promote qwen3_math_ckpt2 to math_model

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

@@ -1,7 +1,4 @@
-{%- set enable_thinking = true %}
-        {%- if not messages or messages[0].role != 'system' %}
-        {%- set messages = [{'role': 'system', 'content': 'Solve the problem. End your response with the final answer in \\boxed{...}.'}] + messages %}
-        {%- endif %}{%- if tools %}
+{%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0].role == 'system' %}
         {{- messages[0].content + '\n\n' }}

config.json

@@ -4,8 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": null,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -54,9 +53,11 @@
     "rope_theta": 1000000,
     "rope_type": "default"
   },
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "5.7.0",
+  "transformers_version": "4.57.1",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -1,12 +1,12 @@
 {
   "do_sample": true,
   "eos_token_id": [
-    151645,
-    151643
+    151645
   ],
   "pad_token_id": 151643,
+  "repetition_penalty": 1.03,
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "5.7.0"
+  "transformers_version": "4.57.1"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12020c36dfd2add85f747b4c674eb7013cb7392a46d0b28c4368f85e7d3dfab
+size 4969539560

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f17b35bfcfb06adf3834216e6520fc1760105d39693c18fbc11533a546fce1
+size 1912795688

model.safetensors.index.json

@@ -0,0 +1,318 @@
+{
+  "metadata": {
+    "total_parameters": 1720574976,
+    "total_size": 6882299904
+  },
+  "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-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-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.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.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16195961b97904f7ff5bf2a94b8ebe32b9a86449b21a40558985717e7f4084e2
+size 5353236089

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917436801ac5217a1e1e84e072c1517531250f3b5e6f89db6c0c040b980b662c
+size 14581

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb7acb1c40910e7feb841dc828e243dbd15a50d3387e5ea17cca443975f99a59
+size 1465

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "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_config.json

@@ -1,26 +1,222 @@
 {
   "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
+    }
+  },
   "backend": "tokenizers",
   "bos_token": null,
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_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|>"
-  ],
-  "is_local": true,
+  "extra_special_tokens": {},
+  "is_local": false,
   "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",

trainer_state.json

@@ -0,0 +1,1314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5856515373352855,
+  "eval_steps": 500,
+  "global_step": 400,
+  "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": 0.25,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2823.1,
+      "completions/mean_length": 2212.6015625,
+      "completions/mean_terminated_length": 1598.5629760742188,
+      "completions/min_length": 548.3,
+      "completions/min_terminated_length": 548.3,
+      "entropy": 0.37419939059764146,
+      "epoch": 0.014641288433382138,
+      "frac_reward_zero_std": 0.1625,
+      "grad_norm": 0.3435262143611908,
+      "learning_rate": 2.5e-07,
+      "loss": -0.0206,
+      "num_tokens": 1461489.0,
+      "reward": 0.55625,
+      "reward_std": 0.490439248085022,
+      "rewards/reward_correct/mean": 0.55625,
+      "rewards/reward_correct/std": 0.4904392629861832,
+      "sampling/importance_sampling_ratio/max": 2.5085304737091065,
+      "sampling/importance_sampling_ratio/mean": 0.38461052924394606,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 20.57911796569824,
+      "sampling/sampling_logp_difference/mean": 0.01642625266686082,
+      "step": 10,
+      "step_time": 39.29108169283718
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2515625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2959.5,
+      "completions/mean_length": 2154.1875,
+      "completions/mean_terminated_length": 1502.6771606445313,
+      "completions/min_length": 541.6,
+      "completions/min_terminated_length": 541.6,
+      "entropy": 0.37666908781975506,
+      "epoch": 0.029282576866764276,
+      "frac_reward_zero_std": 0.2,
+      "grad_norm": 0.20618420839309692,
+      "learning_rate": 5.277777777777777e-07,
+      "loss": -0.046,
+      "num_tokens": 2883441.0,
+      "reward": 0.5515625,
+      "reward_std": 0.4889607191085815,
+      "rewards/reward_correct/mean": 0.5515625,
+      "rewards/reward_correct/std": 0.4889607191085815,
+      "sampling/importance_sampling_ratio/max": 2.602067708969116,
+      "sampling/importance_sampling_ratio/mean": 0.433729550242424,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 19.137638902664186,
+      "sampling/sampling_logp_difference/mean": 0.01647020932286978,
+      "step": 20,
+      "step_time": 38.75275211557746
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.19375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2938.4,
+      "completions/mean_length": 2001.1296875,
+      "completions/mean_terminated_length": 1499.7443725585938,
+      "completions/min_length": 549.0,
+      "completions/min_terminated_length": 549.0,
+      "entropy": 0.3806160856038332,
+      "epoch": 0.043923865300146414,
+      "frac_reward_zero_std": 0.1375,
+      "grad_norm": 0.38085469603538513,
+      "learning_rate": 8.055555555555556e-07,
+      "loss": -0.0399,
+      "num_tokens": 4208244.0,
+      "reward": 0.63125,
+      "reward_std": 0.47393213510513305,
+      "rewards/reward_correct/mean": 0.63125,
+      "rewards/reward_correct/std": 0.47393215000629424,
+      "sampling/importance_sampling_ratio/max": 2.777843475341797,
+      "sampling/importance_sampling_ratio/mean": 0.46774761080741883,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.171199893951417,
+      "sampling/sampling_logp_difference/mean": 0.016388929169625043,
+      "step": 30,
+      "step_time": 36.90585096795112
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2015625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2892.9,
+      "completions/mean_length": 2092.4609375,
+      "completions/mean_terminated_length": 1596.0179565429687,
+      "completions/min_length": 682.9,
+      "completions/min_terminated_length": 682.9,
+      "entropy": 0.39871342200785875,
+      "epoch": 0.05856515373352855,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.3075981140136719,
+      "learning_rate": 9.99983610189578e-07,
+      "loss": -0.0413,
+      "num_tokens": 5591619.0,
+      "reward": 0.5671875,
+      "reward_std": 0.49184212982654574,
+      "rewards/reward_correct/mean": 0.5671875,
+      "rewards/reward_correct/std": 0.4918421536684036,
+      "sampling/importance_sampling_ratio/max": 2.5808013796806337,
+      "sampling/importance_sampling_ratio/mean": 0.4000511050224304,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.92250967025757,
+      "sampling/sampling_logp_difference/mean": 0.017202667891979218,
+      "step": 40,
+      "step_time": 37.50205779653042
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2453125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2909.8,
+      "completions/mean_length": 2165.5484375,
+      "completions/mean_terminated_length": 1548.968701171875,
+      "completions/min_length": 612.0,
+      "completions/min_terminated_length": 612.0,
+      "entropy": 0.3838326945900917,
+      "epoch": 0.07320644216691069,
+      "frac_reward_zero_std": 0.1125,
+      "grad_norm": 0.23338092863559723,
+      "learning_rate": 9.996922656726519e-07,
+      "loss": -0.03,
+      "num_tokens": 7020274.0,
+      "reward": 0.609375,
+      "reward_std": 0.48490735292434695,
+      "rewards/reward_correct/mean": 0.609375,
+      "rewards/reward_correct/std": 0.48490736782550814,
+      "sampling/importance_sampling_ratio/max": 2.5837005376815796,
+      "sampling/importance_sampling_ratio/mean": 0.42594734132289885,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 18.403625679016113,
+      "sampling/sampling_logp_difference/mean": 0.01675282260403037,
+      "step": 50,
+      "step_time": 38.06877801399678
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2991.2,
+      "completions/mean_length": 2021.078125,
+      "completions/mean_terminated_length": 1476.2773681640624,
+      "completions/min_length": 552.9,
+      "completions/min_terminated_length": 552.9,
+      "entropy": 0.38246585726737975,
+      "epoch": 0.08784773060029283,
+      "frac_reward_zero_std": 0.2375,
+      "grad_norm": 0.25549644231796265,
+      "learning_rate": 9.990369474177287e-07,
+      "loss": -0.0368,
+      "num_tokens": 8357548.0,
+      "reward": 0.6078125,
+      "reward_std": 0.4822483420372009,
+      "rewards/reward_correct/mean": 0.6078125,
+      "rewards/reward_correct/std": 0.4822483569383621,
+      "sampling/importance_sampling_ratio/max": 2.551281487941742,
+      "sampling/importance_sampling_ratio/mean": 0.418478462100029,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 18.59011764526367,
+      "sampling/sampling_logp_difference/mean": 0.016825519781559706,
+      "step": 60,
+      "step_time": 37.431954508833584
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2578125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2829.8,
+      "completions/mean_length": 2135.79375,
+      "completions/mean_terminated_length": 1463.258203125,
+      "completions/min_length": 575.9,
+      "completions/min_terminated_length": 575.9,
+      "entropy": 0.37964062821120026,
+      "epoch": 0.10248901903367497,
+      "frac_reward_zero_std": 0.1625,
+      "grad_norm": 0.25282272696495056,
+      "learning_rate": 9.980181327558608e-07,
+      "loss": -0.0358,
+      "num_tokens": 9767000.0,
+      "reward": 0.559375,
+      "reward_std": 0.49146345555782317,
+      "rewards/reward_correct/mean": 0.559375,
+      "rewards/reward_correct/std": 0.4914634644985199,
+      "sampling/importance_sampling_ratio/max": 2.3558115363121033,
+      "sampling/importance_sampling_ratio/mean": 0.38055962324142456,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 20.664661979675294,
+      "sampling/sampling_logp_difference/mean": 0.017013431526720524,
+      "step": 70,
+      "step_time": 38.171042419783774
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2836.0,
+      "completions/mean_length": 2114.996875,
+      "completions/mean_terminated_length": 1504.2937377929688,
+      "completions/min_length": 585.6,
+      "completions/min_terminated_length": 585.6,
+      "entropy": 0.3977603709325194,
+      "epoch": 0.1171303074670571,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.46693727374076843,
+      "learning_rate": 9.966365637873492e-07,
+      "loss": -0.0226,
+      "num_tokens": 11167270.0,
+      "reward": 0.559375,
+      "reward_std": 0.4926549673080444,
+      "rewards/reward_correct/mean": 0.559375,
+      "rewards/reward_correct/std": 0.49265498518943784,
+      "sampling/importance_sampling_ratio/max": 2.3486295104026795,
+      "sampling/importance_sampling_ratio/mean": 0.3683971896767616,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 18.408472061157227,
+      "sampling/sampling_logp_difference/mean": 0.01794397095218301,
+      "step": 80,
+      "step_time": 37.9683697424829
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2390625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2789.4,
+      "completions/mean_length": 2129.534375,
+      "completions/mean_terminated_length": 1521.5262451171875,
+      "completions/min_length": 624.7,
+      "completions/min_terminated_length": 624.7,
+      "entropy": 0.40029386449605225,
+      "epoch": 0.13177159590043924,
+      "frac_reward_zero_std": 0.1375,
+      "grad_norm": 0.16561612486839294,
+      "learning_rate": 9.948932468412012e-07,
+      "loss": -0.053,
+      "num_tokens": 12573820.0,
+      "reward": 0.575,
+      "reward_std": 0.4877741277217865,
+      "rewards/reward_correct/mean": 0.575,
+      "rewards/reward_correct/std": 0.4877741366624832,
+      "sampling/importance_sampling_ratio/max": 2.4529914021492005,
+      "sampling/importance_sampling_ratio/mean": 0.4125220000743866,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 18.997866821289062,
+      "sampling/sampling_logp_difference/mean": 0.017977293580770493,
+      "step": 90,
+      "step_time": 37.94527961928397
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.228125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2833.4,
+      "completions/mean_length": 2073.121875,
+      "completions/mean_terminated_length": 1485.735498046875,
+      "completions/min_length": 600.1,
+      "completions/min_terminated_length": 600.1,
+      "entropy": 0.3927433954551816,
+      "epoch": 0.14641288433382138,
+      "frac_reward_zero_std": 0.1625,
+      "grad_norm": 0.5592489242553711,
+      "learning_rate": 9.927894517421252e-07,
+      "loss": -0.0537,
+      "num_tokens": 13944442.0,
+      "reward": 0.590625,
+      "reward_std": 0.4901668787002563,
+      "rewards/reward_correct/mean": 0.590625,
+      "rewards/reward_correct/std": 0.4901668787002563,
+      "sampling/importance_sampling_ratio/max": 2.6186608552932737,
+      "sampling/importance_sampling_ratio/mean": 0.42541288733482363,
+      "sampling/importance_sampling_ratio/min": 4.2618070530964227e-13,
+      "sampling/sampling_logp_difference/max": 18.757488679885864,
+      "sampling/sampling_logp_difference/mean": 0.017926841229200362,
+      "step": 100,
+      "step_time": 37.48693933803588
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1921875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2794.9,
+      "completions/mean_length": 1990.153125,
+      "completions/mean_terminated_length": 1495.9714721679688,
+      "completions/min_length": 576.9,
+      "completions/min_terminated_length": 576.9,
+      "entropy": 0.3959382362663746,
+      "epoch": 0.16105417276720352,
+      "frac_reward_zero_std": 0.15,
+      "grad_norm": 0.33283355832099915,
+      "learning_rate": 9.903267108855945e-07,
+      "loss": -0.0336,
+      "num_tokens": 15261116.0,
+      "reward": 0.584375,
+      "reward_std": 0.49319341480731965,
+      "rewards/reward_correct/mean": 0.584375,
+      "rewards/reward_correct/std": 0.4931934326887131,
+      "sampling/importance_sampling_ratio/max": 2.7180028676986696,
+      "sampling/importance_sampling_ratio/mean": 0.40315236151218414,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 20.270559215545653,
+      "sampling/sampling_logp_difference/mean": 0.017832764610648155,
+      "step": 110,
+      "step_time": 36.91583805456757
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2546875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2807.0,
+      "completions/mean_length": 2134.259375,
+      "completions/mean_terminated_length": 1486.4429077148438,
+      "completions/min_length": 579.3,
+      "completions/min_terminated_length": 579.3,
+      "entropy": 0.3854369256645441,
+      "epoch": 0.17569546120058566,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 0.20058169960975647,
+      "learning_rate": 9.875068181216587e-07,
+      "loss": -0.0449,
+      "num_tokens": 16669290.0,
+      "reward": 0.5765625,
+      "reward_std": 0.48694353699684145,
+      "rewards/reward_correct/mean": 0.5765625,
+      "rewards/reward_correct/std": 0.48694354891777036,
+      "sampling/importance_sampling_ratio/max": 2.4384738564491273,
+      "sampling/importance_sampling_ratio/mean": 0.39437868595123293,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.982333517074586,
+      "sampling/sampling_logp_difference/mean": 0.017579753790050744,
+      "step": 120,
+      "step_time": 38.01051993258297
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.184375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2856.2,
+      "completions/mean_length": 1977.4796875,
+      "completions/mean_terminated_length": 1499.6147705078124,
+      "completions/min_length": 579.4,
+      "completions/min_terminated_length": 579.4,
+      "entropy": 0.38940617023035884,
+      "epoch": 0.1903367496339678,
+      "frac_reward_zero_std": 0.1375,
+      "grad_norm": 1.0070384740829468,
+      "learning_rate": 9.843318274483087e-07,
+      "loss": -0.0516,
+      "num_tokens": 17979685.0,
+      "reward": 0.6375,
+      "reward_std": 0.47116253077983855,
+      "rewards/reward_correct/mean": 0.6375,
+      "rewards/reward_correct/std": 0.4711625397205353,
+      "sampling/importance_sampling_ratio/max": 2.4777760744094848,
+      "sampling/importance_sampling_ratio/mean": 0.4186276912689209,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 19.95844659805298,
+      "sampling/sampling_logp_difference/mean": 0.017811466939747334,
+      "step": 130,
+      "step_time": 36.8255618410185
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.21875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2830.2,
+      "completions/mean_length": 2012.015625,
+      "completions/mean_terminated_length": 1436.9541870117187,
+      "completions/min_length": 505.1,
+      "completions/min_terminated_length": 505.1,
+      "entropy": 0.3977817573584616,
+      "epoch": 0.20497803806734993,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 0.22780311107635498,
+      "learning_rate": 9.808040515153556e-07,
+      "loss": -0.0363,
+      "num_tokens": 19310607.0,
+      "reward": 0.55625,
+      "reward_std": 0.48927740156650545,
+      "rewards/reward_correct/mean": 0.55625,
+      "rewards/reward_correct/std": 0.48927741646766665,
+      "sampling/importance_sampling_ratio/max": 2.4563987016677857,
+      "sampling/importance_sampling_ratio/mean": 0.409631285071373,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.072743701934815,
+      "sampling/sampling_logp_difference/mean": 0.01845102310180664,
+      "step": 140,
+      "step_time": 37.086776703968646
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1609375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2787.6,
+      "completions/mean_length": 1766.853125,
+      "completions/mean_terminated_length": 1328.84560546875,
+      "completions/min_length": 406.8,
+      "completions/min_terminated_length": 406.8,
+      "entropy": 0.392044834792614,
+      "epoch": 0.21961932650073207,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 0.17948757112026215,
+      "learning_rate": 9.769260599399039e-07,
+      "loss": -0.0457,
+      "num_tokens": 20486505.0,
+      "reward": 0.596875,
+      "reward_std": 0.47513407170772554,
+      "rewards/reward_correct/mean": 0.596875,
+      "rewards/reward_correct/std": 0.47513407468795776,
+      "sampling/importance_sampling_ratio/max": 2.5963918924331666,
+      "sampling/importance_sampling_ratio/mean": 0.5011082530021668,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.8177583694458,
+      "sampling/sampling_logp_difference/mean": 0.01750883022323251,
+      "step": 150,
+      "step_time": 35.45692438371479
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2935.8,
+      "completions/mean_length": 1923.7125,
+      "completions/mean_terminated_length": 1428.9456909179687,
+      "completions/min_length": 506.1,
+      "completions/min_terminated_length": 506.1,
+      "entropy": 0.381333545409143,
+      "epoch": 0.2342606149341142,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.41639286279678345,
+      "learning_rate": 9.72700677434655e-07,
+      "loss": -0.0459,
+      "num_tokens": 21760313.0,
+      "reward": 0.6390625,
+      "reward_std": 0.4709364324808121,
+      "rewards/reward_correct/mean": 0.6390625,
+      "rewards/reward_correct/std": 0.4709364533424377,
+      "sampling/importance_sampling_ratio/max": 2.5141386866569517,
+      "sampling/importance_sampling_ratio/mean": 0.4655365616083145,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 19.548265552520753,
+      "sampling/sampling_logp_difference/mean": 0.017716512829065324,
+      "step": 160,
+      "step_time": 36.49282261896879
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2799.0,
+      "completions/mean_length": 1909.315625,
+      "completions/mean_terminated_length": 1408.5566040039062,
+      "completions/min_length": 540.9,
+      "completions/min_terminated_length": 540.9,
+      "entropy": 0.3857618235051632,
+      "epoch": 0.24890190336749635,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.17534476518630981,
+      "learning_rate": 9.68130981750398e-07,
+      "loss": -0.0643,
+      "num_tokens": 23027003.0,
+      "reward": 0.609375,
+      "reward_std": 0.47989254295825956,
+      "rewards/reward_correct/mean": 0.609375,
+      "rewards/reward_correct/std": 0.47989254891872407,
+      "sampling/importance_sampling_ratio/max": 2.462973582744598,
+      "sampling/importance_sampling_ratio/mean": 0.43628491163253785,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 19.400583267211914,
+      "sampling/sampling_logp_difference/mean": 0.01854742243885994,
+      "step": 170,
+      "step_time": 36.428762685880066
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.16875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2686.4,
+      "completions/mean_length": 1844.8015625,
+      "completions/mean_terminated_length": 1392.41220703125,
+      "completions/min_length": 535.8,
+      "completions/min_terminated_length": 535.8,
+      "entropy": 0.3859222376719117,
+      "epoch": 0.2635431918008785,
+      "frac_reward_zero_std": 0.1375,
+      "grad_norm": 0.25816696882247925,
+      "learning_rate": 9.632203014341889e-07,
+      "loss": -0.0448,
+      "num_tokens": 24250292.0,
+      "reward": 0.64375,
+      "reward_std": 0.4732906401157379,
+      "rewards/reward_correct/mean": 0.64375,
+      "rewards/reward_correct/std": 0.4732906550168991,
+      "sampling/importance_sampling_ratio/max": 2.515523314476013,
+      "sampling/importance_sampling_ratio/mean": 0.45121900737285614,
+      "sampling/importance_sampling_ratio/min": 5.720088031707649e-16,
+      "sampling/sampling_logp_difference/max": 18.85363140106201,
+      "sampling/sampling_logp_difference/mean": 0.01874276315793395,
+      "step": 180,
+      "step_time": 35.822446891106665
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1421875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2912.1,
+      "completions/mean_length": 1814.25,
+      "completions/mean_terminated_length": 1438.4544067382812,
+      "completions/min_length": 485.2,
+      "completions/min_terminated_length": 485.2,
+      "entropy": 0.38771476671099664,
+      "epoch": 0.2781844802342606,
+      "frac_reward_zero_std": 0.2125,
+      "grad_norm": 0.5499361157417297,
+      "learning_rate": 9.579722134048505e-07,
+      "loss": -0.0664,
+      "num_tokens": 25455380.0,
+      "reward": 0.696875,
+      "reward_std": 0.45076643824577334,
+      "rewards/reward_correct/mean": 0.696875,
+      "rewards/reward_correct/std": 0.45076645314693453,
+      "sampling/importance_sampling_ratio/max": 2.7236300706863403,
+      "sampling/importance_sampling_ratio/mean": 0.4416166603565216,
+      "sampling/importance_sampling_ratio/min": 4.50560732981835e-14,
+      "sampling/sampling_logp_difference/max": 18.057205963134766,
+      "sampling/sampling_logp_difference/mean": 0.018269804771989584,
+      "step": 190,
+      "step_time": 35.50249644275755
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.178125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2725.0,
+      "completions/mean_length": 1798.475,
+      "completions/mean_terminated_length": 1306.3749267578125,
+      "completions/min_length": 467.3,
+      "completions/min_terminated_length": 467.3,
+      "entropy": 0.403516604192555,
+      "epoch": 0.29282576866764276,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.24104301631450653,
+      "learning_rate": 9.523905403475602e-07,
+      "loss": -0.0377,
+      "num_tokens": 26657748.0,
+      "reward": 0.6421875,
+      "reward_std": 0.4670192450284958,
+      "rewards/reward_correct/mean": 0.6421875,
+      "rewards/reward_correct/std": 0.467019259929657,
+      "sampling/importance_sampling_ratio/max": 2.6622950792312623,
+      "sampling/importance_sampling_ratio/mean": 0.4573585122823715,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 14.958099842071533,
+      "sampling/sampling_logp_difference/mean": 0.019307527132332324,
+      "step": 200,
+      "step_time": 35.87465734221041
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1484375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2780.8,
+      "completions/mean_length": 1691.4671875,
+      "completions/mean_terminated_length": 1279.5517211914062,
+      "completions/min_length": 462.5,
+      "completions/min_terminated_length": 462.5,
+      "entropy": 0.4017993725836277,
+      "epoch": 0.3074670571010249,
+      "frac_reward_zero_std": 0.2125,
+      "grad_norm": 0.43709596991539,
+      "learning_rate": 9.464793479294231e-07,
+      "loss": -0.0476,
+      "num_tokens": 27786791.0,
+      "reward": 0.6515625,
+      "reward_std": 0.4750798672437668,
+      "rewards/reward_correct/mean": 0.6515625,
+      "rewards/reward_correct/std": 0.4750798732042313,
+      "sampling/importance_sampling_ratio/max": 2.6835455656051637,
+      "sampling/importance_sampling_ratio/mean": 0.5069015234708786,
+      "sampling/importance_sampling_ratio/min": 5.857610837350924e-13,
+      "sampling/sampling_logp_difference/max": 14.076149034500123,
+      "sampling/sampling_logp_difference/mean": 0.018997256830334663,
+      "step": 210,
+      "step_time": 34.91050934363157
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1140625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2781.9,
+      "completions/mean_length": 1601.453125,
+      "completions/mean_terminated_length": 1284.7239868164063,
+      "completions/min_length": 455.6,
+      "completions/min_terminated_length": 455.6,
+      "entropy": 0.35529792681336403,
+      "epoch": 0.32210834553440704,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.47860920429229736,
+      "learning_rate": 9.402429418380553e-07,
+      "loss": -0.0524,
+      "num_tokens": 28853673.0,
+      "reward": 0.6625,
+      "reward_std": 0.4586958348751068,
+      "rewards/reward_correct/mean": 0.6625,
+      "rewards/reward_correct/std": 0.45869584381580353,
+      "sampling/importance_sampling_ratio/max": 2.5586405754089356,
+      "sampling/importance_sampling_ratio/mean": 0.5027410387992859,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.85229778289795,
+      "sampling/sampling_logp_difference/mean": 0.016478382982313633,
+      "step": 220,
+      "step_time": 34.23139138985425
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.115625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2731.4,
+      "completions/mean_length": 1624.2125,
+      "completions/mean_terminated_length": 1311.4201293945312,
+      "completions/min_length": 476.9,
+      "completions/min_terminated_length": 476.9,
+      "entropy": 0.3669202409684658,
+      "epoch": 0.3367496339677892,
+      "frac_reward_zero_std": 0.3,
+      "grad_norm": 0.24832919239997864,
+      "learning_rate": 9.336858646453414e-07,
+      "loss": -0.0322,
+      "num_tokens": 29936905.0,
+      "reward": 0.6765625,
+      "reward_std": 0.4523905426263809,
+      "rewards/reward_correct/mean": 0.6765625,
+      "rewards/reward_correct/std": 0.4523905456066132,
+      "sampling/importance_sampling_ratio/max": 2.542170763015747,
+      "sampling/importance_sampling_ratio/mean": 0.4556583046913147,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 12.38556728363037,
+      "sampling/sampling_logp_difference/mean": 0.016565939877182245,
+      "step": 230,
+      "step_time": 34.123054202459755
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1015625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2746.9,
+      "completions/mean_length": 1570.1953125,
+      "completions/mean_terminated_length": 1285.9392578125,
+      "completions/min_length": 418.9,
+      "completions/min_terminated_length": 418.9,
+      "entropy": 0.3694750224240124,
+      "epoch": 0.3513909224011713,
+      "frac_reward_zero_std": 0.2625,
+      "grad_norm": 0.257592111825943,
+      "learning_rate": 9.268128924986423e-07,
+      "loss": -0.0237,
+      "num_tokens": 30982974.0,
+      "reward": 0.7078125,
+      "reward_std": 0.44998968243598936,
+      "rewards/reward_correct/mean": 0.7078125,
+      "rewards/reward_correct/std": 0.44998968839645387,
+      "sampling/importance_sampling_ratio/max": 2.7356862783432008,
+      "sampling/importance_sampling_ratio/mean": 0.5219734072685241,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.76656379699707,
+      "sampling/sampling_logp_difference/mean": 0.01709262877702713,
+      "step": 240,
+      "step_time": 33.79627364780754
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1515625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2862.5,
+      "completions/mean_length": 1752.46875,
+      "completions/mean_terminated_length": 1339.9485717773437,
+      "completions/min_length": 511.6,
+      "completions/min_terminated_length": 511.6,
+      "entropy": 0.3790203006006777,
+      "epoch": 0.36603221083455345,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.2643333077430725,
+      "learning_rate": 9.196290316418711e-07,
+      "loss": -0.0167,
+      "num_tokens": 32148106.0,
+      "reward": 0.69375,
+      "reward_std": 0.4524209886789322,
+      "rewards/reward_correct/mean": 0.69375,
+      "rewards/reward_correct/std": 0.45242099165916444,
+      "sampling/importance_sampling_ratio/max": 2.5667138576507567,
+      "sampling/importance_sampling_ratio/mean": 0.46120509803295134,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.062857961654665,
+      "sampling/sampling_logp_difference/mean": 0.017286003567278385,
+      "step": 250,
+      "step_time": 35.38917248025537
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.14375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2649.3,
+      "completions/mean_length": 1679.1015625,
+      "completions/mean_terminated_length": 1278.3498779296874,
+      "completions/min_length": 455.0,
+      "completions/min_terminated_length": 455.0,
+      "entropy": 0.3729710878804326,
+      "epoch": 0.3806734992679356,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 0.3721376955509186,
+      "learning_rate": 9.121395147689656e-07,
+      "loss": -0.0324,
+      "num_tokens": 33263731.0,
+      "reward": 0.709375,
+      "reward_std": 0.44895724058151243,
+      "rewards/reward_correct/mean": 0.709375,
+      "rewards/reward_correct/std": 0.4489572554826736,
+      "sampling/importance_sampling_ratio/max": 2.6168325543403625,
+      "sampling/importance_sampling_ratio/mean": 0.4866025298833847,
+      "sampling/importance_sampling_ratio/min": 4.2161274329675353e-20,
+      "sampling/sampling_logp_difference/max": 17.691544580459595,
+      "sampling/sampling_logp_difference/mean": 0.017986807506531477,
+      "step": 260,
+      "step_time": 34.72450201679021
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1640625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2785.0,
+      "completions/mean_length": 1751.3421875,
+      "completions/mean_terminated_length": 1291.7200805664063,
+      "completions/min_length": 444.2,
+      "completions/min_terminated_length": 444.2,
+      "entropy": 0.38200761983171105,
+      "epoch": 0.3953147877013177,
+      "frac_reward_zero_std": 0.2375,
+      "grad_norm": 0.4049576222896576,
+      "learning_rate": 9.043497972124159e-07,
+      "loss": -0.0661,
+      "num_tokens": 34428686.0,
+      "reward": 0.60625,
+      "reward_std": 0.4841457366943359,
+      "rewards/reward_correct/mean": 0.60625,
+      "rewards/reward_correct/std": 0.4841457486152649,
+      "sampling/importance_sampling_ratio/max": 2.7381280183792116,
+      "sampling/importance_sampling_ratio/mean": 0.46350172758102415,
+      "sampling/importance_sampling_ratio/min": 1.7057631492547668e-22,
+      "sampling/sampling_logp_difference/max": 17.866797351837157,
+      "sampling/sampling_logp_difference/mean": 0.018646900169551374,
+      "step": 270,
+      "step_time": 35.4160362392664
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.115625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2516.1,
+      "completions/mean_length": 1570.7015625,
+      "completions/mean_terminated_length": 1243.3549255371095,
+      "completions/min_length": 434.5,
+      "completions/min_terminated_length": 434.5,
+      "entropy": 0.36390284188091754,
+      "epoch": 0.40995607613469986,
+      "frac_reward_zero_std": 0.2625,
+      "grad_norm": 0.3584902286529541,
+      "learning_rate": 8.962655529696235e-07,
+      "loss": -0.0418,
+      "num_tokens": 35477679.0,
+      "reward": 0.6875,
+      "reward_std": 0.4531699061393738,
+      "rewards/reward_correct/mean": 0.6875,
+      "rewards/reward_correct/std": 0.4531699150800705,
+      "sampling/importance_sampling_ratio/max": 2.442759966850281,
+      "sampling/importance_sampling_ratio/mean": 0.5131819605827331,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 15.253278446197509,
+      "sampling/sampling_logp_difference/mean": 0.016866661701351406,
+      "step": 280,
+      "step_time": 33.91963651422411
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 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": 4096.0,
+      "completions/max_terminated_length": 2782.3,
+      "completions/mean_length": 1638.540625,
+      "completions/mean_terminated_length": 1286.608056640625,
+      "completions/min_length": 470.6,
+      "completions/min_terminated_length": 470.6,
+      "entropy": 0.3610599435865879,
+      "epoch": 0.424597364568082,
+      "frac_reward_zero_std": 0.2625,
+      "grad_norm": 0.7691017985343933,
+      "learning_rate": 8.878926705699856e-07,
+      "loss": -0.0281,
+      "num_tokens": 36571065.0,
+      "reward": 0.6671875,
+      "reward_std": 0.4638109654188156,
+      "rewards/reward_correct/mean": 0.6671875,
+      "rewards/reward_correct/std": 0.46381097137928007,
+      "sampling/importance_sampling_ratio/max": 2.665994715690613,
+      "sampling/importance_sampling_ratio/mean": 0.5255463659763336,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 18.80701427459717,
+      "sampling/sampling_logp_difference/mean": 0.01755312941968441,
+      "step": 290,
+      "step_time": 34.501018999516965
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0828125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2752.6,
+      "completions/mean_length": 1450.7203125,
+      "completions/mean_terminated_length": 1214.2732421875,
+      "completions/min_length": 393.4,
+      "completions/min_terminated_length": 393.4,
+      "entropy": 0.3570564230903983,
+      "epoch": 0.43923865300146414,
+      "frac_reward_zero_std": 0.2875,
+      "grad_norm": 0.3508993685245514,
+      "learning_rate": 8.79237248785715e-07,
+      "loss": -0.0214,
+      "num_tokens": 37543510.0,
+      "reward": 0.7234375,
+      "reward_std": 0.4414018362760544,
+      "rewards/reward_correct/mean": 0.7234375,
+      "rewards/reward_correct/std": 0.4414018452167511,
+      "sampling/importance_sampling_ratio/max": 2.632966458797455,
+      "sampling/importance_sampling_ratio/mean": 0.5690318822860718,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 15.237814354896546,
+      "sampling/sampling_logp_difference/mean": 0.016272421553730966,
+      "step": 300,
+      "step_time": 32.97251550052315
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.11875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2646.6,
+      "completions/mean_length": 1567.734375,
+      "completions/mean_terminated_length": 1226.1940612792969,
+      "completions/min_length": 445.7,
+      "completions/min_terminated_length": 445.7,
+      "entropy": 0.3664493842050433,
+      "epoch": 0.4538799414348463,
+      "frac_reward_zero_std": 0.175,
+      "grad_norm": 0.3325318694114685,
+      "learning_rate": 8.703055921895199e-07,
+      "loss": -0.0714,
+      "num_tokens": 38588412.0,
+      "reward": 0.671875,
+      "reward_std": 0.4696904391050339,
+      "rewards/reward_correct/mean": 0.671875,
+      "rewards/reward_correct/std": 0.46969045102596285,
+      "sampling/importance_sampling_ratio/max": 2.6194750547409056,
+      "sampling/importance_sampling_ratio/mean": 0.5207919716835022,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.138701295852663,
+      "sampling/sampling_logp_difference/mean": 0.017311585228890182,
+      "step": 310,
+      "step_time": 33.91836810335517
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.15625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2812.6,
+      "completions/mean_length": 1737.5203125,
+      "completions/mean_terminated_length": 1304.576318359375,
+      "completions/min_length": 466.3,
+      "completions/min_terminated_length": 466.3,
+      "entropy": 0.36455219322815535,
+      "epoch": 0.4685212298682284,
+      "frac_reward_zero_std": 0.2625,
+      "grad_norm": 0.29537466168403625,
+      "learning_rate": 8.611042065623803e-07,
+      "loss": -0.0326,
+      "num_tokens": 39742889.0,
+      "reward": 0.653125,
+      "reward_std": 0.4676573634147644,
+      "rewards/reward_correct/mean": 0.653125,
+      "rewards/reward_correct/std": 0.4676573842763901,
+      "sampling/importance_sampling_ratio/max": 2.652678394317627,
+      "sampling/importance_sampling_ratio/mean": 0.4831114441156387,
+      "sampling/importance_sampling_ratio/min": 0.00019024546490982176,
+      "sampling/sampling_logp_difference/max": 19.12404477596283,
+      "sampling/sampling_logp_difference/mean": 0.01720849359408021,
+      "step": 320,
+      "step_time": 35.216385383345184
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1375,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2757.1,
+      "completions/mean_length": 1635.178125,
+      "completions/mean_terminated_length": 1247.730126953125,
+      "completions/min_length": 447.5,
+      "completions/min_terminated_length": 447.5,
+      "entropy": 0.3698131384328008,
+      "epoch": 0.48316251830161056,
+      "frac_reward_zero_std": 0.275,
+      "grad_norm": 0.4860650897026062,
+      "learning_rate": 8.516397941547642e-07,
+      "loss": -0.0379,
+      "num_tokens": 40831555.0,
+      "reward": 0.64375,
+      "reward_std": 0.4675807595252991,
+      "rewards/reward_correct/mean": 0.64375,
+      "rewards/reward_correct/std": 0.4675807744264603,
+      "sampling/importance_sampling_ratio/max": 2.4814563751220704,
+      "sampling/importance_sampling_ratio/mean": 0.5446478247642517,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.6794762134552,
+      "sampling/sampling_logp_difference/mean": 0.017301212623715402,
+      "step": 330,
+      "step_time": 34.54350109342486
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1296875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2816.2,
+      "completions/mean_length": 1657.74375,
+      "completions/mean_terminated_length": 1297.5836242675782,
+      "completions/min_length": 437.8,
+      "completions/min_terminated_length": 437.8,
+      "entropy": 0.36472494443878534,
+      "epoch": 0.4978038067349927,
+      "frac_reward_zero_std": 0.2875,
+      "grad_norm": 0.35601162910461426,
+      "learning_rate": 8.419192488047369e-07,
+      "loss": -0.0519,
+      "num_tokens": 41934135.0,
+      "reward": 0.7125,
+      "reward_std": 0.43097937405109404,
+      "rewards/reward_correct/mean": 0.7125,
+      "rewards/reward_correct/std": 0.43097938448190687,
+      "sampling/importance_sampling_ratio/max": 2.605836796760559,
+      "sampling/importance_sampling_ratio/mean": 0.483393257856369,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.06987910270691,
+      "sampling/sampling_logp_difference/mean": 0.017136862501502037,
+      "step": 340,
+      "step_time": 34.51869362480939
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1453125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2704.6,
+      "completions/mean_length": 1647.3359375,
+      "completions/mean_terminated_length": 1231.4567504882812,
+      "completions/min_length": 438.2,
+      "completions/min_terminated_length": 438.2,
+      "entropy": 0.356427114829421,
+      "epoch": 0.5124450951683748,
+      "frac_reward_zero_std": 0.3125,
+      "grad_norm": 0.27125442028045654,
+      "learning_rate": 8.319496509165178e-07,
+      "loss": -0.0427,
+      "num_tokens": 43034726.0,
+      "reward": 0.709375,
+      "reward_std": 0.44495919346809387,
+      "rewards/reward_correct/mean": 0.709375,
+      "rewards/reward_correct/std": 0.4449592143297195,
+      "sampling/importance_sampling_ratio/max": 2.544973075389862,
+      "sampling/importance_sampling_ratio/mean": 0.5312303602695465,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.840685081481933,
+      "sampling/sampling_logp_difference/mean": 0.016760549787431956,
+      "step": 350,
+      "step_time": 34.627660664729774
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.2046875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2759.0,
+      "completions/mean_length": 1936.9046875,
+      "completions/mean_terminated_length": 1389.5431640625,
+      "completions/min_length": 513.5,
+      "completions/min_terminated_length": 513.5,
+      "entropy": 0.3591486904770136,
+      "epoch": 0.527086383601757,
+      "frac_reward_zero_std": 0.1875,
+      "grad_norm": 0.47527405619621277,
+      "learning_rate": 8.217382623031446e-07,
+      "loss": -0.0398,
+      "num_tokens": 44324201.0,
+      "reward": 0.6375,
+      "reward_std": 0.4755891412496567,
+      "rewards/reward_correct/mean": 0.6375,
+      "rewards/reward_correct/std": 0.4755891591310501,
+      "sampling/importance_sampling_ratio/max": 2.5801383018493653,
+      "sampling/importance_sampling_ratio/mean": 0.4459040939807892,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 17.53456029891968,
+      "sampling/sampling_logp_difference/mean": 0.01709551801905036,
+      "step": 360,
+      "step_time": 36.787907522358
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.146875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2759.7,
+      "completions/mean_length": 1691.0171875,
+      "completions/mean_terminated_length": 1281.7273559570312,
+      "completions/min_length": 458.1,
+      "completions/min_terminated_length": 458.1,
+      "entropy": 0.35544084664434195,
+      "epoch": 0.541727672035139,
+      "frac_reward_zero_std": 0.225,
+      "grad_norm": 0.40646737813949585,
+      "learning_rate": 8.112925208969994e-07,
+      "loss": -0.0476,
+      "num_tokens": 45452780.0,
+      "reward": 0.6625,
+      "reward_std": 0.4693898320198059,
+      "rewards/reward_correct/mean": 0.6625,
+      "rewards/reward_correct/std": 0.46938984394073485,
+      "sampling/importance_sampling_ratio/max": 2.414482605457306,
+      "sampling/importance_sampling_ratio/mean": 0.4706720381975174,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 16.63887777328491,
+      "sampling/sampling_logp_difference/mean": 0.016511439718306063,
+      "step": 370,
+      "step_time": 35.02858482897282
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1640625,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2776.2,
+      "completions/mean_length": 1821.15625,
+      "completions/mean_terminated_length": 1381.08876953125,
+      "completions/min_length": 544.9,
+      "completions/min_terminated_length": 544.9,
+      "entropy": 0.3640032488852739,
+      "epoch": 0.5563689604685212,
+      "frac_reward_zero_std": 0.2625,
+      "grad_norm": 0.4008844196796417,
+      "learning_rate": 8.006200353320491e-07,
+      "loss": -0.0189,
+      "num_tokens": 46661216.0,
+      "reward": 0.703125,
+      "reward_std": 0.44935562610626223,
+      "rewards/reward_correct/mean": 0.703125,
+      "rewards/reward_correct/std": 0.44935562908649446,
+      "sampling/importance_sampling_ratio/max": 2.6022926807403564,
+      "sampling/importance_sampling_ratio/mean": 0.463966104388237,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 21.094895362854004,
+      "sampling/sampling_logp_difference/mean": 0.016442943084985017,
+      "step": 380,
+      "step_time": 35.73085868619383
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.16875,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2768.1,
+      "completions/mean_length": 1857.7375,
+      "completions/mean_terminated_length": 1399.4028930664062,
+      "completions/min_length": 489.4,
+      "completions/min_terminated_length": 489.4,
+      "entropy": 0.35788101237267256,
+      "epoch": 0.5710102489019033,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 0.23576705157756805,
+      "learning_rate": 7.897285794017496e-07,
+      "loss": -0.0209,
+      "num_tokens": 47894416.0,
+      "reward": 0.6875,
+      "reward_std": 0.45242039263248446,
+      "rewards/reward_correct/mean": 0.6875,
+      "rewards/reward_correct/std": 0.45242040455341337,
+      "sampling/importance_sampling_ratio/max": 2.3218968152999877,
+      "sampling/importance_sampling_ratio/mean": 0.42465601563453675,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 20.939725494384767,
+      "sampling/sampling_logp_difference/mean": 0.016080015711486338,
+      "step": 390,
+      "step_time": 36.061240384168926
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1578125,
+      "completions/max_length": 4096.0,
+      "completions/max_terminated_length": 2684.6,
+      "completions/mean_length": 1719.9484375,
+      "completions/mean_terminated_length": 1274.9297119140624,
+      "completions/min_length": 438.0,
+      "completions/min_terminated_length": 438.0,
+      "entropy": 0.3516252673231065,
+      "epoch": 0.5856515373352855,
+      "frac_reward_zero_std": 0.2125,
+      "grad_norm": 0.37620285153388977,
+      "learning_rate": 7.786260863966467e-07,
+      "loss": -0.0155,
+      "num_tokens": 49039495.0,
+      "reward": 0.65,
+      "reward_std": 0.47073342502117155,
+      "rewards/reward_correct/mean": 0.65,
+      "rewards/reward_correct/std": 0.47073343098163606,
+      "sampling/importance_sampling_ratio/max": 2.62828643321991,
+      "sampling/importance_sampling_ratio/mean": 0.5133629143238068,
+      "sampling/importance_sampling_ratio/min": 0.0,
+      "sampling/sampling_logp_difference/max": 14.084659862518311,
+      "sampling/sampling_logp_difference/mean": 0.015848731249570848,
+      "step": 400,
+      "step_time": 35.166023310273886
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 49039495,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596dd98aa77206a5954b6dc999536f12bb284d199abe2b21f40a7593e36df1a6
-size 5841
+oid sha256:4dc7eaa6b2fd30b7c86489abf67d70e5a110193f4ce54ac38c13cd2ba3a192c2
+size 8017