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 5.233441910966341e-06,
+      "loss": -0.0151,
+      "num_tokens": 17706023.0,
+      "reward": 0.9375,
+      "reward_std": 0.03650856465101242,
+      "rewards/qwen_accuracy_reward/mean": 0.9375,
+      "rewards/qwen_accuracy_reward/std": 0.12034976184368133,
+      "step": 440,
+      "step_time": 62.81698907474056
+    },
+    {
+      "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": 1834.9,
+      "completions/max_terminated_length": 1834.9,
+      "completions/mean_length": 688.871875,
+      "completions/mean_terminated_length": 688.871875,
+      "completions/min_length": 224.1,
+      "completions/min_terminated_length": 224.1,
+      "entropy": 0.226864817738533,
+      "epoch": 1.4657980456026058,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 5.124864277958741e-06,
+      "loss": 0.0071,
+      "num_tokens": 18040222.0,
+      "reward": 0.99375,
+      "reward_std": 0.01767766922712326,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.03535533845424652,
+      "step": 450,
+      "step_time": 50.243652266729626
+    },
+    {
+      "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": 2076.6,
+      "completions/max_terminated_length": 2076.6,
+      "completions/mean_length": 820.065625,
+      "completions/mean_terminated_length": 820.065625,
+      "completions/min_length": 224.3,
+      "completions/min_terminated_length": 224.3,
+      "entropy": 0.26836813539266585,
+      "epoch": 1.498371335504886,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 5.016286644951141e-06,
+      "loss": 0.0114,
+      "num_tokens": 18417267.0,
+      "reward": 0.965625,
+      "reward_std": 0.01293872892856598,
+      "rewards/qwen_accuracy_reward/mean": 0.965625,
+      "rewards/qwen_accuracy_reward/std": 0.07360859215259552,
+      "step": 460,
+      "step_time": 53.481527561508116
+    },
+    {
+      "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": 2273.2,
+      "completions/max_terminated_length": 2273.2,
+      "completions/mean_length": 806.01875,
+      "completions/mean_terminated_length": 806.01875,
+      "completions/min_length": 223.9,
+      "completions/min_terminated_length": 223.9,
+      "entropy": 0.2538841128349304,
+      "epoch": 1.5309446254071661,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 4.90770901194354e-06,
+      "loss": 0.0067,
+      "num_tokens": 18785505.0,
+      "reward": 0.971875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.971875,
+      "rewards/qwen_accuracy_reward/std": 0.061671803891658786,
+      "step": 470,
+      "step_time": 62.839932213444264
+    },
+    {
+      "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": 0.03125,
+      "completions/max_length": 2714.5,
+      "completions/max_terminated_length": 2495.2,
+      "completions/mean_length": 925.478125,
+      "completions/mean_terminated_length": 824.1982543945312,
+      "completions/min_length": 265.8,
+      "completions/min_terminated_length": 265.8,
+      "entropy": 0.25242401361465455,
+      "epoch": 1.5635179153094463,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 1.03125,
+      "learning_rate": 4.79913137893594e-06,
+      "loss": 0.0221,
+      "num_tokens": 19233306.0,
+      "reward": 0.940625,
+      "reward_std": 0.0306163989007473,
+      "rewards/qwen_accuracy_reward/mean": 0.940625,
+      "rewards/qwen_accuracy_reward/std": 0.11959655284881592,
+      "step": 480,
+      "step_time": 77.10490596247837
+    },
+    {
+      "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": 1684.3,
+      "completions/max_terminated_length": 1684.3,
+      "completions/mean_length": 707.128125,
+      "completions/mean_terminated_length": 707.128125,
+      "completions/min_length": 215.6,
+      "completions/min_terminated_length": 215.6,
+      "entropy": 0.24735355526208877,
+      "epoch": 1.5960912052117264,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 4.690553745928339e-06,
+      "loss": 0.0074,
+      "num_tokens": 19559787.0,
+      "reward": 0.965625,
+      "reward_std": 0.02041158601641655,
+      "rewards/qwen_accuracy_reward/mean": 0.965625,
+      "rewards/qwen_accuracy_reward/std": 0.08626527190208436,
+      "step": 490,
+      "step_time": 46.93290213858709
+    },
+    {
+      "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": 1979.4,
+      "completions/max_terminated_length": 1979.4,
+      "completions/mean_length": 789.7125,
+      "completions/mean_terminated_length": 789.7125,
+      "completions/min_length": 224.6,
+      "completions/min_terminated_length": 224.6,
+      "entropy": 0.2521603599190712,
+      "epoch": 1.6286644951140063,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 4.5819761129207385e-06,
+      "loss": 0.0058,
+      "num_tokens": 19946527.0,
+      "reward": 0.96875,
+      "reward_std": 0.02925042062997818,
+      "rewards/qwen_accuracy_reward/mean": 0.96875,
+      "rewards/qwen_accuracy_reward/std": 0.08427248001098633,
+      "step": 500,
+      "step_time": 55.279600530304016
+    },
+    {
+      "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": 2161.8,
+      "completions/max_terminated_length": 2161.8,
+      "completions/mean_length": 712.140625,
+      "completions/mean_terminated_length": 712.140625,
+      "completions/min_length": 201.2,
+      "completions/min_terminated_length": 201.2,
+      "entropy": 0.24787612855434418,
+      "epoch": 1.6612377850162865,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 4.473398479913138e-06,
+      "loss": 0.0066,
+      "num_tokens": 20305956.0,
+      "reward": 0.990625,
+      "reward_std": 0.01293872892856598,
+      "rewards/qwen_accuracy_reward/mean": 0.990625,
+      "rewards/qwen_accuracy_reward/std": 0.02961445748806,
+      "step": 510,
+      "step_time": 60.03746303850785
+    },
+    {
+      "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": 2452.2,
+      "completions/max_terminated_length": 2452.2,
+      "completions/mean_length": 877.840625,
+      "completions/mean_terminated_length": 877.840625,
+      "completions/min_length": 227.3,
+      "completions/min_terminated_length": 227.3,
+      "entropy": 0.2712139129638672,
+      "epoch": 1.6938110749185666,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 4.364820846905538e-06,
+      "loss": 0.0001,
+      "num_tokens": 20699457.0,
+      "reward": 0.975,
+      "reward_std": 0.023145502805709837,
+      "rewards/qwen_accuracy_reward/mean": 0.975,
+      "rewards/qwen_accuracy_reward/std": 0.06424924582242966,
+      "step": 520,
+      "step_time": 68.02793372562155
+    },
+    {
+      "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": 2466.4,
+      "completions/max_terminated_length": 2373.3,
+      "completions/mean_length": 999.05625,
+      "completions/mean_terminated_length": 971.425537109375,
+      "completions/min_length": 245.0,
+      "completions/min_terminated_length": 245.0,
+      "entropy": 0.28852569311857224,
+      "epoch": 1.7263843648208468,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.796875,
+      "learning_rate": 4.256243213897938e-06,
+      "loss": 0.028,
+      "num_tokens": 21126627.0,
+      "reward": 0.98125,
+      "reward_std": 0.024935813248157503,
+      "rewards/qwen_accuracy_reward/mean": 0.98125,
+      "rewards/qwen_accuracy_reward/std": 0.03965577781200409,
+      "step": 530,
+      "step_time": 67.80073131825775
+    },
+    {
+      "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": 2564.1,
+      "completions/max_terminated_length": 2539.0,
+      "completions/mean_length": 898.35,
+      "completions/mean_terminated_length": 879.8432373046875,
+      "completions/min_length": 242.9,
+      "completions/min_terminated_length": 242.9,
+      "entropy": 0.2612716257572174,
+      "epoch": 1.758957654723127,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 4.147665580890337e-06,
+      "loss": 0.0223,
+      "num_tokens": 21547283.0,
+      "reward": 0.990625,
+      "reward_std": 0.02041158601641655,
+      "rewards/qwen_accuracy_reward/mean": 0.990625,
+      "rewards/qwen_accuracy_reward/std": 0.04227113723754883,
+      "step": 540,
+      "step_time": 71.55222802590579
+    },
+    {
+      "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": 2065.7,
+      "completions/max_terminated_length": 2065.7,
+      "completions/mean_length": 810.70625,
+      "completions/mean_terminated_length": 810.70625,
+      "completions/min_length": 235.2,
+      "completions/min_terminated_length": 235.2,
+      "entropy": 0.2687004327774048,
+      "epoch": 1.791530944625407,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 4.039087947882737e-06,
+      "loss": 0.0018,
+      "num_tokens": 21932085.0,
+      "reward": 0.94375,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.94375,
+      "rewards/qwen_accuracy_reward/std": 0.11258173733949661,
+      "step": 550,
+      "step_time": 57.344520951993765
+    },
+    {
+      "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": 2237.9,
+      "completions/max_terminated_length": 2022.3,
+      "completions/mean_length": 804.046875,
+      "completions/mean_terminated_length": 793.9167297363281,
+      "completions/min_length": 228.6,
+      "completions/min_terminated_length": 228.6,
+      "entropy": 0.26058160662651064,
+      "epoch": 1.8241042345276872,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9305103148751365e-06,
+      "loss": 0.0297,
+      "num_tokens": 22301164.0,
+      "reward": 0.99375,
+      "reward_std": 0.01767766922712326,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.03535533845424652,
+      "step": 560,
+      "step_time": 58.96651698555797
+    },
+    {
+      "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": 2615.8,
+      "completions/max_terminated_length": 2586.3,
+      "completions/mean_length": 919.284375,
+      "completions/mean_terminated_length": 910.6251953125,
+      "completions/min_length": 227.2,
+      "completions/min_terminated_length": 227.2,
+      "entropy": 0.26033716797828677,
+      "epoch": 1.8566775244299674,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8219326818675354e-06,
+      "loss": 0.0202,
+      "num_tokens": 22748151.0,
+      "reward": 0.965625,
+      "reward_std": 0.03377464786171913,
+      "rewards/qwen_accuracy_reward/mean": 0.965625,
+      "rewards/qwen_accuracy_reward/std": 0.09093452244997025,
+      "step": 570,
+      "step_time": 73.18712518224493
+    },
+    {
+      "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": 1869.4,
+      "completions/max_terminated_length": 1869.4,
+      "completions/mean_length": 819.878125,
+      "completions/mean_terminated_length": 819.878125,
+      "completions/min_length": 241.7,
+      "completions/min_terminated_length": 241.7,
+      "entropy": 0.27983673214912413,
+      "epoch": 1.8892508143322475,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 3.7133550488599353e-06,
+      "loss": -0.0055,
+      "num_tokens": 23116952.0,
+      "reward": 0.971875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.971875,
+      "rewards/qwen_accuracy_reward/std": 0.061671803891658786,
+      "step": 580,
+      "step_time": 51.42270092964172
+    },
+    {
+      "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": 2110.1,
+      "completions/max_terminated_length": 2110.1,
+      "completions/mean_length": 817.971875,
+      "completions/mean_terminated_length": 817.971875,
+      "completions/min_length": 217.9,
+      "completions/min_terminated_length": 217.9,
+      "entropy": 0.27436681389808654,
+      "epoch": 1.9218241042345277,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 3.6047774158523346e-06,
+      "loss": -0.0143,
+      "num_tokens": 23493583.0,
+      "reward": 0.978125,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.978125,
+      "rewards/qwen_accuracy_reward/std": 0.0420013427734375,
+      "step": 590,
+      "step_time": 59.06694948039949
+    },
+    {
+      "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": 2356.0,
+      "completions/max_terminated_length": 2309.1,
+      "completions/mean_length": 819.525,
+      "completions/mean_terminated_length": 800.2312561035156,
+      "completions/min_length": 223.6,
+      "completions/min_terminated_length": 223.6,
+      "entropy": 0.2655492052435875,
+      "epoch": 1.9543973941368078,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 3.496199782844734e-06,
+      "loss": 0.0383,
+      "num_tokens": 23881743.0,
+      "reward": 0.928125,
+      "reward_std": 0.03471629247069359,
+      "rewards/qwen_accuracy_reward/mean": 0.928125,
+      "rewards/qwen_accuracy_reward/std": 0.1648948535323143,
+      "step": 600,
+      "step_time": 65.24080129675568
+    },
+    {
+      "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": 1854.6,
+      "completions/max_terminated_length": 1804.7,
+      "completions/mean_length": 747.76875,
+      "completions/mean_terminated_length": 738.7992919921875,
+      "completions/min_length": 230.1,
+      "completions/min_terminated_length": 230.1,
+      "entropy": 0.24497835338115692,
+      "epoch": 1.986970684039088,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 3.387622149837134e-06,
+      "loss": 0.0066,
+      "num_tokens": 24238917.0,
+      "reward": 0.946875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.946875,
+      "rewards/qwen_accuracy_reward/std": 0.06847771853208542,
+      "step": 610,
+      "step_time": 50.64491728274152
+    },
+    {
+      "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": 1993.9,
+      "completions/max_terminated_length": 1993.9,
+      "completions/mean_length": 801.025,
+      "completions/mean_terminated_length": 801.025,
+      "completions/min_length": 243.0,
+      "completions/min_terminated_length": 243.0,
+      "entropy": 0.26399993896484375,
+      "epoch": 2.019543973941368,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2790445168295332e-06,
+      "loss": 0.0,
+      "num_tokens": 24616733.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 1.0,
+      "rewards/qwen_accuracy_reward/std": 0.0,
+      "step": 620,
+      "step_time": 54.987590356636794
+    },
+    {
+      "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": 1921.4,
+      "completions/max_terminated_length": 1921.4,
+      "completions/mean_length": 671.61875,
+      "completions/mean_terminated_length": 671.61875,
+      "completions/min_length": 230.8,
+      "completions/min_terminated_length": 230.8,
+      "entropy": 0.23809937834739686,
+      "epoch": 2.0521172638436482,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 3.1704668838219326e-06,
+      "loss": 0.0118,
+      "num_tokens": 24948163.0,
+      "reward": 0.990625,
+      "reward_std": 0.02041158601641655,
+      "rewards/qwen_accuracy_reward/mean": 0.990625,
+      "rewards/qwen_accuracy_reward/std": 0.04227113723754883,
+      "step": 630,
+      "step_time": 53.22267805170268
+    },
+    {
+      "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": 1944.5,
+      "completions/max_terminated_length": 1944.5,
+      "completions/mean_length": 739.3125,
+      "completions/mean_terminated_length": 739.3125,
+      "completions/min_length": 225.3,
+      "completions/min_terminated_length": 225.3,
+      "entropy": 0.24684822857379912,
+      "epoch": 2.0846905537459284,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.061889250814333e-06,
+      "loss": 0.0,
+      "num_tokens": 25299887.0,
+      "reward": 0.975,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 0.975,
+      "rewards/qwen_accuracy_reward/std": 0.04399413466453552,
+      "step": 640,
+      "step_time": 52.247175365500155
+    },
+    {
+      "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": 1997.9,
+      "completions/max_terminated_length": 1997.9,
+      "completions/mean_length": 915.025,
+      "completions/mean_terminated_length": 915.025,
+      "completions/min_length": 241.7,
+      "completions/min_terminated_length": 241.7,
+      "entropy": 0.30182347595691683,
+      "epoch": 2.1172638436482085,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9533116178067322e-06,
+      "loss": 0.0144,
+      "num_tokens": 25695087.0,
+      "reward": 0.93125,
+      "reward_std": 0.02177756354212761,
+      "rewards/qwen_accuracy_reward/mean": 0.93125,
+      "rewards/qwen_accuracy_reward/std": 0.1425561413168907,
+      "step": 650,
+      "step_time": 55.97678603949025
+    },
+    {
+      "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": 2010.0,
+      "completions/max_terminated_length": 2010.0,
+      "completions/mean_length": 773.621875,
+      "completions/mean_terminated_length": 773.621875,
+      "completions/min_length": 240.4,
+      "completions/min_terminated_length": 240.4,
+      "entropy": 0.26853514164686204,
+      "epoch": 2.1498371335504887,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8447339847991316e-06,
+      "loss": -0.0101,
+      "num_tokens": 26070318.0,
+      "reward": 0.9375,
+      "reward_std": 0.02177756354212761,
+      "rewards/qwen_accuracy_reward/mean": 0.9375,
+      "rewards/qwen_accuracy_reward/std": 0.09809217602014542,
+      "step": 660,
+      "step_time": 51.58728506108746
+    },
+    {
+      "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": 2261.4,
+      "completions/max_terminated_length": 2261.4,
+      "completions/mean_length": 841.809375,
+      "completions/mean_terminated_length": 841.809375,
+      "completions/min_length": 240.7,
+      "completions/min_terminated_length": 240.7,
+      "entropy": 0.28256789445877073,
+      "epoch": 2.182410423452769,
+      "frac_reward_zero_std": 0.925,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7361563517915314e-06,
+      "loss": 0.022,
+      "num_tokens": 26466761.0,
+      "reward": 0.915625,
+      "reward_std": 0.02651650384068489,
+      "rewards/qwen_accuracy_reward/mean": 0.915625,
+      "rewards/qwen_accuracy_reward/std": 0.18501541167497634,
+      "step": 670,
+      "step_time": 62.65867903856561
+    },
+    {
+      "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": 2004.7,
+      "completions/max_terminated_length": 2004.7,
+      "completions/mean_length": 806.809375,
+      "completions/mean_terminated_length": 806.809375,
+      "completions/min_length": 247.0,
+      "completions/min_terminated_length": 247.0,
+      "entropy": 0.25492543578147886,
+      "epoch": 2.214983713355049,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 2.627578718783931e-06,
+      "loss": 0.0105,
+      "num_tokens": 26856028.0,
+      "reward": 0.99375,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.024593468010425567,
+      "step": 680,
+      "step_time": 55.284398326464
+    },
+    {
+      "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": 1603.7,
+      "completions/max_terminated_length": 1603.7,
+      "completions/mean_length": 693.71875,
+      "completions/mean_terminated_length": 693.71875,
+      "completions/min_length": 248.6,
+      "completions/min_terminated_length": 248.6,
+      "entropy": 0.24292832612991333,
+      "epoch": 2.247557003257329,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5190010857763302e-06,
+      "loss": -0.001,
+      "num_tokens": 27217034.0,
+      "reward": 0.978125,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.978125,
+      "rewards/qwen_accuracy_reward/std": 0.0420013427734375,
+      "step": 690,
+      "step_time": 43.892345847841355
+    },
+    {
+      "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": 2109.6,
+      "completions/max_terminated_length": 2109.6,
+      "completions/mean_length": 732.25625,
+      "completions/mean_terminated_length": 732.25625,
+      "completions/min_length": 207.3,
+      "completions/min_terminated_length": 207.3,
+      "entropy": 0.24278154224157333,
+      "epoch": 2.2801302931596092,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 2.4104234527687296e-06,
+      "loss": 0.0079,
+      "num_tokens": 27584884.0,
+      "reward": 0.984375,
+      "reward_std": 0.022201896458864213,
+      "rewards/qwen_accuracy_reward/mean": 0.984375,
+      "rewards/qwen_accuracy_reward/std": 0.05127874463796615,
+      "step": 700,
+      "step_time": 58.4371213012375
+    },
+    {
+      "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": 2012.2,
+      "completions/max_terminated_length": 2012.2,
+      "completions/mean_length": 874.60625,
+      "completions/mean_terminated_length": 874.60625,
+      "completions/min_length": 250.3,
+      "completions/min_terminated_length": 250.3,
+      "entropy": 0.2829678565263748,
+      "epoch": 2.3127035830618894,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3018458197611294e-06,
+      "loss": 0.0006,
+      "num_tokens": 27971566.0,
+      "reward": 0.95,
+      "reward_std": 0.01767766922712326,
+      "rewards/qwen_accuracy_reward/mean": 0.95,
+      "rewards/qwen_accuracy_reward/std": 0.05080004930496216,
+      "step": 710,
+      "step_time": 51.538982132449746
+    },
+    {
+      "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": 1950.8,
+      "completions/max_terminated_length": 1950.8,
+      "completions/mean_length": 741.321875,
+      "completions/mean_terminated_length": 741.321875,
+      "completions/min_length": 216.0,
+      "completions/min_terminated_length": 216.0,
+      "entropy": 0.2639204204082489,
+      "epoch": 2.3452768729641695,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 2.193268186753529e-06,
+      "loss": 0.0133,
+      "num_tokens": 28322077.0,
+      "reward": 0.996875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.996875,
+      "rewards/qwen_accuracy_reward/std": 0.01767766922712326,
+      "step": 720,
+      "step_time": 53.80062342043966
+    },
+    {
+      "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": 1992.0,
+      "completions/max_terminated_length": 1984.1,
+      "completions/mean_length": 763.175,
+      "completions/mean_terminated_length": 737.0316772460938,
+      "completions/min_length": 232.5,
+      "completions/min_terminated_length": 232.5,
+      "entropy": 0.2350025877356529,
+      "epoch": 2.3778501628664497,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0846905537459286e-06,
+      "loss": -0.0018,
+      "num_tokens": 28713133.0,
+      "reward": 0.959375,
+      "reward_std": 0.020411586761474608,
+      "rewards/qwen_accuracy_reward/mean": 0.959375,
+      "rewards/qwen_accuracy_reward/std": 0.049899089336395266,
+      "step": 730,
+      "step_time": 56.30837788451463
+    },
+    {
+      "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": 1953.1,
+      "completions/max_terminated_length": 1953.1,
+      "completions/mean_length": 760.65,
+      "completions/mean_terminated_length": 760.65,
+      "completions/min_length": 248.0,
+      "completions/min_terminated_length": 248.0,
+      "entropy": 0.2552919015288353,
+      "epoch": 2.41042345276873,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 1.976112920738328e-06,
+      "loss": -0.0,
+      "num_tokens": 29084557.0,
+      "reward": 0.996875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.996875,
+      "rewards/qwen_accuracy_reward/std": 0.01767766922712326,
+      "step": 740,
+      "step_time": 53.73468600921333
+    },
+    {
+      "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": 2096.5,
+      "completions/max_terminated_length": 2096.5,
+      "completions/mean_length": 763.521875,
+      "completions/mean_terminated_length": 763.521875,
+      "completions/min_length": 229.0,
+      "completions/min_terminated_length": 229.0,
+      "entropy": 0.2697294756770134,
+      "epoch": 2.44299674267101,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8675352877307276e-06,
+      "loss": 0.0,
+      "num_tokens": 29421564.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 1.0,
+      "rewards/qwen_accuracy_reward/std": 0.0,
+      "step": 750,
+      "step_time": 57.729420161712916
+    },
+    {
+      "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": 2107.5,
+      "completions/max_terminated_length": 2107.5,
+      "completions/mean_length": 830.36875,
+      "completions/mean_terminated_length": 830.36875,
+      "completions/min_length": 239.4,
+      "completions/min_terminated_length": 239.4,
+      "entropy": 0.2688334047794342,
+      "epoch": 2.47557003257329,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.7589576547231272e-06,
+      "loss": 0.0025,
+      "num_tokens": 29814434.0,
+      "reward": 0.9625,
+      "reward_std": 0.02177756354212761,
+      "rewards/qwen_accuracy_reward/mean": 0.9625,
+      "rewards/qwen_accuracy_reward/std": 0.09128626137971878,
+      "step": 760,
+      "step_time": 55.252242975588885
+    },
+    {
+      "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": 1695.7,
+      "completions/max_terminated_length": 1695.7,
+      "completions/mean_length": 702.753125,
+      "completions/mean_terminated_length": 702.753125,
+      "completions/min_length": 224.7,
+      "completions/min_terminated_length": 224.7,
+      "entropy": 0.24166983664035796,
+      "epoch": 2.5081433224755703,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 1.171875,
+      "learning_rate": 1.6503800217155266e-06,
+      "loss": -0.0015,
+      "num_tokens": 30160107.0,
+      "reward": 0.99375,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.024593468010425567,
+      "step": 770,
+      "step_time": 46.50829186448827
+    },
+    {
+      "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": 2194.7,
+      "completions/max_terminated_length": 2194.7,
+      "completions/mean_length": 810.775,
+      "completions/mean_terminated_length": 810.775,
+      "completions/min_length": 242.2,
+      "completions/min_terminated_length": 242.2,
+      "entropy": 0.26336751878261566,
+      "epoch": 2.5407166123778504,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5418023887079264e-06,
+      "loss": -0.0058,
+      "num_tokens": 30525939.0,
+      "reward": 0.978125,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.978125,
+      "rewards/qwen_accuracy_reward/std": 0.0420013427734375,
+      "step": 780,
+      "step_time": 60.35267236959189
+    },
+    {
+      "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": 2411.8,
+      "completions/max_terminated_length": 2286.5,
+      "completions/mean_length": 815.034375,
+      "completions/mean_terminated_length": 804.432958984375,
+      "completions/min_length": 211.4,
+      "completions/min_terminated_length": 211.4,
+      "entropy": 0.24477785527706147,
+      "epoch": 2.5732899022801305,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.0,
+      "learning_rate": 1.433224755700326e-06,
+      "loss": 0.0022,
+      "num_tokens": 30932030.0,
+      "reward": 0.921875,
+      "reward_std": 0.06102004498243332,
+      "rewards/qwen_accuracy_reward/mean": 0.921875,
+      "rewards/qwen_accuracy_reward/std": 0.169888436794281,
+      "step": 790,
+      "step_time": 66.54381455238908
+    },
+    {
+      "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": 1845.2,
+      "completions/max_terminated_length": 1845.2,
+      "completions/mean_length": 748.1375,
+      "completions/mean_terminated_length": 748.1375,
+      "completions/min_length": 237.0,
+      "completions/min_terminated_length": 237.0,
+      "entropy": 0.2624224051833153,
+      "epoch": 2.6058631921824107,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3246471226927254e-06,
+      "loss": -0.0098,
+      "num_tokens": 31279306.0,
+      "reward": 0.903125,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.903125,
+      "rewards/qwen_accuracy_reward/std": 0.17398374676704406,
+      "step": 800,
+      "step_time": 50.52960663391277
+    },
+    {
+      "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": 2163.7,
+      "completions/max_terminated_length": 2090.4,
+      "completions/mean_length": 855.071875,
+      "completions/mean_terminated_length": 837.5410522460937,
+      "completions/min_length": 213.2,
+      "completions/min_terminated_length": 213.2,
+      "entropy": 0.25761414915323255,
+      "epoch": 2.6384364820846904,
+      "frac_reward_zero_std": 0.875,
+      "grad_norm": 0.0,
+      "learning_rate": 1.216069489685125e-06,
+      "loss": 0.0102,
+      "num_tokens": 31703561.0,
+      "reward": 0.946875,
+      "reward_std": 0.05145231783390045,
+      "rewards/qwen_accuracy_reward/mean": 0.946875,
+      "rewards/qwen_accuracy_reward/std": 0.14256500601768493,
+      "step": 810,
+      "step_time": 58.85951620331034
+    },
+    {
+      "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": 2240.4,
+      "completions/max_terminated_length": 2168.3,
+      "completions/mean_length": 908.7,
+      "completions/mean_terminated_length": 899.4978759765625,
+      "completions/min_length": 271.1,
+      "completions/min_terminated_length": 271.1,
+      "entropy": 0.279021093249321,
+      "epoch": 2.6710097719869705,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1074918566775244e-06,
+      "loss": 0.0045,
+      "num_tokens": 32114609.0,
+      "reward": 0.99375,
+      "reward_std": 0.011572751402854919,
+      "rewards/qwen_accuracy_reward/mean": 0.99375,
+      "rewards/qwen_accuracy_reward/std": 0.024593468010425567,
+      "step": 820,
+      "step_time": 62.48456142954528
+    },
+    {
+      "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": 1864.0,
+      "completions/max_terminated_length": 1864.0,
+      "completions/mean_length": 750.0875,
+      "completions/mean_terminated_length": 750.0875,
+      "completions/min_length": 230.4,
+      "completions/min_terminated_length": 230.4,
+      "entropy": 0.262259940803051,
+      "epoch": 2.7035830618892507,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 9.989142236699242e-07,
+      "loss": 0.0,
+      "num_tokens": 32478965.0,
+      "reward": 0.975,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 0.975,
+      "rewards/qwen_accuracy_reward/std": 0.04399413466453552,
+      "step": 830,
+      "step_time": 51.756828672252595
+    },
+    {
+      "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": 1758.2,
+      "completions/max_terminated_length": 1758.2,
+      "completions/mean_length": 777.496875,
+      "completions/mean_terminated_length": 777.496875,
+      "completions/min_length": 292.6,
+      "completions/min_terminated_length": 292.6,
+      "entropy": 0.2636624053120613,
+      "epoch": 2.736156351791531,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 8.903365906623236e-07,
+      "loss": 0.0,
+      "num_tokens": 32855788.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 1.0,
+      "rewards/qwen_accuracy_reward/std": 0.0,
+      "step": 840,
+      "step_time": 47.54948642067611
+    },
+    {
+      "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": 1865.4,
+      "completions/max_terminated_length": 1865.4,
+      "completions/mean_length": 758.2375,
+      "completions/mean_terminated_length": 758.2375,
+      "completions/min_length": 212.1,
+      "completions/min_terminated_length": 212.1,
+      "entropy": 0.26781439036130905,
+      "epoch": 2.768729641693811,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 7.817589576547231e-07,
+      "loss": 0.0175,
+      "num_tokens": 33208816.0,
+      "reward": 0.971875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.971875,
+      "rewards/qwen_accuracy_reward/std": 0.061671803891658786,
+      "step": 850,
+      "step_time": 51.30761405080557
+    },
+    {
+      "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": 2093.8,
+      "completions/max_terminated_length": 2093.8,
+      "completions/mean_length": 874.303125,
+      "completions/mean_terminated_length": 874.303125,
+      "completions/min_length": 268.3,
+      "completions/min_terminated_length": 268.3,
+      "entropy": 0.28648746609687803,
+      "epoch": 2.801302931596091,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 6.731813246471228e-07,
+      "loss": 0.0294,
+      "num_tokens": 33613025.0,
+      "reward": 0.9875,
+      "reward_std": 0.02177756354212761,
+      "rewards/qwen_accuracy_reward/mean": 0.9875,
+      "rewards/qwen_accuracy_reward/std": 0.04729212671518326,
+      "step": 860,
+      "step_time": 56.19616959039122
+    },
+    {
+      "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": 2066.2,
+      "completions/max_terminated_length": 2066.2,
+      "completions/mean_length": 887.94375,
+      "completions/mean_terminated_length": 887.94375,
+      "completions/min_length": 235.5,
+      "completions/min_terminated_length": 235.5,
+      "entropy": 0.2825250759720802,
+      "epoch": 2.8338762214983713,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 5.646036916395223e-07,
+      "loss": 0.0,
+      "num_tokens": 34016103.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 1.0,
+      "rewards/qwen_accuracy_reward/std": 0.0,
+      "step": 870,
+      "step_time": 56.39509414639324
+    },
+    {
+      "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": 2083.2,
+      "completions/max_terminated_length": 2015.4,
+      "completions/mean_length": 834.1625,
+      "completions/mean_terminated_length": 824.3365905761718,
+      "completions/min_length": 240.6,
+      "completions/min_terminated_length": 240.6,
+      "entropy": 0.275046506524086,
+      "epoch": 2.8664495114006514,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.71875,
+      "learning_rate": 4.5602605863192187e-07,
+      "loss": 0.0176,
+      "num_tokens": 34391867.0,
+      "reward": 0.984375,
+      "reward_std": 0.022201896458864213,
+      "rewards/qwen_accuracy_reward/mean": 0.984375,
+      "rewards/qwen_accuracy_reward/std": 0.05127874463796615,
+      "step": 880,
+      "step_time": 57.167689157929274
+    },
+    {
+      "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": 2087.8,
+      "completions/max_terminated_length": 2087.8,
+      "completions/mean_length": 843.36875,
+      "completions/mean_terminated_length": 843.36875,
+      "completions/min_length": 256.4,
+      "completions/min_terminated_length": 256.4,
+      "entropy": 0.27352436184883117,
+      "epoch": 2.8990228013029316,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.474484256243214e-07,
+      "loss": 0.0,
+      "num_tokens": 34796825.0,
+      "reward": 0.95,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 0.95,
+      "rewards/qwen_accuracy_reward/std": 0.08798826932907104,
+      "step": 890,
+      "step_time": 57.07374393362552
+    },
+    {
+      "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": 2076.1,
+      "completions/max_terminated_length": 2076.1,
+      "completions/mean_length": 821.371875,
+      "completions/mean_terminated_length": 821.371875,
+      "completions/min_length": 255.8,
+      "completions/min_terminated_length": 255.8,
+      "entropy": 0.25859465897083284,
+      "epoch": 2.9315960912052117,
+      "frac_reward_zero_std": 0.975,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3887079261672097e-07,
+      "loss": 0.0052,
+      "num_tokens": 35194008.0,
+      "reward": 0.971875,
+      "reward_std": 0.00883883461356163,
+      "rewards/qwen_accuracy_reward/mean": 0.971875,
+      "rewards/qwen_accuracy_reward/std": 0.061671803891658786,
+      "step": 900,
+      "step_time": 57.363739002589135
+    },
+    {
+      "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": 1843.8,
+      "completions/max_terminated_length": 1843.8,
+      "completions/mean_length": 770.575,
+      "completions/mean_terminated_length": 770.575,
+      "completions/min_length": 229.7,
+      "completions/min_terminated_length": 229.7,
+      "entropy": 0.26421869844198226,
+      "epoch": 2.964169381107492,
+      "frac_reward_zero_std": 0.95,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3029315960912054e-07,
+      "loss": 0.0081,
+      "num_tokens": 35559488.0,
+      "reward": 0.984375,
+      "reward_std": 0.022201896458864213,
+      "rewards/qwen_accuracy_reward/mean": 0.984375,
+      "rewards/qwen_accuracy_reward/std": 0.05127874463796615,
+      "step": 910,
+      "step_time": 49.7163490107283
+    },
+    {
+      "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": 1876.2,
+      "completions/max_terminated_length": 1876.2,
+      "completions/mean_length": 694.903125,
+      "completions/mean_terminated_length": 694.903125,
+      "completions/min_length": 201.0,
+      "completions/min_terminated_length": 201.0,
+      "entropy": 0.2524524837732315,
+      "epoch": 2.996742671009772,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 2.171552660152009e-08,
+      "loss": 0.0,
+      "num_tokens": 35893057.0,
+      "reward": 1.0,
+      "reward_std": 0.0,
+      "rewards/qwen_accuracy_reward/mean": 1.0,
+      "rewards/qwen_accuracy_reward/std": 0.0,
+      "step": 920,
+      "step_time": 51.581244880892335
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 921,
+  "num_input_tokens_seen": 35924229,
+  "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 sha256:21a3bc205409ada0f4bd091b5802a3a909a88a398d16e497eac781eae7630236
+size 7096