Update scenario_ratio_7B

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* 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_ratio_7B/tokenizer.json filter=lfs diff=lfs merge=lfs -text

scenario_ratio_7B/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_ratio_7B/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9947275922671355,
+    "eval_loss": 0.49775850772857666,
+    "eval_runtime": 6.9042,
+    "eval_samples_per_second": 12.022,
+    "eval_steps_per_second": 3.042,
+    "total_flos": 457793516601344.0,
+    "train_loss": 0.4100710519229489,
+    "train_runtime": 44735.0493,
+    "train_samples_per_second": 2.747,
+    "train_steps_per_second": 0.029
+}

scenario_ratio_7B/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/public/code/zhaojihao/models/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

scenario_ratio_7B/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9947275922671355,
+    "eval_loss": 0.49775850772857666,
+    "eval_runtime": 6.9042,
+    "eval_samples_per_second": 12.022,
+    "eval_steps_per_second": 3.042
+}

scenario_ratio_7B/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_ratio_7B/model.safetensors.index.json

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

scenario_ratio_7B/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_ratio_7B/tokenizer.json

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

scenario_ratio_7B/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_ratio_7B/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9947275922671355,
+    "total_flos": 457793516601344.0,
+    "train_loss": 0.4100710519229489,
+    "train_runtime": 44735.0493,
+    "train_samples_per_second": 2.747,
+    "train_steps_per_second": 0.029
+}

scenario_ratio_7B/trainer_state.json

@@ -0,0 +1,1435 @@
+{
+  "best_metric": 0.49775850772857666,
+  "best_model_checkpoint": "/mnt/public/code/zhaojihao/train_model/scenario_train_40K_ratio_sc_qwen25_7B_3/checkpoint-840",
+  "epoch": 2.9947275922671355,
+  "eval_steps": 20,
+  "global_step": 1278,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023432923257176334,
+      "grad_norm": 5.322404495641149,
+      "learning_rate": 7.8125e-07,
+      "loss": 0.9704,
+      "step": 10
+    },
+    {
+      "epoch": 0.04686584651435267,
+      "grad_norm": 2.3537050585240715,
+      "learning_rate": 1.5625e-06,
+      "loss": 0.8803,
+      "step": 20
+    },
+    {
+      "epoch": 0.04686584651435267,
+      "eval_loss": 0.8319932222366333,
+      "eval_runtime": 6.8796,
+      "eval_samples_per_second": 12.065,
+      "eval_steps_per_second": 3.053,
+      "step": 20
+    },
+    {
+      "epoch": 0.070298769771529,
+      "grad_norm": 1.6370151600501506,
+      "learning_rate": 2.3437500000000002e-06,
+      "loss": 0.7536,
+      "step": 30
+    },
+    {
+      "epoch": 0.09373169302870533,
+      "grad_norm": 1.2654389222184044,
+      "learning_rate": 3.125e-06,
+      "loss": 0.6914,
+      "step": 40
+    },
+    {
+      "epoch": 0.09373169302870533,
+      "eval_loss": 0.6773133277893066,
+      "eval_runtime": 6.8557,
+      "eval_samples_per_second": 12.107,
+      "eval_steps_per_second": 3.063,
+      "step": 40
+    },
+    {
+      "epoch": 0.11716461628588166,
+      "grad_norm": 1.0702172390482234,
+      "learning_rate": 3.90625e-06,
+      "loss": 0.6413,
+      "step": 50
+    },
+    {
+      "epoch": 0.140597539543058,
+      "grad_norm": 1.095731735126781,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 0.6208,
+      "step": 60
+    },
+    {
+      "epoch": 0.140597539543058,
+      "eval_loss": 0.6241949200630188,
+      "eval_runtime": 6.8616,
+      "eval_samples_per_second": 12.096,
+      "eval_steps_per_second": 3.061,
+      "step": 60
+    },
+    {
+      "epoch": 0.16403046280023434,
+      "grad_norm": 0.9546483943590885,
+      "learning_rate": 5.468750000000001e-06,
+      "loss": 0.6025,
+      "step": 70
+    },
+    {
+      "epoch": 0.18746338605741067,
+      "grad_norm": 1.0361366241819066,
+      "learning_rate": 6.25e-06,
+      "loss": 0.5861,
+      "step": 80
+    },
+    {
+      "epoch": 0.18746338605741067,
+      "eval_loss": 0.5996931195259094,
+      "eval_runtime": 6.8864,
+      "eval_samples_per_second": 12.053,
+      "eval_steps_per_second": 3.049,
+      "step": 80
+    },
+    {
+      "epoch": 0.210896309314587,
+      "grad_norm": 1.0427070615586196,
+      "learning_rate": 7.031250000000001e-06,
+      "loss": 0.5703,
+      "step": 90
+    },
+    {
+      "epoch": 0.23432923257176333,
+      "grad_norm": 1.0759019184355236,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.5783,
+      "step": 100
+    },
+    {
+      "epoch": 0.23432923257176333,
+      "eval_loss": 0.5848845839500427,
+      "eval_runtime": 6.8445,
+      "eval_samples_per_second": 12.127,
+      "eval_steps_per_second": 3.068,
+      "step": 100
+    },
+    {
+      "epoch": 0.2577621558289397,
+      "grad_norm": 1.1101574933120002,
+      "learning_rate": 8.59375e-06,
+      "loss": 0.5545,
+      "step": 110
+    },
+    {
+      "epoch": 0.281195079086116,
+      "grad_norm": 0.9659337459766423,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.5613,
+      "step": 120
+    },
+    {
+      "epoch": 0.281195079086116,
+      "eval_loss": 0.5744733214378357,
+      "eval_runtime": 6.8747,
+      "eval_samples_per_second": 12.073,
+      "eval_steps_per_second": 3.055,
+      "step": 120
+    },
+    {
+      "epoch": 0.30462800234329235,
+      "grad_norm": 0.9238292800857061,
+      "learning_rate": 9.999925371796981e-06,
+      "loss": 0.5535,
+      "step": 130
+    },
+    {
+      "epoch": 0.3280609256004687,
+      "grad_norm": 0.9822222379228975,
+      "learning_rate": 9.997313618597327e-06,
+      "loss": 0.5528,
+      "step": 140
+    },
+    {
+      "epoch": 0.3280609256004687,
+      "eval_loss": 0.5670329332351685,
+      "eval_runtime": 6.861,
+      "eval_samples_per_second": 12.097,
+      "eval_steps_per_second": 3.061,
+      "step": 140
+    },
+    {
+      "epoch": 0.351493848857645,
+      "grad_norm": 1.0326786821314324,
+      "learning_rate": 9.990972682695259e-06,
+      "loss": 0.5413,
+      "step": 150
+    },
+    {
+      "epoch": 0.37492677211482134,
+      "grad_norm": 1.0249998992485643,
+      "learning_rate": 9.980907295934779e-06,
+      "loss": 0.5437,
+      "step": 160
+    },
+    {
+      "epoch": 0.37492677211482134,
+      "eval_loss": 0.5599193572998047,
+      "eval_runtime": 6.8567,
+      "eval_samples_per_second": 12.105,
+      "eval_steps_per_second": 3.063,
+      "step": 160
+    },
+    {
+      "epoch": 0.39835969537199767,
+      "grad_norm": 1.063100555759153,
+      "learning_rate": 9.967124969484698e-06,
+      "loss": 0.5423,
+      "step": 170
+    },
+    {
+      "epoch": 0.421792618629174,
+      "grad_norm": 1.691657845814101,
+      "learning_rate": 9.949635988233529e-06,
+      "loss": 0.5309,
+      "step": 180
+    },
+    {
+      "epoch": 0.421792618629174,
+      "eval_loss": 0.5551030039787292,
+      "eval_runtime": 6.8522,
+      "eval_samples_per_second": 12.113,
+      "eval_steps_per_second": 3.065,
+      "step": 180
+    },
+    {
+      "epoch": 0.44522554188635033,
+      "grad_norm": 0.9865934019961338,
+      "learning_rate": 9.928453403114494e-06,
+      "loss": 0.5387,
+      "step": 190
+    },
+    {
+      "epoch": 0.46865846514352666,
+      "grad_norm": 0.953318930671763,
+      "learning_rate": 9.903593021366454e-06,
+      "loss": 0.5296,
+      "step": 200
+    },
+    {
+      "epoch": 0.46865846514352666,
+      "eval_loss": 0.5467991828918457,
+      "eval_runtime": 6.8469,
+      "eval_samples_per_second": 12.122,
+      "eval_steps_per_second": 3.067,
+      "step": 200
+    },
+    {
+      "epoch": 0.492091388400703,
+      "grad_norm": 0.9596895597138875,
+      "learning_rate": 9.875073394737942e-06,
+      "loss": 0.531,
+      "step": 210
+    },
+    {
+      "epoch": 0.5155243116578794,
+      "grad_norm": 0.978494551368458,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 0.525,
+      "step": 220
+    },
+    {
+      "epoch": 0.5155243116578794,
+      "eval_loss": 0.5445288419723511,
+      "eval_runtime": 6.8538,
+      "eval_samples_per_second": 12.11,
+      "eval_steps_per_second": 3.064,
+      "step": 220
+    },
+    {
+      "epoch": 0.5389572349150556,
+      "grad_norm": 0.9199420171408795,
+      "learning_rate": 9.80714425128022e-06,
+      "loss": 0.5257,
+      "step": 230
+    },
+    {
+      "epoch": 0.562390158172232,
+      "grad_norm": 0.9191286288617249,
+      "learning_rate": 9.767785425723583e-06,
+      "loss": 0.5275,
+      "step": 240
+    },
+    {
+      "epoch": 0.562390158172232,
+      "eval_loss": 0.5388731956481934,
+      "eval_runtime": 6.8481,
+      "eval_samples_per_second": 12.12,
+      "eval_steps_per_second": 3.067,
+      "step": 240
+    },
+    {
+      "epoch": 0.5858230814294083,
+      "grad_norm": 0.8620180370758664,
+      "learning_rate": 9.72486870000389e-06,
+      "loss": 0.5255,
+      "step": 250
+    },
+    {
+      "epoch": 0.6092560046865847,
+      "grad_norm": 0.9694636843087077,
+      "learning_rate": 9.678426100190233e-06,
+      "loss": 0.5237,
+      "step": 260
+    },
+    {
+      "epoch": 0.6092560046865847,
+      "eval_loss": 0.5360087156295776,
+      "eval_runtime": 6.8739,
+      "eval_samples_per_second": 12.075,
+      "eval_steps_per_second": 3.055,
+      "step": 260
+    },
+    {
+      "epoch": 0.632688927943761,
+      "grad_norm": 0.9720308463682571,
+      "learning_rate": 9.62849228349108e-06,
+      "loss": 0.5144,
+      "step": 270
+    },
+    {
+      "epoch": 0.6561218512009374,
+      "grad_norm": 0.8618200334281626,
+      "learning_rate": 9.575104512391782e-06,
+      "loss": 0.5151,
+      "step": 280
+    },
+    {
+      "epoch": 0.6561218512009374,
+      "eval_loss": 0.529883861541748,
+      "eval_runtime": 6.8621,
+      "eval_samples_per_second": 12.095,
+      "eval_steps_per_second": 3.06,
+      "step": 280
+    },
+    {
+      "epoch": 0.6795547744581136,
+      "grad_norm": 0.8328693224294863,
+      "learning_rate": 9.518302626847902e-06,
+      "loss": 0.5116,
+      "step": 290
+    },
+    {
+      "epoch": 0.70298769771529,
+      "grad_norm": 0.9487518588285567,
+      "learning_rate": 9.458129014555153e-06,
+      "loss": 0.5151,
+      "step": 300
+    },
+    {
+      "epoch": 0.70298769771529,
+      "eval_loss": 0.5296659469604492,
+      "eval_runtime": 6.8545,
+      "eval_samples_per_second": 12.109,
+      "eval_steps_per_second": 3.064,
+      "step": 300
+    },
+    {
+      "epoch": 0.7264206209724663,
+      "grad_norm": 0.8035196037537721,
+      "learning_rate": 9.394628579318101e-06,
+      "loss": 0.5161,
+      "step": 310
+    },
+    {
+      "epoch": 0.7498535442296427,
+      "grad_norm": 0.9081989609390617,
+      "learning_rate": 9.327848707541278e-06,
+      "loss": 0.5134,
+      "step": 320
+    },
+    {
+      "epoch": 0.7498535442296427,
+      "eval_loss": 0.5256572365760803,
+      "eval_runtime": 6.8588,
+      "eval_samples_per_second": 12.101,
+      "eval_steps_per_second": 3.062,
+      "step": 320
+    },
+    {
+      "epoch": 0.773286467486819,
+      "grad_norm": 0.8379141500133639,
+      "learning_rate": 9.257839232867655e-06,
+      "loss": 0.5109,
+      "step": 330
+    },
+    {
+      "epoch": 0.7967193907439953,
+      "grad_norm": 0.8521116642129963,
+      "learning_rate": 9.184652398990922e-06,
+      "loss": 0.5055,
+      "step": 340
+    },
+    {
+      "epoch": 0.7967193907439953,
+      "eval_loss": 0.5245722532272339,
+      "eval_runtime": 6.8843,
+      "eval_samples_per_second": 12.056,
+      "eval_steps_per_second": 3.05,
+      "step": 340
+    },
+    {
+      "epoch": 0.8201523140011716,
+      "grad_norm": 0.8488295021912736,
+      "learning_rate": 9.108342820669281e-06,
+      "loss": 0.5019,
+      "step": 350
+    },
+    {
+      "epoch": 0.843585237258348,
+      "grad_norm": 0.8826068981490273,
+      "learning_rate": 9.028967442969867e-06,
+      "loss": 0.5033,
+      "step": 360
+    },
+    {
+      "epoch": 0.843585237258348,
+      "eval_loss": 0.520741879940033,
+      "eval_runtime": 6.8577,
+      "eval_samples_per_second": 12.103,
+      "eval_steps_per_second": 3.062,
+      "step": 360
+    },
+    {
+      "epoch": 0.8670181605155243,
+      "grad_norm": 0.8910334376436055,
+      "learning_rate": 8.946585498774205e-06,
+      "loss": 0.5041,
+      "step": 370
+    },
+    {
+      "epoch": 0.8904510837727007,
+      "grad_norm": 0.8982259489892881,
+      "learning_rate": 8.861258464576414e-06,
+      "loss": 0.5027,
+      "step": 380
+    },
+    {
+      "epoch": 0.8904510837727007,
+      "eval_loss": 0.5193905830383301,
+      "eval_runtime": 6.8577,
+      "eval_samples_per_second": 12.103,
+      "eval_steps_per_second": 3.062,
+      "step": 380
+    },
+    {
+      "epoch": 0.9138840070298769,
+      "grad_norm": 0.8219909336141432,
+      "learning_rate": 8.773050014607143e-06,
+      "loss": 0.5044,
+      "step": 390
+    },
+    {
+      "epoch": 0.9373169302870533,
+      "grad_norm": 0.8891456423396452,
+      "learning_rate": 8.682025973317477e-06,
+      "loss": 0.495,
+      "step": 400
+    },
+    {
+      "epoch": 0.9373169302870533,
+      "eval_loss": 0.5158688426017761,
+      "eval_runtime": 6.8596,
+      "eval_samples_per_second": 12.1,
+      "eval_steps_per_second": 3.061,
+      "step": 400
+    },
+    {
+      "epoch": 0.9607498535442296,
+      "grad_norm": 0.9171436951550399,
+      "learning_rate": 8.588254266258256e-06,
+      "loss": 0.4989,
+      "step": 410
+    },
+    {
+      "epoch": 0.984182776801406,
+      "grad_norm": 1.012773072840449,
+      "learning_rate": 8.491804869391496e-06,
+      "loss": 0.4927,
+      "step": 420
+    },
+    {
+      "epoch": 0.984182776801406,
+      "eval_loss": 0.5127629041671753,
+      "eval_runtime": 6.867,
+      "eval_samples_per_second": 12.087,
+      "eval_steps_per_second": 3.058,
+      "step": 420
+    },
+    {
+      "epoch": 1.0076157000585824,
+      "grad_norm": 0.8457730568193386,
+      "learning_rate": 8.392749756871692e-06,
+      "loss": 0.4767,
+      "step": 430
+    },
+    {
+      "epoch": 1.0310486233157587,
+      "grad_norm": 0.8687230168733169,
+      "learning_rate": 8.291162847336016e-06,
+      "loss": 0.4007,
+      "step": 440
+    },
+    {
+      "epoch": 1.0310486233157587,
+      "eval_loss": 0.5217759609222412,
+      "eval_runtime": 6.8612,
+      "eval_samples_per_second": 12.097,
+      "eval_steps_per_second": 3.061,
+      "step": 440
+    },
+    {
+      "epoch": 1.054481546572935,
+      "grad_norm": 0.8116863071274668,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 0.3936,
+      "step": 450
+    },
+    {
+      "epoch": 1.0779144698301113,
+      "grad_norm": 0.837351977617299,
+      "learning_rate": 8.080698701804054e-06,
+      "loss": 0.3969,
+      "step": 460
+    },
+    {
+      "epoch": 1.0779144698301113,
+      "eval_loss": 0.5214633345603943,
+      "eval_runtime": 6.8716,
+      "eval_samples_per_second": 12.079,
+      "eval_steps_per_second": 3.056,
+      "step": 460
+    },
+    {
+      "epoch": 1.1013473930872877,
+      "grad_norm": 0.8716458213370734,
+      "learning_rate": 7.971978522040558e-06,
+      "loss": 0.3941,
+      "step": 470
+    },
+    {
+      "epoch": 1.124780316344464,
+      "grad_norm": 0.8632857661517701,
+      "learning_rate": 7.861040540525516e-06,
+      "loss": 0.3908,
+      "step": 480
+    },
+    {
+      "epoch": 1.124780316344464,
+      "eval_loss": 0.518416166305542,
+      "eval_runtime": 6.8705,
+      "eval_samples_per_second": 12.081,
+      "eval_steps_per_second": 3.057,
+      "step": 480
+    },
+    {
+      "epoch": 1.1482132396016402,
+      "grad_norm": 0.8128564971451065,
+      "learning_rate": 7.747967543338267e-06,
+      "loss": 0.3881,
+      "step": 490
+    },
+    {
+      "epoch": 1.1716461628588166,
+      "grad_norm": 0.8124913426413789,
+      "learning_rate": 7.632843909786855e-06,
+      "loss": 0.392,
+      "step": 500
+    },
+    {
+      "epoch": 1.1716461628588166,
+      "eval_loss": 0.5162045359611511,
+      "eval_runtime": 6.8548,
+      "eval_samples_per_second": 12.108,
+      "eval_steps_per_second": 3.064,
+      "step": 500
+    },
+    {
+      "epoch": 1.195079086115993,
+      "grad_norm": 0.8291827276231823,
+      "learning_rate": 7.515755549441035e-06,
+      "loss": 0.3932,
+      "step": 510
+    },
+    {
+      "epoch": 1.2185120093731694,
+      "grad_norm": 0.8111013960927249,
+      "learning_rate": 7.396789838023315e-06,
+      "loss": 0.3915,
+      "step": 520
+    },
+    {
+      "epoch": 1.2185120093731694,
+      "eval_loss": 0.5183687806129456,
+      "eval_runtime": 6.8513,
+      "eval_samples_per_second": 12.115,
+      "eval_steps_per_second": 3.065,
+      "step": 520
+    },
+    {
+      "epoch": 1.2419449326303456,
+      "grad_norm": 0.800639602353055,
+      "learning_rate": 7.276035552205937e-06,
+      "loss": 0.3927,
+      "step": 530
+    },
+    {
+      "epoch": 1.265377855887522,
+      "grad_norm": 0.7874134726983582,
+      "learning_rate": 7.153582803362389e-06,
+      "loss": 0.394,
+      "step": 540
+    },
+    {
+      "epoch": 1.265377855887522,
+      "eval_loss": 0.5163713097572327,
+      "eval_runtime": 6.8463,
+      "eval_samples_per_second": 12.123,
+      "eval_steps_per_second": 3.067,
+      "step": 540
+    },
+    {
+      "epoch": 1.2888107791446983,
+      "grad_norm": 0.7958820231310323,
+      "learning_rate": 7.029522970322917e-06,
+      "loss": 0.3905,
+      "step": 550
+    },
+    {
+      "epoch": 1.3122437024018747,
+      "grad_norm": 0.825205844506711,
+      "learning_rate": 6.903948631184226e-06,
+      "loss": 0.387,
+      "step": 560
+    },
+    {
+      "epoch": 1.3122437024018747,
+      "eval_loss": 0.5151952505111694,
+      "eval_runtime": 6.8584,
+      "eval_samples_per_second": 12.102,
+      "eval_steps_per_second": 3.062,
+      "step": 560
+    },
+    {
+      "epoch": 1.335676625659051,
+      "grad_norm": 0.8710831645647001,
+      "learning_rate": 6.7769534942242254e-06,
+      "loss": 0.3951,
+      "step": 570
+    },
+    {
+      "epoch": 1.3591095489162273,
+      "grad_norm": 0.8696018041192264,
+      "learning_rate": 6.648632327973408e-06,
+      "loss": 0.3883,
+      "step": 580
+    },
+    {
+      "epoch": 1.3591095489162273,
+      "eval_loss": 0.5164257287979126,
+      "eval_runtime": 6.8397,
+      "eval_samples_per_second": 12.135,
+      "eval_steps_per_second": 3.07,
+      "step": 580
+    },
+    {
+      "epoch": 1.3825424721734036,
+      "grad_norm": 0.892897577421514,
+      "learning_rate": 6.519080890495018e-06,
+      "loss": 0.3875,
+      "step": 590
+    },
+    {
+      "epoch": 1.40597539543058,
+      "grad_norm": 0.7921096071047794,
+      "learning_rate": 6.388395857926792e-06,
+      "loss": 0.3909,
+      "step": 600
+    },
+    {
+      "epoch": 1.40597539543058,
+      "eval_loss": 0.5130771994590759,
+      "eval_runtime": 6.8687,
+      "eval_samples_per_second": 12.084,
+      "eval_steps_per_second": 3.057,
+      "step": 600
+    },
+    {
+      "epoch": 1.4294083186877562,
+      "grad_norm": 0.8264883945144167,
+      "learning_rate": 6.25667475233761e-06,
+      "loss": 0.391,
+      "step": 610
+    },
+    {
+      "epoch": 1.4528412419449326,
+      "grad_norm": 0.8968652842301085,
+      "learning_rate": 6.124015868952866e-06,
+      "loss": 0.3929,
+      "step": 620
+    },
+    {
+      "epoch": 1.4528412419449326,
+      "eval_loss": 0.5109802484512329,
+      "eval_runtime": 6.8606,
+      "eval_samples_per_second": 12.098,
+      "eval_steps_per_second": 3.061,
+      "step": 620
+    },
+    {
+      "epoch": 1.476274165202109,
+      "grad_norm": 0.8306275748506837,
+      "learning_rate": 5.990518202802891e-06,
+      "loss": 0.3828,
+      "step": 630
+    },
+    {
+      "epoch": 1.4997070884592854,
+      "grad_norm": 0.8240169999467182,
+      "learning_rate": 5.856281374849145e-06,
+      "loss": 0.3851,
+      "step": 640
+    },
+    {
+      "epoch": 1.4997070884592854,
+      "eval_loss": 0.5105913877487183,
+      "eval_runtime": 6.8745,
+      "eval_samples_per_second": 12.074,
+      "eval_steps_per_second": 3.055,
+      "step": 640
+    },
+    {
+      "epoch": 1.5231400117164617,
+      "grad_norm": 0.8306537386986356,
+      "learning_rate": 5.721405557643335e-06,
+      "loss": 0.3961,
+      "step": 650
+    },
+    {
+      "epoch": 1.546572934973638,
+      "grad_norm": 0.810960861463703,
+      "learning_rate": 5.585991400574887e-06,
+      "loss": 0.3886,
+      "step": 660
+    },
+    {
+      "epoch": 1.546572934973638,
+      "eval_loss": 0.5089380741119385,
+      "eval_runtime": 6.8494,
+      "eval_samples_per_second": 12.118,
+      "eval_steps_per_second": 3.066,
+      "step": 660
+    },
+    {
+      "epoch": 1.5700058582308143,
+      "grad_norm": 0.8037169402375282,
+      "learning_rate": 5.450139954762613e-06,
+      "loss": 0.3849,
+      "step": 670
+    },
+    {
+      "epoch": 1.5934387814879907,
+      "grad_norm": 0.7977881960247427,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 0.3881,
+      "step": 680
+    },
+    {
+      "epoch": 1.5934387814879907,
+      "eval_loss": 0.5068591237068176,
+      "eval_runtime": 6.854,
+      "eval_samples_per_second": 12.11,
+      "eval_steps_per_second": 3.064,
+      "step": 680
+    },
+    {
+      "epoch": 1.6168717047451668,
+      "grad_norm": 0.8763739319196168,
+      "learning_rate": 5.177530957336416e-06,
+      "loss": 0.3843,
+      "step": 690
+    },
+    {
+      "epoch": 1.6403046280023434,
+      "grad_norm": 0.8246419787355598,
+      "learning_rate": 5.040976836772716e-06,
+      "loss": 0.3872,
+      "step": 700
+    },
+    {
+      "epoch": 1.6403046280023434,
+      "eval_loss": 0.5053003430366516,
+      "eval_runtime": 6.8707,
+      "eval_samples_per_second": 12.08,
+      "eval_steps_per_second": 3.056,
+      "step": 700
+    },
+    {
+      "epoch": 1.6637375512595196,
+      "grad_norm": 0.8082079535284143,
+      "learning_rate": 4.904392137757763e-06,
+      "loss": 0.3917,
+      "step": 710
+    },
+    {
+      "epoch": 1.687170474516696,
+      "grad_norm": 0.824319156844654,
+      "learning_rate": 4.767878784912633e-06,
+      "loss": 0.3805,
+      "step": 720
+    },
+    {
+      "epoch": 1.687170474516696,
+      "eval_loss": 0.5057860612869263,
+      "eval_runtime": 6.8434,
+      "eval_samples_per_second": 12.129,
+      "eval_steps_per_second": 3.069,
+      "step": 720
+    },
+    {
+      "epoch": 1.7106033977738724,
+      "grad_norm": 0.7794468295076807,
+      "learning_rate": 4.631538649617216e-06,
+      "loss": 0.3853,
+      "step": 730
+    },
+    {
+      "epoch": 1.7340363210310485,
+      "grad_norm": 0.7751509790235215,
+      "learning_rate": 4.495473473989978e-06,
+      "loss": 0.3945,
+      "step": 740
+    },
+    {
+      "epoch": 1.7340363210310485,
+      "eval_loss": 0.5034079551696777,
+      "eval_runtime": 6.8524,
+      "eval_samples_per_second": 12.113,
+      "eval_steps_per_second": 3.065,
+      "step": 740
+    },
+    {
+      "epoch": 1.757469244288225,
+      "grad_norm": 0.7972803167188072,
+      "learning_rate": 4.359784794964177e-06,
+      "loss": 0.3846,
+      "step": 750
+    },
+    {
+      "epoch": 1.7809021675454013,
+      "grad_norm": 0.7752264515722079,
+      "learning_rate": 4.22457386851719e-06,
+      "loss": 0.3849,
+      "step": 760
+    },
+    {
+      "epoch": 1.7809021675454013,
+      "eval_loss": 0.5030991435050964,
+      "eval_runtime": 6.8441,
+      "eval_samples_per_second": 12.127,
+      "eval_steps_per_second": 3.068,
+      "step": 760
+    },
+    {
+      "epoch": 1.8043350908025775,
+      "grad_norm": 0.787198802328244,
+      "learning_rate": 4.089941594109526e-06,
+      "loss": 0.3911,
+      "step": 770
+    },
+    {
+      "epoch": 1.827768014059754,
+      "grad_norm": 0.770272193314466,
+      "learning_rate": 3.955988439389848e-06,
+      "loss": 0.3816,
+      "step": 780
+    },
+    {
+      "epoch": 1.827768014059754,
+      "eval_loss": 0.5016986131668091,
+      "eval_runtime": 6.8514,
+      "eval_samples_per_second": 12.114,
+      "eval_steps_per_second": 3.065,
+      "step": 780
+    },
+    {
+      "epoch": 1.8512009373169303,
+      "grad_norm": 0.8058458013189954,
+      "learning_rate": 3.822814365222262e-06,
+      "loss": 0.3798,
+      "step": 790
+    },
+    {
+      "epoch": 1.8746338605741066,
+      "grad_norm": 0.7983222377047167,
+      "learning_rate": 3.6905187510917637e-06,
+      "loss": 0.3761,
+      "step": 800
+    },
+    {
+      "epoch": 1.8746338605741066,
+      "eval_loss": 0.5020421743392944,
+      "eval_runtime": 6.8752,
+      "eval_samples_per_second": 12.072,
+      "eval_steps_per_second": 3.054,
+      "step": 800
+    },
+    {
+      "epoch": 1.898066783831283,
+      "grad_norm": 0.770513769734169,
+      "learning_rate": 3.559200320943558e-06,
+      "loss": 0.387,
+      "step": 810
+    },
+    {
+      "epoch": 1.9214997070884592,
+      "grad_norm": 0.7954439749067661,
+      "learning_rate": 3.428957069511529e-06,
+      "loss": 0.3833,
+      "step": 820
+    },
+    {
+      "epoch": 1.9214997070884592,
+      "eval_loss": 0.5001519918441772,
+      "eval_runtime": 6.8592,
+      "eval_samples_per_second": 12.101,
+      "eval_steps_per_second": 3.062,
+      "step": 820
+    },
+    {
+      "epoch": 1.9449326303456356,
+      "grad_norm": 0.8598513804397304,
+      "learning_rate": 3.299886189190915e-06,
+      "loss": 0.3821,
+      "step": 830
+    },
+    {
+      "epoch": 1.968365553602812,
+      "grad_norm": 0.8059028573927589,
+      "learning_rate": 3.1720839975096974e-06,
+      "loss": 0.3901,
+      "step": 840
+    },
+    {
+      "epoch": 1.968365553602812,
+      "eval_loss": 0.49775850772857666,
+      "eval_runtime": 6.854,
+      "eval_samples_per_second": 12.11,
+      "eval_steps_per_second": 3.064,
+      "step": 840
+    },
+    {
+      "epoch": 1.9917984768599881,
+      "grad_norm": 0.7755185376536994,
+      "learning_rate": 3.045645865252842e-06,
+      "loss": 0.3821,
+      "step": 850
+    },
+    {
+      "epoch": 2.0152314001171647,
+      "grad_norm": 0.7446976776165791,
+      "learning_rate": 2.920666145293063e-06,
+      "loss": 0.3308,
+      "step": 860
+    },
+    {
+      "epoch": 2.0152314001171647,
+      "eval_loss": 0.5402255058288574,
+      "eval_runtime": 6.8591,
+      "eval_samples_per_second": 12.101,
+      "eval_steps_per_second": 3.062,
+      "step": 860
+    },
+    {
+      "epoch": 2.038664323374341,
+      "grad_norm": 0.8019698063933417,
+      "learning_rate": 2.7972381021811516e-06,
+      "loss": 0.2848,
+      "step": 870
+    },
+    {
+      "epoch": 2.0620972466315175,
+      "grad_norm": 0.7857469076146663,
+      "learning_rate": 2.6754538425484916e-06,
+      "loss": 0.2839,
+      "step": 880
+    },
+    {
+      "epoch": 2.0620972466315175,
+      "eval_loss": 0.5463818907737732,
+      "eval_runtime": 6.8434,
+      "eval_samples_per_second": 12.128,
+      "eval_steps_per_second": 3.069,
+      "step": 880
+    },
+    {
+      "epoch": 2.0855301698886937,
+      "grad_norm": 0.7854881029413089,
+      "learning_rate": 2.555404246373629e-06,
+      "loss": 0.2823,
+      "step": 890
+    },
+    {
+      "epoch": 2.10896309314587,
+      "grad_norm": 0.7550663193272501,
+      "learning_rate": 2.437178899164232e-06,
+      "loss": 0.2758,
+      "step": 900
+    },
+    {
+      "epoch": 2.10896309314587,
+      "eval_loss": 0.5424033999443054,
+      "eval_runtime": 6.8494,
+      "eval_samples_per_second": 12.118,
+      "eval_steps_per_second": 3.066,
+      "step": 900
+    },
+    {
+      "epoch": 2.1323960164030464,
+      "grad_norm": 0.7969738859168018,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.2781,
+      "step": 910
+    },
+    {
+      "epoch": 2.1558289396602226,
+      "grad_norm": 0.8499713790472351,
+      "learning_rate": 2.2065524212215744e-06,
+      "loss": 0.2791,
+      "step": 920
+    },
+    {
+      "epoch": 2.1558289396602226,
+      "eval_loss": 0.539867103099823,
+      "eval_runtime": 6.8724,
+      "eval_samples_per_second": 12.077,
+      "eval_steps_per_second": 3.056,
+      "step": 920
+    },
+    {
+      "epoch": 2.1792618629173988,
+      "grad_norm": 0.8183505012542354,
+      "learning_rate": 2.094323392609158e-06,
+      "loss": 0.2829,
+      "step": 930
+    },
+    {
+      "epoch": 2.2026947861745754,
+      "grad_norm": 0.7706018482843252,
+      "learning_rate": 1.9842626887748284e-06,
+      "loss": 0.2806,
+      "step": 940
+    },
+    {
+      "epoch": 2.2026947861745754,
+      "eval_loss": 0.5386549830436707,
+      "eval_runtime": 6.8669,
+      "eval_samples_per_second": 12.087,
+      "eval_steps_per_second": 3.058,
+      "step": 940
+    },
+    {
+      "epoch": 2.2261277094317515,
+      "grad_norm": 0.7698613159139776,
+      "learning_rate": 1.8764524411404494e-06,
+      "loss": 0.2789,
+      "step": 950
+    },
+    {
+      "epoch": 2.249560632688928,
+      "grad_norm": 0.7721254751332236,
+      "learning_rate": 1.7709731017531156e-06,
+      "loss": 0.2767,
+      "step": 960
+    },
+    {
+      "epoch": 2.249560632688928,
+      "eval_loss": 0.5390830039978027,
+      "eval_runtime": 6.8539,
+      "eval_samples_per_second": 12.11,
+      "eval_steps_per_second": 3.064,
+      "step": 960
+    },
+    {
+      "epoch": 2.2729935559461043,
+      "grad_norm": 0.7787204109197058,
+      "learning_rate": 1.6679033832488433e-06,
+      "loss": 0.2822,
+      "step": 970
+    },
+    {
+      "epoch": 2.2964264792032805,
+      "grad_norm": 0.7551294204947154,
+      "learning_rate": 1.5673202001142396e-06,
+      "loss": 0.2812,
+      "step": 980
+    },
+    {
+      "epoch": 2.2964264792032805,
+      "eval_loss": 0.5422590970993042,
+      "eval_runtime": 6.8622,
+      "eval_samples_per_second": 12.095,
+      "eval_steps_per_second": 3.06,
+      "step": 980
+    },
+    {
+      "epoch": 2.319859402460457,
+      "grad_norm": 0.7971177799209123,
+      "learning_rate": 1.4692986112900315e-06,
+      "loss": 0.2772,
+      "step": 990
+    },
+    {
+      "epoch": 2.3432923257176332,
+      "grad_norm": 0.7450176462899643,
+      "learning_rate": 1.3739117641592752e-06,
+      "loss": 0.2834,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3432923257176332,
+      "eval_loss": 0.5395219922065735,
+      "eval_runtime": 6.8503,
+      "eval_samples_per_second": 12.116,
+      "eval_steps_per_second": 3.066,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3667252489748094,
+      "grad_norm": 0.7786111586051575,
+      "learning_rate": 1.281230839962036e-06,
+      "loss": 0.2791,
+      "step": 1010
+    },
+    {
+      "epoch": 2.390158172231986,
+      "grad_norm": 0.7892304948420056,
+      "learning_rate": 1.1913250006772714e-06,
+      "loss": 0.2816,
+      "step": 1020
+    },
+    {
+      "epoch": 2.390158172231986,
+      "eval_loss": 0.5420347452163696,
+      "eval_runtime": 6.859,
+      "eval_samples_per_second": 12.101,
+      "eval_steps_per_second": 3.062,
+      "step": 1020
+    },
+    {
+      "epoch": 2.413591095489162,
+      "grad_norm": 0.7497724325591187,
+      "learning_rate": 1.1042613374115896e-06,
+      "loss": 0.2783,
+      "step": 1030
+    },
+    {
+      "epoch": 2.437024018746339,
+      "grad_norm": 0.7554247942043497,
+      "learning_rate": 1.0201048203333281e-06,
+      "loss": 0.2762,
+      "step": 1040
+    },
+    {
+      "epoch": 2.437024018746339,
+      "eval_loss": 0.5414301156997681,
+      "eval_runtime": 6.8613,
+      "eval_samples_per_second": 12.097,
+      "eval_steps_per_second": 3.061,
+      "step": 1040
+    },
+    {
+      "epoch": 2.460456942003515,
+      "grad_norm": 0.7700211768619959,
+      "learning_rate": 9.389182501893967e-07,
+      "loss": 0.285,
+      "step": 1050
+    },
+    {
+      "epoch": 2.483889865260691,
+      "grad_norm": 0.7872827371301152,
+      "learning_rate": 8.607622114410014e-07,
+      "loss": 0.2756,
+      "step": 1060
+    },
+    {
+      "epoch": 2.483889865260691,
+      "eval_loss": 0.5417543053627014,
+      "eval_runtime": 6.8646,
+      "eval_samples_per_second": 12.091,
+      "eval_steps_per_second": 3.059,
+      "step": 1060
+    },
+    {
+      "epoch": 2.5073227885178677,
+      "grad_norm": 0.7540422712115158,
+      "learning_rate": 7.85695027053241e-07,
+      "loss": 0.2799,
+      "step": 1070
+    },
+    {
+      "epoch": 2.530755711775044,
+      "grad_norm": 0.7730676814596346,
+      "learning_rate": 7.137727149723417e-07,
+      "loss": 0.2763,
+      "step": 1080
+    },
+    {
+      "epoch": 2.530755711775044,
+      "eval_loss": 0.5400538444519043,
+      "eval_runtime": 6.8581,
+      "eval_samples_per_second": 12.102,
+      "eval_steps_per_second": 3.062,
+      "step": 1080
+    },
+    {
+      "epoch": 2.5541886350322205,
+      "grad_norm": 0.7712875898736462,
+      "learning_rate": 6.450489463229493e-07,
+      "loss": 0.2774,
+      "step": 1090
+    },
+    {
+      "epoch": 2.5776215582893967,
+      "grad_norm": 0.7745963503844014,
+      "learning_rate": 5.79575005356735e-07,
+      "loss": 0.2804,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5776215582893967,
+      "eval_loss": 0.5401105880737305,
+      "eval_runtime": 6.8424,
+      "eval_samples_per_second": 12.13,
+      "eval_steps_per_second": 3.069,
+      "step": 1100
+    },
+    {
+      "epoch": 2.601054481546573,
+      "grad_norm": 0.7504131613402398,
+      "learning_rate": 5.173997511821599e-07,
+      "loss": 0.2789,
+      "step": 1110
+    },
+    {
+      "epoch": 2.6244874048037494,
+      "grad_norm": 0.8168437409441466,
+      "learning_rate": 4.5856958130398146e-07,
+      "loss": 0.2818,
+      "step": 1120
+    },
+    {
+      "epoch": 2.6244874048037494,
+      "eval_loss": 0.5402423739433289,
+      "eval_runtime": 6.9174,
+      "eval_samples_per_second": 11.999,
+      "eval_steps_per_second": 3.036,
+      "step": 1120
+    },
+    {
+      "epoch": 2.6479203280609256,
+      "grad_norm": 0.7542096198684458,
+      "learning_rate": 4.031283969996919e-07,
+      "loss": 0.2816,
+      "step": 1130
+    },
+    {
+      "epoch": 2.671353251318102,
+      "grad_norm": 0.7623696532356496,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.2768,
+      "step": 1140
+    },
+    {
+      "epoch": 2.671353251318102,
+      "eval_loss": 0.5399875044822693,
+      "eval_runtime": 6.8446,
+      "eval_samples_per_second": 12.126,
+      "eval_steps_per_second": 3.068,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6947861745752784,
+      "grad_norm": 0.7398703147625436,
+      "learning_rate": 3.0257591440899235e-07,
+      "loss": 0.2815,
+      "step": 1150
+    },
+    {
+      "epoch": 2.7182190978324545,
+      "grad_norm": 0.7747620467860837,
+      "learning_rate": 2.5753965215341347e-07,
+      "loss": 0.2801,
+      "step": 1160
+    },
+    {
+      "epoch": 2.7182190978324545,
+      "eval_loss": 0.5402843952178955,
+      "eval_runtime": 6.854,
+      "eval_samples_per_second": 12.11,
+      "eval_steps_per_second": 3.064,
+      "step": 1160
+    },
+    {
+      "epoch": 2.7416520210896307,
+      "grad_norm": 0.7679336009171306,
+      "learning_rate": 2.1604239153869e-07,
+      "loss": 0.2778,
+      "step": 1170
+    },
+    {
+      "epoch": 2.7650849443468073,
+      "grad_norm": 0.7664516899549186,
+      "learning_rate": 1.7811509937584958e-07,
+      "loss": 0.2762,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7650849443468073,
+      "eval_loss": 0.5398624539375305,
+      "eval_runtime": 6.8692,
+      "eval_samples_per_second": 12.083,
+      "eval_steps_per_second": 3.057,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7885178676039835,
+      "grad_norm": 0.762559792665266,
+      "learning_rate": 1.4378607843167635e-07,
+      "loss": 0.2813,
+      "step": 1190
+    },
+    {
+      "epoch": 2.81195079086116,
+      "grad_norm": 0.8002177486857107,
+      "learning_rate": 1.1308094630811784e-07,
+      "loss": 0.2778,
+      "step": 1200
+    },
+    {
+      "epoch": 2.81195079086116,
+      "eval_loss": 0.5403096675872803,
+      "eval_runtime": 6.8495,
+      "eval_samples_per_second": 12.118,
+      "eval_steps_per_second": 3.066,
+      "step": 1200
+    },
+    {
+      "epoch": 2.8353837141183362,
+      "grad_norm": 0.7570680096628735,
+      "learning_rate": 8.602261632547626e-08,
+      "loss": 0.2765,
+      "step": 1210
+    },
+    {
+      "epoch": 2.8588166373755124,
+      "grad_norm": 0.7760197671672417,
+      "learning_rate": 6.263128042362676e-08,
+      "loss": 0.2803,
+      "step": 1220
+    },
+    {
+      "epoch": 2.8588166373755124,
+      "eval_loss": 0.5402877926826477,
+      "eval_runtime": 6.8585,
+      "eval_samples_per_second": 12.102,
+      "eval_steps_per_second": 3.062,
+      "step": 1220
+    },
+    {
+      "epoch": 2.882249560632689,
+      "grad_norm": 0.7516124827349755,
+      "learning_rate": 4.292439409403826e-08,
+      "loss": 0.2788,
+      "step": 1230
+    },
+    {
+      "epoch": 2.905682483889865,
+      "grad_norm": 0.7881049831837009,
+      "learning_rate": 2.6916663353828142e-08,
+      "loss": 0.2796,
+      "step": 1240
+    },
+    {
+      "epoch": 2.905682483889865,
+      "eval_loss": 0.5403096079826355,
+      "eval_runtime": 6.877,
+      "eval_samples_per_second": 12.069,
+      "eval_steps_per_second": 3.054,
+      "step": 1240
+    },
+    {
+      "epoch": 2.9291154071470418,
+      "grad_norm": 0.7610329760613732,
+      "learning_rate": 1.4620033771582942e-08,
+      "loss": 0.2785,
+      "step": 1250
+    },
+    {
+      "epoch": 2.952548330404218,
+      "grad_norm": 0.7470432261004997,
+      "learning_rate": 6.0436815531284e-09,
+      "loss": 0.2731,
+      "step": 1260
+    },
+    {
+      "epoch": 2.952548330404218,
+      "eval_loss": 0.5395792722702026,
+      "eval_runtime": 6.8492,
+      "eval_samples_per_second": 12.118,
+      "eval_steps_per_second": 3.066,
+      "step": 1260
+    },
+    {
+      "epoch": 2.975981253661394,
+      "grad_norm": 0.753761854450565,
+      "learning_rate": 1.1940066938981309e-09,
+      "loss": 0.275,
+      "step": 1270
+    },
+    {
+      "epoch": 2.9947275922671355,
+      "step": 1278,
+      "total_flos": 457793516601344.0,
+      "train_loss": 0.4100710519229489,
+      "train_runtime": 44735.0493,
+      "train_samples_per_second": 2.747,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1278,
+  "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": 457793516601344.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

scenario_ratio_7B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a1e0f18c51026803005827722fc6dc1cfde8004d2d24ffd9e7c30897b72e26
+size 7288