Update scenario_cot_ratio_3B

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 scenario_cot_ratio_1.5B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+scenario_cot_ratio_3B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

scenario_cot_ratio_3B/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
+}

scenario_cot_ratio_3B/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9986708925467744,
+    "eval_loss": 0.7144020795822144,
+    "eval_runtime": 8.853,
+    "eval_samples_per_second": 8.924,
+    "eval_steps_per_second": 4.518,
+    "total_flos": 531028544847872.0,
+    "train_loss": 0.7064719163714637,
+    "train_runtime": 53129.6318,
+    "train_samples_per_second": 2.209,
+    "train_steps_per_second": 0.035
+}

scenario_cot_ratio_3B/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/users/u2023000898/model/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

scenario_cot_ratio_3B/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9986708925467744,
+    "eval_loss": 0.7144020795822144,
+    "eval_runtime": 8.853,
+    "eval_samples_per_second": 8.924,
+    "eval_steps_per_second": 4.518
+}

scenario_cot_ratio_3B/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": "4.46.1"
+}

scenario_cot_ratio_3B/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62102813362c9a3355400dcd1ebb125d3239166021cacb002fee26d088c8e441
+size 4957560304

scenario_cot_ratio_3B/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15c0a5f414a315be27482e86dd327c23ed3831e374aad69dfbec8e582fbe98e
+size 1214366696

scenario_cot_ratio_3B/model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

scenario_cot_ratio_3B/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
+  }
+}

scenario_cot_ratio_3B/tokenizer.json

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

scenario_cot_ratio_3B/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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

scenario_cot_ratio_3B/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9986708925467744,
+    "total_flos": 531028544847872.0,
+    "train_loss": 0.7064719163714637,
+    "train_runtime": 53129.6318,
+    "train_samples_per_second": 2.209,
+    "train_steps_per_second": 0.035
+}

scenario_cot_ratio_3B/trainer_state.json

@@ -0,0 +1,2051 @@
+{
+  "best_metric": 0.7144020795822144,
+  "best_model_checkpoint": "/users/u2023000898/model/atrain_qc/scenario_train_40K_cot_ratio_3/checkpoint-1220",
+  "epoch": 2.9986708925467744,
+  "eval_steps": 20,
+  "global_step": 1833,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01635824557816174,
+      "grad_norm": 5.295344734073509,
+      "learning_rate": 5.434782608695653e-07,
+      "loss": 1.4359,
+      "step": 10
+    },
+    {
+      "epoch": 0.03271649115632348,
+      "grad_norm": 3.422164657559387,
+      "learning_rate": 1.0869565217391306e-06,
+      "loss": 1.4181,
+      "step": 20
+    },
+    {
+      "epoch": 0.03271649115632348,
+      "eval_loss": 1.3935878276824951,
+      "eval_runtime": 8.9905,
+      "eval_samples_per_second": 8.787,
+      "eval_steps_per_second": 4.449,
+      "step": 20
+    },
+    {
+      "epoch": 0.04907473673448522,
+      "grad_norm": 1.986613395208058,
+      "learning_rate": 1.6304347826086957e-06,
+      "loss": 1.303,
+      "step": 30
+    },
+    {
+      "epoch": 0.06543298231264696,
+      "grad_norm": 1.4523886723377106,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 1.1795,
+      "step": 40
+    },
+    {
+      "epoch": 0.06543298231264696,
+      "eval_loss": 1.1402088403701782,
+      "eval_runtime": 8.8832,
+      "eval_samples_per_second": 8.893,
+      "eval_steps_per_second": 4.503,
+      "step": 40
+    },
+    {
+      "epoch": 0.08179122789080871,
+      "grad_norm": 1.1700390466976565,
+      "learning_rate": 2.7173913043478263e-06,
+      "loss": 1.0727,
+      "step": 50
+    },
+    {
+      "epoch": 0.09814947346897045,
+      "grad_norm": 0.8879790034956169,
+      "learning_rate": 3.2608695652173914e-06,
+      "loss": 0.9978,
+      "step": 60
+    },
+    {
+      "epoch": 0.09814947346897045,
+      "eval_loss": 0.9959300756454468,
+      "eval_runtime": 8.9186,
+      "eval_samples_per_second": 8.858,
+      "eval_steps_per_second": 4.485,
+      "step": 60
+    },
+    {
+      "epoch": 0.1145077190471322,
+      "grad_norm": 0.8251876813224245,
+      "learning_rate": 3.804347826086957e-06,
+      "loss": 0.962,
+      "step": 70
+    },
+    {
+      "epoch": 0.13086596462529393,
+      "grad_norm": 0.7597303029800314,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.9344,
+      "step": 80
+    },
+    {
+      "epoch": 0.13086596462529393,
+      "eval_loss": 0.9332086443901062,
+      "eval_runtime": 9.1918,
+      "eval_samples_per_second": 8.595,
+      "eval_steps_per_second": 4.352,
+      "step": 80
+    },
+    {
+      "epoch": 0.1472242102034557,
+      "grad_norm": 0.7643744159525921,
+      "learning_rate": 4.891304347826087e-06,
+      "loss": 0.9113,
+      "step": 90
+    },
+    {
+      "epoch": 0.16358245578161743,
+      "grad_norm": 0.7298856847403965,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.8836,
+      "step": 100
+    },
+    {
+      "epoch": 0.16358245578161743,
+      "eval_loss": 0.8985484838485718,
+      "eval_runtime": 9.0729,
+      "eval_samples_per_second": 8.707,
+      "eval_steps_per_second": 4.409,
+      "step": 100
+    },
+    {
+      "epoch": 0.17994070135977916,
+      "grad_norm": 0.7853004926976781,
+      "learning_rate": 5.978260869565218e-06,
+      "loss": 0.873,
+      "step": 110
+    },
+    {
+      "epoch": 0.1962989469379409,
+      "grad_norm": 0.8086725449370039,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.8649,
+      "step": 120
+    },
+    {
+      "epoch": 0.1962989469379409,
+      "eval_loss": 0.8743940591812134,
+      "eval_runtime": 8.8733,
+      "eval_samples_per_second": 8.903,
+      "eval_steps_per_second": 4.508,
+      "step": 120
+    },
+    {
+      "epoch": 0.21265719251610266,
+      "grad_norm": 0.78611945621464,
+      "learning_rate": 7.065217391304349e-06,
+      "loss": 0.8502,
+      "step": 130
+    },
+    {
+      "epoch": 0.2290154380942644,
+      "grad_norm": 0.8139497555344073,
+      "learning_rate": 7.608695652173914e-06,
+      "loss": 0.8424,
+      "step": 140
+    },
+    {
+      "epoch": 0.2290154380942644,
+      "eval_loss": 0.8560407757759094,
+      "eval_runtime": 12.0219,
+      "eval_samples_per_second": 6.571,
+      "eval_steps_per_second": 3.327,
+      "step": 140
+    },
+    {
+      "epoch": 0.24537368367242612,
+      "grad_norm": 0.8656686458129763,
+      "learning_rate": 8.15217391304348e-06,
+      "loss": 0.8449,
+      "step": 150
+    },
+    {
+      "epoch": 0.26173192925058786,
+      "grad_norm": 0.9283042437403443,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.8265,
+      "step": 160
+    },
+    {
+      "epoch": 0.26173192925058786,
+      "eval_loss": 0.8416913747787476,
+      "eval_runtime": 9.036,
+      "eval_samples_per_second": 8.743,
+      "eval_steps_per_second": 4.427,
+      "step": 160
+    },
+    {
+      "epoch": 0.2780901748287496,
+      "grad_norm": 0.810298408576699,
+      "learning_rate": 9.23913043478261e-06,
+      "loss": 0.8293,
+      "step": 170
+    },
+    {
+      "epoch": 0.2944484204069114,
+      "grad_norm": 0.8313112566441393,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 0.8159,
+      "step": 180
+    },
+    {
+      "epoch": 0.2944484204069114,
+      "eval_loss": 0.8295494318008423,
+      "eval_runtime": 8.8777,
+      "eval_samples_per_second": 8.899,
+      "eval_steps_per_second": 4.506,
+      "step": 180
+    },
+    {
+      "epoch": 0.3108066659850731,
+      "grad_norm": 0.8697727174133723,
+      "learning_rate": 9.999673339806799e-06,
+      "loss": 0.8191,
+      "step": 190
+    },
+    {
+      "epoch": 0.32716491156323485,
+      "grad_norm": 0.900525558157214,
+      "learning_rate": 9.997677237639758e-06,
+      "loss": 0.8024,
+      "step": 200
+    },
+    {
+      "epoch": 0.32716491156323485,
+      "eval_loss": 0.822140097618103,
+      "eval_runtime": 8.8793,
+      "eval_samples_per_second": 8.897,
+      "eval_steps_per_second": 4.505,
+      "step": 200
+    },
+    {
+      "epoch": 0.3435231571413966,
+      "grad_norm": 0.8222174164436653,
+      "learning_rate": 9.993867234795303e-06,
+      "loss": 0.7988,
+      "step": 210
+    },
+    {
+      "epoch": 0.3598814027195583,
+      "grad_norm": 0.8209330165865478,
+      "learning_rate": 9.98824471410918e-06,
+      "loss": 0.7934,
+      "step": 220
+    },
+    {
+      "epoch": 0.3598814027195583,
+      "eval_loss": 0.8108458518981934,
+      "eval_runtime": 8.8086,
+      "eval_samples_per_second": 8.969,
+      "eval_steps_per_second": 4.541,
+      "step": 220
+    },
+    {
+      "epoch": 0.37623964829772005,
+      "grad_norm": 0.7678941313429579,
+      "learning_rate": 9.980811716268215e-06,
+      "loss": 0.7959,
+      "step": 230
+    },
+    {
+      "epoch": 0.3925978938758818,
+      "grad_norm": 0.82512300528877,
+      "learning_rate": 9.971570939069637e-06,
+      "loss": 0.7903,
+      "step": 240
+    },
+    {
+      "epoch": 0.3925978938758818,
+      "eval_loss": 0.8030208349227905,
+      "eval_runtime": 8.8553,
+      "eval_samples_per_second": 8.921,
+      "eval_steps_per_second": 4.517,
+      "step": 240
+    },
+    {
+      "epoch": 0.4089561394540436,
+      "grad_norm": 0.7846619918234344,
+      "learning_rate": 9.96052573644193e-06,
+      "loss": 0.7893,
+      "step": 250
+    },
+    {
+      "epoch": 0.4253143850322053,
+      "grad_norm": 0.7731531067943592,
+      "learning_rate": 9.947680117227512e-06,
+      "loss": 0.7858,
+      "step": 260
+    },
+    {
+      "epoch": 0.4253143850322053,
+      "eval_loss": 0.7969117164611816,
+      "eval_runtime": 8.8378,
+      "eval_samples_per_second": 8.939,
+      "eval_steps_per_second": 4.526,
+      "step": 260
+    },
+    {
+      "epoch": 0.44167263061036705,
+      "grad_norm": 0.8323139648125473,
+      "learning_rate": 9.933038743727749e-06,
+      "loss": 0.7882,
+      "step": 270
+    },
+    {
+      "epoch": 0.4580308761885288,
+      "grad_norm": 0.8203697180665835,
+      "learning_rate": 9.916606930010765e-06,
+      "loss": 0.7794,
+      "step": 280
+    },
+    {
+      "epoch": 0.4580308761885288,
+      "eval_loss": 0.7901803255081177,
+      "eval_runtime": 8.873,
+      "eval_samples_per_second": 8.903,
+      "eval_steps_per_second": 4.508,
+      "step": 280
+    },
+    {
+      "epoch": 0.4743891217666905,
+      "grad_norm": 0.7847835132710914,
+      "learning_rate": 9.898390639982715e-06,
+      "loss": 0.7771,
+      "step": 290
+    },
+    {
+      "epoch": 0.49074736734485225,
+      "grad_norm": 0.899857567905345,
+      "learning_rate": 9.878396485223187e-06,
+      "loss": 0.7759,
+      "step": 300
+    },
+    {
+      "epoch": 0.49074736734485225,
+      "eval_loss": 0.7846674919128418,
+      "eval_runtime": 8.9104,
+      "eval_samples_per_second": 8.866,
+      "eval_steps_per_second": 4.489,
+      "step": 300
+    },
+    {
+      "epoch": 0.507105612923014,
+      "grad_norm": 0.8725377228611381,
+      "learning_rate": 9.856631722585545e-06,
+      "loss": 0.7694,
+      "step": 310
+    },
+    {
+      "epoch": 0.5234638585011757,
+      "grad_norm": 0.8975303080276704,
+      "learning_rate": 9.833104251563058e-06,
+      "loss": 0.7702,
+      "step": 320
+    },
+    {
+      "epoch": 0.5234638585011757,
+      "eval_loss": 0.7819108366966248,
+      "eval_runtime": 9.1634,
+      "eval_samples_per_second": 8.621,
+      "eval_steps_per_second": 4.365,
+      "step": 320
+    },
+    {
+      "epoch": 0.5398221040793375,
+      "grad_norm": 0.8040447653131452,
+      "learning_rate": 9.807822611421783e-06,
+      "loss": 0.7737,
+      "step": 330
+    },
+    {
+      "epoch": 0.5561803496574992,
+      "grad_norm": 0.7791606284623682,
+      "learning_rate": 9.780795978101265e-06,
+      "loss": 0.7687,
+      "step": 340
+    },
+    {
+      "epoch": 0.5561803496574992,
+      "eval_loss": 0.7773299217224121,
+      "eval_runtime": 8.8107,
+      "eval_samples_per_second": 8.966,
+      "eval_steps_per_second": 4.54,
+      "step": 340
+    },
+    {
+      "epoch": 0.572538595235661,
+      "grad_norm": 0.7841990500752456,
+      "learning_rate": 9.752034160884126e-06,
+      "loss": 0.7685,
+      "step": 350
+    },
+    {
+      "epoch": 0.5888968408138228,
+      "grad_norm": 0.8046795669671181,
+      "learning_rate": 9.721547598835807e-06,
+      "loss": 0.7481,
+      "step": 360
+    },
+    {
+      "epoch": 0.5888968408138228,
+      "eval_loss": 0.774566113948822,
+      "eval_runtime": 9.0394,
+      "eval_samples_per_second": 8.739,
+      "eval_steps_per_second": 4.425,
+      "step": 360
+    },
+    {
+      "epoch": 0.6052550863919844,
+      "grad_norm": 1.183625080940533,
+      "learning_rate": 9.689347357015721e-06,
+      "loss": 0.748,
+      "step": 370
+    },
+    {
+      "epoch": 0.6216133319701462,
+      "grad_norm": 0.8040310134429428,
+      "learning_rate": 9.6554451224612e-06,
+      "loss": 0.7548,
+      "step": 380
+    },
+    {
+      "epoch": 0.6216133319701462,
+      "eval_loss": 0.7700055241584778,
+      "eval_runtime": 8.8572,
+      "eval_samples_per_second": 8.919,
+      "eval_steps_per_second": 4.516,
+      "step": 380
+    },
+    {
+      "epoch": 0.6379715775483079,
+      "grad_norm": 0.9470332937426067,
+      "learning_rate": 9.619853199945699e-06,
+      "loss": 0.7517,
+      "step": 390
+    },
+    {
+      "epoch": 0.6543298231264697,
+      "grad_norm": 0.8950375364388944,
+      "learning_rate": 9.5825845075128e-06,
+      "loss": 0.7502,
+      "step": 400
+    },
+    {
+      "epoch": 0.6543298231264697,
+      "eval_loss": 0.7674439549446106,
+      "eval_runtime": 8.9218,
+      "eval_samples_per_second": 8.855,
+      "eval_steps_per_second": 4.483,
+      "step": 400
+    },
+    {
+      "epoch": 0.6706880687046314,
+      "grad_norm": 0.9169203286801689,
+      "learning_rate": 9.543652571787623e-06,
+      "loss": 0.7496,
+      "step": 410
+    },
+    {
+      "epoch": 0.6870463142827932,
+      "grad_norm": 0.8093191265332849,
+      "learning_rate": 9.503071523067346e-06,
+      "loss": 0.7544,
+      "step": 420
+    },
+    {
+      "epoch": 0.6870463142827932,
+      "eval_loss": 0.7653623223304749,
+      "eval_runtime": 8.8891,
+      "eval_samples_per_second": 8.887,
+      "eval_steps_per_second": 4.5,
+      "step": 420
+    },
+    {
+      "epoch": 0.703404559860955,
+      "grad_norm": 0.8858043762442335,
+      "learning_rate": 9.460856090192643e-06,
+      "loss": 0.7455,
+      "step": 430
+    },
+    {
+      "epoch": 0.7197628054391166,
+      "grad_norm": 0.7155973463395218,
+      "learning_rate": 9.417021595201864e-06,
+      "loss": 0.7527,
+      "step": 440
+    },
+    {
+      "epoch": 0.7197628054391166,
+      "eval_loss": 0.7620683908462524,
+      "eval_runtime": 8.8784,
+      "eval_samples_per_second": 8.898,
+      "eval_steps_per_second": 4.505,
+      "step": 440
+    },
+    {
+      "epoch": 0.7361210510172784,
+      "grad_norm": 0.737512769355951,
+      "learning_rate": 9.371583947769914e-06,
+      "loss": 0.7457,
+      "step": 450
+    },
+    {
+      "epoch": 0.7524792965954401,
+      "grad_norm": 0.8059791945207864,
+      "learning_rate": 9.324559639433874e-06,
+      "loss": 0.7498,
+      "step": 460
+    },
+    {
+      "epoch": 0.7524792965954401,
+      "eval_loss": 0.7595985531806946,
+      "eval_runtime": 8.8587,
+      "eval_samples_per_second": 8.918,
+      "eval_steps_per_second": 4.515,
+      "step": 460
+    },
+    {
+      "epoch": 0.7688375421736019,
+      "grad_norm": 0.8453208453911044,
+      "learning_rate": 9.2759657376074e-06,
+      "loss": 0.7399,
+      "step": 470
+    },
+    {
+      "epoch": 0.7851957877517636,
+      "grad_norm": 0.7794080969117457,
+      "learning_rate": 9.225819879386137e-06,
+      "loss": 0.7422,
+      "step": 480
+    },
+    {
+      "epoch": 0.7851957877517636,
+      "eval_loss": 0.757483959197998,
+      "eval_runtime": 8.8082,
+      "eval_samples_per_second": 8.969,
+      "eval_steps_per_second": 4.541,
+      "step": 480
+    },
+    {
+      "epoch": 0.8015540333299254,
+      "grad_norm": 0.7170361500782209,
+      "learning_rate": 9.174140265146356e-06,
+      "loss": 0.7366,
+      "step": 490
+    },
+    {
+      "epoch": 0.8179122789080872,
+      "grad_norm": 0.886247962125953,
+      "learning_rate": 9.120945651939146e-06,
+      "loss": 0.7385,
+      "step": 500
+    },
+    {
+      "epoch": 0.8179122789080872,
+      "eval_loss": 0.7534403800964355,
+      "eval_runtime": 8.8411,
+      "eval_samples_per_second": 8.936,
+      "eval_steps_per_second": 4.524,
+      "step": 500
+    },
+    {
+      "epoch": 0.8342705244862488,
+      "grad_norm": 0.7303115546636174,
+      "learning_rate": 9.066255346682567e-06,
+      "loss": 0.7426,
+      "step": 510
+    },
+    {
+      "epoch": 0.8506287700644106,
+      "grad_norm": 0.720904332688552,
+      "learning_rate": 9.010089199154238e-06,
+      "loss": 0.7396,
+      "step": 520
+    },
+    {
+      "epoch": 0.8506287700644106,
+      "eval_loss": 0.7510408163070679,
+      "eval_runtime": 8.8187,
+      "eval_samples_per_second": 8.958,
+      "eval_steps_per_second": 4.536,
+      "step": 520
+    },
+    {
+      "epoch": 0.8669870156425723,
+      "grad_norm": 0.7269189612270449,
+      "learning_rate": 8.952467594786867e-06,
+      "loss": 0.7372,
+      "step": 530
+    },
+    {
+      "epoch": 0.8833452612207341,
+      "grad_norm": 0.7411165689482159,
+      "learning_rate": 8.8934114472694e-06,
+      "loss": 0.7455,
+      "step": 540
+    },
+    {
+      "epoch": 0.8833452612207341,
+      "eval_loss": 0.7494012117385864,
+      "eval_runtime": 8.8703,
+      "eval_samples_per_second": 8.906,
+      "eval_steps_per_second": 4.509,
+      "step": 540
+    },
+    {
+      "epoch": 0.8997035067988958,
+      "grad_norm": 0.7222933451317762,
+      "learning_rate": 8.83294219095642e-06,
+      "loss": 0.7396,
+      "step": 550
+    },
+    {
+      "epoch": 0.9160617523770576,
+      "grad_norm": 0.7405492243894416,
+      "learning_rate": 8.771081773088568e-06,
+      "loss": 0.7275,
+      "step": 560
+    },
+    {
+      "epoch": 0.9160617523770576,
+      "eval_loss": 0.747172474861145,
+      "eval_runtime": 8.8684,
+      "eval_samples_per_second": 8.908,
+      "eval_steps_per_second": 4.51,
+      "step": 560
+    },
+    {
+      "epoch": 0.9324199979552193,
+      "grad_norm": 0.7343527467764037,
+      "learning_rate": 8.707852645826824e-06,
+      "loss": 0.7227,
+      "step": 570
+    },
+    {
+      "epoch": 0.948778243533381,
+      "grad_norm": 0.8149960345815405,
+      "learning_rate": 8.643277758103527e-06,
+      "loss": 0.74,
+      "step": 580
+    },
+    {
+      "epoch": 0.948778243533381,
+      "eval_loss": 0.745248019695282,
+      "eval_runtime": 8.8473,
+      "eval_samples_per_second": 8.929,
+      "eval_steps_per_second": 4.521,
+      "step": 580
+    },
+    {
+      "epoch": 0.9651364891115428,
+      "grad_norm": 0.7210978276382376,
+      "learning_rate": 8.577380547293089e-06,
+      "loss": 0.7387,
+      "step": 590
+    },
+    {
+      "epoch": 0.9814947346897045,
+      "grad_norm": 0.7095208468673599,
+      "learning_rate": 8.510184930705413e-06,
+      "loss": 0.7339,
+      "step": 600
+    },
+    {
+      "epoch": 0.9814947346897045,
+      "eval_loss": 0.7437242269515991,
+      "eval_runtime": 8.82,
+      "eval_samples_per_second": 8.957,
+      "eval_steps_per_second": 4.535,
+      "step": 600
+    },
+    {
+      "epoch": 0.9978529802678663,
+      "grad_norm": 0.7505905361093098,
+      "learning_rate": 8.44171529690516e-06,
+      "loss": 0.7248,
+      "step": 610
+    },
+    {
+      "epoch": 1.0143134648808916,
+      "grad_norm": 0.6979646401902959,
+      "learning_rate": 8.371996496859938e-06,
+      "loss": 0.7404,
+      "step": 620
+    },
+    {
+      "epoch": 1.0143134648808916,
+      "eval_loss": 0.7440437078475952,
+      "eval_runtime": 8.7724,
+      "eval_samples_per_second": 9.005,
+      "eval_steps_per_second": 4.56,
+      "step": 620
+    },
+    {
+      "epoch": 1.0306717104590533,
+      "grad_norm": 0.7236767629054202,
+      "learning_rate": 8.30105383492067e-06,
+      "loss": 0.6848,
+      "step": 630
+    },
+    {
+      "epoch": 1.047029956037215,
+      "grad_norm": 0.6872848093215694,
+      "learning_rate": 8.228913059637414e-06,
+      "loss": 0.6877,
+      "step": 640
+    },
+    {
+      "epoch": 1.047029956037215,
+      "eval_loss": 0.7421544790267944,
+      "eval_runtime": 8.8557,
+      "eval_samples_per_second": 8.921,
+      "eval_steps_per_second": 4.517,
+      "step": 640
+    },
+    {
+      "epoch": 1.0633882016153768,
+      "grad_norm": 0.7171174222919368,
+      "learning_rate": 8.155600354413971e-06,
+      "loss": 0.6752,
+      "step": 650
+    },
+    {
+      "epoch": 1.0797464471935385,
+      "grad_norm": 0.6937193535340093,
+      "learning_rate": 8.081142328004638e-06,
+      "loss": 0.6785,
+      "step": 660
+    },
+    {
+      "epoch": 1.0797464471935385,
+      "eval_loss": 0.7413665056228638,
+      "eval_runtime": 8.7177,
+      "eval_samples_per_second": 9.062,
+      "eval_steps_per_second": 4.588,
+      "step": 660
+    },
+    {
+      "epoch": 1.0961046927717002,
+      "grad_norm": 0.7347355982975387,
+      "learning_rate": 8.005566004856593e-06,
+      "loss": 0.6746,
+      "step": 670
+    },
+    {
+      "epoch": 1.1124629383498619,
+      "grad_norm": 0.8465986634067116,
+      "learning_rate": 7.928898815301418e-06,
+      "loss": 0.6723,
+      "step": 680
+    },
+    {
+      "epoch": 1.1124629383498619,
+      "eval_loss": 0.7399634122848511,
+      "eval_runtime": 8.9138,
+      "eval_samples_per_second": 8.863,
+      "eval_steps_per_second": 4.487,
+      "step": 680
+    },
+    {
+      "epoch": 1.1288211839280238,
+      "grad_norm": 0.7674101027640446,
+      "learning_rate": 7.851168585599285e-06,
+      "loss": 0.6756,
+      "step": 690
+    },
+    {
+      "epoch": 1.1451794295061855,
+      "grad_norm": 0.7525909134460642,
+      "learning_rate": 7.77240352783945e-06,
+      "loss": 0.6807,
+      "step": 700
+    },
+    {
+      "epoch": 1.1451794295061855,
+      "eval_loss": 0.7387439608573914,
+      "eval_runtime": 8.8038,
+      "eval_samples_per_second": 8.973,
+      "eval_steps_per_second": 4.544,
+      "step": 700
+    },
+    {
+      "epoch": 1.1615376750843471,
+      "grad_norm": 0.7798312578850733,
+      "learning_rate": 7.692632229700718e-06,
+      "loss": 0.6779,
+      "step": 710
+    },
+    {
+      "epoch": 1.177895920662509,
+      "grad_norm": 0.7474295968254813,
+      "learning_rate": 7.611883644075573e-06,
+      "loss": 0.6823,
+      "step": 720
+    },
+    {
+      "epoch": 1.177895920662509,
+      "eval_loss": 0.7377986907958984,
+      "eval_runtime": 8.8162,
+      "eval_samples_per_second": 8.961,
+      "eval_steps_per_second": 4.537,
+      "step": 720
+    },
+    {
+      "epoch": 1.1942541662406707,
+      "grad_norm": 0.7587723123453163,
+      "learning_rate": 7.5301870785617635e-06,
+      "loss": 0.675,
+      "step": 730
+    },
+    {
+      "epoch": 1.2106124118188324,
+      "grad_norm": 0.7440613541332155,
+      "learning_rate": 7.447572184825149e-06,
+      "loss": 0.6792,
+      "step": 740
+    },
+    {
+      "epoch": 1.2106124118188324,
+      "eval_loss": 0.7359431982040405,
+      "eval_runtime": 8.8106,
+      "eval_samples_per_second": 8.966,
+      "eval_steps_per_second": 4.54,
+      "step": 740
+    },
+    {
+      "epoch": 1.2269706573969943,
+      "grad_norm": 0.7463811292658835,
+      "learning_rate": 7.3640689478376695e-06,
+      "loss": 0.682,
+      "step": 750
+    },
+    {
+      "epoch": 1.243328902975156,
+      "grad_norm": 0.7709021578765768,
+      "learning_rate": 7.2797076749943214e-06,
+      "loss": 0.6799,
+      "step": 760
+    },
+    {
+      "epoch": 1.243328902975156,
+      "eval_loss": 0.7348581552505493,
+      "eval_runtime": 8.8852,
+      "eval_samples_per_second": 8.891,
+      "eval_steps_per_second": 4.502,
+      "step": 760
+    },
+    {
+      "epoch": 1.2596871485533176,
+      "grad_norm": 0.7343520193643218,
+      "learning_rate": 7.194518985113149e-06,
+      "loss": 0.6765,
+      "step": 770
+    },
+    {
+      "epoch": 1.2760453941314793,
+      "grad_norm": 0.7190112773845664,
+      "learning_rate": 7.108533797322166e-06,
+      "loss": 0.6804,
+      "step": 780
+    },
+    {
+      "epoch": 1.2760453941314793,
+      "eval_loss": 0.7342889904975891,
+      "eval_runtime": 8.8721,
+      "eval_samples_per_second": 8.904,
+      "eval_steps_per_second": 4.508,
+      "step": 780
+    },
+    {
+      "epoch": 1.292403639709641,
+      "grad_norm": 0.7133811365918709,
+      "learning_rate": 7.021783319837298e-06,
+      "loss": 0.6767,
+      "step": 790
+    },
+    {
+      "epoch": 1.308761885287803,
+      "grad_norm": 0.7307976869448247,
+      "learning_rate": 6.934299038635414e-06,
+      "loss": 0.6812,
+      "step": 800
+    },
+    {
+      "epoch": 1.308761885287803,
+      "eval_loss": 0.7325922846794128,
+      "eval_runtime": 8.8154,
+      "eval_samples_per_second": 8.962,
+      "eval_steps_per_second": 4.538,
+      "step": 800
+    },
+    {
+      "epoch": 1.3251201308659646,
+      "grad_norm": 0.7219505844302012,
+      "learning_rate": 6.8461127060265135e-06,
+      "loss": 0.679,
+      "step": 810
+    },
+    {
+      "epoch": 1.3414783764441265,
+      "grad_norm": 0.7057903127014294,
+      "learning_rate": 6.7572563291292724e-06,
+      "loss": 0.6714,
+      "step": 820
+    },
+    {
+      "epoch": 1.3414783764441265,
+      "eval_loss": 0.7310522794723511,
+      "eval_runtime": 8.9723,
+      "eval_samples_per_second": 8.805,
+      "eval_steps_per_second": 4.458,
+      "step": 820
+    },
+    {
+      "epoch": 1.3578366220222882,
+      "grad_norm": 0.7481237758190087,
+      "learning_rate": 6.667762158254104e-06,
+      "loss": 0.671,
+      "step": 830
+    },
+    {
+      "epoch": 1.3741948676004498,
+      "grad_norm": 0.6771887136482816,
+      "learning_rate": 6.57766267519794e-06,
+      "loss": 0.6764,
+      "step": 840
+    },
+    {
+      "epoch": 1.3741948676004498,
+      "eval_loss": 0.7305134534835815,
+      "eval_runtime": 8.7821,
+      "eval_samples_per_second": 8.996,
+      "eval_steps_per_second": 4.555,
+      "step": 840
+    },
+    {
+      "epoch": 1.3905531131786115,
+      "grad_norm": 0.7720857727869926,
+      "learning_rate": 6.486990581455011e-06,
+      "loss": 0.6819,
+      "step": 850
+    },
+    {
+      "epoch": 1.4069113587567732,
+      "grad_norm": 0.7488122619323809,
+      "learning_rate": 6.395778786347878e-06,
+      "loss": 0.6801,
+      "step": 860
+    },
+    {
+      "epoch": 1.4069113587567732,
+      "eval_loss": 0.7291988134384155,
+      "eval_runtime": 8.8848,
+      "eval_samples_per_second": 8.892,
+      "eval_steps_per_second": 4.502,
+      "step": 860
+    },
+    {
+      "epoch": 1.423269604334935,
+      "grad_norm": 0.7831777981437086,
+      "learning_rate": 6.304060395083031e-06,
+      "loss": 0.6687,
+      "step": 870
+    },
+    {
+      "epoch": 1.4396278499130968,
+      "grad_norm": 0.7391424956481155,
+      "learning_rate": 6.211868696735405e-06,
+      "loss": 0.6693,
+      "step": 880
+    },
+    {
+      "epoch": 1.4396278499130968,
+      "eval_loss": 0.727660059928894,
+      "eval_runtime": 8.8922,
+      "eval_samples_per_second": 8.884,
+      "eval_steps_per_second": 4.498,
+      "step": 880
+    },
+    {
+      "epoch": 1.4559860954912587,
+      "grad_norm": 0.6633367855169299,
+      "learning_rate": 6.119237152166139e-06,
+      "loss": 0.6657,
+      "step": 890
+    },
+    {
+      "epoch": 1.4723443410694204,
+      "grad_norm": 0.6920250318389223,
+      "learning_rate": 6.026199381878011e-06,
+      "loss": 0.6726,
+      "step": 900
+    },
+    {
+      "epoch": 1.4723443410694204,
+      "eval_loss": 0.7265572547912598,
+      "eval_runtime": 8.8512,
+      "eval_samples_per_second": 8.925,
+      "eval_steps_per_second": 4.519,
+      "step": 900
+    },
+    {
+      "epoch": 1.488702586647582,
+      "grad_norm": 0.7081219959408172,
+      "learning_rate": 5.932789153812911e-06,
+      "loss": 0.6672,
+      "step": 910
+    },
+    {
+      "epoch": 1.5050608322257437,
+      "grad_norm": 0.7707103364304354,
+      "learning_rate": 5.839040371095814e-06,
+      "loss": 0.6762,
+      "step": 920
+    },
+    {
+      "epoch": 1.5050608322257437,
+      "eval_loss": 0.7252368330955505,
+      "eval_runtime": 8.8447,
+      "eval_samples_per_second": 8.932,
+      "eval_steps_per_second": 4.522,
+      "step": 920
+    },
+    {
+      "epoch": 1.5214190778039054,
+      "grad_norm": 0.7285700753630275,
+      "learning_rate": 5.74498705972968e-06,
+      "loss": 0.6716,
+      "step": 930
+    },
+    {
+      "epoch": 1.5377773233820673,
+      "grad_norm": 0.6719863494102282,
+      "learning_rate": 5.650663356245756e-06,
+      "loss": 0.6666,
+      "step": 940
+    },
+    {
+      "epoch": 1.5377773233820673,
+      "eval_loss": 0.7246092557907104,
+      "eval_runtime": 8.7654,
+      "eval_samples_per_second": 9.013,
+      "eval_steps_per_second": 4.563,
+      "step": 940
+    },
+    {
+      "epoch": 1.554135568960229,
+      "grad_norm": 0.697927897632164,
+      "learning_rate": 5.556103495313774e-06,
+      "loss": 0.6679,
+      "step": 950
+    },
+    {
+      "epoch": 1.5704938145383909,
+      "grad_norm": 0.6843159800619036,
+      "learning_rate": 5.46134179731651e-06,
+      "loss": 0.6713,
+      "step": 960
+    },
+    {
+      "epoch": 1.5704938145383909,
+      "eval_loss": 0.7233731150627136,
+      "eval_runtime": 8.9372,
+      "eval_samples_per_second": 8.839,
+      "eval_steps_per_second": 4.476,
+      "step": 960
+    },
+    {
+      "epoch": 1.5868520601165526,
+      "grad_norm": 0.6766351504145809,
+      "learning_rate": 5.366412655893256e-06,
+      "loss": 0.6689,
+      "step": 970
+    },
+    {
+      "epoch": 1.6032103056947142,
+      "grad_norm": 0.7167144088999912,
+      "learning_rate": 5.271350525456679e-06,
+      "loss": 0.6659,
+      "step": 980
+    },
+    {
+      "epoch": 1.6032103056947142,
+      "eval_loss": 0.7226489186286926,
+      "eval_runtime": 8.789,
+      "eval_samples_per_second": 8.989,
+      "eval_steps_per_second": 4.551,
+      "step": 980
+    },
+    {
+      "epoch": 1.619568551272876,
+      "grad_norm": 0.7126879315212699,
+      "learning_rate": 5.176189908687646e-06,
+      "loss": 0.6695,
+      "step": 990
+    },
+    {
+      "epoch": 1.6359267968510376,
+      "grad_norm": 0.6583586257751949,
+      "learning_rate": 5.080965344012509e-06,
+      "loss": 0.6694,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6359267968510376,
+      "eval_loss": 0.7216107249259949,
+      "eval_runtime": 8.8487,
+      "eval_samples_per_second": 8.928,
+      "eval_steps_per_second": 4.52,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6522850424291995,
+      "grad_norm": 0.6561297313170917,
+      "learning_rate": 4.985711393067437e-06,
+      "loss": 0.6674,
+      "step": 1010
+    },
+    {
+      "epoch": 1.6686432880073612,
+      "grad_norm": 0.6626437713636341,
+      "learning_rate": 4.890462628154309e-06,
+      "loss": 0.6667,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6686432880073612,
+      "eval_loss": 0.7210881114006042,
+      "eval_runtime": 8.7877,
+      "eval_samples_per_second": 8.99,
+      "eval_steps_per_second": 4.552,
+      "step": 1020
+    },
+    {
+      "epoch": 1.685001533585523,
+      "grad_norm": 0.7166433188372661,
+      "learning_rate": 4.795253619692737e-06,
+      "loss": 0.663,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7013597791636847,
+      "grad_norm": 0.741234806048152,
+      "learning_rate": 4.700118923672779e-06,
+      "loss": 0.6739,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7013597791636847,
+      "eval_loss": 0.7206884622573853,
+      "eval_runtime": 8.8528,
+      "eval_samples_per_second": 8.924,
+      "eval_steps_per_second": 4.518,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7177180247418464,
+      "grad_norm": 0.7016761274840421,
+      "learning_rate": 4.605093069112892e-06,
+      "loss": 0.6711,
+      "step": 1050
+    },
+    {
+      "epoch": 1.734076270320008,
+      "grad_norm": 0.6970244053157433,
+      "learning_rate": 4.5102105455276525e-06,
+      "loss": 0.6745,
+      "step": 1060
+    },
+    {
+      "epoch": 1.734076270320008,
+      "eval_loss": 0.7203969955444336,
+      "eval_runtime": 8.8182,
+      "eval_samples_per_second": 8.959,
+      "eval_steps_per_second": 4.536,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7504345158981698,
+      "grad_norm": 0.7335723892483486,
+      "learning_rate": 4.415505790409847e-06,
+      "loss": 0.6686,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7667927614763317,
+      "grad_norm": 0.6956225175618133,
+      "learning_rate": 4.321013176731414e-06,
+      "loss": 0.6665,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7667927614763317,
+      "eval_loss": 0.7191005945205688,
+      "eval_runtime": 8.9226,
+      "eval_samples_per_second": 8.854,
+      "eval_steps_per_second": 4.483,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7831510070544934,
+      "grad_norm": 0.698587154786482,
+      "learning_rate": 4.226767000467826e-06,
+      "loss": 0.6666,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7995092526326553,
+      "grad_norm": 0.7438773573796561,
+      "learning_rate": 4.1328014681504105e-06,
+      "loss": 0.6626,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7995092526326553,
+      "eval_loss": 0.7183343768119812,
+      "eval_runtime": 8.8586,
+      "eval_samples_per_second": 8.918,
+      "eval_steps_per_second": 4.515,
+      "step": 1100
+    },
+    {
+      "epoch": 1.815867498210817,
+      "grad_norm": 0.6947292310543136,
+      "learning_rate": 4.039150684451117e-06,
+      "loss": 0.66,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8322257437889786,
+      "grad_norm": 0.6477593004868593,
+      "learning_rate": 3.945848639804287e-06,
+      "loss": 0.6583,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8322257437889786,
+      "eval_loss": 0.7178105711936951,
+      "eval_runtime": 8.8059,
+      "eval_samples_per_second": 8.971,
+      "eval_steps_per_second": 4.542,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8485839893671403,
+      "grad_norm": 0.6753153859283428,
+      "learning_rate": 3.852929198069856e-06,
+      "loss": 0.6551,
+      "step": 1130
+    },
+    {
+      "epoch": 1.864942234945302,
+      "grad_norm": 0.734130420389638,
+      "learning_rate": 3.7604260842425146e-06,
+      "loss": 0.665,
+      "step": 1140
+    },
+    {
+      "epoch": 1.864942234945302,
+      "eval_loss": 0.7165009379386902,
+      "eval_runtime": 8.8639,
+      "eval_samples_per_second": 8.913,
+      "eval_steps_per_second": 4.513,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8813004805234639,
+      "grad_norm": 0.6466537300434777,
+      "learning_rate": 3.668372872211266e-06,
+      "loss": 0.6601,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8976587261016256,
+      "grad_norm": 0.6650377275740064,
+      "learning_rate": 3.5768029725738157e-06,
+      "loss": 0.6609,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8976587261016256,
+      "eval_loss": 0.7164144515991211,
+      "eval_runtime": 8.8323,
+      "eval_samples_per_second": 8.944,
+      "eval_steps_per_second": 4.529,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9140169716797875,
+      "grad_norm": 0.6705397336213909,
+      "learning_rate": 3.4857496205102475e-06,
+      "loss": 0.6558,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9303752172579491,
+      "grad_norm": 0.6821158056706338,
+      "learning_rate": 3.3952458637203475e-06,
+      "loss": 0.6715,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9303752172579491,
+      "eval_loss": 0.715703010559082,
+      "eval_runtime": 8.8492,
+      "eval_samples_per_second": 8.927,
+      "eval_steps_per_second": 4.52,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9467334628361108,
+      "grad_norm": 0.6630764255722235,
+      "learning_rate": 3.3053245504289894e-06,
+      "loss": 0.656,
+      "step": 1190
+    },
+    {
+      "epoch": 1.9630917084142725,
+      "grad_norm": 0.669639110840792,
+      "learning_rate": 3.216018317463914e-06,
+      "loss": 0.6755,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9630917084142725,
+      "eval_loss": 0.7149642109870911,
+      "eval_runtime": 8.6929,
+      "eval_samples_per_second": 9.088,
+      "eval_steps_per_second": 4.601,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9794499539924342,
+      "grad_norm": 0.677640160297301,
+      "learning_rate": 3.1273595784102244e-06,
+      "loss": 0.6656,
+      "step": 1210
+    },
+    {
+      "epoch": 1.995808199570596,
+      "grad_norm": 0.6478481336084418,
+      "learning_rate": 3.0393805118459257e-06,
+      "loss": 0.6654,
+      "step": 1220
+    },
+    {
+      "epoch": 1.995808199570596,
+      "eval_loss": 0.7144020795822144,
+      "eval_runtime": 8.7728,
+      "eval_samples_per_second": 9.005,
+      "eval_steps_per_second": 4.56,
+      "step": 1220
+    },
+    {
+      "epoch": 2.0122686841836215,
+      "grad_norm": 0.7160988089736929,
+      "learning_rate": 2.952113049662744e-06,
+      "loss": 0.6911,
+      "step": 1230
+    },
+    {
+      "epoch": 2.028626929761783,
+      "grad_norm": 0.6658394367051226,
+      "learning_rate": 2.86558886547649e-06,
+      "loss": 0.6207,
+      "step": 1240
+    },
+    {
+      "epoch": 2.028626929761783,
+      "eval_loss": 0.7192620038986206,
+      "eval_runtime": 8.7807,
+      "eval_samples_per_second": 8.997,
+      "eval_steps_per_second": 4.555,
+      "step": 1240
+    },
+    {
+      "epoch": 2.044985175339945,
+      "grad_norm": 0.654677579170524,
+      "learning_rate": 2.7798393631311565e-06,
+      "loss": 0.6216,
+      "step": 1250
+    },
+    {
+      "epoch": 2.0613434209181065,
+      "grad_norm": 0.6845236856939948,
+      "learning_rate": 2.6948956653009416e-06,
+      "loss": 0.618,
+      "step": 1260
+    },
+    {
+      "epoch": 2.0613434209181065,
+      "eval_loss": 0.7191548347473145,
+      "eval_runtime": 8.8502,
+      "eval_samples_per_second": 8.926,
+      "eval_steps_per_second": 4.52,
+      "step": 1260
+    },
+    {
+      "epoch": 2.077701666496268,
+      "grad_norm": 0.6800346983315418,
+      "learning_rate": 2.6107886021942984e-06,
+      "loss": 0.6219,
+      "step": 1270
+    },
+    {
+      "epoch": 2.09405991207443,
+      "grad_norm": 0.6473993386866002,
+      "learning_rate": 2.527548700364164e-06,
+      "loss": 0.6182,
+      "step": 1280
+    },
+    {
+      "epoch": 2.09405991207443,
+      "eval_loss": 0.7187679409980774,
+      "eval_runtime": 8.8369,
+      "eval_samples_per_second": 8.94,
+      "eval_steps_per_second": 4.526,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1104181576525916,
+      "grad_norm": 0.680332157190334,
+      "learning_rate": 2.4452061716283764e-06,
+      "loss": 0.6247,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1267764032307537,
+      "grad_norm": 0.6713647024120337,
+      "learning_rate": 2.3637909021043332e-06,
+      "loss": 0.6188,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1267764032307537,
+      "eval_loss": 0.7195940017700195,
+      "eval_runtime": 8.934,
+      "eval_samples_per_second": 8.843,
+      "eval_steps_per_second": 4.477,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1431346488089154,
+      "grad_norm": 0.6905966915530017,
+      "learning_rate": 2.2833324413618695e-06,
+      "loss": 0.6213,
+      "step": 1310
+    },
+    {
+      "epoch": 2.159492894387077,
+      "grad_norm": 0.6961837258954594,
+      "learning_rate": 2.2038599916982775e-06,
+      "loss": 0.6173,
+      "step": 1320
+    },
+    {
+      "epoch": 2.159492894387077,
+      "eval_loss": 0.718852162361145,
+      "eval_runtime": 8.7975,
+      "eval_samples_per_second": 8.98,
+      "eval_steps_per_second": 4.547,
+      "step": 1320
+    },
+    {
+      "epoch": 2.1758511399652387,
+      "grad_norm": 0.7109159972241073,
+      "learning_rate": 2.1254023975393585e-06,
+      "loss": 0.6193,
+      "step": 1330
+    },
+    {
+      "epoch": 2.1922093855434004,
+      "grad_norm": 0.6856177780539675,
+      "learning_rate": 2.0479881349703885e-06,
+      "loss": 0.6206,
+      "step": 1340
+    },
+    {
+      "epoch": 2.1922093855434004,
+      "eval_loss": 0.719401478767395,
+      "eval_runtime": 9.6891,
+      "eval_samples_per_second": 8.154,
+      "eval_steps_per_second": 4.128,
+      "step": 1340
+    },
+    {
+      "epoch": 2.208567631121562,
+      "grad_norm": 0.6846382708470592,
+      "learning_rate": 1.9716453014007493e-06,
+      "loss": 0.6172,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2249258766997237,
+      "grad_norm": 0.6821924271490651,
+      "learning_rate": 1.8964016053660167e-06,
+      "loss": 0.6206,
+      "step": 1360
+    },
+    {
+      "epoch": 2.2249258766997237,
+      "eval_loss": 0.7185901403427124,
+      "eval_runtime": 10.538,
+      "eval_samples_per_second": 7.497,
+      "eval_steps_per_second": 3.796,
+      "step": 1360
+    },
+    {
+      "epoch": 2.241284122277886,
+      "grad_norm": 0.7020054137197129,
+      "learning_rate": 1.822284356471179e-06,
+      "loss": 0.628,
+      "step": 1370
+    },
+    {
+      "epoch": 2.2576423678560475,
+      "grad_norm": 0.6827467082055568,
+      "learning_rate": 1.7493204554786453e-06,
+      "loss": 0.6192,
+      "step": 1380
+    },
+    {
+      "epoch": 2.2576423678560475,
+      "eval_loss": 0.7185772657394409,
+      "eval_runtime": 8.7402,
+      "eval_samples_per_second": 9.039,
+      "eval_steps_per_second": 4.577,
+      "step": 1380
+    },
+    {
+      "epoch": 2.2740006134342092,
+      "grad_norm": 0.6787057813877333,
+      "learning_rate": 1.6775363845446552e-06,
+      "loss": 0.6215,
+      "step": 1390
+    },
+    {
+      "epoch": 2.290358859012371,
+      "grad_norm": 0.6965105305161102,
+      "learning_rate": 1.6069581976076059e-06,
+      "loss": 0.6168,
+      "step": 1400
+    },
+    {
+      "epoch": 2.290358859012371,
+      "eval_loss": 0.7182484269142151,
+      "eval_runtime": 8.8061,
+      "eval_samples_per_second": 8.971,
+      "eval_steps_per_second": 4.542,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3067171045905326,
+      "grad_norm": 0.657899834231394,
+      "learning_rate": 1.537611510931819e-06,
+      "loss": 0.622,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3230753501686943,
+      "grad_norm": 0.6763933278225029,
+      "learning_rate": 1.4695214938101394e-06,
+      "loss": 0.6247,
+      "step": 1420
+    },
+    {
+      "epoch": 2.3230753501686943,
+      "eval_loss": 0.7175112962722778,
+      "eval_runtime": 8.833,
+      "eval_samples_per_second": 8.944,
+      "eval_steps_per_second": 4.528,
+      "step": 1420
+    },
+    {
+      "epoch": 2.339433595746856,
+      "grad_norm": 0.6445654002256987,
+      "learning_rate": 1.4027128594287743e-06,
+      "loss": 0.6124,
+      "step": 1430
+    },
+    {
+      "epoch": 2.355791841325018,
+      "grad_norm": 0.6483502135699247,
+      "learning_rate": 1.3372098558976753e-06,
+      "loss": 0.6152,
+      "step": 1440
+    },
+    {
+      "epoch": 2.355791841325018,
+      "eval_loss": 0.7176142930984497,
+      "eval_runtime": 8.7696,
+      "eval_samples_per_second": 9.008,
+      "eval_steps_per_second": 4.561,
+      "step": 1440
+    },
+    {
+      "epoch": 2.3721500869031797,
+      "grad_norm": 0.6748060520638486,
+      "learning_rate": 1.2730362574497146e-06,
+      "loss": 0.6191,
+      "step": 1450
+    },
+    {
+      "epoch": 2.3885083324813414,
+      "grad_norm": 0.6411389753036478,
+      "learning_rate": 1.2102153558118635e-06,
+      "loss": 0.6118,
+      "step": 1460
+    },
+    {
+      "epoch": 2.3885083324813414,
+      "eval_loss": 0.7174015641212463,
+      "eval_runtime": 8.8824,
+      "eval_samples_per_second": 8.894,
+      "eval_steps_per_second": 4.503,
+      "step": 1460
+    },
+    {
+      "epoch": 2.404866578059503,
+      "grad_norm": 0.6147421703730933,
+      "learning_rate": 1.1487699517514828e-06,
+      "loss": 0.6213,
+      "step": 1470
+    },
+    {
+      "epoch": 2.421224823637665,
+      "grad_norm": 0.6564011388418958,
+      "learning_rate": 1.088722346800813e-06,
+      "loss": 0.6192,
+      "step": 1480
+    },
+    {
+      "epoch": 2.421224823637665,
+      "eval_loss": 0.7174366116523743,
+      "eval_runtime": 8.8213,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.534,
+      "step": 1480
+    },
+    {
+      "epoch": 2.4375830692158265,
+      "grad_norm": 0.6637159235119273,
+      "learning_rate": 1.0300943351626642e-06,
+      "loss": 0.6172,
+      "step": 1490
+    },
+    {
+      "epoch": 2.4539413147939886,
+      "grad_norm": 0.6399937055494419,
+      "learning_rate": 9.729071958002356e-07,
+      "loss": 0.6125,
+      "step": 1500
+    },
+    {
+      "epoch": 2.4539413147939886,
+      "eval_loss": 0.7172605395317078,
+      "eval_runtime": 8.8588,
+      "eval_samples_per_second": 8.918,
+      "eval_steps_per_second": 4.515,
+      "step": 1500
+    },
+    {
+      "epoch": 2.4702995603721503,
+      "grad_norm": 0.6548848015845544,
+      "learning_rate": 9.171816847139447e-07,
+      "loss": 0.6197,
+      "step": 1510
+    },
+    {
+      "epoch": 2.486657805950312,
+      "grad_norm": 0.652681143911981,
+      "learning_rate": 8.62938027408064e-07,
+      "loss": 0.6067,
+      "step": 1520
+    },
+    {
+      "epoch": 2.486657805950312,
+      "eval_loss": 0.7170479893684387,
+      "eval_runtime": 8.821,
+      "eval_samples_per_second": 8.956,
+      "eval_steps_per_second": 4.535,
+      "step": 1520
+    },
+    {
+      "epoch": 2.5030160515284736,
+      "grad_norm": 0.6223909947895746,
+      "learning_rate": 8.10195911549892e-07,
+      "loss": 0.6229,
+      "step": 1530
+    },
+    {
+      "epoch": 2.5193742971066353,
+      "grad_norm": 0.6675446368924337,
+      "learning_rate": 7.589744798241472e-07,
+      "loss": 0.6196,
+      "step": 1540
+    },
+    {
+      "epoch": 2.5193742971066353,
+      "eval_loss": 0.7164150476455688,
+      "eval_runtime": 8.8151,
+      "eval_samples_per_second": 8.962,
+      "eval_steps_per_second": 4.538,
+      "step": 1540
+    },
+    {
+      "epoch": 2.535732542684797,
+      "grad_norm": 0.6748594529596444,
+      "learning_rate": 7.092923229851506e-07,
+      "loss": 0.6259,
+      "step": 1550
+    },
+    {
+      "epoch": 2.5520907882629587,
+      "grad_norm": 0.6436382148035624,
+      "learning_rate": 6.611674731093376e-07,
+      "loss": 0.6147,
+      "step": 1560
+    },
+    {
+      "epoch": 2.5520907882629587,
+      "eval_loss": 0.7163916826248169,
+      "eval_runtime": 8.7789,
+      "eval_samples_per_second": 8.999,
+      "eval_steps_per_second": 4.556,
+      "step": 1560
+    },
+    {
+      "epoch": 2.5684490338411203,
+      "grad_norm": 0.6954982109692219,
+      "learning_rate": 6.146173970505387e-07,
+      "loss": 0.6221,
+      "step": 1570
+    },
+    {
+      "epoch": 2.584807279419282,
+      "grad_norm": 0.6636316314884414,
+      "learning_rate": 5.696589901004001e-07,
+      "loss": 0.6166,
+      "step": 1580
+    },
+    {
+      "epoch": 2.584807279419282,
+      "eval_loss": 0.7162200808525085,
+      "eval_runtime": 8.8522,
+      "eval_samples_per_second": 8.924,
+      "eval_steps_per_second": 4.519,
+      "step": 1580
+    },
+    {
+      "epoch": 2.601165524997444,
+      "grad_norm": 0.6348189748255966,
+      "learning_rate": 5.263085698562675e-07,
+      "loss": 0.6162,
+      "step": 1590
+    },
+    {
+      "epoch": 2.617523770575606,
+      "grad_norm": 0.6656187164775476,
+      "learning_rate": 4.845818702987287e-07,
+      "loss": 0.6235,
+      "step": 1600
+    },
+    {
+      "epoch": 2.617523770575606,
+      "eval_loss": 0.7161623239517212,
+      "eval_runtime": 8.9168,
+      "eval_samples_per_second": 8.86,
+      "eval_steps_per_second": 4.486,
+      "step": 1600
+    },
+    {
+      "epoch": 2.6338820161537675,
+      "grad_norm": 0.644537564705373,
+      "learning_rate": 4.4449403608098965e-07,
+      "loss": 0.6126,
+      "step": 1610
+    },
+    {
+      "epoch": 2.650240261731929,
+      "grad_norm": 0.6394762326342863,
+      "learning_rate": 4.0605961703213845e-07,
+      "loss": 0.6112,
+      "step": 1620
+    },
+    {
+      "epoch": 2.650240261731929,
+      "eval_loss": 0.7161468267440796,
+      "eval_runtime": 8.9454,
+      "eval_samples_per_second": 8.831,
+      "eval_steps_per_second": 4.472,
+      "step": 1620
+    },
+    {
+      "epoch": 2.666598507310091,
+      "grad_norm": 0.6651958412760407,
+      "learning_rate": 3.692925628763033e-07,
+      "loss": 0.6218,
+      "step": 1630
+    },
+    {
+      "epoch": 2.682956752888253,
+      "grad_norm": 0.6547622124607134,
+      "learning_rate": 3.3420621816961874e-07,
+      "loss": 0.6186,
+      "step": 1640
+    },
+    {
+      "epoch": 2.682956752888253,
+      "eval_loss": 0.7159026265144348,
+      "eval_runtime": 8.8156,
+      "eval_samples_per_second": 8.961,
+      "eval_steps_per_second": 4.537,
+      "step": 1640
+    },
+    {
+      "epoch": 2.6993149984664147,
+      "grad_norm": 0.6391386777884149,
+      "learning_rate": 3.0081331745683395e-07,
+      "loss": 0.613,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7156732440445763,
+      "grad_norm": 0.6368321437722378,
+      "learning_rate": 2.691259806493296e-07,
+      "loss": 0.6164,
+      "step": 1660
+    },
+    {
+      "epoch": 2.7156732440445763,
+      "eval_loss": 0.7158184051513672,
+      "eval_runtime": 8.7951,
+      "eval_samples_per_second": 8.982,
+      "eval_steps_per_second": 4.548,
+      "step": 1660
+    },
+    {
+      "epoch": 2.732031489622738,
+      "grad_norm": 0.6365243949451423,
+      "learning_rate": 2.391557086262086e-07,
+      "loss": 0.6228,
+      "step": 1670
+    },
+    {
+      "epoch": 2.7483897352008997,
+      "grad_norm": 0.6321404050434235,
+      "learning_rate": 2.109133790600648e-07,
+      "loss": 0.6147,
+      "step": 1680
+    },
+    {
+      "epoch": 2.7483897352008997,
+      "eval_loss": 0.7158446311950684,
+      "eval_runtime": 8.8513,
+      "eval_samples_per_second": 8.925,
+      "eval_steps_per_second": 4.519,
+      "step": 1680
+    },
+    {
+      "epoch": 2.7647479807790614,
+      "grad_norm": 0.6903153602015651,
+      "learning_rate": 1.8440924246894753e-07,
+      "loss": 0.6158,
+      "step": 1690
+    },
+    {
+      "epoch": 2.781106226357223,
+      "grad_norm": 0.6670191692486903,
+      "learning_rate": 1.5965291849594944e-07,
+      "loss": 0.6098,
+      "step": 1700
+    },
+    {
+      "epoch": 2.781106226357223,
+      "eval_loss": 0.7158127427101135,
+      "eval_runtime": 8.8596,
+      "eval_samples_per_second": 8.917,
+      "eval_steps_per_second": 4.515,
+      "step": 1700
+    },
+    {
+      "epoch": 2.7974644719353847,
+      "grad_norm": 0.6357999130773923,
+      "learning_rate": 1.3665339241776765e-07,
+      "loss": 0.6212,
+      "step": 1710
+    },
+    {
+      "epoch": 2.8138227175135464,
+      "grad_norm": 0.6630012411471573,
+      "learning_rate": 1.1541901188351134e-07,
+      "loss": 0.6126,
+      "step": 1720
+    },
+    {
+      "epoch": 2.8138227175135464,
+      "eval_loss": 0.7158257365226746,
+      "eval_runtime": 9.6888,
+      "eval_samples_per_second": 8.154,
+      "eval_steps_per_second": 4.128,
+      "step": 1720
+    },
+    {
+      "epoch": 2.8301809630917085,
+      "grad_norm": 0.6453855721831139,
+      "learning_rate": 9.59574838849281e-08,
+      "loss": 0.6162,
+      "step": 1730
+    },
+    {
+      "epoch": 2.84653920866987,
+      "grad_norm": 0.647793683675027,
+      "learning_rate": 7.827587195916697e-08,
+      "loss": 0.6179,
+      "step": 1740
+    },
+    {
+      "epoch": 2.84653920866987,
+      "eval_loss": 0.7156850695610046,
+      "eval_runtime": 8.8101,
+      "eval_samples_per_second": 8.967,
+      "eval_steps_per_second": 4.54,
+      "step": 1740
+    },
+    {
+      "epoch": 2.862897454248032,
+      "grad_norm": 0.627906665508174,
+      "learning_rate": 6.238059362507043e-08,
+      "loss": 0.6157,
+      "step": 1750
+    },
+    {
+      "epoch": 2.8792556998261936,
+      "grad_norm": 0.6991824017680971,
+      "learning_rate": 4.827741805395025e-08,
+      "loss": 0.6229,
+      "step": 1760
+    },
+    {
+      "epoch": 2.8792556998261936,
+      "eval_loss": 0.7156457901000977,
+      "eval_runtime": 8.8917,
+      "eval_samples_per_second": 8.885,
+      "eval_steps_per_second": 4.499,
+      "step": 1760
+    },
+    {
+      "epoch": 2.8956139454043552,
+      "grad_norm": 0.6604597808333147,
+      "learning_rate": 3.59714639756692e-08,
+      "loss": 0.6198,
+      "step": 1770
+    },
+    {
+      "epoch": 2.9119721909825174,
+      "grad_norm": 0.6412019833547566,
+      "learning_rate": 2.5467197820805977e-08,
+      "loss": 0.624,
+      "step": 1780
+    },
+    {
+      "epoch": 2.9119721909825174,
+      "eval_loss": 0.7153981328010559,
+      "eval_runtime": 8.897,
+      "eval_samples_per_second": 8.879,
+      "eval_steps_per_second": 4.496,
+      "step": 1780
+    },
+    {
+      "epoch": 2.928330436560679,
+      "grad_norm": 0.6539771563156503,
+      "learning_rate": 1.6768432099570907e-08,
+      "loss": 0.6181,
+      "step": 1790
+    },
+    {
+      "epoch": 2.9446886821388407,
+      "grad_norm": 0.6484588822526755,
+      "learning_rate": 9.878324018058327e-09,
+      "loss": 0.6155,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9446886821388407,
+      "eval_loss": 0.7157188653945923,
+      "eval_runtime": 8.8628,
+      "eval_samples_per_second": 8.914,
+      "eval_steps_per_second": 4.513,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9610469277170024,
+      "grad_norm": 0.6119368873622615,
+      "learning_rate": 4.799374332344342e-09,
+      "loss": 0.6189,
+      "step": 1810
+    },
+    {
+      "epoch": 2.977405173295164,
+      "grad_norm": 0.6333710387576432,
+      "learning_rate": 1.533426440839536e-09,
+      "loss": 0.6211,
+      "step": 1820
+    },
+    {
+      "epoch": 2.977405173295164,
+      "eval_loss": 0.7156268358230591,
+      "eval_runtime": 8.9113,
+      "eval_samples_per_second": 8.865,
+      "eval_steps_per_second": 4.489,
+      "step": 1820
+    },
+    {
+      "epoch": 2.9937634188733258,
+      "grad_norm": 0.6603951738557682,
+      "learning_rate": 8.166571522916222e-11,
+      "loss": 0.6176,
+      "step": 1830
+    },
+    {
+      "epoch": 2.9986708925467744,
+      "step": 1833,
+      "total_flos": 531028544847872.0,
+      "train_loss": 0.7064719163714637,
+      "train_runtime": 53129.6318,
+      "train_samples_per_second": 2.209,
+      "train_steps_per_second": 0.035
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1833,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 531028544847872.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

scenario_cot_ratio_3B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f421d93c1891f88c006b5531b6846225381e71427c61d3610289adb9c3428f
+size 7224