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,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

conversion_info.json

@@ -0,0 +1,7 @@
+{
+  "base_model": "Qwen/Qwen3-8B",
+  "lora_checkpoint": "/home/zhuoran-nebius/repos/price_bargaining_agent/storage/bargaining/8B_buyer_20251007_044932/checkpoint-60",
+  "lora_rank": 64,
+  "lora_alpha": 128,
+  "conversion_note": "Merged LoRA adapter into base model"
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92656ae621c1c38ce2b4ded8c9fc2789e2d97e2e9e07ce4ff7d10a3d0ee05cd
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d913b0bdb0a7edc2ad97237880c5221e318a6e9edc32bfdd1e3cd0b55421a803
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f96b546594d4b23122be0c9d2334f1a985a5a4f769831aa6f9d7cea33cc6b20
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfb5599865b0587b5761f4a4cd09447fd0607463dc944b2140c00c9c9967c5e
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1714 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1282051282051282,
+  "eval_steps": 500,
+  "global_step": 60,
+  "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": 0.0625,
+      "completions/max_length": 9194.0,
+      "completions/max_terminated_length": 9194.0,
+      "completions/mean_length": 5745.15625,
+      "completions/mean_terminated_length": 6128.166666666667,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3974.0,
+      "epoch": 0.002136752136752137,
+      "grad_norm": 0.06384662206039221,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "num_tokens": 345573.0,
+      "reward": 0.3754020035266876,
+      "reward_std": 0.64158034324646,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6662575006484985,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9164310693740845,
+      "rewards/utility_reward_func": 0.07276386767625809,
+      "step": 1
+    },
+    {
+      "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": 10133.0,
+      "completions/max_terminated_length": 10133.0,
+      "completions/mean_length": 6297.9375,
+      "completions/mean_terminated_length": 6297.9375,
+      "completions/min_length": 2801.0,
+      "completions/min_terminated_length": 2801.0,
+      "epoch": 0.004273504273504274,
+      "grad_norm": 0.06139459826368875,
+      "kl": 0.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": -0.0013,
+      "num_tokens": 689634.0,
+      "reward": 0.8823189735412598,
+      "reward_std": 0.7824905514717102,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8089037537574768,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9081597328186035,
+      "rewards/utility_reward_func": 0.17412039637565613,
+      "step": 2
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9356.0,
+      "completions/max_terminated_length": 9356.0,
+      "completions/mean_length": 5507.4375,
+      "completions/mean_terminated_length": 5874.6,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2936.0,
+      "epoch": 0.00641025641025641,
+      "grad_norm": 0.16125877365096486,
+      "kl": 0.00312042236328125,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": -0.0375,
+      "num_tokens": 1020236.0,
+      "reward": 0.7772555351257324,
+      "reward_std": 1.0026202201843262,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7187950611114502,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8661947250366211,
+      "rewards/utility_reward_func": 0.15313410758972168,
+      "step": 3
+    },
+    {
+      "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": 9044.0,
+      "completions/max_terminated_length": 9044.0,
+      "completions/mean_length": 5101.34375,
+      "completions/mean_terminated_length": 5265.903225806452,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3087.0,
+      "epoch": 0.008547008547008548,
+      "grad_norm": 0.1331600814415893,
+      "kl": 0.003368377685546875,
+      "learning_rate": 1.5e-06,
+      "loss": -0.0146,
+      "num_tokens": 1322850.0,
+      "reward": 0.7779074907302856,
+      "reward_std": 0.866315484046936,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.682944118976593,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8875845670700073,
+      "rewards/utility_reward_func": 0.15326739847660065,
+      "step": 4
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9605.0,
+      "completions/max_terminated_length": 9605.0,
+      "completions/mean_length": 5633.96875,
+      "completions/mean_terminated_length": 6009.566666666667,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3806.0,
+      "epoch": 0.010683760683760684,
+      "grad_norm": 0.10043275978920585,
+      "kl": 0.0031251907348632812,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0091,
+      "num_tokens": 1667050.0,
+      "reward": 0.5307067036628723,
+      "reward_std": 0.6169852018356323,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6832882165908813,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8644717335700989,
+      "rewards/utility_reward_func": 0.10383178293704987,
+      "step": 5
+    },
+    {
+      "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": 9829.0,
+      "completions/max_terminated_length": 9829.0,
+      "completions/mean_length": 6319.625,
+      "completions/mean_terminated_length": 6319.625,
+      "completions/min_length": 2801.0,
+      "completions/min_terminated_length": 2801.0,
+      "epoch": 0.01282051282051282,
+      "grad_norm": 0.09138627686091379,
+      "kl": 0.0031518936157226562,
+      "learning_rate": 2.5e-06,
+      "loss": -0.0105,
+      "num_tokens": 1999042.0,
+      "reward": 0.6561113595962524,
+      "reward_std": 0.8523557782173157,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7507439851760864,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9472808837890625,
+      "rewards/utility_reward_func": 0.12888266146183014,
+      "step": 6
+    },
+    {
+      "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": 10098.0,
+      "completions/max_terminated_length": 10098.0,
+      "completions/mean_length": 6040.21875,
+      "completions/mean_terminated_length": 6040.21875,
+      "completions/min_length": 2345.0,
+      "completions/min_terminated_length": 2345.0,
+      "epoch": 0.014957264957264958,
+      "grad_norm": 0.09859665471586132,
+      "kl": 0.0033817291259765625,
+      "learning_rate": 3e-06,
+      "loss": -0.0343,
+      "num_tokens": 2313691.0,
+      "reward": 1.0388803482055664,
+      "reward_std": 0.9269991517066956,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.6589781641960144,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9249492883682251,
+      "rewards/utility_reward_func": 0.20549052953720093,
+      "step": 7
+    },
+    {
+      "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": 8935.0,
+      "completions/max_terminated_length": 8935.0,
+      "completions/mean_length": 4837.3125,
+      "completions/mean_terminated_length": 4993.354838709677,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2192.0,
+      "epoch": 0.017094017094017096,
+      "grad_norm": 0.13927683938664606,
+      "kl": 0.0035686492919921875,
+      "learning_rate": 3.5e-06,
+      "loss": -0.0218,
+      "num_tokens": 2607775.0,
+      "reward": 0.7573515176773071,
+      "reward_std": 0.747157633304596,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7197544574737549,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8988715410232544,
+      "rewards/utility_reward_func": 0.14914658665657043,
+      "step": 8
+    },
+    {
+      "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": 8868.0,
+      "completions/max_terminated_length": 8868.0,
+      "completions/mean_length": 5284.78125,
+      "completions/mean_terminated_length": 5455.258064516129,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2504.0,
+      "epoch": 0.019230769230769232,
+      "grad_norm": 0.11735526956696517,
+      "kl": 0.0043468475341796875,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0019,
+      "num_tokens": 2915637.0,
+      "reward": 0.365405797958374,
+      "reward_std": 0.5554816722869873,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.579179048538208,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9264745712280273,
+      "rewards/utility_reward_func": 0.07081127166748047,
+      "step": 9
+    },
+    {
+      "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": 9892.0,
+      "completions/max_terminated_length": 9892.0,
+      "completions/mean_length": 5311.21875,
+      "completions/mean_terminated_length": 5482.548387096775,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1337.0,
+      "epoch": 0.021367521367521368,
+      "grad_norm": 0.08243472782779405,
+      "kl": 0.0046443939208984375,
+      "learning_rate": 4.5e-06,
+      "loss": -0.0052,
+      "num_tokens": 3218433.0,
+      "reward": 0.7362505197525024,
+      "reward_std": 0.9180038571357727,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6661200523376465,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9426835179328918,
+      "rewards/utility_reward_func": 0.14492833614349365,
+      "step": 10
+    },
+    {
+      "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": 8914.0,
+      "completions/max_terminated_length": 8914.0,
+      "completions/mean_length": 5811.75,
+      "completions/mean_terminated_length": 5811.75,
+      "completions/min_length": 2232.0,
+      "completions/min_terminated_length": 2232.0,
+      "epoch": 0.023504273504273504,
+      "grad_norm": 0.09543276542415491,
+      "kl": 0.00598907470703125,
+      "learning_rate": 5e-06,
+      "loss": -0.0049,
+      "num_tokens": 3529160.0,
+      "reward": 0.5771545171737671,
+      "reward_std": 0.8459901809692383,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5785590410232544,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9260044693946838,
+      "rewards/utility_reward_func": 0.11312998831272125,
+      "step": 11
+    },
+    {
+      "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": 8499.0,
+      "completions/max_terminated_length": 8499.0,
+      "completions/mean_length": 4962.53125,
+      "completions/mean_terminated_length": 5122.612903225807,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2565.0,
+      "epoch": 0.02564102564102564,
+      "grad_norm": 0.06256974070929786,
+      "kl": 0.0071735382080078125,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.0059,
+      "num_tokens": 3838787.0,
+      "reward": 0.7496746778488159,
+      "reward_std": 0.9168016314506531,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.6537078619003296,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9083457589149475,
+      "rewards/utility_reward_func": 0.14768503606319427,
+      "step": 12
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 8518.0,
+      "completions/max_terminated_length": 8518.0,
+      "completions/mean_length": 5306.21875,
+      "completions/mean_terminated_length": 5659.966666666666,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2676.0,
+      "epoch": 0.027777777777777776,
+      "grad_norm": 0.06188426771907535,
+      "kl": 0.011411666870117188,
+      "learning_rate": 6e-06,
+      "loss": 0.0037,
+      "num_tokens": 4162259.0,
+      "reward": 0.4114573001861572,
+      "reward_std": 0.5327050685882568,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7068666219711304,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9097241163253784,
+      "rewards/utility_reward_func": 0.0799993947148323,
+      "step": 13
+    },
+    {
+      "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": 8677.0,
+      "completions/max_terminated_length": 8677.0,
+      "completions/mean_length": 5330.875,
+      "completions/mean_terminated_length": 5330.875,
+      "completions/min_length": 1230.0,
+      "completions/min_terminated_length": 1230.0,
+      "epoch": 0.029914529914529916,
+      "grad_norm": 0.07195177317932434,
+      "kl": 0.020092010498046875,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": -0.0026,
+      "num_tokens": 4465194.0,
+      "reward": 0.26478463411331177,
+      "reward_std": 0.33203744888305664,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.4670758843421936,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9135281443595886,
+      "rewards/utility_reward_func": 0.05068080872297287,
+      "step": 14
+    },
+    {
+      "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": 9578.0,
+      "completions/max_terminated_length": 9578.0,
+      "completions/mean_length": 6203.96875,
+      "completions/mean_terminated_length": 6404.096774193548,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2333.0,
+      "epoch": 0.03205128205128205,
+      "grad_norm": 0.10026513317887245,
+      "kl": 0.018894195556640625,
+      "learning_rate": 7e-06,
+      "loss": 0.0411,
+      "num_tokens": 4803381.0,
+      "reward": 0.3010755777359009,
+      "reward_std": 0.5123584866523743,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.738226056098938,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9183079600334167,
+      "rewards/utility_reward_func": 0.05794630944728851,
+      "step": 15
+    },
+    {
+      "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": 8891.0,
+      "completions/max_terminated_length": 8891.0,
+      "completions/mean_length": 6081.84375,
+      "completions/mean_terminated_length": 6081.84375,
+      "completions/min_length": 2926.0,
+      "completions/min_terminated_length": 2926.0,
+      "epoch": 0.03418803418803419,
+      "grad_norm": 0.060400168503078416,
+      "kl": 0.03104400634765625,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": -0.0067,
+      "num_tokens": 5128775.0,
+      "reward": 0.5646129846572876,
+      "reward_std": 0.7254551649093628,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6118528842926025,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9297844171524048,
+      "rewards/utility_reward_func": 0.11061426997184753,
+      "step": 16
+    },
+    {
+      "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": 9484.0,
+      "completions/max_terminated_length": 9484.0,
+      "completions/mean_length": 5118.625,
+      "completions/mean_terminated_length": 5118.625,
+      "completions/min_length": 1630.0,
+      "completions/min_terminated_length": 1630.0,
+      "epoch": 0.03632478632478633,
+      "grad_norm": 0.05120826577801321,
+      "kl": 0.036815643310546875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.0048,
+      "num_tokens": 5421396.0,
+      "reward": 0.5202240347862244,
+      "reward_std": 0.5871657133102417,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7249752283096313,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8982887268066406,
+      "rewards/utility_reward_func": 0.10172015428543091,
+      "step": 17
+    },
+    {
+      "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": 10314.0,
+      "completions/max_terminated_length": 10314.0,
+      "completions/mean_length": 5530.75,
+      "completions/mean_terminated_length": 5709.1612903225805,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3094.0,
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.8805793412616941,
+      "kl": 0.22267913818359375,
+      "learning_rate": 8.5e-06,
+      "loss": -0.0131,
+      "num_tokens": 5733847.0,
+      "reward": 0.5374739170074463,
+      "reward_std": 0.7667478322982788,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.5694985389709473,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8748263716697693,
+      "rewards/utility_reward_func": 0.10523717105388641,
+      "step": 18
+    },
+    {
+      "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": 9009.0,
+      "completions/max_terminated_length": 9009.0,
+      "completions/mean_length": 4953.90625,
+      "completions/mean_terminated_length": 5113.709677419355,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1940.0,
+      "epoch": 0.0405982905982906,
+      "grad_norm": 0.05562338889561032,
+      "kl": 0.05136871337890625,
+      "learning_rate": 9e-06,
+      "loss": -0.0207,
+      "num_tokens": 6040038.0,
+      "reward": 0.40647947788238525,
+      "reward_std": 0.5132466554641724,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6577438116073608,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9326636791229248,
+      "rewards/utility_reward_func": 0.07897782325744629,
+      "step": 19
+    },
+    {
+      "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": 9768.0,
+      "completions/max_terminated_length": 9768.0,
+      "completions/mean_length": 5553.15625,
+      "completions/mean_terminated_length": 5732.290322580645,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2971.0,
+      "epoch": 0.042735042735042736,
+      "grad_norm": 0.05415251247993026,
+      "kl": 0.0604705810546875,
+      "learning_rate": 9.5e-06,
+      "loss": -0.0159,
+      "num_tokens": 6356055.0,
+      "reward": 0.6564894914627075,
+      "reward_std": 0.9057918787002563,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.6670262813568115,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9299107193946838,
+      "rewards/utility_reward_func": 0.12900978326797485,
+      "step": 20
+    },
+    {
+      "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": 8973.0,
+      "completions/max_terminated_length": 8973.0,
+      "completions/mean_length": 4999.53125,
+      "completions/mean_terminated_length": 5160.806451612903,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2484.0,
+      "epoch": 0.04487179487179487,
+      "grad_norm": 0.07150378564767108,
+      "kl": 0.05039215087890625,
+      "learning_rate": 1e-05,
+      "loss": 0.0295,
+      "num_tokens": 6650399.0,
+      "reward": 0.3270576596260071,
+      "reward_std": 0.48058632016181946,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5520957112312317,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9284598231315613,
+      "rewards/utility_reward_func": 0.0631154254078865,
+      "step": 21
+    },
+    {
+      "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": 9046.0,
+      "completions/max_terminated_length": 9046.0,
+      "completions/mean_length": 5165.90625,
+      "completions/mean_terminated_length": 5332.548387096775,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3100.0,
+      "epoch": 0.04700854700854701,
+      "grad_norm": 0.06845908919994707,
+      "kl": 0.0538330078125,
+      "learning_rate": 9.986128001799077e-06,
+      "loss": 0.0153,
+      "num_tokens": 6954265.0,
+      "reward": 0.4070006310939789,
+      "reward_std": 0.5391647815704346,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.624727189540863,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.887859582901001,
+      "rewards/utility_reward_func": 0.07909761369228363,
+      "step": 22
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9026.0,
+      "completions/max_terminated_length": 9026.0,
+      "completions/mean_length": 4882.46875,
+      "completions/mean_terminated_length": 5207.966666666666,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2413.0,
+      "epoch": 0.049145299145299144,
+      "grad_norm": 0.0575950278172028,
+      "kl": 0.06992721557617188,
+      "learning_rate": 9.94459753267812e-06,
+      "loss": -0.0033,
+      "num_tokens": 7263856.0,
+      "reward": 0.14356863498687744,
+      "reward_std": 0.22449877858161926,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5870039463043213,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8971620798110962,
+      "rewards/utility_reward_func": 0.026416894048452377,
+      "step": 23
+    },
+    {
+      "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": 8652.0,
+      "completions/max_terminated_length": 8652.0,
+      "completions/mean_length": 4892.875,
+      "completions/mean_terminated_length": 5050.709677419355,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1523.0,
+      "epoch": 0.05128205128205128,
+      "grad_norm": 0.04255156882342247,
+      "kl": 0.0586090087890625,
+      "learning_rate": 9.875664641789545e-06,
+      "loss": 0.0203,
+      "num_tokens": 7571389.0,
+      "reward": 0.6160452365875244,
+      "reward_std": 1.0084484815597534,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7209370136260986,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9045882821083069,
+      "rewards/utility_reward_func": 0.12088394165039062,
+      "step": 24
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9417.0,
+      "completions/max_terminated_length": 9417.0,
+      "completions/mean_length": 4552.21875,
+      "completions/mean_terminated_length": 4855.7,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2353.0,
+      "epoch": 0.053418803418803416,
+      "grad_norm": 0.033573562073913446,
+      "kl": 0.0653076171875,
+      "learning_rate": 9.779754323328192e-06,
+      "loss": -0.0009,
+      "num_tokens": 7861415.0,
+      "reward": 0.7228190898895264,
+      "reward_std": 0.5367074608802795,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.614422082901001,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9327523708343506,
+      "rewards/utility_reward_func": 0.14225439727306366,
+      "step": 25
+    },
+    {
+      "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": 9038.0,
+      "completions/max_terminated_length": 9038.0,
+      "completions/mean_length": 5255.71875,
+      "completions/mean_terminated_length": 5255.71875,
+      "completions/min_length": 2542.0,
+      "completions/min_terminated_length": 2542.0,
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.047795685473935486,
+      "kl": 0.05504608154296875,
+      "learning_rate": 9.65745789630079e-06,
+      "loss": -0.0161,
+      "num_tokens": 8175576.0,
+      "reward": 0.5497658848762512,
+      "reward_std": 0.7453822493553162,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5872892141342163,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8717837333679199,
+      "rewards/utility_reward_func": 0.10766136646270752,
+      "step": 26
+    },
+    {
+      "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": 9164.0,
+      "completions/max_terminated_length": 9164.0,
+      "completions/mean_length": 5544.21875,
+      "completions/mean_terminated_length": 5544.21875,
+      "completions/min_length": 1633.0,
+      "completions/min_terminated_length": 1633.0,
+      "epoch": 0.057692307692307696,
+      "grad_norm": 0.09411711877281828,
+      "kl": 0.0565032958984375,
+      "learning_rate": 9.509529358847655e-06,
+      "loss": 0.0178,
+      "num_tokens": 8475111.0,
+      "reward": 0.6063368320465088,
+      "reward_std": 0.7418020963668823,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.615506649017334,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9354557991027832,
+      "rewards/utility_reward_func": 0.11898841708898544,
+      "step": 27
+    },
+    {
+      "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": 8644.0,
+      "completions/max_terminated_length": 8644.0,
+      "completions/mean_length": 5628.8125,
+      "completions/mean_terminated_length": 5628.8125,
+      "completions/min_length": 2365.0,
+      "completions/min_terminated_length": 2365.0,
+      "epoch": 0.05982905982905983,
+      "grad_norm": 0.07320321937335796,
+      "kl": 0.1031036376953125,
+      "learning_rate": 9.336880739593415e-06,
+      "loss": 0.0119,
+      "num_tokens": 8780720.0,
+      "reward": 0.6854258179664612,
+      "reward_std": 0.8022749423980713,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.6049659252166748,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9334280490875244,
+      "rewards/utility_reward_func": 0.1348087340593338,
+      "step": 28
+    },
+    {
+      "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": 9075.0,
+      "completions/max_terminated_length": 9075.0,
+      "completions/mean_length": 5317.21875,
+      "completions/mean_terminated_length": 5488.741935483871,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1165.0,
+      "epoch": 0.06196581196581197,
+      "grad_norm": 0.04791948119741524,
+      "kl": 0.07018280029296875,
+      "learning_rate": 9.140576474687263e-06,
+      "loss": -0.0028,
+      "num_tokens": 9102714.0,
+      "reward": 0.47284555435180664,
+      "reward_std": 0.5441389679908752,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.644345223903656,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9321033954620361,
+      "rewards/utility_reward_func": 0.09228507429361343,
+      "step": 29
+    },
+    {
+      "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": 8686.0,
+      "completions/max_terminated_length": 8686.0,
+      "completions/mean_length": 5109.75,
+      "completions/mean_terminated_length": 5274.580645161291,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2237.0,
+      "epoch": 0.0641025641025641,
+      "grad_norm": 0.08100156568534053,
+      "kl": 0.0840911865234375,
+      "learning_rate": 8.92182684520014e-06,
+      "loss": 0.0168,
+      "num_tokens": 9403599.0,
+      "reward": 0.2536351680755615,
+      "reward_std": 0.4151955246925354,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6711061000823975,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9160714149475098,
+      "rewards/utility_reward_func": 0.048409603536129,
+      "step": 30
+    },
+    {
+      "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": 8613.0,
+      "completions/max_terminated_length": 8613.0,
+      "completions/mean_length": 5094.875,
+      "completions/mean_terminated_length": 5259.225806451613,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1385.0,
+      "epoch": 0.06623931623931624,
+      "grad_norm": 0.05053782868196005,
+      "kl": 0.10784912109375,
+      "learning_rate": 8.681980515339464e-06,
+      "loss": 0.0073,
+      "num_tokens": 9713252.0,
+      "reward": 0.2064223438501358,
+      "reward_std": 0.29352596402168274,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7445651292800903,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.926922082901001,
+      "rewards/utility_reward_func": 0.038981422781944275,
+      "step": 31
+    },
+    {
+      "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": 8011.0,
+      "completions/max_terminated_length": 8011.0,
+      "completions/mean_length": 5101.9375,
+      "completions/mean_terminated_length": 5101.9375,
+      "completions/min_length": 2572.0,
+      "completions/min_terminated_length": 2572.0,
+      "epoch": 0.06837606837606838,
+      "grad_norm": 0.05517114109543934,
+      "kl": 0.153045654296875,
+      "learning_rate": 8.422516217485826e-06,
+      "loss": -0.0196,
+      "num_tokens": 10013403.0,
+      "reward": 0.6316404938697815,
+      "reward_std": 0.7787704467773438,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6698119640350342,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8996039628982544,
+      "rewards/utility_reward_func": 0.12401421368122101,
+      "step": 32
+    },
+    {
+      "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": 9270.0,
+      "completions/max_terminated_length": 9270.0,
+      "completions/mean_length": 5491.46875,
+      "completions/mean_terminated_length": 5491.46875,
+      "completions/min_length": 2332.0,
+      "completions/min_terminated_length": 2332.0,
+      "epoch": 0.07051282051282051,
+      "grad_norm": 0.20802919593498223,
+      "kl": 0.469573974609375,
+      "learning_rate": 8.14503363531613e-06,
+      "loss": -0.0119,
+      "num_tokens": 10312689.0,
+      "reward": 0.9118640422821045,
+      "reward_std": 1.0636224746704102,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5969223976135254,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9264756441116333,
+      "rewards/utility_reward_func": 0.18006812036037445,
+      "step": 33
+    },
+    {
+      "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": 9056.0,
+      "completions/max_terminated_length": 9056.0,
+      "completions/mean_length": 5139.9375,
+      "completions/mean_terminated_length": 5305.741935483871,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2597.0,
+      "epoch": 0.07264957264957266,
+      "grad_norm": 0.8404594204961415,
+      "kl": 0.9882049560546875,
+      "learning_rate": 7.85124354122177e-06,
+      "loss": -0.0162,
+      "num_tokens": 10607350.0,
+      "reward": 0.8799901008605957,
+      "reward_std": 1.1067553758621216,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.46376484632492065,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.910142719745636,
+      "rewards/utility_reward_func": 0.1737232506275177,
+      "step": 34
+    },
+    {
+      "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": 9108.0,
+      "completions/max_terminated_length": 9108.0,
+      "completions/mean_length": 5446.0625,
+      "completions/mean_terminated_length": 5621.741935483871,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2769.0,
+      "epoch": 0.07478632478632478,
+      "grad_norm": 0.10678545617196525,
+      "kl": 0.215911865234375,
+      "learning_rate": 7.5429572488279615e-06,
+      "loss": 0.0023,
+      "num_tokens": 10928816.0,
+      "reward": 1.17676842212677,
+      "reward_std": 1.2874033451080322,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7114211320877075,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8751848936080933,
+      "rewards/utility_reward_func": 0.2330363690853119,
+      "step": 35
+    },
+    {
+      "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": 9427.0,
+      "completions/max_terminated_length": 9427.0,
+      "completions/mean_length": 5561.625,
+      "completions/mean_terminated_length": 5561.625,
+      "completions/min_length": 2739.0,
+      "completions/min_terminated_length": 2739.0,
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.13555129034265773,
+      "kl": 0.295166015625,
+      "learning_rate": 7.222075445642904e-06,
+      "loss": 0.0035,
+      "num_tokens": 11225979.0,
+      "reward": 1.0547581911087036,
+      "reward_std": 0.7715986967086792,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6989527344703674,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9386740326881409,
+      "rewards/utility_reward_func": 0.20862412452697754,
+      "step": 36
+    },
+    {
+      "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": 9042.0,
+      "completions/max_terminated_length": 9042.0,
+      "completions/mean_length": 4831.125,
+      "completions/mean_terminated_length": 4986.967741935484,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2146.0,
+      "epoch": 0.07905982905982906,
+      "grad_norm": 0.24559297239149214,
+      "kl": 0.448211669921875,
+      "learning_rate": 6.890576474687264e-06,
+      "loss": -0.0071,
+      "num_tokens": 11511340.0,
+      "reward": 0.502151370048523,
+      "reward_std": 0.784339427947998,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6361043453216553,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9133680462837219,
+      "rewards/utility_reward_func": 0.09812036901712418,
+      "step": 37
+    },
+    {
+      "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": 7620.0,
+      "completions/max_terminated_length": 7620.0,
+      "completions/mean_length": 4775.96875,
+      "completions/mean_terminated_length": 4775.96875,
+      "completions/min_length": 2299.0,
+      "completions/min_terminated_length": 2299.0,
+      "epoch": 0.0811965811965812,
+      "grad_norm": 0.09317535164809768,
+      "kl": 0.346588134765625,
+      "learning_rate": 6.550504137351576e-06,
+      "loss": 0.0011,
+      "num_tokens": 11786543.0,
+      "reward": 0.3758894205093384,
+      "reward_std": 0.5644346475601196,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6146777868270874,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9283109903335571,
+      "rewards/utility_reward_func": 0.07286929339170456,
+      "step": 38
+    },
+    {
+      "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": 8610.0,
+      "completions/max_terminated_length": 8610.0,
+      "completions/mean_length": 5071.4375,
+      "completions/mean_terminated_length": 5235.032258064516,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2368.0,
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.11546537555277975,
+      "kl": 0.41107177734375,
+      "learning_rate": 6.20395509268104e-06,
+      "loss": 0.0004,
+      "num_tokens": 12090692.0,
+      "reward": 0.3179802894592285,
+      "reward_std": 0.403035968542099,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.4927416443824768,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9184781312942505,
+      "rewards/utility_reward_func": 0.06131381541490555,
+      "step": 39
+    },
+    {
+      "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": 9147.0,
+      "completions/max_terminated_length": 9147.0,
+      "completions/mean_length": 4912.9375,
+      "completions/mean_terminated_length": 4912.9375,
+      "completions/min_length": 1763.0,
+      "completions/min_terminated_length": 1763.0,
+      "epoch": 0.08547008547008547,
+      "grad_norm": 0.12462480268811632,
+      "kl": 0.5187835693359375,
+      "learning_rate": 5.8530659307753034e-06,
+      "loss": -0.0116,
+      "num_tokens": 12375359.0,
+      "reward": 0.31748560070991516,
+      "reward_std": 0.4341599941253662,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.4765625,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9282118082046509,
+      "rewards/utility_reward_func": 0.061247408390045166,
+      "step": 40
+    },
+    {
+      "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": 9041.0,
+      "completions/max_terminated_length": 9041.0,
+      "completions/mean_length": 5569.53125,
+      "completions/mean_terminated_length": 5569.53125,
+      "completions/min_length": 1926.0,
+      "completions/min_terminated_length": 1926.0,
+      "epoch": 0.0876068376068376,
+      "grad_norm": 0.5440516549354221,
+      "kl": 0.73486328125,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.0102,
+      "num_tokens": 12677098.0,
+      "reward": 0.4059770703315735,
+      "reward_std": 0.4924428462982178,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6707386374473572,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9652777910232544,
+      "rewards/utility_reward_func": 0.07886820286512375,
+      "step": 41
+    },
+    {
+      "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": 8277.0,
+      "completions/max_terminated_length": 8277.0,
+      "completions/mean_length": 5186.34375,
+      "completions/mean_terminated_length": 5186.34375,
+      "completions/min_length": 2468.0,
+      "completions/min_terminated_length": 2468.0,
+      "epoch": 0.08974358974358974,
+      "grad_norm": 0.07323387926836804,
+      "kl": 0.26275634765625,
+      "learning_rate": 5.1469340692247e-06,
+      "loss": -0.0073,
+      "num_tokens": 12967501.0,
+      "reward": 0.36183637380599976,
+      "reward_std": 0.38023996353149414,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.577970564365387,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9075149297714233,
+      "rewards/utility_reward_func": 0.07007017731666565,
+      "step": 42
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 8859.0,
+      "completions/max_terminated_length": 8859.0,
+      "completions/mean_length": 4840.65625,
+      "completions/mean_terminated_length": 5163.366666666667,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2604.0,
+      "epoch": 0.09188034188034189,
+      "grad_norm": 0.13037129951366888,
+      "kl": 0.36981201171875,
+      "learning_rate": 4.79604490731896e-06,
+      "loss": 0.0331,
+      "num_tokens": 13268952.0,
+      "reward": 0.6934996843338013,
+      "reward_std": 0.9891730546951294,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6411582231521606,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9228783249855042,
+      "rewards/utility_reward_func": 0.13638713955879211,
+      "step": 43
+    },
+    {
+      "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": 8947.0,
+      "completions/max_terminated_length": 8947.0,
+      "completions/mean_length": 4978.1875,
+      "completions/mean_terminated_length": 5138.774193548387,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2443.0,
+      "epoch": 0.09401709401709402,
+      "grad_norm": 0.11949859363278825,
+      "kl": 0.3361663818359375,
+      "learning_rate": 4.449495862648427e-06,
+      "loss": -0.0085,
+      "num_tokens": 13556932.0,
+      "reward": 0.3446043133735657,
+      "reward_std": 0.4400365352630615,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6666632890701294,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.92415452003479,
+      "rewards/utility_reward_func": 0.06660269945859909,
+      "step": 44
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9695.0,
+      "completions/max_terminated_length": 9695.0,
+      "completions/mean_length": 5289.65625,
+      "completions/mean_terminated_length": 5642.3,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2270.0,
+      "epoch": 0.09615384615384616,
+      "grad_norm": 0.10187792105154207,
+      "kl": 0.206329345703125,
+      "learning_rate": 4.109423525312737e-06,
+      "loss": -0.014,
+      "num_tokens": 13878344.0,
+      "reward": 1.069939136505127,
+      "reward_std": 1.3795127868652344,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6028566956520081,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9103050231933594,
+      "rewards/utility_reward_func": 0.2116851955652237,
+      "step": 45
+    },
+    {
+      "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": 9234.0,
+      "completions/max_terminated_length": 9234.0,
+      "completions/mean_length": 5689.28125,
+      "completions/mean_terminated_length": 5689.28125,
+      "completions/min_length": 2629.0,
+      "completions/min_terminated_length": 2629.0,
+      "epoch": 0.09829059829059829,
+      "grad_norm": 0.09907432590761146,
+      "kl": 0.252288818359375,
+      "learning_rate": 3.777924554357096e-06,
+      "loss": 0.0125,
+      "num_tokens": 14191060.0,
+      "reward": 0.8821263313293457,
+      "reward_std": 0.9199132323265076,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6297247409820557,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8932163715362549,
+      "rewards/utility_reward_func": 0.17412066459655762,
+      "step": 46
+    },
+    {
+      "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": 9690.0,
+      "completions/max_terminated_length": 9690.0,
+      "completions/mean_length": 5127.65625,
+      "completions/mean_terminated_length": 5293.064516129032,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3001.0,
+      "epoch": 0.10042735042735043,
+      "grad_norm": 0.117442853699414,
+      "kl": 0.20562744140625,
+      "learning_rate": 3.45704275117204e-06,
+      "loss": -0.0347,
+      "num_tokens": 14487972.0,
+      "reward": 0.9619556069374084,
+      "reward_std": 1.1848845481872559,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.7243213057518005,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8971354365348816,
+      "rewards/utility_reward_func": 0.19012930989265442,
+      "step": 47
+    },
+    {
+      "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": 9927.0,
+      "completions/max_terminated_length": 9927.0,
+      "completions/mean_length": 5571.90625,
+      "completions/mean_terminated_length": 5571.90625,
+      "completions/min_length": 2299.0,
+      "completions/min_terminated_length": 2299.0,
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.11263502888805668,
+      "kl": 0.3785247802734375,
+      "learning_rate": 3.1487564587782306e-06,
+      "loss": -0.0166,
+      "num_tokens": 14796817.0,
+      "reward": 0.6865731477737427,
+      "reward_std": 0.9901103973388672,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7390385866165161,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9030382037162781,
+      "rewards/utility_reward_func": 0.13498620688915253,
+      "step": 48
+    },
+    {
+      "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": 8879.0,
+      "completions/max_terminated_length": 8879.0,
+      "completions/mean_length": 5262.96875,
+      "completions/mean_terminated_length": 5432.741935483871,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2690.0,
+      "epoch": 0.1047008547008547,
+      "grad_norm": 0.07011556216519438,
+      "kl": 0.29779052734375,
+      "learning_rate": 2.8549663646838717e-06,
+      "loss": -0.0141,
+      "num_tokens": 15126585.0,
+      "reward": 0.11910636723041534,
+      "reward_std": 0.14076979458332062,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5717679262161255,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.896297812461853,
+      "rewards/utility_reward_func": 0.02152765914797783,
+      "step": 49
+    },
+    {
+      "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": 8900.0,
+      "completions/max_terminated_length": 8900.0,
+      "completions/mean_length": 5700.8125,
+      "completions/mean_terminated_length": 5700.8125,
+      "completions/min_length": 2535.0,
+      "completions/min_terminated_length": 2535.0,
+      "epoch": 0.10683760683760683,
+      "grad_norm": 0.41419598815650255,
+      "kl": 0.519134521484375,
+      "learning_rate": 2.577483782514174e-06,
+      "loss": 0.0138,
+      "num_tokens": 15442066.0,
+      "reward": 0.22905027866363525,
+      "reward_std": 0.3577722907066345,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7121212482452393,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9120686650276184,
+      "rewards/utility_reward_func": 0.04351647198200226,
+      "step": 50
+    },
+    {
+      "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": 10034.0,
+      "completions/max_terminated_length": 10034.0,
+      "completions/mean_length": 5278.96875,
+      "completions/mean_terminated_length": 5278.96875,
+      "completions/min_length": 1832.0,
+      "completions/min_terminated_length": 1832.0,
+      "epoch": 0.10897435897435898,
+      "grad_norm": 0.09133923773827608,
+      "kl": 0.3924560546875,
+      "learning_rate": 2.3180194846605362e-06,
+      "loss": 0.0272,
+      "num_tokens": 15741043.0,
+      "reward": 0.27375099062919617,
+      "reward_std": 0.4570543169975281,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5625715255737305,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9071673154830933,
+      "rewards/utility_reward_func": 0.05245624855160713,
+      "step": 51
+    },
+    {
+      "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": 7426.0,
+      "completions/max_terminated_length": 7426.0,
+      "completions/mean_length": 4905.0625,
+      "completions/mean_terminated_length": 5063.290322580645,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2637.0,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.06136048782432445,
+      "kl": 0.271026611328125,
+      "learning_rate": 2.078173154799861e-06,
+      "loss": -0.0061,
+      "num_tokens": 16037534.0,
+      "reward": 0.24373172223567963,
+      "reward_std": 0.32430875301361084,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5638384222984314,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.924727201461792,
+      "rewards/utility_reward_func": 0.04644863307476044,
+      "step": 52
+    },
+    {
+      "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": 0.0625,
+      "completions/max_length": 9527.0,
+      "completions/max_terminated_length": 9527.0,
+      "completions/mean_length": 4619.46875,
+      "completions/mean_terminated_length": 4927.433333333333,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1581.0,
+      "epoch": 0.11324786324786325,
+      "grad_norm": 0.05808359717947583,
+      "kl": 0.22265625,
+      "learning_rate": 1.859423525312737e-06,
+      "loss": 0.0079,
+      "num_tokens": 16335450.0,
+      "reward": 0.21148943901062012,
+      "reward_std": 0.2547459900379181,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6628144979476929,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9208818674087524,
+      "rewards/utility_reward_func": 0.03998114913702011,
+      "step": 53
+    },
+    {
+      "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": 9463.0,
+      "completions/max_terminated_length": 9463.0,
+      "completions/mean_length": 5099.0,
+      "completions/mean_terminated_length": 5263.4838709677415,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2053.0,
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.08558113646292538,
+      "kl": 0.288360595703125,
+      "learning_rate": 1.6631192604065856e-06,
+      "loss": 0.0064,
+      "num_tokens": 16636420.0,
+      "reward": 0.28765812516212463,
+      "reward_std": 0.46562910079956055,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6401413679122925,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9321180582046509,
+      "rewards/utility_reward_func": 0.05521716922521591,
+      "step": 54
+    },
+    {
+      "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": 8165.0,
+      "completions/max_terminated_length": 8165.0,
+      "completions/mean_length": 4702.5,
+      "completions/mean_terminated_length": 4854.193548387097,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1435.0,
+      "epoch": 0.11752136752136752,
+      "grad_norm": 0.06964602043928762,
+      "kl": 0.302154541015625,
+      "learning_rate": 1.490470641152345e-06,
+      "loss": -0.0101,
+      "num_tokens": 16923891.0,
+      "reward": 0.1673395037651062,
+      "reward_std": 0.2552884519100189,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5235062837600708,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9171998500823975,
+      "rewards/utility_reward_func": 0.0311797596514225,
+      "step": 55
+    },
+    {
+      "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": 8940.0,
+      "completions/max_terminated_length": 8940.0,
+      "completions/mean_length": 5183.78125,
+      "completions/mean_terminated_length": 5351.0,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2205.0,
+      "epoch": 0.11965811965811966,
+      "grad_norm": 0.06968922813852535,
+      "kl": 0.2431640625,
+      "learning_rate": 1.3425421036992098e-06,
+      "loss": 0.002,
+      "num_tokens": 17234992.0,
+      "reward": 0.3152891993522644,
+      "reward_std": 0.4457589387893677,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6660599708557129,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8508894443511963,
+      "rewards/utility_reward_func": 0.0607544481754303,
+      "step": 56
+    },
+    {
+      "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": 7843.0,
+      "completions/max_terminated_length": 7843.0,
+      "completions/mean_length": 4938.625,
+      "completions/mean_terminated_length": 4938.625,
+      "completions/min_length": 2325.0,
+      "completions/min_terminated_length": 2325.0,
+      "epoch": 0.12179487179487179,
+      "grad_norm": 0.10517713287333766,
+      "kl": 0.155487060546875,
+      "learning_rate": 1.2202456766718092e-06,
+      "loss": -0.0089,
+      "num_tokens": 17528965.0,
+      "reward": 0.6346352100372314,
+      "reward_std": 0.614031195640564,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7036257982254028,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8766368627548218,
+      "rewards/utility_reward_func": 0.12461098283529282,
+      "step": 57
+    },
+    {
+      "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": 9878.0,
+      "completions/max_terminated_length": 9878.0,
+      "completions/mean_length": 5030.96875,
+      "completions/mean_terminated_length": 5030.96875,
+      "completions/min_length": 2257.0,
+      "completions/min_terminated_length": 2257.0,
+      "epoch": 0.12393162393162394,
+      "grad_norm": 0.11120189846420504,
+      "kl": 0.26873779296875,
+      "learning_rate": 1.1243353582104554e-06,
+      "loss": -0.0108,
+      "num_tokens": 17819650.0,
+      "reward": 0.22769173979759216,
+      "reward_std": 0.24561473727226257,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6461749076843262,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.923301100730896,
+      "rewards/utility_reward_func": 0.043224453926086426,
+      "step": 58
+    },
+    {
+      "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": 0.09375,
+      "completions/max_length": 9634.0,
+      "completions/max_terminated_length": 9634.0,
+      "completions/mean_length": 4724.53125,
+      "completions/mean_terminated_length": 5213.275862068966,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2819.0,
+      "epoch": 0.12606837606837606,
+      "grad_norm": 0.07749116939560954,
+      "kl": 0.22208786010742188,
+      "learning_rate": 1.0554024673218806e-06,
+      "loss": 0.0051,
+      "num_tokens": 18126661.0,
+      "reward": 0.3350598216056824,
+      "reward_std": 0.4074792265892029,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.5758612751960754,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.8875744342803955,
+      "rewards/utility_reward_func": 0.06471927464008331,
+      "step": 59
+    },
+    {
+      "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": 9403.0,
+      "completions/max_terminated_length": 9403.0,
+      "completions/mean_length": 5518.96875,
+      "completions/mean_terminated_length": 5518.96875,
+      "completions/min_length": 2955.0,
+      "completions/min_terminated_length": 2955.0,
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.11648518986862501,
+      "kl": 0.1890869140625,
+      "learning_rate": 1.013871998200924e-06,
+      "loss": 0.0471,
+      "num_tokens": 18432399.0,
+      "reward": 0.4429653584957123,
+      "reward_std": 0.6282458305358887,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.6058531999588013,
+      "rewards/successful_no_deal_reward_func": 0.0,
+      "rewards/successful_parsing_reward_func": 0.9258173108100891,
+      "rewards/utility_reward_func": 0.08628673851490021,
+      "step": 60
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 18432399,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "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": 1,
+  "trial_name": null,
+  "trial_params": null
+}