Add files using upload-large-folder tool

.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 +1,61 @@
+{%- 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 %}
+{%- 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" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- 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' }}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743584f76219bade44886a8cb569d1218a6751fe5338ac032aac689bc7e4d632
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6318e7030f8c0f8893cbd288476b9f8f2279b9f154097c9c0b132b5f662dabc6
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 196096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1474 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05509641873278237,
+  "eval_steps": 500,
+  "global_step": 40,
+  "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": 2915.0,
+      "completions/max_terminated_length": 2915.0,
+      "completions/mean_length": 1900.916748046875,
+      "completions/mean_terminated_length": 1900.916748046875,
+      "completions/min_length": 1153.0,
+      "completions/min_terminated_length": 1153.0,
+      "entropy": 0.29732953757047653,
+      "epoch": 0.0013774104683195593,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2848003042646487,
+      "kl": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.065,
+      "num_tokens": 62470.0,
+      "reward": 1.875,
+      "reward_std": 0.7653362154960632,
+      "rewards/cloze_reward/mean": 0.25,
+      "rewards/cloze_reward/std": 0.4423258602619171,
+      "rewards/code_reward/mean": 0.9166666865348816,
+      "rewards/code_reward/std": 0.28232985734939575,
+      "rewards/format_reward/mean": 0.7083333134651184,
+      "rewards/format_reward/std": 0.4643056094646454,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0003361701965332,
+      "sampling/importance_sampling_ratio/min": 0.12010933458805084,
+      "sampling/sampling_logp_difference/max": 2.1193528175354004,
+      "sampling/sampling_logp_difference/mean": 0.013728929683566093,
+      "step": 1
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 4209.0,
+      "completions/max_terminated_length": 4209.0,
+      "completions/mean_length": 1807.125,
+      "completions/mean_terminated_length": 1807.125,
+      "completions/min_length": 3.0,
+      "completions/min_terminated_length": 3.0,
+      "entropy": 0.4276350364089012,
+      "epoch": 0.0027548209366391185,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.27170591036025904,
+      "kl": 0.0017779993431759067,
+      "learning_rate": 9.999953187068845e-07,
+      "loss": -0.0052,
+      "num_tokens": 144433.0,
+      "reward": 1.375,
+      "reward_std": 0.697779655456543,
+      "rewards/cloze_reward/mean": 0.4166666567325592,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 0.4166666567325592,
+      "rewards/code_reward/std": 0.5036101937294006,
+      "rewards/format_reward/mean": 0.5416666865348816,
+      "rewards/format_reward/std": 0.5089773535728455,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000282526016235,
+      "sampling/importance_sampling_ratio/min": 0.054640088230371475,
+      "sampling/sampling_logp_difference/max": 2.906987428665161,
+      "sampling/sampling_logp_difference/mean": 0.014421815052628517,
+      "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": 0.0,
+      "completions/max_length": 5955.0,
+      "completions/max_terminated_length": 5955.0,
+      "completions/mean_length": 1929.8333740234375,
+      "completions/mean_terminated_length": 1929.8333740234375,
+      "completions/min_length": 30.0,
+      "completions/min_terminated_length": 30.0,
+      "entropy": 0.15682650730013847,
+      "epoch": 0.004132231404958678,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.23379512087809812,
+      "kl": 0.00041251888615079224,
+      "learning_rate": 9.999812749151967e-07,
+      "loss": 0.0655,
+      "num_tokens": 208821.0,
+      "reward": 2.375,
+      "reward_std": 0.9505624771118164,
+      "rewards/cloze_reward/mean": 0.7916666865348816,
+      "rewards/cloze_reward/std": 0.4148511290550232,
+      "rewards/code_reward/mean": 0.7916666865348816,
+      "rewards/code_reward/std": 0.4148510992527008,
+      "rewards/format_reward/mean": 0.7916666865348816,
+      "rewards/format_reward/std": 0.4148511290550232,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0001002550125122,
+      "sampling/importance_sampling_ratio/min": 0.04702043533325195,
+      "sampling/sampling_logp_difference/max": 3.057173013687134,
+      "sampling/sampling_logp_difference/mean": 0.008513483218848705,
+      "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": 0.0,
+      "completions/max_length": 6342.0,
+      "completions/max_terminated_length": 6342.0,
+      "completions/mean_length": 3278.5,
+      "completions/mean_terminated_length": 3278.5,
+      "completions/min_length": 990.0,
+      "completions/min_terminated_length": 990.0,
+      "entropy": 0.23897437751293182,
+      "epoch": 0.005509641873278237,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16457158766091876,
+      "kl": 0.0004863361318712123,
+      "learning_rate": 9.999578688879084e-07,
+      "loss": 0.0713,
+      "num_tokens": 306505.0,
+      "reward": 2.1666667461395264,
+      "reward_std": 0.6947464346885681,
+      "rewards/cloze_reward/mean": 0.4583333432674408,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.7916666865348816,
+      "rewards/code_reward/std": 0.4148511290550232,
+      "rewards/format_reward/mean": 0.9166666865348816,
+      "rewards/format_reward/std": 0.28232985734939575,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0001260042190552,
+      "sampling/importance_sampling_ratio/min": 0.1858593225479126,
+      "sampling/sampling_logp_difference/max": 1.682765245437622,
+      "sampling/sampling_logp_difference/mean": 0.012356276623904705,
+      "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": 0.0833333358168602,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 5875.0,
+      "completions/mean_length": 2768.08349609375,
+      "completions/mean_terminated_length": 2275.0,
+      "completions/min_length": 772.0,
+      "completions/min_terminated_length": 772.0,
+      "entropy": 0.30327995866537094,
+      "epoch": 0.006887052341597796,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.24551726103614221,
+      "kl": 0.000520530593348667,
+      "learning_rate": 9.999251010633018e-07,
+      "loss": 0.1599,
+      "num_tokens": 388843.0,
+      "reward": 1.875,
+      "reward_std": 0.6055297255516052,
+      "rewards/cloze_reward/mean": 0.5833333134651184,
+      "rewards/cloze_reward/std": 0.5036101341247559,
+      "rewards/code_reward/mean": 0.5,
+      "rewards/code_reward/std": 0.5107539296150208,
+      "rewards/format_reward/mean": 0.7916666865348816,
+      "rewards/format_reward/std": 0.4148510992527008,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0001081228256226,
+      "sampling/importance_sampling_ratio/min": 0.07036004215478897,
+      "sampling/sampling_logp_difference/max": 2.65412974357605,
+      "sampling/sampling_logp_difference/mean": 0.014815382659435272,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 4871.0,
+      "completions/mean_length": 2609.45849609375,
+      "completions/mean_terminated_length": 2366.7392578125,
+      "completions/min_length": 1340.0,
+      "completions/min_terminated_length": 1340.0,
+      "entropy": 0.2581055983901024,
+      "epoch": 0.008264462809917356,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2529070676429162,
+      "kl": 0.0005087396057206206,
+      "learning_rate": 9.998829720549602e-07,
+      "loss": 0.1667,
+      "num_tokens": 468398.0,
+      "reward": 2.1666667461395264,
+      "reward_std": 0.5970090627670288,
+      "rewards/cloze_reward/mean": 0.4583333432674408,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.75,
+      "rewards/code_reward/std": 0.4423258602619171,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9997397065162659,
+      "sampling/importance_sampling_ratio/min": 0.13575026392936707,
+      "sampling/sampling_logp_difference/max": 1.9969384670257568,
+      "sampling/sampling_logp_difference/mean": 0.012986009940505028,
+      "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": 0.2916666865348816,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7889.0,
+      "completions/mean_length": 4482.95849609375,
+      "completions/mean_terminated_length": 2955.705810546875,
+      "completions/min_length": 809.0,
+      "completions/min_terminated_length": 809.0,
+      "entropy": 0.3291335925459862,
+      "epoch": 0.009641873278236915,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.15909916853519945,
+      "kl": 0.000712596025550738,
+      "learning_rate": 9.998314826517563e-07,
+      "loss": 0.062,
+      "num_tokens": 600053.0,
+      "reward": 0.8333333730697632,
+      "reward_std": 0.48678088188171387,
+      "rewards/cloze_reward/mean": 0.0,
+      "rewards/cloze_reward/std": 0.0,
+      "rewards/code_reward/mean": 0.125,
+      "rewards/code_reward/std": 0.337831974029541,
+      "rewards/format_reward/mean": 0.7083333134651184,
+      "rewards/format_reward/std": 0.4643056094646454,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999268054962158,
+      "sampling/importance_sampling_ratio/min": 0.1226503923535347,
+      "sampling/sampling_logp_difference/max": 2.098417282104492,
+      "sampling/sampling_logp_difference/mean": 0.01600910723209381,
+      "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": 4810.0,
+      "completions/max_terminated_length": 4810.0,
+      "completions/mean_length": 1951.5,
+      "completions/mean_terminated_length": 1951.5,
+      "completions/min_length": 779.0,
+      "completions/min_terminated_length": 779.0,
+      "entropy": 0.2874010130763054,
+      "epoch": 0.011019283746556474,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.22479321113386752,
+      "kl": 0.0006854519015178084,
+      "learning_rate": 9.99770633817838e-07,
+      "loss": 0.0803,
+      "num_tokens": 666825.0,
+      "reward": 2.0833334922790527,
+      "reward_std": 0.4778915345668793,
+      "rewards/cloze_reward/mean": 0.4166666567325592,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 0.6666666865348816,
+      "rewards/code_reward/std": 0.4815434217453003,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.00015127658844,
+      "sampling/importance_sampling_ratio/min": 0.3547181487083435,
+      "sampling/sampling_logp_difference/max": 1.0364317893981934,
+      "sampling/sampling_logp_difference/mean": 0.012998003512620926,
+      "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": 7278.0,
+      "completions/max_terminated_length": 7278.0,
+      "completions/mean_length": 3300.791748046875,
+      "completions/mean_terminated_length": 3300.791748046875,
+      "completions/min_length": 1615.0,
+      "completions/min_terminated_length": 1615.0,
+      "entropy": 0.3161199018359184,
+      "epoch": 0.012396694214876033,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.22023288782689693,
+      "kl": 0.0009353299537906423,
+      "learning_rate": 9.997004266926104e-07,
+      "loss": -0.063,
+      "num_tokens": 769572.0,
+      "reward": 1.7083333730697632,
+      "reward_std": 0.5078567266464233,
+      "rewards/cloze_reward/mean": 0.375,
+      "rewards/cloze_reward/std": 0.494535356760025,
+      "rewards/code_reward/mean": 0.3333333432674408,
+      "rewards/code_reward/std": 0.4815433919429779,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000706911087036,
+      "sampling/importance_sampling_ratio/min": 0.0014537055976688862,
+      "sampling/sampling_logp_difference/max": 6.533639430999756,
+      "sampling/sampling_logp_difference/mean": 0.015122607350349426,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6813.0,
+      "completions/mean_length": 2792.58349609375,
+      "completions/mean_terminated_length": 2557.826171875,
+      "completions/min_length": 875.0,
+      "completions/min_terminated_length": 875.0,
+      "entropy": 0.28332703560590744,
+      "epoch": 0.013774104683195593,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.16710769042355098,
+      "kl": 0.0008509723120369017,
+      "learning_rate": 9.99620862590714e-07,
+      "loss": 0.1348,
+      "num_tokens": 858722.0,
+      "reward": 2.0,
+      "reward_std": 0.39000558853149414,
+      "rewards/cloze_reward/mean": 0.375,
+      "rewards/cloze_reward/std": 0.494535356760025,
+      "rewards/code_reward/mean": 0.7083333134651184,
+      "rewards/code_reward/std": 0.4643056094646454,
+      "rewards/format_reward/mean": 0.9166666865348816,
+      "rewards/format_reward/std": 0.28232985734939575,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.000204086303711,
+      "sampling/importance_sampling_ratio/min": 0.2697003185749054,
+      "sampling/sampling_logp_difference/max": 1.3104438781738281,
+      "sampling/sampling_logp_difference/mean": 0.012643387541174889,
+      "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": 0.125,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7190.0,
+      "completions/mean_length": 3368.791748046875,
+      "completions/mean_terminated_length": 2679.761962890625,
+      "completions/min_length": 785.0,
+      "completions/min_terminated_length": 785.0,
+      "entropy": 0.25256290286779404,
+      "epoch": 0.015151515151515152,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.17645257817462404,
+      "kl": 0.0011589039204409346,
+      "learning_rate": 9.995319430020003e-07,
+      "loss": 0.1181,
+      "num_tokens": 959845.0,
+      "reward": 1.9583333730697632,
+      "reward_std": 0.7435590624809265,
+      "rewards/cloze_reward/mean": 0.5416666865348816,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 0.875,
+      "rewards/format_reward/std": 0.337831974029541,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000051259994507,
+      "sampling/importance_sampling_ratio/min": 0.011985468678176403,
+      "sampling/sampling_logp_difference/max": 4.424060344696045,
+      "sampling/sampling_logp_difference/mean": 0.012076009064912796,
+      "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": 6058.0,
+      "completions/max_terminated_length": 6058.0,
+      "completions/mean_length": 2589.5,
+      "completions/mean_terminated_length": 2589.5,
+      "completions/min_length": 1266.0,
+      "completions/min_terminated_length": 1266.0,
+      "entropy": 0.2638929449021816,
+      "epoch": 0.01652892561983471,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18010496944516938,
+      "kl": 0.00098221683583688,
+      "learning_rate": 9.99433669591504e-07,
+      "loss": 0.1127,
+      "num_tokens": 1042353.0,
+      "reward": 1.5,
+      "reward_std": 0.3900056481361389,
+      "rewards/cloze_reward/mean": 0.125,
+      "rewards/cloze_reward/std": 0.337831974029541,
+      "rewards/code_reward/mean": 0.375,
+      "rewards/code_reward/std": 0.494535356760025,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999534487724304,
+      "sampling/importance_sampling_ratio/min": 0.36291250586509705,
+      "sampling/sampling_logp_difference/max": 1.3159668445587158,
+      "sampling/sampling_logp_difference/mean": 0.013833053410053253,
+      "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": 3234.0,
+      "completions/max_terminated_length": 3234.0,
+      "completions/mean_length": 2078.20849609375,
+      "completions/mean_terminated_length": 2078.20849609375,
+      "completions/min_length": 1470.0,
+      "completions/min_terminated_length": 1470.0,
+      "entropy": 0.18643449991941452,
+      "epoch": 0.01790633608815427,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.23135066334203877,
+      "kl": 0.0031637964711990207,
+      "learning_rate": 9.993260441994114e-07,
+      "loss": -0.002,
+      "num_tokens": 1140390.0,
+      "reward": 1.375,
+      "reward_std": 0.5085179209709167,
+      "rewards/cloze_reward/mean": 0.2083333283662796,
+      "rewards/cloze_reward/std": 0.4148511290550232,
+      "rewards/code_reward/mean": 0.2083333283662796,
+      "rewards/code_reward/std": 0.4148511290550232,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 1.9693641662597656,
+      "sampling/importance_sampling_ratio/mean": 0.9994663596153259,
+      "sampling/importance_sampling_ratio/min": 0.0002035096986219287,
+      "sampling/sampling_logp_difference/max": 8.499796867370605,
+      "sampling/sampling_logp_difference/mean": 0.011178883723914623,
+      "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": 6206.0,
+      "completions/max_terminated_length": 6206.0,
+      "completions/mean_length": 3248.25,
+      "completions/mean_terminated_length": 3248.25,
+      "completions/min_length": 686.0,
+      "completions/min_terminated_length": 686.0,
+      "entropy": 0.28004511073231697,
+      "epoch": 0.01928374655647383,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2111608534215747,
+      "kl": 0.0016034767031669617,
+      "learning_rate": 9.99209068841027e-07,
+      "loss": -0.055,
+      "num_tokens": 1235948.0,
+      "reward": 2.125,
+      "reward_std": 0.4082186818122864,
+      "rewards/cloze_reward/mean": 0.625,
+      "rewards/cloze_reward/std": 0.494535356760025,
+      "rewards/code_reward/mean": 0.5,
+      "rewards/code_reward/std": 0.5107539296150208,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9996271133422852,
+      "sampling/importance_sampling_ratio/min": 0.16397786140441895,
+      "sampling/sampling_logp_difference/max": 1.8080238103866577,
+      "sampling/sampling_logp_difference/mean": 0.014200962148606777,
+      "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": 0.0,
+      "completions/max_length": 6290.0,
+      "completions/max_terminated_length": 6290.0,
+      "completions/mean_length": 2156.5,
+      "completions/mean_terminated_length": 2156.5,
+      "completions/min_length": 851.0,
+      "completions/min_terminated_length": 851.0,
+      "entropy": 0.275097768753767,
+      "epoch": 0.02066115702479339,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.26723864416803433,
+      "kl": 0.0022536640462931246,
+      "learning_rate": 9.99082745706734e-07,
+      "loss": 0.2325,
+      "num_tokens": 1304496.0,
+      "reward": 2.125,
+      "reward_std": 0.503990888595581,
+      "rewards/cloze_reward/mean": 0.4166666567325592,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 0.7083333134651184,
+      "rewards/code_reward/std": 0.4643056094646454,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9997144341468811,
+      "sampling/importance_sampling_ratio/min": 0.01566636748611927,
+      "sampling/sampling_logp_difference/max": 4.156239032745361,
+      "sampling/sampling_logp_difference/mean": 0.013950522057712078,
+      "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": 0.0833333358168602,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 5627.0,
+      "completions/mean_length": 2773.95849609375,
+      "completions/mean_terminated_length": 2281.4091796875,
+      "completions/min_length": 1168.0,
+      "completions/min_terminated_length": 1168.0,
+      "entropy": 0.24988408759236336,
+      "epoch": 0.02203856749311295,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.2002566600366291,
+      "kl": 0.0017052267503459007,
+      "learning_rate": 9.989470771619553e-07,
+      "loss": 0.1211,
+      "num_tokens": 1394159.0,
+      "reward": 1.875,
+      "reward_std": 0.5535047054290771,
+      "rewards/cloze_reward/mean": 0.2083333283662796,
+      "rewards/cloze_reward/std": 0.4148511290550232,
+      "rewards/code_reward/mean": 0.75,
+      "rewards/code_reward/std": 0.4423258602619171,
+      "rewards/format_reward/mean": 0.9166666865348816,
+      "rewards/format_reward/std": 0.28232985734939575,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.000037670135498,
+      "sampling/importance_sampling_ratio/min": 0.08789712190628052,
+      "sampling/sampling_logp_difference/max": 4.325733184814453,
+      "sampling/sampling_logp_difference/mean": 0.012733320705592632,
+      "step": 16
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 7212.0,
+      "completions/max_terminated_length": 7212.0,
+      "completions/mean_length": 3347.291748046875,
+      "completions/mean_terminated_length": 3347.291748046875,
+      "completions/min_length": 829.0,
+      "completions/min_terminated_length": 829.0,
+      "entropy": 0.2636777497828007,
+      "epoch": 0.023415977961432508,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.1893310489949768,
+      "kl": 0.0020791269780602306,
+      "learning_rate": 9.988020657471077e-07,
+      "loss": -0.1188,
+      "num_tokens": 1504110.0,
+      "reward": 1.625,
+      "reward_std": 0.5480016469955444,
+      "rewards/cloze_reward/mean": 0.125,
+      "rewards/cloze_reward/std": 0.337831974029541,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9997584819793701,
+      "sampling/importance_sampling_ratio/min": 0.021851731464266777,
+      "sampling/sampling_logp_difference/max": 3.8234751224517822,
+      "sampling/sampling_logp_difference/mean": 0.014004481956362724,
+      "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": 0.0,
+      "completions/max_length": 2283.0,
+      "completions/max_terminated_length": 2283.0,
+      "completions/mean_length": 1511.5,
+      "completions/mean_terminated_length": 1511.5,
+      "completions/min_length": 805.0,
+      "completions/min_terminated_length": 805.0,
+      "entropy": 0.14751360192894936,
+      "epoch": 0.024793388429752067,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.20794435707592182,
+      "kl": 0.0025478473398834467,
+      "learning_rate": 9.98647714177555e-07,
+      "loss": -0.0004,
+      "num_tokens": 1567602.0,
+      "reward": 2.3333334922790527,
+      "reward_std": 0.2357022613286972,
+      "rewards/cloze_reward/mean": 0.375,
+      "rewards/cloze_reward/std": 0.494535356760025,
+      "rewards/code_reward/mean": 0.9583333134651184,
+      "rewards/code_reward/std": 0.20412415266036987,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9995601177215576,
+      "sampling/importance_sampling_ratio/min": 0.19188205897808075,
+      "sampling/sampling_logp_difference/max": 1.650874376296997,
+      "sampling/sampling_logp_difference/mean": 0.009327586740255356,
+      "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": 6061.0,
+      "completions/max_terminated_length": 6061.0,
+      "completions/mean_length": 2516.166748046875,
+      "completions/mean_terminated_length": 2516.166748046875,
+      "completions/min_length": 953.0,
+      "completions/min_terminated_length": 953.0,
+      "entropy": 0.27825580164790154,
+      "epoch": 0.026170798898071626,
+      "frac_reward_zero_std": 0.6666666865348816,
+      "grad_norm": 0.16189513218269783,
+      "kl": 0.0023431787849403918,
+      "learning_rate": 9.984840253435568e-07,
+      "loss": 0.0076,
+      "num_tokens": 1653054.0,
+      "reward": 2.125,
+      "reward_std": 0.17251639068126678,
+      "rewards/cloze_reward/mean": 0.6666666865348816,
+      "rewards/cloze_reward/std": 0.4815434217453003,
+      "rewards/code_reward/mean": 0.4583333432674408,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999192357063293,
+      "sampling/importance_sampling_ratio/min": 0.06552005559206009,
+      "sampling/sampling_logp_difference/max": 2.7253990173339844,
+      "sampling/sampling_logp_difference/mean": 0.013308782130479813,
+      "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": 0.0,
+      "completions/max_length": 5089.0,
+      "completions/max_terminated_length": 5089.0,
+      "completions/mean_length": 1440.9583740234375,
+      "completions/mean_terminated_length": 1440.9583740234375,
+      "completions/min_length": 896.0,
+      "completions/min_terminated_length": 896.0,
+      "entropy": 0.2597235403954983,
+      "epoch": 0.027548209366391185,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.3058200238239626,
+      "kl": 0.004811614111531526,
+      "learning_rate": 9.983110023102145e-07,
+      "loss": -0.0732,
+      "num_tokens": 1709421.0,
+      "reward": 2.0833334922790527,
+      "reward_std": 0.6257078647613525,
+      "rewards/cloze_reward/mean": 0.5833333134651184,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0002235174179077,
+      "sampling/importance_sampling_ratio/min": 0.010991987772285938,
+      "sampling/sampling_logp_difference/max": 4.510588645935059,
+      "sampling/sampling_logp_difference/mean": 0.012450532987713814,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6266.0,
+      "completions/mean_length": 2971.95849609375,
+      "completions/mean_terminated_length": 2745.0,
+      "completions/min_length": 725.0,
+      "completions/min_terminated_length": 725.0,
+      "entropy": 0.23062221333384514,
+      "epoch": 0.028925619834710745,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.20922776699151296,
+      "kl": 0.002331310883164406,
+      "learning_rate": 9.981286483174148e-07,
+      "loss": 0.0302,
+      "num_tokens": 1808892.0,
+      "reward": 1.6666667461395264,
+      "reward_std": 0.6947464346885681,
+      "rewards/cloze_reward/mean": 0.1666666716337204,
+      "rewards/cloze_reward/std": 0.3806934952735901,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.999830424785614,
+      "sampling/importance_sampling_ratio/min": 5.94212829982399e-13,
+      "sampling/sampling_logp_difference/max": 28.151538848876953,
+      "sampling/sampling_logp_difference/mean": 0.013190208002924919,
+      "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": 3810.0,
+      "completions/max_terminated_length": 3810.0,
+      "completions/mean_length": 2031.5,
+      "completions/mean_terminated_length": 2031.5,
+      "completions/min_length": 1207.0,
+      "completions/min_terminated_length": 1207.0,
+      "entropy": 0.1824016384780407,
+      "epoch": 0.030303030303030304,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2952973607886351,
+      "kl": 0.004044964851345867,
+      "learning_rate": 9.979369667797674e-07,
+      "loss": 0.0554,
+      "num_tokens": 1911664.0,
+      "reward": 1.5,
+      "reward_std": 0.48678088188171387,
+      "rewards/cloze_reward/mean": 0.0,
+      "rewards/cloze_reward/std": 0.0,
+      "rewards/code_reward/mean": 0.5,
+      "rewards/code_reward/std": 0.5107539296150208,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9998181462287903,
+      "sampling/importance_sampling_ratio/min": 0.0026749928947538137,
+      "sampling/sampling_logp_difference/max": 5.923808574676514,
+      "sampling/sampling_logp_difference/mean": 0.011196551844477654,
+      "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": 7742.0,
+      "completions/max_terminated_length": 7742.0,
+      "completions/mean_length": 2664.791748046875,
+      "completions/mean_terminated_length": 2664.791748046875,
+      "completions/min_length": 716.0,
+      "completions/min_terminated_length": 716.0,
+      "entropy": 0.16602139174938202,
+      "epoch": 0.03168044077134986,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.18646426939832977,
+      "kl": 0.0027883301954716444,
+      "learning_rate": 9.977359612865422e-07,
+      "loss": -0.1659,
+      "num_tokens": 2005483.0,
+      "reward": 2.0,
+      "reward_std": 0.34503278136253357,
+      "rewards/cloze_reward/mean": 0.5416666865348816,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.4583333432674408,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000344514846802,
+      "sampling/importance_sampling_ratio/min": 2.7512096333753844e-12,
+      "sampling/sampling_logp_difference/max": 26.618980407714844,
+      "sampling/sampling_logp_difference/mean": 0.010194670408964157,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7718.0,
+      "completions/mean_length": 4289.5,
+      "completions/mean_terminated_length": 4119.826171875,
+      "completions/min_length": 979.0,
+      "completions/min_terminated_length": 979.0,
+      "entropy": 0.2995450422167778,
+      "epoch": 0.03305785123966942,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.170700316120424,
+      "kl": 0.0018004105950240046,
+      "learning_rate": 9.975256356016017e-07,
+      "loss": 0.0699,
+      "num_tokens": 2128183.0,
+      "reward": 2.0,
+      "reward_std": 0.6288648843765259,
+      "rewards/cloze_reward/mean": 0.4583333432674408,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.5833333134651184,
+      "rewards/code_reward/std": 0.5036101341247559,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999317526817322,
+      "sampling/importance_sampling_ratio/min": 0.08646544814109802,
+      "sampling/sampling_logp_difference/max": 2.4480104446411133,
+      "sampling/sampling_logp_difference/mean": 0.014326645992696285,
+      "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": 7758.0,
+      "completions/max_terminated_length": 7758.0,
+      "completions/mean_length": 3043.45849609375,
+      "completions/mean_terminated_length": 3043.45849609375,
+      "completions/min_length": 1282.0,
+      "completions/min_terminated_length": 1282.0,
+      "entropy": 0.2883247286081314,
+      "epoch": 0.03443526170798898,
+      "frac_reward_zero_std": 0.6666666865348816,
+      "grad_norm": 0.12988436998967914,
+      "kl": 0.0025270123151130974,
+      "learning_rate": 9.973059936633306e-07,
+      "loss": 0.0545,
+      "num_tokens": 2218418.0,
+      "reward": 2.2916667461395264,
+      "reward_std": 0.21362332999706268,
+      "rewards/cloze_reward/mean": 0.75,
+      "rewards/cloze_reward/std": 0.4423258602619171,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999663829803467,
+      "sampling/importance_sampling_ratio/min": 0.10468851774930954,
+      "sampling/sampling_logp_difference/max": 2.256765842437744,
+      "sampling/sampling_logp_difference/mean": 0.012674104422330856,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 4710.0,
+      "completions/mean_length": 2069.625,
+      "completions/mean_terminated_length": 1803.434814453125,
+      "completions/min_length": 935.0,
+      "completions/min_terminated_length": 935.0,
+      "entropy": 0.1856878437101841,
+      "epoch": 0.03581267217630854,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.2189265719041607,
+      "kl": 0.0038806990487501025,
+      "learning_rate": 9.970770395845622e-07,
+      "loss": 0.3118,
+      "num_tokens": 2309321.0,
+      "reward": 2.375,
+      "reward_std": 0.5061727166175842,
+      "rewards/cloze_reward/mean": 0.5833333134651184,
+      "rewards/cloze_reward/std": 0.5036101341247559,
+      "rewards/code_reward/mean": 0.8333333134651184,
+      "rewards/code_reward/std": 0.3806934952735901,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9998181462287903,
+      "sampling/importance_sampling_ratio/min": 0.23940998315811157,
+      "sampling/sampling_logp_difference/max": 1.4295778274536133,
+      "sampling/sampling_logp_difference/mean": 0.009506626054644585,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 8177.0,
+      "completions/mean_length": 4914.20849609375,
+      "completions/mean_terminated_length": 4771.69580078125,
+      "completions/min_length": 1792.0,
+      "completions/min_terminated_length": 1792.0,
+      "entropy": 0.3651472330093384,
+      "epoch": 0.0371900826446281,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.16794783472528907,
+      "kl": 0.0032920141238719225,
+      "learning_rate": 9.968387776525007e-07,
+      "loss": 0.0044,
+      "num_tokens": 2447670.0,
+      "reward": 1.7083333730697632,
+      "reward_std": 0.6274997591972351,
+      "rewards/cloze_reward/mean": 0.5,
+      "rewards/cloze_reward/std": 0.5107539296150208,
+      "rewards/code_reward/mean": 0.2916666567325592,
+      "rewards/code_reward/std": 0.4643056094646454,
+      "rewards/format_reward/mean": 0.9166666865348816,
+      "rewards/format_reward/std": 0.28232985734939575,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9998521208763123,
+      "sampling/importance_sampling_ratio/min": 0.00022299536794889718,
+      "sampling/sampling_logp_difference/max": 8.40835952758789,
+      "sampling/sampling_logp_difference/mean": 0.017919987440109253,
+      "step": 27
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 7702.0,
+      "completions/max_terminated_length": 7702.0,
+      "completions/mean_length": 3003.375,
+      "completions/mean_terminated_length": 3003.375,
+      "completions/min_length": 1013.0,
+      "completions/min_terminated_length": 1013.0,
+      "entropy": 0.30894363671541214,
+      "epoch": 0.03856749311294766,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.2662075831826717,
+      "kl": 0.003954145242460072,
+      "learning_rate": 9.965912123286424e-07,
+      "loss": 0.085,
+      "num_tokens": 2537663.0,
+      "reward": 2.5416667461395264,
+      "reward_std": 0.4082186222076416,
+      "rewards/cloze_reward/mean": 0.7083333134651184,
+      "rewards/cloze_reward/std": 0.4643056094646454,
+      "rewards/code_reward/mean": 0.8333333134651184,
+      "rewards/code_reward/std": 0.3806934952735901,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000332593917847,
+      "sampling/importance_sampling_ratio/min": 0.21365012228488922,
+      "sampling/sampling_logp_difference/max": 2.255774974822998,
+      "sampling/sampling_logp_difference/mean": 0.014759156852960587,
+      "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": 0.0416666679084301,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7521.0,
+      "completions/mean_length": 2249.291748046875,
+      "completions/mean_terminated_length": 1990.9130859375,
+      "completions/min_length": 932.0,
+      "completions/min_terminated_length": 932.0,
+      "entropy": 0.20293106883764267,
+      "epoch": 0.03994490358126722,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.30621070115238647,
+      "kl": 0.004532316525001079,
+      "learning_rate": 9.963343482486905e-07,
+      "loss": 0.1541,
+      "num_tokens": 2608934.0,
+      "reward": 2.4166667461395264,
+      "reward_std": 0.5028601884841919,
+      "rewards/cloze_reward/mean": 0.5833333134651184,
+      "rewards/cloze_reward/std": 0.5036101341247559,
+      "rewards/code_reward/mean": 0.875,
+      "rewards/code_reward/std": 0.337831974029541,
+      "rewards/format_reward/mean": 0.9583333134651184,
+      "rewards/format_reward/std": 0.20412415266036987,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.000059962272644,
+      "sampling/importance_sampling_ratio/min": 0.2822778820991516,
+      "sampling/sampling_logp_difference/max": 1.3750309944152832,
+      "sampling/sampling_logp_difference/mean": 0.011287961155176163,
+      "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": 6912.0,
+      "completions/max_terminated_length": 6912.0,
+      "completions/mean_length": 2896.416748046875,
+      "completions/mean_terminated_length": 2896.416748046875,
+      "completions/min_length": 1072.0,
+      "completions/min_terminated_length": 1072.0,
+      "entropy": 0.24397730827331543,
+      "epoch": 0.04132231404958678,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2637496585585402,
+      "kl": 0.0052707926370203495,
+      "learning_rate": 9.96068190222469e-07,
+      "loss": -0.0809,
+      "num_tokens": 2696368.0,
+      "reward": 2.3333334922790527,
+      "reward_std": 0.7106520533561707,
+      "rewards/cloze_reward/mean": 0.7916666865348816,
+      "rewards/cloze_reward/std": 0.4148511290550232,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.000116229057312,
+      "sampling/importance_sampling_ratio/min": 0.26414525508880615,
+      "sampling/sampling_logp_difference/max": 1.3681449890136719,
+      "sampling/sampling_logp_difference/mean": 0.012104719877243042,
+      "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": 0.0,
+      "completions/max_length": 5352.0,
+      "completions/max_terminated_length": 5352.0,
+      "completions/mean_length": 1967.75,
+      "completions/mean_terminated_length": 1967.75,
+      "completions/min_length": 804.0,
+      "completions/min_terminated_length": 804.0,
+      "entropy": 0.21574077382683754,
+      "epoch": 0.04269972451790634,
+      "frac_reward_zero_std": 0.6666666865348816,
+      "grad_norm": 0.12651354951166632,
+      "kl": 0.0038389787659980357,
+      "learning_rate": 9.95792743233833e-07,
+      "loss": 0.1096,
+      "num_tokens": 2766314.0,
+      "reward": 2.4166667461395264,
+      "reward_std": 0.15430335700511932,
+      "rewards/cloze_reward/mean": 0.4166666567325592,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 1.0,
+      "rewards/code_reward/std": 0.0,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9996727108955383,
+      "sampling/importance_sampling_ratio/min": 0.11743912100791931,
+      "sampling/sampling_logp_difference/max": 2.1418352127075195,
+      "sampling/sampling_logp_difference/mean": 0.011217731051146984,
+      "step": 31
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 6975.0,
+      "completions/max_terminated_length": 6975.0,
+      "completions/mean_length": 2998.25,
+      "completions/mean_terminated_length": 2998.25,
+      "completions/min_length": 1004.0,
+      "completions/min_terminated_length": 1004.0,
+      "entropy": 0.34803634136915207,
+      "epoch": 0.0440771349862259,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.18832712543023003,
+      "kl": 0.003418200241867453,
+      "learning_rate": 9.95508012440575e-07,
+      "loss": 0.0195,
+      "num_tokens": 2858208.0,
+      "reward": 2.25,
+      "reward_std": 0.5748276710510254,
+      "rewards/cloze_reward/mean": 0.625,
+      "rewards/cloze_reward/std": 0.494535356760025,
+      "rewards/code_reward/mean": 0.625,
+      "rewards/code_reward/std": 0.494535356760025,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0001078844070435,
+      "sampling/importance_sampling_ratio/min": 0.33018070459365845,
+      "sampling/sampling_logp_difference/max": 1.1081151962280273,
+      "sampling/sampling_logp_difference/mean": 0.01556301862001419,
+      "step": 32
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 4436.0,
+      "completions/max_terminated_length": 4436.0,
+      "completions/mean_length": 2222.33349609375,
+      "completions/mean_terminated_length": 2222.33349609375,
+      "completions/min_length": 961.0,
+      "completions/min_terminated_length": 961.0,
+      "entropy": 0.2771223820745945,
+      "epoch": 0.045454545454545456,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.17495461933111076,
+      "kl": 0.0048337242333218455,
+      "learning_rate": 9.95214003174328e-07,
+      "loss": -0.0133,
+      "num_tokens": 2930472.0,
+      "reward": 2.5,
+      "reward_std": 0.36585909128189087,
+      "rewards/cloze_reward/mean": 0.6666666865348816,
+      "rewards/cloze_reward/std": 0.4815434217453003,
+      "rewards/code_reward/mean": 0.8333333134651184,
+      "rewards/code_reward/std": 0.3806934952735901,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9997199177742004,
+      "sampling/importance_sampling_ratio/min": 0.17066244781017303,
+      "sampling/sampling_logp_difference/max": 2.808061122894287,
+      "sampling/sampling_logp_difference/mean": 0.012434008531272411,
+      "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": 6776.0,
+      "completions/max_terminated_length": 6776.0,
+      "completions/mean_length": 3140.70849609375,
+      "completions/mean_terminated_length": 3140.70849609375,
+      "completions/min_length": 726.0,
+      "completions/min_terminated_length": 726.0,
+      "entropy": 0.28713061660528183,
+      "epoch": 0.046831955922865015,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.5763177612619246,
+      "kl": 0.005852235772181302,
+      "learning_rate": 9.949107209404663e-07,
+      "loss": 0.0443,
+      "num_tokens": 3043473.0,
+      "reward": 2.0416667461395264,
+      "reward_std": 0.5222300291061401,
+      "rewards/cloze_reward/mean": 0.5,
+      "rewards/cloze_reward/std": 0.5107539296150208,
+      "rewards/code_reward/mean": 0.5416666865348816,
+      "rewards/code_reward/std": 0.5089773535728455,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0002092123031616,
+      "sampling/importance_sampling_ratio/min": 0.010155132971704006,
+      "sampling/sampling_logp_difference/max": 4.589776039123535,
+      "sampling/sampling_logp_difference/mean": 0.012913873419165611,
+      "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": 0.0833333358168602,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7808.0,
+      "completions/mean_length": 2782.75,
+      "completions/mean_terminated_length": 2291.0,
+      "completions/min_length": 736.0,
+      "completions/min_terminated_length": 736.0,
+      "entropy": 0.23918093740940094,
+      "epoch": 0.048209366391184574,
+      "frac_reward_zero_std": 0.6666666865348816,
+      "grad_norm": 0.19663548974567993,
+      "kl": 0.004491619183681905,
+      "learning_rate": 9.94598171418002e-07,
+      "loss": 0.1035,
+      "num_tokens": 3126827.0,
+      "reward": 2.1666667461395264,
+      "reward_std": 0.35634833574295044,
+      "rewards/cloze_reward/mean": 0.4166666567325592,
+      "rewards/cloze_reward/std": 0.5036101937294006,
+      "rewards/code_reward/mean": 0.8333333134651184,
+      "rewards/code_reward/std": 0.3806934952735901,
+      "rewards/format_reward/mean": 0.9166666865348816,
+      "rewards/format_reward/std": 0.28232985734939575,
+      "sampling/importance_sampling_ratio/max": 1.8434656858444214,
+      "sampling/importance_sampling_ratio/mean": 1.0001463890075684,
+      "sampling/importance_sampling_ratio/min": 0.14892546832561493,
+      "sampling/sampling_logp_difference/max": 1.9043092727661133,
+      "sampling/sampling_logp_difference/mean": 0.011121454648673534,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 6397.0,
+      "completions/max_terminated_length": 6397.0,
+      "completions/mean_length": 2130.70849609375,
+      "completions/mean_terminated_length": 2130.70849609375,
+      "completions/min_length": 908.0,
+      "completions/min_terminated_length": 908.0,
+      "entropy": 0.25559694319963455,
+      "epoch": 0.049586776859504134,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.20044650714243367,
+      "kl": 0.004921266925521195,
+      "learning_rate": 9.94276360459479e-07,
+      "loss": 0.0668,
+      "num_tokens": 3204780.0,
+      "reward": 2.0,
+      "reward_std": 0.34503278136253357,
+      "rewards/cloze_reward/mean": 0.125,
+      "rewards/cloze_reward/std": 0.337831974029541,
+      "rewards/code_reward/mean": 0.875,
+      "rewards/code_reward/std": 0.337831974029541,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9998623728752136,
+      "sampling/importance_sampling_ratio/min": 0.17689232528209686,
+      "sampling/sampling_logp_difference/max": 1.732214093208313,
+      "sampling/sampling_logp_difference/mean": 0.012361792847514153,
+      "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": 0.0,
+      "completions/max_length": 4222.0,
+      "completions/max_terminated_length": 4222.0,
+      "completions/mean_length": 1950.666748046875,
+      "completions/mean_terminated_length": 1950.666748046875,
+      "completions/min_length": 1084.0,
+      "completions/min_terminated_length": 1084.0,
+      "entropy": 0.2424805425107479,
+      "epoch": 0.05096418732782369,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2413970223564091,
+      "kl": 0.004224332165904343,
+      "learning_rate": 9.939452940908626e-07,
+      "loss": 0.0541,
+      "num_tokens": 3282572.0,
+      "reward": 1.8333333730697632,
+      "reward_std": 0.48678088188171387,
+      "rewards/cloze_reward/mean": 0.0833333358168602,
+      "rewards/cloze_reward/std": 0.28232985734939575,
+      "rewards/code_reward/mean": 0.75,
+      "rewards/code_reward/std": 0.4423258602619171,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.999829113483429,
+      "sampling/importance_sampling_ratio/min": 0.16516301035881042,
+      "sampling/sampling_logp_difference/max": 1.800822377204895,
+      "sampling/sampling_logp_difference/mean": 0.01168552041053772,
+      "step": 37
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 6989.0,
+      "completions/max_terminated_length": 6989.0,
+      "completions/mean_length": 2920.041748046875,
+      "completions/mean_terminated_length": 2920.041748046875,
+      "completions/min_length": 1364.0,
+      "completions/min_terminated_length": 1364.0,
+      "entropy": 0.2422230765223503,
+      "epoch": 0.05234159779614325,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.16283138475922154,
+      "kl": 0.004039893392473459,
+      "learning_rate": 9.936049785114279e-07,
+      "loss": 0.0391,
+      "num_tokens": 3380365.0,
+      "reward": 1.8333333730697632,
+      "reward_std": 0.43015047907829285,
+      "rewards/cloze_reward/mean": 0.125,
+      "rewards/cloze_reward/std": 0.337831974029541,
+      "rewards/code_reward/mean": 0.7083333134651184,
+      "rewards/code_reward/std": 0.4643056094646454,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9998534321784973,
+      "sampling/importance_sampling_ratio/min": 0.11749733984470367,
+      "sampling/sampling_logp_difference/max": 2.1413395404815674,
+      "sampling/sampling_logp_difference/mean": 0.012631865218281746,
+      "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": 0.0,
+      "completions/max_length": 7304.0,
+      "completions/max_terminated_length": 7304.0,
+      "completions/mean_length": 3322.041748046875,
+      "completions/mean_terminated_length": 3322.041748046875,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "entropy": 0.4101082310080528,
+      "epoch": 0.05371900826446281,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.181795370019662,
+      "kl": 0.0036983516183681786,
+      "learning_rate": 9.932554200936426e-07,
+      "loss": -0.1581,
+      "num_tokens": 3488278.0,
+      "reward": 1.2083333730697632,
+      "reward_std": 0.6043562889099121,
+      "rewards/cloze_reward/mean": 0.1666666716337204,
+      "rewards/cloze_reward/std": 0.3806934952735901,
+      "rewards/code_reward/mean": 0.375,
+      "rewards/code_reward/std": 0.494535356760025,
+      "rewards/format_reward/mean": 0.6666666865348816,
+      "rewards/format_reward/std": 0.4815434217453003,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 0.9999675154685974,
+      "sampling/importance_sampling_ratio/min": 0.04754088446497917,
+      "sampling/sampling_logp_difference/max": 3.0461652278900146,
+      "sampling/sampling_logp_difference/mean": 0.01610734686255455,
+      "step": 39
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 5011.0,
+      "completions/max_terminated_length": 5011.0,
+      "completions/mean_length": 2942.58349609375,
+      "completions/mean_terminated_length": 2942.58349609375,
+      "completions/min_length": 1454.0,
+      "completions/min_terminated_length": 1454.0,
+      "entropy": 0.35880884528160095,
+      "epoch": 0.05509641873278237,
+      "frac_reward_zero_std": 0.3333333432674408,
+      "grad_norm": 0.17000406623354494,
+      "kl": 0.003319010080303997,
+      "learning_rate": 9.92896625383049e-07,
+      "loss": -0.0559,
+      "num_tokens": 3575956.0,
+      "reward": 1.875,
+      "reward_std": 0.4023112952709198,
+      "rewards/cloze_reward/mean": 0.4583333432674408,
+      "rewards/cloze_reward/std": 0.5089773535728455,
+      "rewards/code_reward/mean": 0.4166666567325592,
+      "rewards/code_reward/std": 0.5036101937294006,
+      "rewards/format_reward/mean": 1.0,
+      "rewards/format_reward/std": 0.0,
+      "sampling/importance_sampling_ratio/max": 2.0,
+      "sampling/importance_sampling_ratio/mean": 1.0000556707382202,
+      "sampling/importance_sampling_ratio/min": 0.27387282252311707,
+      "sampling/sampling_logp_difference/max": 1.2950913906097412,
+      "sampling/sampling_logp_difference/mean": 0.01579936034977436,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 726,
+  "num_input_tokens_seen": 3575956,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:400c06d2fd822d2508c9d6f0b826f17d303bbe43322b8eb0e229cb0e2d1a95fa
+size 9553