Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c3204fafb06656d0a120bdf4b939d354039cc887d8007113d17cda0acbeada
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb090689d85ac595f288447fd36ea0ef16384951c925f9e4782d0f4d47cde28c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9a85f406815715a95c31462aeb49d067aaeaab92c35031420402e7d67e443d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:483ba68a8551324aa36ca42ba590a210a9ff8cf217146ce506c7a7fd4b142f9a
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2158 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.136,
+  "eval_steps": 500,
+  "global_step": 170,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2975.1640625,
+      "epoch": 0.0008,
+      "grad_norm": 0.4355019563597344,
+      "kl": 0.0,
+      "learning_rate": 5e-07,
+      "loss": 0.0713,
+      "reward": 0.20156250591389835,
+      "reward_std": 0.3847714839503169,
+      "rewards/end_of_conversation_reward_func": 0.04531250044237822,
+      "rewards/end_rm_reward_func": 0.234375,
+      "rewards/length_reward_func": -0.078125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.004448831474292092,
+      "epoch": 0.0016,
+      "grad_norm": 0.43263977335652204,
+      "kl": 0.0011990070343017578,
+      "learning_rate": 5e-07,
+      "loss": 0.0713,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3296.3828125,
+      "epoch": 0.0024,
+      "grad_norm": 0.4062162240261375,
+      "kl": 0.0015230178833007812,
+      "learning_rate": 5e-07,
+      "loss": 0.0715,
+      "reward": 0.13886718894355,
+      "reward_std": 0.47177961003035307,
+      "rewards/end_of_conversation_reward_func": 0.04218750080326572,
+      "rewards/end_rm_reward_func": 0.1669921875,
+      "rewards/length_reward_func": -0.0703125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.004145426195464097,
+      "epoch": 0.0032,
+      "grad_norm": 0.40276269917704577,
+      "kl": 0.0014390945434570312,
+      "learning_rate": 5e-07,
+      "loss": 0.0715,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3100.2265625,
+      "epoch": 0.004,
+      "grad_norm": 0.4627427111427237,
+      "kl": 0.0020265579223632812,
+      "learning_rate": 5e-07,
+      "loss": 0.0995,
+      "reward": 0.08027344156289473,
+      "reward_std": 0.39663981925696135,
+      "rewards/end_of_conversation_reward_func": 0.042187501152511686,
+      "rewards/end_rm_reward_func": 0.1279296875,
+      "rewards/length_reward_func": -0.08984375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.004560721252346411,
+      "epoch": 0.0048,
+      "grad_norm": 0.46529399802489874,
+      "kl": 0.0024538040161132812,
+      "learning_rate": 5e-07,
+      "loss": 0.0994,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3276.453125,
+      "epoch": 0.0056,
+      "grad_norm": 0.3877916318690821,
+      "kl": 0.0020666122436523438,
+      "learning_rate": 5e-07,
+      "loss": 0.0582,
+      "reward": 0.21875000558793545,
+      "reward_std": 0.4846916552633047,
+      "rewards/end_of_conversation_reward_func": 0.04296875110594556,
+      "rewards/end_rm_reward_func": 0.23828125,
+      "rewards/length_reward_func": -0.0625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.003973798331571743,
+      "epoch": 0.0064,
+      "grad_norm": 0.38615742327777886,
+      "kl": 0.0033469200134277344,
+      "learning_rate": 5e-07,
+      "loss": 0.0582,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3526.203125,
+      "epoch": 0.0072,
+      "grad_norm": 0.4253042896775168,
+      "kl": 0.0022199153900146484,
+      "learning_rate": 5e-07,
+      "loss": 0.0966,
+      "reward": 0.1652343834284693,
+      "reward_std": 0.44294953159987926,
+      "rewards/end_of_conversation_reward_func": 0.04218750086147338,
+      "rewards/end_rm_reward_func": 0.208984375,
+      "rewards/length_reward_func": -0.0859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0041108929144684225,
+      "epoch": 0.008,
+      "grad_norm": 0.4043558511957573,
+      "kl": 0.003947257995605469,
+      "learning_rate": 5e-07,
+      "loss": 0.0965,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3034.078125,
+      "epoch": 0.0088,
+      "grad_norm": 0.49241796839949487,
+      "kl": 0.002953052520751953,
+      "learning_rate": 5e-07,
+      "loss": 0.1329,
+      "reward": 0.17500000772997737,
+      "reward_std": 0.4498265013098717,
+      "rewards/end_of_conversation_reward_func": 0.0421875009778887,
+      "rewards/end_rm_reward_func": 0.18359375,
+      "rewards/length_reward_func": -0.05078125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0041437734180362895,
+      "epoch": 0.0096,
+      "grad_norm": 0.4951138738584942,
+      "kl": 0.0035958290100097656,
+      "learning_rate": 5e-07,
+      "loss": 0.1329,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3284.0234375,
+      "epoch": 0.0104,
+      "grad_norm": 0.41732249846603825,
+      "kl": 0.020305156707763672,
+      "learning_rate": 5e-07,
+      "loss": 0.0294,
+      "reward": 0.20390625670552254,
+      "reward_std": 0.4014717759564519,
+      "rewards/end_of_conversation_reward_func": 0.047656250884756446,
+      "rewards/end_rm_reward_func": 0.22265625,
+      "rewards/length_reward_func": -0.06640625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.00431825453415513,
+      "epoch": 0.0112,
+      "grad_norm": 0.4109822678418246,
+      "kl": 0.030427932739257812,
+      "learning_rate": 5e-07,
+      "loss": 0.0295,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2969.1953125,
+      "epoch": 0.012,
+      "grad_norm": 0.48270296374119925,
+      "kl": 0.010631561279296875,
+      "learning_rate": 5e-07,
+      "loss": 0.0477,
+      "reward": 0.2396484500495717,
+      "reward_std": 0.3797372495755553,
+      "rewards/end_of_conversation_reward_func": 0.04921875154832378,
+      "rewards/end_rm_reward_func": 0.2255859375,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.004689372595748864,
+      "epoch": 0.0128,
+      "grad_norm": 0.4751005673450339,
+      "kl": 0.011091232299804688,
+      "learning_rate": 5e-07,
+      "loss": 0.0476,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2861.1953125,
+      "epoch": 0.0136,
+      "grad_norm": 0.5567124142202874,
+      "kl": 0.014386177062988281,
+      "learning_rate": 5e-07,
+      "loss": 0.0303,
+      "reward": 0.21015625749714673,
+      "reward_std": 0.4733537929132581,
+      "rewards/end_of_conversation_reward_func": 0.05781250004656613,
+      "rewards/end_rm_reward_func": 0.2265625,
+      "rewards/length_reward_func": -0.07421875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.004998111340682954,
+      "epoch": 0.0144,
+      "grad_norm": 0.5465399440176335,
+      "kl": 0.013627052307128906,
+      "learning_rate": 5e-07,
+      "loss": 0.0301,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2829.671875,
+      "epoch": 0.0152,
+      "grad_norm": 0.5293451315346432,
+      "kl": 0.01097869873046875,
+      "learning_rate": 5e-07,
+      "loss": 0.0218,
+      "reward": 0.28183594974689186,
+      "reward_std": 0.49502080073580146,
+      "rewards/end_of_conversation_reward_func": 0.0523437510128133,
+      "rewards/end_rm_reward_func": 0.2646484375,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.004524174742982723,
+      "epoch": 0.016,
+      "grad_norm": 0.5117856717280709,
+      "kl": 0.010786056518554688,
+      "learning_rate": 5e-07,
+      "loss": 0.0217,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3161.296875,
+      "epoch": 0.0168,
+      "grad_norm": 0.41948668078238804,
+      "kl": 0.008313179016113281,
+      "learning_rate": 5e-07,
+      "loss": 0.0421,
+      "reward": 0.3046874995343387,
+      "reward_std": 0.40682537760585546,
+      "rewards/end_of_conversation_reward_func": 0.04296875046566129,
+      "rewards/end_rm_reward_func": 0.33203125,
+      "rewards/length_reward_func": -0.0703125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.004059915816469584,
+      "epoch": 0.0176,
+      "grad_norm": 0.41427480690422763,
+      "kl": 0.008981704711914062,
+      "learning_rate": 5e-07,
+      "loss": 0.042,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3201.0703125,
+      "epoch": 0.0184,
+      "grad_norm": 0.43906528625565505,
+      "kl": 0.0200042724609375,
+      "learning_rate": 5e-07,
+      "loss": 0.0944,
+      "reward": 0.30175782716833055,
+      "reward_std": 0.40742881037294865,
+      "rewards/end_of_conversation_reward_func": 0.0546875013387762,
+      "rewards/end_rm_reward_func": 0.3291015625,
+      "rewards/length_reward_func": -0.08203125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.004639639038941823,
+      "epoch": 0.0192,
+      "grad_norm": 0.43593248124452694,
+      "kl": 0.022314071655273438,
+      "learning_rate": 5e-07,
+      "loss": 0.0943,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3829.46875,
+      "epoch": 0.02,
+      "grad_norm": 0.38202405603939055,
+      "kl": 0.009199142456054688,
+      "learning_rate": 5e-07,
+      "loss": 0.1122,
+      "reward": 0.16308594099245965,
+      "reward_std": 0.5269097108393908,
+      "rewards/end_of_conversation_reward_func": 0.04296875064028427,
+      "rewards/end_rm_reward_func": 0.2138671875,
+      "rewards/length_reward_func": -0.09375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.003962479371693917,
+      "epoch": 0.0208,
+      "grad_norm": 0.3735492080285575,
+      "kl": 0.010051727294921875,
+      "learning_rate": 5e-07,
+      "loss": 0.1122,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2547.2109375,
+      "epoch": 0.0216,
+      "grad_norm": 0.610378722681955,
+      "kl": 0.0273590087890625,
+      "learning_rate": 5e-07,
+      "loss": 0.0282,
+      "reward": 0.27187501452863216,
+      "reward_std": 0.4403302203863859,
+      "rewards/end_of_conversation_reward_func": 0.05703125102445483,
+      "rewards/end_rm_reward_func": 0.25,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.005169034717255272,
+      "epoch": 0.0224,
+      "grad_norm": 0.6320276760824112,
+      "kl": 0.0298004150390625,
+      "learning_rate": 5e-07,
+      "loss": 0.028,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3147.9140625,
+      "epoch": 0.0232,
+      "grad_norm": 0.48988346522636234,
+      "kl": 0.018934249877929688,
+      "learning_rate": 5e-07,
+      "loss": 0.1053,
+      "reward": 0.14648437302093953,
+      "reward_std": 0.3592515978962183,
+      "rewards/end_of_conversation_reward_func": 0.03906250069849193,
+      "rewards/end_rm_reward_func": 0.166015625,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0043003826576750726,
+      "epoch": 0.024,
+      "grad_norm": 0.4903022425159312,
+      "kl": 0.022472381591796875,
+      "learning_rate": 5e-07,
+      "loss": 0.1051,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3250.6953125,
+      "epoch": 0.0248,
+      "grad_norm": 0.4722499061352693,
+      "kl": 0.0226593017578125,
+      "learning_rate": 5e-07,
+      "loss": 0.09,
+      "reward": 0.27050781436264515,
+      "reward_std": 0.5021275784820318,
+      "rewards/end_of_conversation_reward_func": 0.04687500075669959,
+      "rewards/end_rm_reward_func": 0.2900390625,
+      "rewards/length_reward_func": -0.06640625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.004512525454629213,
+      "epoch": 0.0256,
+      "grad_norm": 0.47562899020814536,
+      "kl": 0.023143768310546875,
+      "learning_rate": 5e-07,
+      "loss": 0.09,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2877.4140625,
+      "epoch": 0.0264,
+      "grad_norm": 0.5889200019558475,
+      "kl": 0.029821395874023438,
+      "learning_rate": 5e-07,
+      "loss": 0.0587,
+      "reward": 0.21738281490979716,
+      "reward_std": 0.43986387038603425,
+      "rewards/end_of_conversation_reward_func": 0.048437500605359674,
+      "rewards/end_rm_reward_func": 0.2275390625,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.004839819855988026,
+      "epoch": 0.0272,
+      "grad_norm": 0.5773456233238853,
+      "kl": 0.04634857177734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0584,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3019.0078125,
+      "epoch": 0.028,
+      "grad_norm": 0.5859980971392886,
+      "kl": 0.05249786376953125,
+      "learning_rate": 5e-07,
+      "loss": 0.0516,
+      "reward": 0.16308594855945557,
+      "reward_std": 0.4561401130631566,
+      "rewards/end_of_conversation_reward_func": 0.046875000989530236,
+      "rewards/end_rm_reward_func": 0.1904296875,
+      "rewards/length_reward_func": -0.07421875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.005565648170886561,
+      "epoch": 0.0288,
+      "grad_norm": 0.5723337880881523,
+      "kl": 0.07667350769042969,
+      "learning_rate": 5e-07,
+      "loss": 0.0514,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3228.2421875,
+      "epoch": 0.0296,
+      "grad_norm": 0.44518950059783957,
+      "kl": 0.0410919189453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0187,
+      "reward": 0.13417969300644472,
+      "reward_std": 0.40079194540157914,
+      "rewards/end_of_conversation_reward_func": 0.04531250096624717,
+      "rewards/end_rm_reward_func": 0.1240234375,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.003970242956711445,
+      "epoch": 0.0304,
+      "grad_norm": 0.4361401996932686,
+      "kl": 0.03826141357421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0186,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3131.0546875,
+      "epoch": 0.0312,
+      "grad_norm": 0.47844256212930125,
+      "kl": 0.03959083557128906,
+      "learning_rate": 5e-07,
+      "loss": 0.0714,
+      "reward": 0.19863281957805157,
+      "reward_std": 0.46341709420084953,
+      "rewards/end_of_conversation_reward_func": 0.04140625090803951,
+      "rewards/end_rm_reward_func": 0.2041015625,
+      "rewards/length_reward_func": -0.046875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.004569632888888009,
+      "epoch": 0.032,
+      "grad_norm": 0.4703050101042975,
+      "kl": 0.033267974853515625,
+      "learning_rate": 5e-07,
+      "loss": 0.0714,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3917.1875,
+      "epoch": 0.0328,
+      "grad_norm": 0.3673788800178079,
+      "kl": 0.046047210693359375,
+      "learning_rate": 5e-07,
+      "loss": 0.0997,
+      "reward": 0.18164063431322575,
+      "reward_std": 0.4014846673235297,
+      "rewards/end_of_conversation_reward_func": 0.042968751047737896,
+      "rewards/end_rm_reward_func": 0.220703125,
+      "rewards/length_reward_func": -0.08203125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 41
+    },
+    {
+      "clip_ratio": 0.0038312822725856677,
+      "epoch": 0.0336,
+      "grad_norm": 0.3586932712636358,
+      "kl": 0.0465850830078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0996,
+      "step": 42
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3266.2734375,
+      "epoch": 0.0344,
+      "grad_norm": 0.5611692724392116,
+      "kl": 0.0754852294921875,
+      "learning_rate": 5e-07,
+      "loss": 0.0169,
+      "reward": 0.026171877863816917,
+      "reward_std": 0.3950889599509537,
+      "rewards/end_of_conversation_reward_func": 0.03593750059371814,
+      "rewards/end_rm_reward_func": 0.064453125,
+      "rewards/length_reward_func": -0.07421875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 43
+    },
+    {
+      "clip_ratio": 0.004459991134353913,
+      "epoch": 0.0352,
+      "grad_norm": 0.650232454614409,
+      "kl": 0.05011749267578125,
+      "learning_rate": 5e-07,
+      "loss": 0.0168,
+      "step": 44
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3211.5859375,
+      "epoch": 0.036,
+      "grad_norm": 0.44021307945681076,
+      "kl": 0.09033966064453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0972,
+      "reward": 0.2980468822643161,
+      "reward_std": 0.4539717771112919,
+      "rewards/end_of_conversation_reward_func": 0.0421875006868504,
+      "rewards/end_rm_reward_func": 0.314453125,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.004655172117054462,
+      "epoch": 0.0368,
+      "grad_norm": 0.432964397523799,
+      "kl": 0.10763931274414062,
+      "learning_rate": 5e-07,
+      "loss": 0.0971,
+      "step": 46
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2954.6171875,
+      "epoch": 0.0376,
+      "grad_norm": 0.506733600693208,
+      "kl": 0.080352783203125,
+      "learning_rate": 5e-07,
+      "loss": 0.1313,
+      "reward": 0.1996093881316483,
+      "reward_std": 0.4217355151195079,
+      "rewards/end_of_conversation_reward_func": 0.04921875084983185,
+      "rewards/end_rm_reward_func": 0.224609375,
+      "rewards/length_reward_func": -0.07421875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 47
+    },
+    {
+      "clip_ratio": 0.00481395295355469,
+      "epoch": 0.0384,
+      "grad_norm": 0.4925165842097727,
+      "kl": 0.09535980224609375,
+      "learning_rate": 5e-07,
+      "loss": 0.1311,
+      "step": 48
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3474.7890625,
+      "epoch": 0.0392,
+      "grad_norm": 0.4471083539693922,
+      "kl": 0.10435867309570312,
+      "learning_rate": 5e-07,
+      "loss": 0.1437,
+      "reward": 0.32910157029982656,
+      "reward_std": 0.508234778419137,
+      "rewards/end_of_conversation_reward_func": 0.046875000873114914,
+      "rewards/end_rm_reward_func": 0.3525390625,
+      "rewards/length_reward_func": -0.0703125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 49
+    },
+    {
+      "clip_ratio": 0.0046363398869289085,
+      "epoch": 0.04,
+      "grad_norm": 0.43209286829846705,
+      "kl": 0.17406082153320312,
+      "learning_rate": 5e-07,
+      "loss": 0.1436,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2888.265625,
+      "epoch": 0.0408,
+      "grad_norm": 0.5175016713586391,
+      "kl": 0.17282867431640625,
+      "learning_rate": 5e-07,
+      "loss": 0.0991,
+      "reward": 0.27207032637670636,
+      "reward_std": 0.4736290629953146,
+      "rewards/end_of_conversation_reward_func": 0.052343750779982656,
+      "rewards/end_rm_reward_func": 0.2705078125,
+      "rewards/length_reward_func": -0.05078125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 51
+    },
+    {
+      "clip_ratio": 0.005186622860492207,
+      "epoch": 0.0416,
+      "grad_norm": 0.5022931530008493,
+      "kl": 0.64031982421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0989,
+      "step": 52
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2426.1796875,
+      "epoch": 0.0424,
+      "grad_norm": 0.6255369968307551,
+      "kl": 0.22528839111328125,
+      "learning_rate": 5e-07,
+      "loss": -0.0125,
+      "reward": 0.3054687652620487,
+      "reward_std": 0.3840066557750106,
+      "rewards/end_of_conversation_reward_func": 0.06328125123400241,
+      "rewards/end_rm_reward_func": 0.2734375,
+      "rewards/length_reward_func": -0.03125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 53
+    },
+    {
+      "clip_ratio": 0.00623530795564875,
+      "epoch": 0.0432,
+      "grad_norm": 0.6007417569260441,
+      "kl": 0.28375244140625,
+      "learning_rate": 5e-07,
+      "loss": -0.0127,
+      "step": 54
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3665.03125,
+      "epoch": 0.044,
+      "grad_norm": 0.44582887064322585,
+      "kl": 0.31996917724609375,
+      "learning_rate": 5e-07,
+      "loss": 0.0533,
+      "reward": 0.15429688058793545,
+      "reward_std": 0.42791955079883337,
+      "rewards/end_of_conversation_reward_func": 0.046875000989530236,
+      "rewards/end_rm_reward_func": 0.189453125,
+      "rewards/length_reward_func": -0.08203125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.004688024055212736,
+      "epoch": 0.0448,
+      "grad_norm": 0.4305811562261461,
+      "kl": 0.25885772705078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0533,
+      "step": 56
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3248.5,
+      "epoch": 0.0456,
+      "grad_norm": 0.4802130548748173,
+      "kl": 1.8993988037109375,
+      "learning_rate": 5e-07,
+      "loss": -0.0111,
+      "reward": 0.23535156849538907,
+      "reward_std": 0.49618958681821823,
+      "rewards/end_of_conversation_reward_func": 0.05078125128056854,
+      "rewards/end_rm_reward_func": 0.2275390625,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 57
+    },
+    {
+      "clip_ratio": 0.005161113862413913,
+      "epoch": 0.0464,
+      "grad_norm": 0.4715970994501386,
+      "kl": 2.4185791015625,
+      "learning_rate": 5e-07,
+      "loss": -0.0113,
+      "step": 58
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3355.9921875,
+      "epoch": 0.0472,
+      "grad_norm": 0.4817763963120568,
+      "kl": 3.2315750122070312,
+      "learning_rate": 5e-07,
+      "loss": 0.1374,
+      "reward": 0.1996093873749487,
+      "reward_std": 0.39307427662424743,
+      "rewards/end_of_conversation_reward_func": 0.04921875096624717,
+      "rewards/end_rm_reward_func": 0.212890625,
+      "rewards/length_reward_func": -0.0625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 59
+    },
+    {
+      "clip_ratio": 0.004419020988279954,
+      "epoch": 0.048,
+      "grad_norm": 0.4663422707726828,
+      "kl": 1.4642868041992188,
+      "learning_rate": 5e-07,
+      "loss": 0.1374,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2897.2890625,
+      "epoch": 0.0488,
+      "grad_norm": 0.588164762943858,
+      "kl": 0.23455047607421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0579,
+      "reward": 0.2761718816473149,
+      "reward_std": 0.4508576055523008,
+      "rewards/end_of_conversation_reward_func": 0.051562500884756446,
+      "rewards/end_rm_reward_func": 0.251953125,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 61
+    },
+    {
+      "clip_ratio": 0.005412581740529276,
+      "epoch": 0.0496,
+      "grad_norm": 0.5649279212366,
+      "kl": 0.44388580322265625,
+      "learning_rate": 5e-07,
+      "loss": 0.0579,
+      "step": 62
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2572.625,
+      "epoch": 0.0504,
+      "grad_norm": 0.7907651458985474,
+      "kl": 38.2191162109375,
+      "learning_rate": 5e-07,
+      "loss": 0.0775,
+      "reward": 0.24921876098960638,
+      "reward_std": 0.4261420601978898,
+      "rewards/end_of_conversation_reward_func": 0.05781250057043508,
+      "rewards/end_rm_reward_func": 0.22265625,
+      "rewards/length_reward_func": -0.03125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 63
+    },
+    {
+      "clip_ratio": 0.005620055002509616,
+      "epoch": 0.0512,
+      "grad_norm": 0.6418001802934817,
+      "kl": 15.695816040039062,
+      "learning_rate": 5e-07,
+      "loss": 0.0772,
+      "step": 64
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2276.734375,
+      "epoch": 0.052,
+      "grad_norm": 0.665222722206486,
+      "kl": 0.13232421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0409,
+      "reward": 0.40312501695007086,
+      "reward_std": 0.4724201774224639,
+      "rewards/end_of_conversation_reward_func": 0.06718750135041773,
+      "rewards/end_rm_reward_func": 0.36328125,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.005610677297227085,
+      "epoch": 0.0528,
+      "grad_norm": 0.5939092022405507,
+      "kl": 0.1356201171875,
+      "learning_rate": 5e-07,
+      "loss": 0.0405,
+      "step": 66
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2571.578125,
+      "epoch": 0.0536,
+      "grad_norm": 0.5313848515306442,
+      "kl": 0.2240753173828125,
+      "learning_rate": 5e-07,
+      "loss": 0.1096,
+      "reward": 0.3613281352445483,
+      "reward_std": 0.5025414768606424,
+      "rewards/end_of_conversation_reward_func": 0.05859375069849193,
+      "rewards/end_rm_reward_func": 0.349609375,
+      "rewards/length_reward_func": -0.046875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 67
+    },
+    {
+      "clip_ratio": 0.005505270150024444,
+      "epoch": 0.0544,
+      "grad_norm": 0.5239589241494494,
+      "kl": 0.351348876953125,
+      "learning_rate": 5e-07,
+      "loss": 0.1093,
+      "step": 68
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2831.0625,
+      "epoch": 0.0552,
+      "grad_norm": 0.5445532025053365,
+      "kl": 0.248504638671875,
+      "learning_rate": 5e-07,
+      "loss": 0.0613,
+      "reward": 0.22050781839061528,
+      "reward_std": 0.4537838753312826,
+      "rewards/end_of_conversation_reward_func": 0.05156250129221007,
+      "rewards/end_rm_reward_func": 0.2275390625,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 69
+    },
+    {
+      "clip_ratio": 0.00578475151269231,
+      "epoch": 0.056,
+      "grad_norm": 0.5324428626427173,
+      "kl": 0.200439453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0611,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2407.078125,
+      "epoch": 0.0568,
+      "grad_norm": 0.7082243961454275,
+      "kl": 0.5781097412109375,
+      "learning_rate": 5e-07,
+      "loss": 0.0656,
+      "reward": 0.44589844811707735,
+      "reward_std": 0.4496405338868499,
+      "rewards/end_of_conversation_reward_func": 0.0640625013038516,
+      "rewards/end_rm_reward_func": 0.4091796875,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 71
+    },
+    {
+      "clip_ratio": 0.006228098354768008,
+      "epoch": 0.0576,
+      "grad_norm": 0.6279502761796933,
+      "kl": 0.60986328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0654,
+      "step": 72
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2754.171875,
+      "epoch": 0.0584,
+      "grad_norm": 0.6511514863553758,
+      "kl": 0.6928863525390625,
+      "learning_rate": 5e-07,
+      "loss": 0.0478,
+      "reward": 0.26621094363508746,
+      "reward_std": 0.3944235248491168,
+      "rewards/end_of_conversation_reward_func": 0.06015625048894435,
+      "rewards/end_rm_reward_func": 0.2451171875,
+      "rewards/length_reward_func": -0.0390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 73
+    },
+    {
+      "clip_ratio": 0.005119593348354101,
+      "epoch": 0.0592,
+      "grad_norm": 0.5405583476661738,
+      "kl": 0.45965576171875,
+      "learning_rate": 5e-07,
+      "loss": 0.0477,
+      "step": 74
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2714.515625,
+      "epoch": 0.06,
+      "grad_norm": 0.5541156231836364,
+      "kl": 1.046234130859375,
+      "learning_rate": 5e-07,
+      "loss": 0.0652,
+      "reward": 0.26230468694120646,
+      "reward_std": 0.4206010536290705,
+      "rewards/end_of_conversation_reward_func": 0.05234375054715201,
+      "rewards/end_rm_reward_func": 0.2373046875,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.005520118284039199,
+      "epoch": 0.0608,
+      "grad_norm": 0.5198654147754546,
+      "kl": 0.9281158447265625,
+      "learning_rate": 5e-07,
+      "loss": 0.0651,
+      "step": 76
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2761.2578125,
+      "epoch": 0.0616,
+      "grad_norm": 0.5969632201148187,
+      "kl": 0.617431640625,
+      "learning_rate": 5e-07,
+      "loss": 0.0339,
+      "reward": 0.30253906978759915,
+      "reward_std": 0.42008747160434723,
+      "rewards/end_of_conversation_reward_func": 0.059375002048909664,
+      "rewards/end_rm_reward_func": 0.2744140625,
+      "rewards/length_reward_func": -0.03125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 77
+    },
+    {
+      "clip_ratio": 0.005989336816128343,
+      "epoch": 0.0624,
+      "grad_norm": 0.5878458096207411,
+      "kl": 0.732513427734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0337,
+      "step": 78
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2543.9453125,
+      "epoch": 0.0632,
+      "grad_norm": 1.0199433093137067,
+      "kl": 1.05322265625,
+      "learning_rate": 5e-07,
+      "loss": 0.0652,
+      "reward": 0.23144532518927008,
+      "reward_std": 0.4124359574634582,
+      "rewards/end_of_conversation_reward_func": 0.06640625139698386,
+      "rewards/end_rm_reward_func": 0.2236328125,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 79
+    },
+    {
+      "clip_ratio": 0.005892957837204449,
+      "epoch": 0.064,
+      "grad_norm": 0.9103349241587038,
+      "kl": 2.14288330078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0649,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3057.0546875,
+      "epoch": 0.0648,
+      "grad_norm": 1.4360222564196798,
+      "kl": 1.4345703125,
+      "learning_rate": 5e-07,
+      "loss": 0.0872,
+      "reward": 0.21894532290752977,
+      "reward_std": 0.44305523252114654,
+      "rewards/end_of_conversation_reward_func": 0.053906250395812094,
+      "rewards/end_rm_reward_func": 0.2197265625,
+      "rewards/length_reward_func": -0.0546875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 81
+    },
+    {
+      "clip_ratio": 0.005477508588228375,
+      "epoch": 0.0656,
+      "grad_norm": 1.0247564904674444,
+      "kl": 1.27581787109375,
+      "learning_rate": 5e-07,
+      "loss": 0.0865,
+      "step": 82
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2772.40625,
+      "epoch": 0.0664,
+      "grad_norm": 0.7761581493328232,
+      "kl": 3.468292236328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0878,
+      "reward": 0.260742200887762,
+      "reward_std": 0.4183371504768729,
+      "rewards/end_of_conversation_reward_func": 0.05468750174622983,
+      "rewards/end_rm_reward_func": 0.2646484375,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 83
+    },
+    {
+      "clip_ratio": 0.006108275701990351,
+      "epoch": 0.0672,
+      "grad_norm": 0.6445774473316636,
+      "kl": 3.2357177734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0874,
+      "step": 84
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2965.75,
+      "epoch": 0.068,
+      "grad_norm": 0.5452316944081127,
+      "kl": 1.18096923828125,
+      "learning_rate": 5e-07,
+      "loss": 0.0644,
+      "reward": 0.19003907265141606,
+      "reward_std": 0.41479692701250315,
+      "rewards/end_of_conversation_reward_func": 0.05625000095460564,
+      "rewards/end_rm_reward_func": 0.1767578125,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio": 0.005549885943764821,
+      "epoch": 0.0688,
+      "grad_norm": 0.5370859324762662,
+      "kl": 1.083465576171875,
+      "learning_rate": 5e-07,
+      "loss": 0.0644,
+      "step": 86
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2448.203125,
+      "epoch": 0.0696,
+      "grad_norm": 0.665995849204049,
+      "kl": 0.88134765625,
+      "learning_rate": 5e-07,
+      "loss": 0.0717,
+      "reward": 0.37382814288139343,
+      "reward_std": 0.43495669635012746,
+      "rewards/end_of_conversation_reward_func": 0.05937500041909516,
+      "rewards/end_rm_reward_func": 0.330078125,
+      "rewards/length_reward_func": -0.015625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 87
+    },
+    {
+      "clip_ratio": 0.006831952749053016,
+      "epoch": 0.0704,
+      "grad_norm": 0.6138460891472821,
+      "kl": 0.7757568359375,
+      "learning_rate": 5e-07,
+      "loss": 0.0715,
+      "step": 88
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2844.96875,
+      "epoch": 0.0712,
+      "grad_norm": 39.91934775938643,
+      "kl": 7.2490234375,
+      "learning_rate": 5e-07,
+      "loss": 0.0724,
+      "reward": 0.2925781449303031,
+      "reward_std": 0.37382530118338764,
+      "rewards/end_of_conversation_reward_func": 0.06015625153668225,
+      "rewards/end_rm_reward_func": 0.279296875,
+      "rewards/length_reward_func": -0.046875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 89
+    },
+    {
+      "clip_ratio": 0.005283550621243194,
+      "epoch": 0.072,
+      "grad_norm": 2.874374713759721,
+      "kl": 2.914276123046875,
+      "learning_rate": 5e-07,
+      "loss": 0.0605,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2769.65625,
+      "epoch": 0.0728,
+      "grad_norm": 0.7216272604731127,
+      "kl": 15.577178955078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0653,
+      "reward": 0.21445313305594027,
+      "reward_std": 0.3568238094449043,
+      "rewards/end_of_conversation_reward_func": 0.056250000779982656,
+      "rewards/end_rm_reward_func": 0.201171875,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 91
+    },
+    {
+      "clip_ratio": 0.006356269208481535,
+      "epoch": 0.0736,
+      "grad_norm": 0.657422156714835,
+      "kl": 3.359100341796875,
+      "learning_rate": 5e-07,
+      "loss": 0.0652,
+      "step": 92
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2521.03125,
+      "epoch": 0.0744,
+      "grad_norm": 0.5916805123057853,
+      "kl": 6.11346435546875,
+      "learning_rate": 5e-07,
+      "loss": 0.0434,
+      "reward": 0.3089843865018338,
+      "reward_std": 0.42485503386706114,
+      "rewards/end_of_conversation_reward_func": 0.05703125149011612,
+      "rewards/end_rm_reward_func": 0.275390625,
+      "rewards/length_reward_func": -0.0234375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 93
+    },
+    {
+      "clip_ratio": 0.00618546042824164,
+      "epoch": 0.0752,
+      "grad_norm": 0.5823172792796925,
+      "kl": 7.6622314453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0433,
+      "step": 94
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2846.6015625,
+      "epoch": 0.076,
+      "grad_norm": 7.8688189093488035,
+      "kl": 11.725372314453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0675,
+      "reward": 0.2693359488621354,
+      "reward_std": 0.41367775388062,
+      "rewards/end_of_conversation_reward_func": 0.05937500059371814,
+      "rewards/end_rm_reward_func": 0.2724609375,
+      "rewards/length_reward_func": -0.0625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 95
+    },
+    {
+      "clip_ratio": 0.005790801937109791,
+      "epoch": 0.0768,
+      "grad_norm": 3.368525315890326,
+      "kl": 13.3575439453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0631,
+      "step": 96
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2476.9765625,
+      "epoch": 0.0776,
+      "grad_norm": 0.7030982161718689,
+      "kl": 1.7344970703125,
+      "learning_rate": 5e-07,
+      "loss": 0.0428,
+      "reward": 0.21621094946749508,
+      "reward_std": 0.35986063024029136,
+      "rewards/end_of_conversation_reward_func": 0.07265625102445483,
+      "rewards/end_rm_reward_func": 0.1708984375,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 97
+    },
+    {
+      "clip_ratio": 0.0070846437884029,
+      "epoch": 0.0784,
+      "grad_norm": 0.7129163912479551,
+      "kl": 1.77899169921875,
+      "learning_rate": 5e-07,
+      "loss": 0.0427,
+      "step": 98
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2593.5234375,
+      "epoch": 0.0792,
+      "grad_norm": 0.7859235708182953,
+      "kl": 2.969696044921875,
+      "learning_rate": 5e-07,
+      "loss": 0.1376,
+      "reward": 0.32734376145526767,
+      "reward_std": 0.288719222182408,
+      "rewards/end_of_conversation_reward_func": 0.06171875155996531,
+      "rewards/end_rm_reward_func": 0.30859375,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 99
+    },
+    {
+      "clip_ratio": 0.0061235044413479045,
+      "epoch": 0.08,
+      "grad_norm": 0.6828444160836236,
+      "kl": 2.0836181640625,
+      "learning_rate": 5e-07,
+      "loss": 0.1373,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2805.28125,
+      "epoch": 0.0808,
+      "grad_norm": 0.5849174504978679,
+      "kl": 1.0841064453125,
+      "learning_rate": 5e-07,
+      "loss": 0.0062,
+      "reward": 0.21914063394069672,
+      "reward_std": 0.43392230197787285,
+      "rewards/end_of_conversation_reward_func": 0.05312500067520887,
+      "rewards/end_rm_reward_func": 0.189453125,
+      "rewards/length_reward_func": -0.0234375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 101
+    },
+    {
+      "clip_ratio": 0.0056501738872611895,
+      "epoch": 0.0816,
+      "grad_norm": 0.5867282574139662,
+      "kl": 0.767822265625,
+      "learning_rate": 5e-07,
+      "loss": 0.006,
+      "step": 102
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2540.4609375,
+      "epoch": 0.0824,
+      "grad_norm": 0.6250029445368647,
+      "kl": 2.111724853515625,
+      "learning_rate": 5e-07,
+      "loss": 0.0241,
+      "reward": 0.29882813175208867,
+      "reward_std": 0.4388907542452216,
+      "rewards/end_of_conversation_reward_func": 0.06250000087311491,
+      "rewards/end_rm_reward_func": 0.271484375,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 103
+    },
+    {
+      "clip_ratio": 0.005285024351906031,
+      "epoch": 0.0832,
+      "grad_norm": 0.6215749933523446,
+      "kl": 2.1219482421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0238,
+      "step": 104
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3044.0,
+      "epoch": 0.084,
+      "grad_norm": 0.6597779710468328,
+      "kl": 6.86090087890625,
+      "learning_rate": 5e-07,
+      "loss": 0.1377,
+      "reward": 0.13828126178123057,
+      "reward_std": 0.43175367498770356,
+      "rewards/end_of_conversation_reward_func": 0.056250001303851604,
+      "rewards/end_rm_reward_func": 0.140625,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio": 0.005206686502788216,
+      "epoch": 0.0848,
+      "grad_norm": 0.5942518563284648,
+      "kl": 2.425811767578125,
+      "learning_rate": 5e-07,
+      "loss": 0.1374,
+      "step": 106
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2281.328125,
+      "epoch": 0.0856,
+      "grad_norm": 0.7014488445783061,
+      "kl": 0.6387939453125,
+      "learning_rate": 5e-07,
+      "loss": -0.0217,
+      "reward": 0.2966797042172402,
+      "reward_std": 0.4203540254384279,
+      "rewards/end_of_conversation_reward_func": 0.059375001466833055,
+      "rewards/end_rm_reward_func": 0.2685546875,
+      "rewards/length_reward_func": -0.03125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 107
+    },
+    {
+      "clip_ratio": 0.005974609957775101,
+      "epoch": 0.0864,
+      "grad_norm": 0.6586072574619627,
+      "kl": 0.62811279296875,
+      "learning_rate": 5e-07,
+      "loss": -0.022,
+      "step": 108
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2565.8515625,
+      "epoch": 0.0872,
+      "grad_norm": 0.644914441904026,
+      "kl": 6.9007568359375,
+      "learning_rate": 5e-07,
+      "loss": 0.0398,
+      "reward": 0.3605468962341547,
+      "reward_std": 0.3907069666311145,
+      "rewards/end_of_conversation_reward_func": 0.0617187509778887,
+      "rewards/end_rm_reward_func": 0.345703125,
+      "rewards/length_reward_func": -0.046875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 109
+    },
+    {
+      "clip_ratio": 0.005732855395763181,
+      "epoch": 0.088,
+      "grad_norm": 0.6042885460634405,
+      "kl": 14.75518798828125,
+      "learning_rate": 5e-07,
+      "loss": 0.0394,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2593.7109375,
+      "epoch": 0.0888,
+      "grad_norm": 0.7580136412646703,
+      "kl": 194.23867797851562,
+      "learning_rate": 5e-07,
+      "loss": 0.0145,
+      "reward": 0.3703125170432031,
+      "reward_std": 0.4818801307119429,
+      "rewards/end_of_conversation_reward_func": 0.06953125121071935,
+      "rewards/end_rm_reward_func": 0.33984375,
+      "rewards/length_reward_func": -0.0390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 111
+    },
+    {
+      "clip_ratio": 0.0058185750094708055,
+      "epoch": 0.0896,
+      "grad_norm": 0.707059333498124,
+      "kl": 93.26089477539062,
+      "learning_rate": 5e-07,
+      "loss": 0.014,
+      "step": 112
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2752.3046875,
+      "epoch": 0.0904,
+      "grad_norm": 1.2282513544713536,
+      "kl": 282.3605651855469,
+      "learning_rate": 5e-07,
+      "loss": -0.0203,
+      "reward": 0.22753907297737896,
+      "reward_std": 0.3849699907004833,
+      "rewards/end_of_conversation_reward_func": 0.06250000139698386,
+      "rewards/end_rm_reward_func": 0.2158203125,
+      "rewards/length_reward_func": -0.05078125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 113
+    },
+    {
+      "clip_ratio": 0.006134674651548266,
+      "epoch": 0.0912,
+      "grad_norm": 0.659663811454641,
+      "kl": 1257.621337890625,
+      "learning_rate": 5e-07,
+      "loss": -0.021,
+      "step": 114
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2639.4375,
+      "epoch": 0.092,
+      "grad_norm": 0.7161070250692486,
+      "kl": 3.4075927734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0562,
+      "reward": 0.279296881868504,
+      "reward_std": 0.36566486582159996,
+      "rewards/end_of_conversation_reward_func": 0.06250000069849193,
+      "rewards/end_rm_reward_func": 0.244140625,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio": 0.005702364520402625,
+      "epoch": 0.0928,
+      "grad_norm": 0.7521060467303439,
+      "kl": 2.76971435546875,
+      "learning_rate": 5e-07,
+      "loss": 0.056,
+      "step": 116
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2755.171875,
+      "epoch": 0.0936,
+      "grad_norm": 0.5773097594300078,
+      "kl": 1.43548583984375,
+      "learning_rate": 5e-07,
+      "loss": 0.0308,
+      "reward": 0.28496095119044185,
+      "reward_std": 0.44529066514223814,
+      "rewards/end_of_conversation_reward_func": 0.07109375135041773,
+      "rewards/end_rm_reward_func": 0.2412109375,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 117
+    },
+    {
+      "clip_ratio": 0.00540813866246026,
+      "epoch": 0.0944,
+      "grad_norm": 0.5453752455228841,
+      "kl": 1.4910888671875,
+      "learning_rate": 5e-07,
+      "loss": 0.0306,
+      "step": 118
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2547.6640625,
+      "epoch": 0.0952,
+      "grad_norm": 0.7741674220919301,
+      "kl": 3.27825927734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0425,
+      "reward": 0.3609375129453838,
+      "reward_std": 0.5046179071068764,
+      "rewards/end_of_conversation_reward_func": 0.05625000031432137,
+      "rewards/end_rm_reward_func": 0.3515625,
+      "rewards/length_reward_func": -0.046875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 119
+    },
+    {
+      "clip_ratio": 0.005344324657926336,
+      "epoch": 0.096,
+      "grad_norm": 0.6695041005132681,
+      "kl": 3.209014892578125,
+      "learning_rate": 5e-07,
+      "loss": 0.0421,
+      "step": 120
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2054.7734375,
+      "epoch": 0.0968,
+      "grad_norm": 0.6599312097182909,
+      "kl": 1.108734130859375,
+      "learning_rate": 5e-07,
+      "loss": 0.0745,
+      "reward": 0.48066408233717084,
+      "reward_std": 0.41660537058487535,
+      "rewards/end_of_conversation_reward_func": 0.06562500132713467,
+      "rewards/end_rm_reward_func": 0.4501953125,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 121
+    },
+    {
+      "clip_ratio": 0.005748817842686549,
+      "epoch": 0.0976,
+      "grad_norm": 0.6350464464579841,
+      "kl": 1.254302978515625,
+      "learning_rate": 5e-07,
+      "loss": 0.0742,
+      "step": 122
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2930.9453125,
+      "epoch": 0.0984,
+      "grad_norm": 0.5357408536545809,
+      "kl": 1.457122802734375,
+      "learning_rate": 5e-07,
+      "loss": 0.0746,
+      "reward": 0.3414062693482265,
+      "reward_std": 0.4845976228825748,
+      "rewards/end_of_conversation_reward_func": 0.056250001420266926,
+      "rewards/end_rm_reward_func": 0.3125,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 123
+    },
+    {
+      "clip_ratio": 0.0055590872943867,
+      "epoch": 0.0992,
+      "grad_norm": 0.48529125845684484,
+      "kl": 3.254119873046875,
+      "learning_rate": 5e-07,
+      "loss": 0.0744,
+      "step": 124
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2267.65625,
+      "epoch": 0.1,
+      "grad_norm": 0.6535834008944279,
+      "kl": 1.0345458984375,
+      "learning_rate": 5e-07,
+      "loss": 0.052,
+      "reward": 0.2982421967899427,
+      "reward_std": 0.3505426752381027,
+      "rewards/end_of_conversation_reward_func": 0.05703125079162419,
+      "rewards/end_rm_reward_func": 0.2607421875,
+      "rewards/length_reward_func": -0.01953125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio": 0.005725323280785233,
+      "epoch": 0.1008,
+      "grad_norm": 0.6302935877001168,
+      "kl": 1.271240234375,
+      "learning_rate": 5e-07,
+      "loss": 0.0516,
+      "step": 126
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2597.3203125,
+      "epoch": 0.1016,
+      "grad_norm": 0.6427620110094884,
+      "kl": 2.03521728515625,
+      "learning_rate": 5e-07,
+      "loss": 0.0256,
+      "reward": 0.3076172007713467,
+      "reward_std": 0.35239528538659215,
+      "rewards/end_of_conversation_reward_func": 0.05859375052386895,
+      "rewards/end_rm_reward_func": 0.2724609375,
+      "rewards/length_reward_func": -0.0234375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 127
+    },
+    {
+      "clip_ratio": 0.006149623615783639,
+      "epoch": 0.1024,
+      "grad_norm": 0.6579464818780976,
+      "kl": 2.0386962890625,
+      "learning_rate": 5e-07,
+      "loss": 0.0253,
+      "step": 128
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2802.3125,
+      "epoch": 0.1032,
+      "grad_norm": 0.8734444908028882,
+      "kl": 17.40386962890625,
+      "learning_rate": 5e-07,
+      "loss": 0.1071,
+      "reward": 0.33613283321028575,
+      "reward_std": 0.38626000890508294,
+      "rewards/end_of_conversation_reward_func": 0.06953125214204192,
+      "rewards/end_rm_reward_func": 0.2978515625,
+      "rewards/length_reward_func": -0.03125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 129
+    },
+    {
+      "clip_ratio": 0.00546567996207159,
+      "epoch": 0.104,
+      "grad_norm": 0.7033969362455426,
+      "kl": 12.68121337890625,
+      "learning_rate": 5e-07,
+      "loss": 0.1066,
+      "step": 130
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3074.7109375,
+      "epoch": 0.1048,
+      "grad_norm": 1.9983054128585318,
+      "kl": 80.3271484375,
+      "learning_rate": 5e-07,
+      "loss": 0.0574,
+      "reward": 0.2843750170432031,
+      "reward_std": 0.5465462752617896,
+      "rewards/end_of_conversation_reward_func": 0.061718751094304025,
+      "rewards/end_rm_reward_func": 0.28125,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 131
+    },
+    {
+      "clip_ratio": 0.005686903212335892,
+      "epoch": 0.1056,
+      "grad_norm": 0.7124750782840086,
+      "kl": 70.491943359375,
+      "learning_rate": 5e-07,
+      "loss": 0.056,
+      "step": 132
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2400.2265625,
+      "epoch": 0.1064,
+      "grad_norm": 0.9314176839191374,
+      "kl": 4.3787841796875,
+      "learning_rate": 5e-07,
+      "loss": -0.0058,
+      "reward": 0.3619140745140612,
+      "reward_std": 0.41163346637040377,
+      "rewards/end_of_conversation_reward_func": 0.06015625118743628,
+      "rewards/end_rm_reward_func": 0.3603515625,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 133
+    },
+    {
+      "clip_ratio": 0.006425623796530999,
+      "epoch": 0.1072,
+      "grad_norm": 0.6428707587124971,
+      "kl": 5.10992431640625,
+      "learning_rate": 5e-07,
+      "loss": -0.0064,
+      "step": 134
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2813.4140625,
+      "epoch": 0.108,
+      "grad_norm": 1.2731691909842648,
+      "kl": 7265.392883300781,
+      "learning_rate": 5e-07,
+      "loss": 0.0596,
+      "reward": 0.2429687607800588,
+      "reward_std": 0.37734482274390757,
+      "rewards/end_of_conversation_reward_func": 0.06328125105937943,
+      "rewards/end_rm_reward_func": 0.22265625,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio": 0.006233511230675504,
+      "epoch": 0.1088,
+      "grad_norm": 0.7280723173732075,
+      "kl": 596.9638061523438,
+      "learning_rate": 5e-07,
+      "loss": 0.0587,
+      "step": 136
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2861.9296875,
+      "epoch": 0.1096,
+      "grad_norm": 0.5765466847825812,
+      "kl": 1.0167236328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0295,
+      "reward": 0.2761718863621354,
+      "reward_std": 0.40949083073064685,
+      "rewards/end_of_conversation_reward_func": 0.05937500135041773,
+      "rewards/end_rm_reward_func": 0.255859375,
+      "rewards/length_reward_func": -0.0390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 137
+    },
+    {
+      "clip_ratio": 0.004913579861749895,
+      "epoch": 0.1104,
+      "grad_norm": 0.561800571593937,
+      "kl": 0.811767578125,
+      "learning_rate": 5e-07,
+      "loss": 0.0293,
+      "step": 138
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2359.171875,
+      "epoch": 0.1112,
+      "grad_norm": 10.321113205088718,
+      "kl": 6.01751708984375,
+      "learning_rate": 5e-07,
+      "loss": 0.0651,
+      "reward": 0.24648438091389835,
+      "reward_std": 0.3026078275870532,
+      "rewards/end_of_conversation_reward_func": 0.06875000149011612,
+      "rewards/end_rm_reward_func": 0.193359375,
+      "rewards/length_reward_func": -0.015625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 139
+    },
+    {
+      "clip_ratio": 0.006259943009354174,
+      "epoch": 0.112,
+      "grad_norm": 1.450404363065613,
+      "kl": 1.487548828125,
+      "learning_rate": 5e-07,
+      "loss": 0.0588,
+      "step": 140
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2657.4375,
+      "epoch": 0.1128,
+      "grad_norm": 1.6913748735699703,
+      "kl": 1.611328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0549,
+      "reward": 0.4406250237952918,
+      "reward_std": 0.38095375150442123,
+      "rewards/end_of_conversation_reward_func": 0.061718751734588295,
+      "rewards/end_rm_reward_func": 0.41796875,
+      "rewards/length_reward_func": -0.0390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 141
+    },
+    {
+      "clip_ratio": 0.005613551795249805,
+      "epoch": 0.1136,
+      "grad_norm": 0.7958482694330619,
+      "kl": 1.34564208984375,
+      "learning_rate": 5e-07,
+      "loss": 0.054,
+      "step": 142
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2331.3984375,
+      "epoch": 0.1144,
+      "grad_norm": 0.6690401528004118,
+      "kl": 0.93682861328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0346,
+      "reward": 0.3912109505617991,
+      "reward_std": 0.4049599929712713,
+      "rewards/end_of_conversation_reward_func": 0.06406250066356733,
+      "rewards/end_rm_reward_func": 0.3466796875,
+      "rewards/length_reward_func": -0.01953125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 143
+    },
+    {
+      "clip_ratio": 0.0052296058856882155,
+      "epoch": 0.1152,
+      "grad_norm": 0.6545569167278118,
+      "kl": 0.91241455078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0342,
+      "step": 144
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2549.3515625,
+      "epoch": 0.116,
+      "grad_norm": 0.5890775780320036,
+      "kl": 26.97711181640625,
+      "learning_rate": 5e-07,
+      "loss": 0.0389,
+      "reward": 0.23417969699949026,
+      "reward_std": 0.3516567766200751,
+      "rewards/end_of_conversation_reward_func": 0.06718750100117177,
+      "rewards/end_rm_reward_func": 0.1748046875,
+      "rewards/length_reward_func": -0.0078125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio": 0.005101009825011715,
+      "epoch": 0.1168,
+      "grad_norm": 0.5467437980921307,
+      "kl": 70.5947265625,
+      "learning_rate": 5e-07,
+      "loss": 0.0386,
+      "step": 146
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2663.859375,
+      "epoch": 0.1176,
+      "grad_norm": 0.6762584056701121,
+      "kl": 47.773193359375,
+      "learning_rate": 5e-07,
+      "loss": 0.0684,
+      "reward": 0.4140625186264515,
+      "reward_std": 0.5097206123173237,
+      "rewards/end_of_conversation_reward_func": 0.06640625069849193,
+      "rewards/end_rm_reward_func": 0.3828125,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 147
+    },
+    {
+      "clip_ratio": 0.005189290648559108,
+      "epoch": 0.1184,
+      "grad_norm": 0.623836517060842,
+      "kl": 270.5855712890625,
+      "learning_rate": 5e-07,
+      "loss": 0.0679,
+      "step": 148
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2959.1171875,
+      "epoch": 0.1192,
+      "grad_norm": 0.6671454736198891,
+      "kl": 0.91912841796875,
+      "learning_rate": 5e-07,
+      "loss": 0.0542,
+      "reward": 0.34667970472946763,
+      "reward_std": 0.3730495397467166,
+      "rewards/end_of_conversation_reward_func": 0.06250000081490725,
+      "rewards/end_rm_reward_func": 0.3193359375,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 149
+    },
+    {
+      "clip_ratio": 0.005951303654001094,
+      "epoch": 0.12,
+      "grad_norm": 0.6116887062182381,
+      "kl": 0.791259765625,
+      "learning_rate": 5e-07,
+      "loss": 0.0538,
+      "step": 150
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3094.140625,
+      "epoch": 0.1208,
+      "grad_norm": 4.667119011332929,
+      "kl": 2.3486328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0428,
+      "reward": 0.27773438883014023,
+      "reward_std": 0.47337998705916107,
+      "rewards/end_of_conversation_reward_func": 0.06093750102445483,
+      "rewards/end_rm_reward_func": 0.240234375,
+      "rewards/length_reward_func": -0.0234375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 151
+    },
+    {
+      "clip_ratio": 0.0058815906959353015,
+      "epoch": 0.1216,
+      "grad_norm": 179.58027001282468,
+      "kl": 15.09307861328125,
+      "learning_rate": 5e-07,
+      "loss": 0.0682,
+      "step": 152
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 3117.2890625,
+      "epoch": 0.1224,
+      "grad_norm": 0.7534678082177136,
+      "kl": 12.952392578125,
+      "learning_rate": 5e-07,
+      "loss": 0.0408,
+      "reward": 0.22148438543081284,
+      "reward_std": 0.42119756643660367,
+      "rewards/end_of_conversation_reward_func": 0.059375000884756446,
+      "rewards/end_rm_reward_func": 0.220703125,
+      "rewards/length_reward_func": -0.05859375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 153
+    },
+    {
+      "clip_ratio": 0.004391293317894451,
+      "epoch": 0.1232,
+      "grad_norm": 0.5828739595215712,
+      "kl": 8.2723388671875,
+      "learning_rate": 5e-07,
+      "loss": 0.0403,
+      "step": 154
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2844.5234375,
+      "epoch": 0.124,
+      "grad_norm": 0.716894901784797,
+      "kl": 7.204345703125,
+      "learning_rate": 5e-07,
+      "loss": 0.0173,
+      "reward": 0.35722657898440957,
+      "reward_std": 0.3928870742674917,
+      "rewards/end_of_conversation_reward_func": 0.07500000135041773,
+      "rewards/end_rm_reward_func": 0.3369140625,
+      "rewards/length_reward_func": -0.0546875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 155
+    },
+    {
+      "clip_ratio": 0.004953728028340265,
+      "epoch": 0.1248,
+      "grad_norm": 0.7207403983692948,
+      "kl": 2.5550537109375,
+      "learning_rate": 5e-07,
+      "loss": 0.0171,
+      "step": 156
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2347.9765625,
+      "epoch": 0.1256,
+      "grad_norm": 0.8185732891233355,
+      "kl": 1.7054443359375,
+      "learning_rate": 5e-07,
+      "loss": 0.0532,
+      "reward": 0.2826172022614628,
+      "reward_std": 0.4683522223494947,
+      "rewards/end_of_conversation_reward_func": 0.06484375114087015,
+      "rewards/end_rm_reward_func": 0.2529296875,
+      "rewards/length_reward_func": -0.03515625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 157
+    },
+    {
+      "clip_ratio": 0.006606276831007563,
+      "epoch": 0.1264,
+      "grad_norm": 0.728399034605529,
+      "kl": 1.5609130859375,
+      "learning_rate": 5e-07,
+      "loss": 0.0526,
+      "step": 158
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2569.265625,
+      "epoch": 0.1272,
+      "grad_norm": 0.7190757659849589,
+      "kl": 0.906005859375,
+      "learning_rate": 5e-07,
+      "loss": -0.0206,
+      "reward": 0.2970703258179128,
+      "reward_std": 0.3366057106759399,
+      "rewards/end_of_conversation_reward_func": 0.06171875074505806,
+      "rewards/end_rm_reward_func": 0.2626953125,
+      "rewards/length_reward_func": -0.02734375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 159
+    },
+    {
+      "clip_ratio": 0.005102125694975257,
+      "epoch": 0.128,
+      "grad_norm": 0.6672444048962334,
+      "kl": 0.8017578125,
+      "learning_rate": 5e-07,
+      "loss": -0.021,
+      "step": 160
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2620.1484375,
+      "epoch": 0.1288,
+      "grad_norm": 0.7595254995251381,
+      "kl": 1.82080078125,
+      "learning_rate": 5e-07,
+      "loss": 0.0537,
+      "reward": 0.3201171928085387,
+      "reward_std": 0.4111205171793699,
+      "rewards/end_of_conversation_reward_func": 0.07109375111758709,
+      "rewards/end_rm_reward_func": 0.2724609375,
+      "rewards/length_reward_func": -0.0234375,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 161
+    },
+    {
+      "clip_ratio": 0.004954093805281445,
+      "epoch": 0.1296,
+      "grad_norm": 0.743108178535059,
+      "kl": 2.1588134765625,
+      "learning_rate": 5e-07,
+      "loss": 0.0532,
+      "step": 162
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2186.5078125,
+      "epoch": 0.1304,
+      "grad_norm": 1.324960021503415,
+      "kl": 3.0037841796875,
+      "learning_rate": 5e-07,
+      "loss": 0.0527,
+      "reward": 0.3619140777736902,
+      "reward_std": 0.38691631401889026,
+      "rewards/end_of_conversation_reward_func": 0.06015625048894435,
+      "rewards/end_rm_reward_func": 0.3056640625,
+      "rewards/length_reward_func": -0.00390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 163
+    },
+    {
+      "clip_ratio": 0.005645596262183972,
+      "epoch": 0.1312,
+      "grad_norm": 1.0819168226765692,
+      "kl": 10.2042236328125,
+      "learning_rate": 5e-07,
+      "loss": 0.052,
+      "step": 164
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2619.4140625,
+      "epoch": 0.132,
+      "grad_norm": 0.7079010578463608,
+      "kl": 1.164794921875,
+      "learning_rate": 5e-07,
+      "loss": 0.0719,
+      "reward": 0.3517578286700882,
+      "reward_std": 0.444250165252015,
+      "rewards/end_of_conversation_reward_func": 0.0695312509778887,
+      "rewards/end_rm_reward_func": 0.3251953125,
+      "rewards/length_reward_func": -0.04296875,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 165
+    },
+    {
+      "clip_ratio": 0.004916784484521486,
+      "epoch": 0.1328,
+      "grad_norm": 0.667503324712686,
+      "kl": 1.4266357421875,
+      "learning_rate": 5e-07,
+      "loss": 0.0714,
+      "step": 166
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2411.8671875,
+      "epoch": 0.1336,
+      "grad_norm": 2.7317288434410036,
+      "kl": 2.0714111328125,
+      "learning_rate": 5e-07,
+      "loss": 0.1114,
+      "reward": 0.21445313666481525,
+      "reward_std": 0.3326614680700004,
+      "rewards/end_of_conversation_reward_func": 0.06796875107102096,
+      "rewards/end_rm_reward_func": 0.166015625,
+      "rewards/length_reward_func": -0.01953125,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 167
+    },
+    {
+      "clip_ratio": 0.0053935582836857066,
+      "epoch": 0.1344,
+      "grad_norm": 1.3387444314477779,
+      "kl": 1.496337890625,
+      "learning_rate": 5e-07,
+      "loss": 0.1094,
+      "step": 168
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 2000.3359375,
+      "epoch": 0.1352,
+      "grad_norm": 159.24137003595405,
+      "kl": 56.654296875,
+      "learning_rate": 5e-07,
+      "loss": 0.1291,
+      "reward": 0.42187501955777407,
+      "reward_std": 0.47698789834976196,
+      "rewards/end_of_conversation_reward_func": 0.0664062510477379,
+      "rewards/end_rm_reward_func": 0.359375,
+      "rewards/length_reward_func": -0.00390625,
+      "rewards/thinking_reward_func": 0.0,
+      "step": 169
+    },
+    {
+      "clip_ratio": 0.006557086948305368,
+      "epoch": 0.136,
+      "grad_norm": 6.8095683630193635,
+      "kl": 18.90185546875,
+      "learning_rate": 5e-07,
+      "loss": 0.0603,
+      "step": 170
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3503309e215459351eb16b54b9cbb4e8e33052d09e649b025b01092f76aea42
+size 7800