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_seller_20250927_140329_completed/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 sha256:0d7eef59149586d2c22520880858c74b6047b6b556bb8429d43c6a7e1aaed5b6
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46d6fe177c0f4168738fbb789dd8f15f88c48e9c444dbc12a64277b9c5f35db
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf254bcaa49e44d0758061c770660d5468cbbdab3128476acb6ed7bbd61831a9
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2649ee0ca088bc26e3748c9d1009d7b95fa73d286b59b42a613e878002782c8e
+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": 0.0,
+      "completions/max_length": 8692.0,
+      "completions/max_terminated_length": 8692.0,
+      "completions/mean_length": 5263.90625,
+      "completions/mean_terminated_length": 5263.90625,
+      "completions/min_length": 2046.0,
+      "completions/min_terminated_length": 2046.0,
+      "epoch": 0.002136752136752137,
+      "grad_norm": 0.13524121910390705,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0183,
+      "num_tokens": 321111.0,
+      "reward": 13.089506149291992,
+      "reward_std": 5.828127861022949,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8307911157608032,
+      "rewards/successful_no_deal_reward_func": 0.453125,
+      "rewards/successful_parsing_reward_func": 0.8847842216491699,
+      "rewards/utility_reward_func": 0.398827463388443,
+      "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": 0.03125,
+      "completions/max_length": 8858.0,
+      "completions/max_terminated_length": 8858.0,
+      "completions/mean_length": 5393.53125,
+      "completions/mean_terminated_length": 5567.5161290322585,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2933.0,
+      "epoch": 0.004273504273504274,
+      "grad_norm": 0.14125326998143348,
+      "kl": 0.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0127,
+      "num_tokens": 681435.0,
+      "reward": 10.29290771484375,
+      "reward_std": 9.241214752197266,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7181423306465149,
+      "rewards/successful_no_deal_reward_func": 0.34375,
+      "rewards/successful_parsing_reward_func": 0.7481849789619446,
+      "rewards/utility_reward_func": 0.31008416414260864,
+      "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": 0.03125,
+      "completions/max_length": 10108.0,
+      "completions/max_terminated_length": 10108.0,
+      "completions/mean_length": 5457.53125,
+      "completions/mean_terminated_length": 5633.580645161291,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2403.0,
+      "epoch": 0.00641025641025641,
+      "grad_norm": 0.12193342337851935,
+      "kl": 0.003643035888671875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": -0.0081,
+      "num_tokens": 1012660.0,
+      "reward": 13.357504844665527,
+      "reward_std": 5.522988796234131,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8510912656784058,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.9299927949905396,
+      "rewards/utility_reward_func": 0.40858402848243713,
+      "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": 10325.0,
+      "completions/max_terminated_length": 10325.0,
+      "completions/mean_length": 5183.53125,
+      "completions/mean_terminated_length": 5350.741935483871,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2541.0,
+      "epoch": 0.008547008547008548,
+      "grad_norm": 0.09992499424145265,
+      "kl": 0.0036802291870117188,
+      "learning_rate": 1.2e-05,
+      "loss": -0.0117,
+      "num_tokens": 1352107.0,
+      "reward": 11.811685562133789,
+      "reward_std": 5.946799278259277,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8307291865348816,
+      "rewards/successful_no_deal_reward_func": 0.390625,
+      "rewards/successful_parsing_reward_func": 0.8160351514816284,
+      "rewards/utility_reward_func": 0.35854610800743103,
+      "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": 0.03125,
+      "completions/max_length": 10002.0,
+      "completions/max_terminated_length": 10002.0,
+      "completions/mean_length": 6005.25,
+      "completions/mean_terminated_length": 6198.967741935484,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2885.0,
+      "epoch": 0.010683760683760684,
+      "grad_norm": 0.09868345069469578,
+      "kl": 0.0058193206787109375,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0168,
+      "num_tokens": 1706933.0,
+      "reward": 6.7459492683410645,
+      "reward_std": 3.5795390605926514,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8775534629821777,
+      "rewards/successful_no_deal_reward_func": 0.578125,
+      "rewards/successful_parsing_reward_func": 0.9091060161590576,
+      "rewards/utility_reward_func": 0.18297193944454193,
+      "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": 0.03125,
+      "completions/max_length": 10113.0,
+      "completions/max_terminated_length": 10113.0,
+      "completions/mean_length": 5148.71875,
+      "completions/mean_terminated_length": 5314.806451612903,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2663.0,
+      "epoch": 0.01282051282051282,
+      "grad_norm": 0.07418858759257596,
+      "kl": 0.014812469482421875,
+      "learning_rate": 2e-05,
+      "loss": 0.019,
+      "num_tokens": 2024143.0,
+      "reward": 7.305600643157959,
+      "reward_std": 2.82883358001709,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8985738754272461,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8988806009292603,
+      "rewards/utility_reward_func": 0.2021118402481079,
+      "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": 0.0625,
+      "completions/max_length": 9059.0,
+      "completions/max_terminated_length": 9059.0,
+      "completions/mean_length": 5224.0625,
+      "completions/mean_terminated_length": 5572.333333333333,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2033.0,
+      "epoch": 0.014957264957264958,
+      "grad_norm": 0.0770740966039767,
+      "kl": 0.023563385009765625,
+      "learning_rate": 2e-05,
+      "loss": -0.0037,
+      "num_tokens": 2368266.0,
+      "reward": 7.440418243408203,
+      "reward_std": 3.8883907794952393,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7994791865348816,
+      "rewards/successful_no_deal_reward_func": 0.53125,
+      "rewards/successful_parsing_reward_func": 0.8668774366378784,
+      "rewards/utility_reward_func": 0.20834481716156006,
+      "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": 0.0,
+      "completions/max_length": 10161.0,
+      "completions/max_terminated_length": 10161.0,
+      "completions/mean_length": 6345.90625,
+      "completions/mean_terminated_length": 6345.90625,
+      "completions/min_length": 3192.0,
+      "completions/min_terminated_length": 3192.0,
+      "epoch": 0.017094017094017096,
+      "grad_norm": 0.13080769358982583,
+      "kl": 0.03223419189453125,
+      "learning_rate": 2e-05,
+      "loss": 0.0234,
+      "num_tokens": 2727219.0,
+      "reward": 6.599692344665527,
+      "reward_std": 3.7256505489349365,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8149601221084595,
+      "rewards/successful_no_deal_reward_func": 0.59375,
+      "rewards/successful_parsing_reward_func": 0.8814631700515747,
+      "rewards/utility_reward_func": 0.17787665128707886,
+      "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": 0.0,
+      "completions/max_length": 8574.0,
+      "completions/max_terminated_length": 8574.0,
+      "completions/mean_length": 5724.71875,
+      "completions/mean_terminated_length": 5724.71875,
+      "completions/min_length": 3321.0,
+      "completions/min_terminated_length": 3321.0,
+      "epoch": 0.019230769230769232,
+      "grad_norm": 0.2718145594331439,
+      "kl": 0.06011962890625,
+      "learning_rate": 2e-05,
+      "loss": 0.0504,
+      "num_tokens": 3052863.0,
+      "reward": 2.8698644638061523,
+      "reward_std": 1.5825773477554321,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9517256021499634,
+      "rewards/successful_no_deal_reward_func": 0.84375,
+      "rewards/successful_parsing_reward_func": 0.946114182472229,
+      "rewards/utility_reward_func": 0.04454435780644417,
+      "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": 0.0,
+      "completions/max_length": 9763.0,
+      "completions/max_terminated_length": 9763.0,
+      "completions/mean_length": 5663.1875,
+      "completions/mean_terminated_length": 5663.1875,
+      "completions/min_length": 2606.0,
+      "completions/min_terminated_length": 2606.0,
+      "epoch": 0.021367521367521368,
+      "grad_norm": 0.1574477673918289,
+      "kl": 0.047687530517578125,
+      "learning_rate": 2e-05,
+      "loss": -0.0117,
+      "num_tokens": 3387072.0,
+      "reward": 2.5430192947387695,
+      "reward_std": 1.3082820177078247,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9754464626312256,
+      "rewards/successful_no_deal_reward_func": 0.8125,
+      "rewards/successful_parsing_reward_func": 0.9150803089141846,
+      "rewards/utility_reward_func": 0.034715551882982254,
+      "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": 0.0625,
+      "completions/max_length": 9994.0,
+      "completions/max_terminated_length": 9994.0,
+      "completions/mean_length": 5518.375,
+      "completions/mean_terminated_length": 5886.266666666666,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3232.0,
+      "epoch": 0.023504273504273504,
+      "grad_norm": 0.14592223795177592,
+      "kl": 0.050079345703125,
+      "learning_rate": 2e-05,
+      "loss": -0.0075,
+      "num_tokens": 3740116.0,
+      "reward": 2.410231828689575,
+      "reward_std": 0.9183810949325562,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9459468126296997,
+      "rewards/successful_no_deal_reward_func": 0.828125,
+      "rewards/successful_parsing_reward_func": 0.8924851417541504,
+      "rewards/utility_reward_func": 0.029942119494080544,
+      "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": 0.0,
+      "completions/max_length": 9545.0,
+      "completions/max_terminated_length": 9545.0,
+      "completions/mean_length": 6346.125,
+      "completions/mean_terminated_length": 6346.125,
+      "completions/min_length": 3742.0,
+      "completions/min_terminated_length": 3742.0,
+      "epoch": 0.02564102564102564,
+      "grad_norm": 3.311026969817496,
+      "kl": 0.34075927734375,
+      "learning_rate": 2e-05,
+      "loss": 0.0373,
+      "num_tokens": 4094936.0,
+      "reward": 2.6738317012786865,
+      "reward_std": 0.92072594165802,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8866342306137085,
+      "rewards/successful_no_deal_reward_func": 0.84375,
+      "rewards/successful_parsing_reward_func": 0.9354434013366699,
+      "rewards/utility_reward_func": 0.038262464106082916,
+      "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": 0.0,
+      "completions/max_length": 10170.0,
+      "completions/max_terminated_length": 10170.0,
+      "completions/mean_length": 5580.75,
+      "completions/mean_terminated_length": 5580.75,
+      "completions/min_length": 1848.0,
+      "completions/min_terminated_length": 1848.0,
+      "epoch": 0.027777777777777776,
+      "grad_norm": 18.64484255853941,
+      "kl": 0.9246597290039062,
+      "learning_rate": 2e-05,
+      "loss": 0.0331,
+      "num_tokens": 4433282.0,
+      "reward": 12.720104217529297,
+      "reward_std": 8.21227741241455,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7824472188949585,
+      "rewards/successful_no_deal_reward_func": 0.40625,
+      "rewards/successful_parsing_reward_func": 0.8727678060531616,
+      "rewards/utility_reward_func": 0.38827773928642273,
+      "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": 9335.0,
+      "completions/max_terminated_length": 9335.0,
+      "completions/mean_length": 5595.25,
+      "completions/mean_terminated_length": 5595.25,
+      "completions/min_length": 2111.0,
+      "completions/min_terminated_length": 2111.0,
+      "epoch": 0.029914529914529916,
+      "grad_norm": 0.07969555942261197,
+      "kl": 0.0496368408203125,
+      "learning_rate": 2e-05,
+      "loss": 0.0091,
+      "num_tokens": 4779367.0,
+      "reward": 13.972558975219727,
+      "reward_std": 6.738990306854248,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8297809958457947,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.8079355955123901,
+      "rewards/utility_reward_func": 0.4298241138458252,
+      "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": 8997.0,
+      "completions/max_terminated_length": 8997.0,
+      "completions/mean_length": 5286.6875,
+      "completions/mean_terminated_length": 5457.225806451613,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2698.0,
+      "epoch": 0.03205128205128205,
+      "grad_norm": 0.06101731197561454,
+      "kl": 0.05796051025390625,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "num_tokens": 5122315.0,
+      "reward": 15.198302268981934,
+      "reward_std": 7.127710342407227,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8440600633621216,
+      "rewards/successful_no_deal_reward_func": 0.4375,
+      "rewards/successful_parsing_reward_func": 0.8397558331489563,
+      "rewards/utility_reward_func": 0.4697473347187042,
+      "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": 0.03125,
+      "completions/max_length": 9528.0,
+      "completions/max_terminated_length": 9528.0,
+      "completions/mean_length": 5658.65625,
+      "completions/mean_terminated_length": 5841.193548387097,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2804.0,
+      "epoch": 0.03418803418803419,
+      "grad_norm": 0.1035264599440814,
+      "kl": 0.056243896484375,
+      "learning_rate": 2e-05,
+      "loss": 0.0203,
+      "num_tokens": 5477111.0,
+      "reward": 12.287153244018555,
+      "reward_std": 6.766469955444336,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7561259865760803,
+      "rewards/successful_no_deal_reward_func": 0.390625,
+      "rewards/successful_parsing_reward_func": 0.8038890957832336,
+      "rewards/utility_reward_func": 0.37468421459198,
+      "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": 0.0625,
+      "completions/max_length": 9185.0,
+      "completions/max_terminated_length": 9185.0,
+      "completions/mean_length": 4713.1875,
+      "completions/mean_terminated_length": 5027.4,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2639.0,
+      "epoch": 0.03632478632478633,
+      "grad_norm": 0.0433494341400444,
+      "kl": 0.070892333984375,
+      "learning_rate": 2e-05,
+      "loss": -0.0119,
+      "num_tokens": 5795811.0,
+      "reward": 8.16100788116455,
+      "reward_std": 2.8902506828308105,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9079613089561462,
+      "rewards/successful_no_deal_reward_func": 0.453125,
+      "rewards/successful_parsing_reward_func": 0.8510779142379761,
+      "rewards/utility_reward_func": 0.23439928889274597,
+      "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": 9330.0,
+      "completions/max_terminated_length": 9330.0,
+      "completions/mean_length": 5696.59375,
+      "completions/mean_terminated_length": 5880.354838709677,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2147.0,
+      "epoch": 0.038461538461538464,
+      "grad_norm": 0.07053711116404891,
+      "kl": 0.065277099609375,
+      "learning_rate": 2e-05,
+      "loss": 0.0277,
+      "num_tokens": 6150385.0,
+      "reward": 7.081500053405762,
+      "reward_std": 4.265430927276611,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.7555555701255798,
+      "rewards/successful_no_deal_reward_func": 0.375,
+      "rewards/successful_parsing_reward_func": 0.862622857093811,
+      "rewards/utility_reward_func": 0.20201024413108826,
+      "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": 0.0,
+      "completions/max_length": 10173.0,
+      "completions/max_terminated_length": 10173.0,
+      "completions/mean_length": 6548.21875,
+      "completions/mean_terminated_length": 6548.21875,
+      "completions/min_length": 2994.0,
+      "completions/min_terminated_length": 2994.0,
+      "epoch": 0.0405982905982906,
+      "grad_norm": 0.09672399682608723,
+      "kl": 0.069854736328125,
+      "learning_rate": 2e-05,
+      "loss": 0.0237,
+      "num_tokens": 6513232.0,
+      "reward": 7.472269058227539,
+      "reward_std": 3.3596060276031494,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8278397917747498,
+      "rewards/successful_no_deal_reward_func": 0.4375,
+      "rewards/successful_parsing_reward_func": 0.9014575481414795,
+      "rewards/utility_reward_func": 0.2120613008737564,
+      "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": 10364.0,
+      "completions/max_terminated_length": 10364.0,
+      "completions/mean_length": 5375.28125,
+      "completions/mean_terminated_length": 5548.677419354839,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2140.0,
+      "epoch": 0.042735042735042736,
+      "grad_norm": 0.04520712883700852,
+      "kl": 0.0749664306640625,
+      "learning_rate": 2e-05,
+      "loss": -0.0097,
+      "num_tokens": 6855140.0,
+      "reward": 9.597513198852539,
+      "reward_std": 3.5805306434631348,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8538690805435181,
+      "rewards/successful_no_deal_reward_func": 0.453125,
+      "rewards/successful_parsing_reward_func": 0.8160218596458435,
+      "rewards/utility_reward_func": 0.28284043073654175,
+      "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": 0.0625,
+      "completions/max_length": 9343.0,
+      "completions/max_terminated_length": 9343.0,
+      "completions/mean_length": 5354.9375,
+      "completions/mean_terminated_length": 5711.933333333333,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2588.0,
+      "epoch": 0.04487179487179487,
+      "grad_norm": 0.13324734003119365,
+      "kl": 0.07419586181640625,
+      "learning_rate": 2e-05,
+      "loss": 0.0278,
+      "num_tokens": 7204532.0,
+      "reward": 8.765981674194336,
+      "reward_std": 5.346878528594971,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7741690874099731,
+      "rewards/successful_no_deal_reward_func": 0.515625,
+      "rewards/successful_parsing_reward_func": 0.8718490600585938,
+      "rewards/utility_reward_func": 0.25311893224716187,
+      "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": 0.0,
+      "completions/max_length": 8788.0,
+      "completions/max_terminated_length": 8788.0,
+      "completions/mean_length": 5734.65625,
+      "completions/mean_terminated_length": 5734.65625,
+      "completions/min_length": 3138.0,
+      "completions/min_terminated_length": 3138.0,
+      "epoch": 0.04700854700854701,
+      "grad_norm": 0.04722558093607279,
+      "kl": 0.0833892822265625,
+      "learning_rate": 2e-05,
+      "loss": 0.0062,
+      "num_tokens": 7540679.0,
+      "reward": 10.483989715576172,
+      "reward_std": 2.554959297180176,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8787944912910461,
+      "rewards/successful_no_deal_reward_func": 0.546875,
+      "rewards/successful_parsing_reward_func": 0.898411750793457,
+      "rewards/utility_reward_func": 0.3089068531990051,
+      "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": 0.0,
+      "completions/max_length": 8693.0,
+      "completions/max_terminated_length": 8693.0,
+      "completions/mean_length": 5031.03125,
+      "completions/mean_terminated_length": 5031.03125,
+      "completions/min_length": 2639.0,
+      "completions/min_terminated_length": 2639.0,
+      "epoch": 0.049145299145299144,
+      "grad_norm": 0.07640969114726487,
+      "kl": 0.08179473876953125,
+      "learning_rate": 2e-05,
+      "loss": 0.0515,
+      "num_tokens": 7855954.0,
+      "reward": 10.10434341430664,
+      "reward_std": 2.6132378578186035,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8531621694564819,
+      "rewards/successful_no_deal_reward_func": 0.609375,
+      "rewards/successful_parsing_reward_func": 0.864062488079071,
+      "rewards/utility_reward_func": 0.29410821199417114,
+      "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": 0.0,
+      "completions/max_length": 9740.0,
+      "completions/max_terminated_length": 9740.0,
+      "completions/mean_length": 6291.0625,
+      "completions/mean_terminated_length": 6291.0625,
+      "completions/min_length": 2627.0,
+      "completions/min_terminated_length": 2627.0,
+      "epoch": 0.05128205128205128,
+      "grad_norm": 0.0976001686813385,
+      "kl": 0.0815277099609375,
+      "learning_rate": 2e-05,
+      "loss": -0.0036,
+      "num_tokens": 8217282.0,
+      "reward": 10.006271362304688,
+      "reward_std": 4.209831237792969,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.779737114906311,
+      "rewards/successful_no_deal_reward_func": 0.578125,
+      "rewards/successful_parsing_reward_func": 0.8936668634414673,
+      "rewards/utility_reward_func": 0.2920268774032593,
+      "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": 0.0,
+      "completions/max_length": 8830.0,
+      "completions/max_terminated_length": 8830.0,
+      "completions/mean_length": 6104.3125,
+      "completions/mean_terminated_length": 6104.3125,
+      "completions/min_length": 3625.0,
+      "completions/min_terminated_length": 3625.0,
+      "epoch": 0.053418803418803416,
+      "grad_norm": 0.0874243589318564,
+      "kl": 0.082855224609375,
+      "learning_rate": 2e-05,
+      "loss": 0.0239,
+      "num_tokens": 8576582.0,
+      "reward": 3.0176899433135986,
+      "reward_std": 1.4519190788269043,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7582464814186096,
+      "rewards/successful_no_deal_reward_func": 0.625,
+      "rewards/successful_parsing_reward_func": 0.893723726272583,
+      "rewards/utility_reward_func": 0.05758309364318848,
+      "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": 0.09375,
+      "completions/max_length": 8970.0,
+      "completions/max_terminated_length": 8970.0,
+      "completions/mean_length": 5440.53125,
+      "completions/mean_terminated_length": 6003.3448275862065,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3231.0,
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.19827483452745304,
+      "kl": 0.111328125,
+      "learning_rate": 2e-05,
+      "loss": -0.0174,
+      "num_tokens": 8944229.0,
+      "reward": 2.325728178024292,
+      "reward_std": 1.4577386379241943,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.791290819644928,
+      "rewards/successful_no_deal_reward_func": 0.59375,
+      "rewards/successful_parsing_reward_func": 0.888812243938446,
+      "rewards/utility_reward_func": 0.03546559810638428,
+      "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": 10391.0,
+      "completions/max_terminated_length": 10391.0,
+      "completions/mean_length": 5703.25,
+      "completions/mean_terminated_length": 5703.25,
+      "completions/min_length": 2291.0,
+      "completions/min_terminated_length": 2291.0,
+      "epoch": 0.057692307692307696,
+      "grad_norm": 0.07807090906536783,
+      "kl": 0.07916259765625,
+      "learning_rate": 2e-05,
+      "loss": -0.0036,
+      "num_tokens": 9298581.0,
+      "reward": 2.7880592346191406,
+      "reward_std": 1.5752832889556885,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8456540703773499,
+      "rewards/successful_no_deal_reward_func": 0.65625,
+      "rewards/successful_parsing_reward_func": 0.8798115253448486,
+      "rewards/utility_reward_func": 0.04864208400249481,
+      "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": 0.03125,
+      "completions/max_length": 9834.0,
+      "completions/max_terminated_length": 9834.0,
+      "completions/mean_length": 5653.6875,
+      "completions/mean_terminated_length": 5836.064516129032,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2561.0,
+      "epoch": 0.05982905982905983,
+      "grad_norm": 0.04981913139295697,
+      "kl": 0.0860748291015625,
+      "learning_rate": 2e-05,
+      "loss": -0.0036,
+      "num_tokens": 9645929.0,
+      "reward": 2.931215763092041,
+      "reward_std": 2.0780129432678223,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9096354246139526,
+      "rewards/successful_no_deal_reward_func": 0.65625,
+      "rewards/successful_parsing_reward_func": 0.9329229593276978,
+      "rewards/utility_reward_func": 0.05302366986870766,
+      "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": 0.0,
+      "completions/max_length": 10930.0,
+      "completions/max_terminated_length": 10930.0,
+      "completions/mean_length": 5840.9375,
+      "completions/mean_terminated_length": 5840.9375,
+      "completions/min_length": 2371.0,
+      "completions/min_terminated_length": 2371.0,
+      "epoch": 0.06196581196581197,
+      "grad_norm": 0.43603578566490725,
+      "kl": 0.163726806640625,
+      "learning_rate": 2e-05,
+      "loss": 0.0195,
+      "num_tokens": 10014133.0,
+      "reward": 11.773115158081055,
+      "reward_std": 6.266353607177734,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.724196195602417,
+      "rewards/successful_no_deal_reward_func": 0.359375,
+      "rewards/successful_parsing_reward_func": 0.7893494367599487,
+      "rewards/utility_reward_func": 0.35874617099761963,
+      "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": 0.0,
+      "completions/max_length": 9489.0,
+      "completions/max_terminated_length": 9489.0,
+      "completions/mean_length": 5918.46875,
+      "completions/mean_terminated_length": 5918.46875,
+      "completions/min_length": 2629.0,
+      "completions/min_terminated_length": 2629.0,
+      "epoch": 0.0641025641025641,
+      "grad_norm": 1.5094761839926756,
+      "kl": 0.1993255615234375,
+      "learning_rate": 2e-05,
+      "loss": -0.0006,
+      "num_tokens": 10389894.0,
+      "reward": 10.936625480651855,
+      "reward_std": 4.752138137817383,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7032060623168945,
+      "rewards/successful_no_deal_reward_func": 0.359375,
+      "rewards/successful_parsing_reward_func": 0.7675862312316895,
+      "rewards/utility_reward_func": 0.331005722284317,
+      "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": 11193.0,
+      "completions/max_terminated_length": 11193.0,
+      "completions/mean_length": 5057.46875,
+      "completions/mean_terminated_length": 5220.612903225807,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1654.0,
+      "epoch": 0.06623931623931624,
+      "grad_norm": 0.045208953033285613,
+      "kl": 0.082183837890625,
+      "learning_rate": 2e-05,
+      "loss": -0.0222,
+      "num_tokens": 10722626.0,
+      "reward": 12.012799263000488,
+      "reward_std": 5.420868873596191,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9069940447807312,
+      "rewards/successful_no_deal_reward_func": 0.4375,
+      "rewards/successful_parsing_reward_func": 0.7996008992195129,
+      "rewards/utility_reward_func": 0.36348801851272583,
+      "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": 0.03125,
+      "completions/max_length": 10599.0,
+      "completions/max_terminated_length": 10599.0,
+      "completions/mean_length": 5630.34375,
+      "completions/mean_terminated_length": 5811.967741935484,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2850.0,
+      "epoch": 0.06837606837606838,
+      "grad_norm": 0.045623682683562025,
+      "kl": 0.0789337158203125,
+      "learning_rate": 2e-05,
+      "loss": -0.0068,
+      "num_tokens": 11085010.0,
+      "reward": 10.26258659362793,
+      "reward_std": 7.012184143066406,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8258308172225952,
+      "rewards/successful_no_deal_reward_func": 0.375,
+      "rewards/successful_parsing_reward_func": 0.8364831209182739,
+      "rewards/utility_reward_func": 0.30737853050231934,
+      "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": 0.03125,
+      "completions/max_length": 8891.0,
+      "completions/max_terminated_length": 8891.0,
+      "completions/mean_length": 4892.84375,
+      "completions/mean_terminated_length": 5050.677419354839,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2852.0,
+      "epoch": 0.07051282051282051,
+      "grad_norm": 0.05892387943921885,
+      "kl": 0.0875091552734375,
+      "learning_rate": 2e-05,
+      "loss": 0.0001,
+      "num_tokens": 11423845.0,
+      "reward": 9.62917423248291,
+      "reward_std": 4.717038631439209,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8024696111679077,
+      "rewards/successful_no_deal_reward_func": 0.4375,
+      "rewards/successful_parsing_reward_func": 0.809061586856842,
+      "rewards/utility_reward_func": 0.2846111059188843,
+      "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": 0.0,
+      "completions/max_length": 9959.0,
+      "completions/max_terminated_length": 9959.0,
+      "completions/mean_length": 5024.46875,
+      "completions/mean_terminated_length": 5024.46875,
+      "completions/min_length": 2542.0,
+      "completions/min_terminated_length": 2542.0,
+      "epoch": 0.07264957264957266,
+      "grad_norm": 0.04089145594446082,
+      "kl": 0.084930419921875,
+      "learning_rate": 2e-05,
+      "loss": -0.0046,
+      "num_tokens": 11749425.0,
+      "reward": 9.058746337890625,
+      "reward_std": 3.817065715789795,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8897197246551514,
+      "rewards/successful_no_deal_reward_func": 0.46875,
+      "rewards/successful_parsing_reward_func": 0.8192257285118103,
+      "rewards/utility_reward_func": 0.26423048973083496,
+      "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": 0.0,
+      "completions/max_length": 9616.0,
+      "completions/max_terminated_length": 9616.0,
+      "completions/mean_length": 5304.84375,
+      "completions/mean_terminated_length": 5304.84375,
+      "completions/min_length": 2674.0,
+      "completions/min_terminated_length": 2674.0,
+      "epoch": 0.07478632478632478,
+      "grad_norm": 0.31033660874854463,
+      "kl": 0.0949249267578125,
+      "learning_rate": 2e-05,
+      "loss": -0.006,
+      "num_tokens": 12101010.0,
+      "reward": 9.125823974609375,
+      "reward_std": 3.129967212677002,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8177951574325562,
+      "rewards/successful_no_deal_reward_func": 0.40625,
+      "rewards/successful_parsing_reward_func": 0.7546502351760864,
+      "rewards/utility_reward_func": 0.2687443196773529,
+      "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": 0.0625,
+      "completions/max_length": 9969.0,
+      "completions/max_terminated_length": 9969.0,
+      "completions/mean_length": 5238.09375,
+      "completions/mean_terminated_length": 5587.3,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3429.0,
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.03256188449171459,
+      "kl": 0.0983734130859375,
+      "learning_rate": 2e-05,
+      "loss": 0.0206,
+      "num_tokens": 12461361.0,
+      "reward": 8.622406959533691,
+      "reward_std": 3.5288777351379395,
+      "rewards/constraint_satisfaction_reward_func": 0.953125,
+      "rewards/successful_code_execution_reward_func": 0.9133804440498352,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.8293843865394592,
+      "rewards/utility_reward_func": 0.2516564726829529,
+      "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": 0.0625,
+      "completions/max_length": 9716.0,
+      "completions/max_terminated_length": 9716.0,
+      "completions/mean_length": 5179.75,
+      "completions/mean_terminated_length": 5525.066666666667,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3120.0,
+      "epoch": 0.07905982905982906,
+      "grad_norm": 0.04889712846302911,
+      "kl": 0.073455810546875,
+      "learning_rate": 2e-05,
+      "loss": 0.0066,
+      "num_tokens": 12817439.0,
+      "reward": 8.959070205688477,
+      "reward_std": 6.533388614654541,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8700520992279053,
+      "rewards/successful_no_deal_reward_func": 0.40625,
+      "rewards/successful_parsing_reward_func": 0.8051215410232544,
+      "rewards/utility_reward_func": 0.26284343004226685,
+      "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": 0.09375,
+      "completions/max_length": 9623.0,
+      "completions/max_terminated_length": 9623.0,
+      "completions/mean_length": 5002.8125,
+      "completions/mean_terminated_length": 5520.3448275862065,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1646.0,
+      "epoch": 0.0811965811965812,
+      "grad_norm": 0.04748836707714437,
+      "kl": 0.07926177978515625,
+      "learning_rate": 2e-05,
+      "loss": 0.0052,
+      "num_tokens": 13177566.0,
+      "reward": 9.607915878295898,
+      "reward_std": 6.371920585632324,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7991071343421936,
+      "rewards/successful_no_deal_reward_func": 0.34375,
+      "rewards/successful_parsing_reward_func": 0.8020461201667786,
+      "rewards/utility_reward_func": 0.28680169582366943,
+      "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": 9332.0,
+      "completions/max_terminated_length": 9332.0,
+      "completions/mean_length": 5509.34375,
+      "completions/mean_terminated_length": 5687.064516129032,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3683.0,
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.08479434572785938,
+      "kl": 0.08233642578125,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "num_tokens": 13541530.0,
+      "reward": 8.508003234863281,
+      "reward_std": 5.044344902038574,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.7092013359069824,
+      "rewards/successful_no_deal_reward_func": 0.34375,
+      "rewards/successful_parsing_reward_func": 0.7772454619407654,
+      "rewards/utility_reward_func": 0.2505202889442444,
+      "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": 0.09375,
+      "completions/max_length": 10125.0,
+      "completions/max_terminated_length": 10125.0,
+      "completions/mean_length": 5366.65625,
+      "completions/mean_terminated_length": 5921.827586206897,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2721.0,
+      "epoch": 0.08547008547008547,
+      "grad_norm": 0.046629736962909236,
+      "kl": 0.074920654296875,
+      "learning_rate": 2e-05,
+      "loss": -0.0057,
+      "num_tokens": 13930554.0,
+      "reward": 9.409976959228516,
+      "reward_std": 6.964659690856934,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8676711320877075,
+      "rewards/successful_no_deal_reward_func": 0.34375,
+      "rewards/successful_parsing_reward_func": 0.7561174035072327,
+      "rewards/utility_reward_func": 0.28012827038764954,
+      "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": 0.03125,
+      "completions/max_length": 10197.0,
+      "completions/max_terminated_length": 10197.0,
+      "completions/mean_length": 5269.65625,
+      "completions/mean_terminated_length": 5439.645161290323,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2822.0,
+      "epoch": 0.0876068376068376,
+      "grad_norm": 0.07532493246421096,
+      "kl": 0.0913238525390625,
+      "learning_rate": 2e-05,
+      "loss": 0.0518,
+      "num_tokens": 14267395.0,
+      "reward": 10.74399185180664,
+      "reward_std": 7.217482566833496,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8700148463249207,
+      "rewards/successful_no_deal_reward_func": 0.40625,
+      "rewards/successful_parsing_reward_func": 0.872061014175415,
+      "rewards/utility_reward_func": 0.32211780548095703,
+      "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": 0.0625,
+      "completions/max_length": 9754.0,
+      "completions/max_terminated_length": 9754.0,
+      "completions/mean_length": 5356.21875,
+      "completions/mean_terminated_length": 5713.3,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2306.0,
+      "epoch": 0.08974358974358974,
+      "grad_norm": 0.041994088388066786,
+      "kl": 0.08880615234375,
+      "learning_rate": 2e-05,
+      "loss": -0.0166,
+      "num_tokens": 14631225.0,
+      "reward": 13.259390830993652,
+      "reward_std": 4.738910675048828,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8736110925674438,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.789508581161499,
+      "rewards/utility_reward_func": 0.40570682287216187,
+      "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": 8233.0,
+      "completions/max_terminated_length": 8233.0,
+      "completions/mean_length": 4819.65625,
+      "completions/mean_terminated_length": 5140.966666666666,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 1512.0,
+      "epoch": 0.09188034188034189,
+      "grad_norm": 0.03565747695965463,
+      "kl": 0.084442138671875,
+      "learning_rate": 2e-05,
+      "loss": -0.015,
+      "num_tokens": 14967668.0,
+      "reward": 11.417985916137695,
+      "reward_std": 5.845874786376953,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8795138597488403,
+      "rewards/successful_no_deal_reward_func": 0.40625,
+      "rewards/successful_parsing_reward_func": 0.7768093347549438,
+      "rewards/utility_reward_func": 0.34487012028694153,
+      "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": 0.0,
+      "completions/max_length": 9785.0,
+      "completions/max_terminated_length": 9785.0,
+      "completions/mean_length": 6039.5,
+      "completions/mean_terminated_length": 6039.5,
+      "completions/min_length": 2790.0,
+      "completions/min_terminated_length": 2790.0,
+      "epoch": 0.09401709401709402,
+      "grad_norm": 0.04878414442627355,
+      "kl": 0.0800628662109375,
+      "learning_rate": 2e-05,
+      "loss": 0.0123,
+      "num_tokens": 15322843.0,
+      "reward": 10.717945098876953,
+      "reward_std": 6.875738143920898,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.8796254992485046,
+      "rewards/successful_no_deal_reward_func": 0.390625,
+      "rewards/successful_parsing_reward_func": 0.8528273701667786,
+      "rewards/utility_reward_func": 0.3223233222961426,
+      "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": 0.09375,
+      "completions/max_length": 10441.0,
+      "completions/max_terminated_length": 10441.0,
+      "completions/mean_length": 5009.0,
+      "completions/mean_terminated_length": 5527.172413793103,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2133.0,
+      "epoch": 0.09615384615384616,
+      "grad_norm": 0.043346101484315204,
+      "kl": 0.090057373046875,
+      "learning_rate": 2e-05,
+      "loss": -0.0255,
+      "num_tokens": 15675494.0,
+      "reward": 6.5747551918029785,
+      "reward_std": 4.603181838989258,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8890997171401978,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8411458730697632,
+      "rewards/utility_reward_func": 0.1782347708940506,
+      "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": 10244.0,
+      "completions/max_terminated_length": 10244.0,
+      "completions/mean_length": 5903.40625,
+      "completions/mean_terminated_length": 5903.40625,
+      "completions/min_length": 2392.0,
+      "completions/min_terminated_length": 2392.0,
+      "epoch": 0.09829059829059829,
+      "grad_norm": 0.05335262654380793,
+      "kl": 0.0872802734375,
+      "learning_rate": 2e-05,
+      "loss": 0.0124,
+      "num_tokens": 16026738.0,
+      "reward": 7.486398220062256,
+      "reward_std": 4.8832197189331055,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8818700313568115,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.836823582649231,
+      "rewards/utility_reward_func": 0.20840096473693848,
+      "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": 0.0,
+      "completions/max_length": 10041.0,
+      "completions/max_terminated_length": 10041.0,
+      "completions/mean_length": 6264.78125,
+      "completions/mean_terminated_length": 6264.78125,
+      "completions/min_length": 2898.0,
+      "completions/min_terminated_length": 2898.0,
+      "epoch": 0.10042735042735043,
+      "grad_norm": 0.06631556073214734,
+      "kl": 0.08795166015625,
+      "learning_rate": 2e-05,
+      "loss": -0.0024,
+      "num_tokens": 16382497.0,
+      "reward": 7.394876480102539,
+      "reward_std": 5.015570640563965,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.7953249216079712,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8512028455734253,
+      "rewards/utility_reward_func": 0.20585119724273682,
+      "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": 0.03125,
+      "completions/max_length": 10786.0,
+      "completions/max_terminated_length": 10786.0,
+      "completions/mean_length": 5614.28125,
+      "completions/mean_terminated_length": 5795.387096774193,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2599.0,
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.02442773109163022,
+      "kl": 0.1008758544921875,
+      "learning_rate": 2e-05,
+      "loss": -0.0175,
+      "num_tokens": 16727867.0,
+      "reward": 9.46392822265625,
+      "reward_std": 5.264253616333008,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9590773582458496,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8479910492897034,
+      "rewards/utility_reward_func": 0.2740240693092346,
+      "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": 10011.0,
+      "completions/max_terminated_length": 10011.0,
+      "completions/mean_length": 6587.53125,
+      "completions/mean_terminated_length": 6800.032258064516,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 4411.0,
+      "epoch": 0.1047008547008547,
+      "grad_norm": 0.04667915631702583,
+      "kl": 0.084930419921875,
+      "learning_rate": 2e-05,
+      "loss": -0.0377,
+      "num_tokens": 17136101.0,
+      "reward": 2.485010862350464,
+      "reward_std": 0.9829912781715393,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9278645515441895,
+      "rewards/successful_no_deal_reward_func": 0.640625,
+      "rewards/successful_parsing_reward_func": 0.7758680582046509,
+      "rewards/utility_reward_func": 0.03913374990224838,
+      "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": 0.09375,
+      "completions/max_length": 10045.0,
+      "completions/max_terminated_length": 10045.0,
+      "completions/mean_length": 6914.71875,
+      "completions/mean_terminated_length": 7630.0344827586205,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3860.0,
+      "epoch": 0.10683760683760683,
+      "grad_norm": 0.05353420751511945,
+      "kl": 0.088897705078125,
+      "learning_rate": 2e-05,
+      "loss": -0.0106,
+      "num_tokens": 17544134.0,
+      "reward": 2.416043758392334,
+      "reward_std": 1.4705603122711182,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.8893229365348816,
+      "rewards/successful_no_deal_reward_func": 0.625,
+      "rewards/successful_parsing_reward_func": 0.8974916934967041,
+      "rewards/utility_reward_func": 0.037078749388456345,
+      "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": 0.0625,
+      "completions/max_length": 10681.0,
+      "completions/max_terminated_length": 10681.0,
+      "completions/mean_length": 7199.34375,
+      "completions/mean_terminated_length": 7679.3,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3120.0,
+      "epoch": 0.10897435897435898,
+      "grad_norm": 0.03946040934713408,
+      "kl": 0.0816192626953125,
+      "learning_rate": 2e-05,
+      "loss": -0.0015,
+      "num_tokens": 17958479.0,
+      "reward": 2.968362331390381,
+      "reward_std": 1.3150081634521484,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9317336082458496,
+      "rewards/successful_no_deal_reward_func": 0.6875,
+      "rewards/successful_parsing_reward_func": 0.9003890752792358,
+      "rewards/utility_reward_func": 0.053254999220371246,
+      "step": 51
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 0.09375,
+      "completions/max_length": 10872.0,
+      "completions/max_terminated_length": 10872.0,
+      "completions/mean_length": 6536.28125,
+      "completions/mean_terminated_length": 7212.448275862069,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 4263.0,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.03718996563528003,
+      "kl": NaN,
+      "learning_rate": 2e-05,
+      "loss": -0.0024,
+      "num_tokens": 18366031.0,
+      "reward": 2.8633077144622803,
+      "reward_std": 1.4587385654449463,
+      "rewards/constraint_satisfaction_reward_func": 0.96875,
+      "rewards/successful_code_execution_reward_func": 0.9080356955528259,
+      "rewards/successful_no_deal_reward_func": 0.625,
+      "rewards/successful_parsing_reward_func": 0.8871028423309326,
+      "rewards/utility_reward_func": 0.05248062312602997,
+      "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": 8489.0,
+      "completions/max_terminated_length": 8489.0,
+      "completions/mean_length": 5517.625,
+      "completions/mean_terminated_length": 5885.466666666666,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3481.0,
+      "epoch": 0.11324786324786325,
+      "grad_norm": 0.07000245223651237,
+      "kl": 0.095703125,
+      "learning_rate": 2e-05,
+      "loss": -0.0067,
+      "num_tokens": 18727862.0,
+      "reward": 9.138480186462402,
+      "reward_std": 5.334235668182373,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.8934895992279053,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8407135009765625,
+      "rewards/utility_reward_func": 0.2636790871620178,
+      "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": 0.09375,
+      "completions/max_length": 10454.0,
+      "completions/max_terminated_length": 10454.0,
+      "completions/mean_length": 5502.0625,
+      "completions/mean_terminated_length": 6071.241379310345,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3344.0,
+      "epoch": 0.11538461538461539,
+      "grad_norm": 0.15958852057504191,
+      "kl": 0.130096435546875,
+      "learning_rate": 2e-05,
+      "loss": -0.029,
+      "num_tokens": 19105506.0,
+      "reward": 8.657028198242188,
+      "reward_std": 5.453444480895996,
+      "rewards/constraint_satisfaction_reward_func": 0.984375,
+      "rewards/successful_code_execution_reward_func": 0.9398065805435181,
+      "rewards/successful_no_deal_reward_func": 0.546875,
+      "rewards/successful_parsing_reward_func": 0.7914034128189087,
+      "rewards/utility_reward_func": 0.24816150963306427,
+      "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": 0.09375,
+      "completions/max_length": 10317.0,
+      "completions/max_terminated_length": 10317.0,
+      "completions/mean_length": 5991.5,
+      "completions/mean_terminated_length": 6611.310344827586,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3320.0,
+      "epoch": 0.11752136752136752,
+      "grad_norm": 0.06674299870442284,
+      "kl": 0.09130859375,
+      "learning_rate": 2e-05,
+      "loss": -0.032,
+      "num_tokens": 19481400.0,
+      "reward": 10.987039566040039,
+      "reward_std": 4.5664963722229,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9111378192901611,
+      "rewards/successful_no_deal_reward_func": 0.5625,
+      "rewards/successful_parsing_reward_func": 0.8698784708976746,
+      "rewards/utility_reward_func": 0.32488125562667847,
+      "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": 0.09375,
+      "completions/max_length": 11647.0,
+      "completions/max_terminated_length": 11647.0,
+      "completions/mean_length": 5948.34375,
+      "completions/mean_terminated_length": 6563.689655172414,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3207.0,
+      "epoch": 0.11965811965811966,
+      "grad_norm": 0.06381001518888112,
+      "kl": 0.09112548828125,
+      "learning_rate": 2e-05,
+      "loss": -0.006,
+      "num_tokens": 19854767.0,
+      "reward": 8.135985374450684,
+      "reward_std": 4.6707611083984375,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9406249523162842,
+      "rewards/successful_no_deal_reward_func": 0.515625,
+      "rewards/successful_parsing_reward_func": 0.8900917768478394,
+      "rewards/utility_reward_func": 0.23124295473098755,
+      "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": 9240.0,
+      "completions/max_terminated_length": 9240.0,
+      "completions/mean_length": 5740.6875,
+      "completions/mean_terminated_length": 5740.6875,
+      "completions/min_length": 2702.0,
+      "completions/min_terminated_length": 2702.0,
+      "epoch": 0.12179487179487179,
+      "grad_norm": 0.04339549040283508,
+      "kl": 0.100372314453125,
+      "learning_rate": 2e-05,
+      "loss": 0.008,
+      "num_tokens": 20191894.0,
+      "reward": 8.311476707458496,
+      "reward_std": 4.060470104217529,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9272196888923645,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.8717137575149536,
+      "rewards/utility_reward_func": 0.24032360315322876,
+      "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": 0.0625,
+      "completions/max_length": 11047.0,
+      "completions/max_terminated_length": 11047.0,
+      "completions/mean_length": 6486.1875,
+      "completions/mean_terminated_length": 6918.6,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2191.0,
+      "epoch": 0.12393162393162394,
+      "grad_norm": 0.047643632225391426,
+      "kl": 0.0866241455078125,
+      "learning_rate": 2e-05,
+      "loss": -0.0208,
+      "num_tokens": 20580540.0,
+      "reward": 9.361209869384766,
+      "reward_std": 4.704495906829834,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9267857074737549,
+      "rewards/successful_no_deal_reward_func": 0.421875,
+      "rewards/successful_parsing_reward_func": 0.8713778257369995,
+      "rewards/utility_reward_func": 0.2753172516822815,
+      "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": 0.0625,
+      "completions/max_length": 9325.0,
+      "completions/max_terminated_length": 9325.0,
+      "completions/mean_length": 5433.3125,
+      "completions/mean_terminated_length": 5795.533333333334,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3548.0,
+      "epoch": 0.12606837606837606,
+      "grad_norm": 0.06527076242487305,
+      "kl": 0.100128173828125,
+      "learning_rate": 2e-05,
+      "loss": -0.0595,
+      "num_tokens": 20929760.0,
+      "reward": 9.511280059814453,
+      "reward_std": 2.9424219131469727,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9066296219825745,
+      "rewards/successful_no_deal_reward_func": 0.453125,
+      "rewards/successful_parsing_reward_func": 0.8526886701583862,
+      "rewards/utility_reward_func": 0.27940744161605835,
+      "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": 0.09375,
+      "completions/max_length": 9701.0,
+      "completions/max_terminated_length": 9701.0,
+      "completions/mean_length": 5489.21875,
+      "completions/mean_terminated_length": 6057.068965517241,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 3070.0,
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.06022558654926435,
+      "kl": 0.087799072265625,
+      "learning_rate": 2e-05,
+      "loss": -0.0458,
+      "num_tokens": 21305760.0,
+      "reward": 8.836292266845703,
+      "reward_std": 4.981121063232422,
+      "rewards/constraint_satisfaction_reward_func": 1.0,
+      "rewards/successful_code_execution_reward_func": 0.9498511552810669,
+      "rewards/successful_no_deal_reward_func": 0.390625,
+      "rewards/successful_parsing_reward_func": 0.8065916299819946,
+      "rewards/utility_reward_func": 0.2590007781982422,
+      "step": 60
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 60,
+  "num_input_tokens_seen": 21305760,
+  "num_train_epochs": 1,
+  "save_steps": 15,
+  "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
+}