m

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
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.9982507288629737,
+    "eval_loss": 0.5850064158439636,
+    "eval_runtime": 50.5058,
+    "eval_samples": 280,
+    "eval_samples_per_second": 5.544,
+    "eval_steps_per_second": 0.693,
+    "total_flos": 21976597397504.0,
+    "train_loss": 0.7188172000590886,
+    "train_runtime": 7093.9262,
+    "train_samples": 13720,
+    "train_samples_per_second": 1.934,
+    "train_steps_per_second": 0.06
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/data/user_data/wentaos/Huggingface_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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9982507288629737,
+    "eval_loss": 0.5850064158439636,
+    "eval_runtime": 50.5058,
+    "eval_samples": 280,
+    "eval_samples_per_second": 5.544,
+    "eval_steps_per_second": 0.693
+}

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": "4.43.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe826c26f7750257e4744559a0e5534e34663efc79fa5c23edf522156d87e388
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd00505d5f2b38efe1f82d13e06f28922bc97d307d29fa7142ba22e72feab6
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62009b66d674798fe4d8b3336e6a7aca68eecd2d5941e14001cb2a61fff8688e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e9b39f55729d0dfc2303efe18a6aea22f5e131bc45be89ec6fc01d8416e57c
+size 1089994880

model.safetensors.index.json

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

runs/Apr05_05-21-12_babel-14-25/events.out.tfevents.1743844932.babel-14-25.160784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6047f355b17ba97779541321b707d8684354546bcfab00f30d4134a83a029daf
+size 24297

runs/Apr05_05-21-12_babel-14-25/events.out.tfevents.1743852128.babel-14-25.160784.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d82bbe9d4c3eb2322ad1792a39f4297a30bf7201ee3c893e801cc5e3216a85
+size 359

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9982507288629737,
+    "total_flos": 21976597397504.0,
+    "train_loss": 0.7188172000590886,
+    "train_runtime": 7093.9262,
+    "train_samples": 13720,
+    "train_samples_per_second": 1.934,
+    "train_steps_per_second": 0.06
+}

trainer_state.json

@@ -0,0 +1,645 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9982507288629737,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011661807580174927,
+      "grad_norm": 26.553807910799254,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 2.8748,
+      "step": 5
+    },
+    {
+      "epoch": 0.023323615160349854,
+      "grad_norm": 11.462149898558295,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 2.3021,
+      "step": 10
+    },
+    {
+      "epoch": 0.03498542274052478,
+      "grad_norm": 8.969332921051663,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 1.4728,
+      "step": 15
+    },
+    {
+      "epoch": 0.04664723032069971,
+      "grad_norm": 1.911516788684923,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 1.008,
+      "step": 20
+    },
+    {
+      "epoch": 0.05830903790087463,
+      "grad_norm": 6.103637733211157,
+      "learning_rate": 1.1627906976744187e-05,
+      "loss": 0.9035,
+      "step": 25
+    },
+    {
+      "epoch": 0.06997084548104957,
+      "grad_norm": 1.4790431060087394,
+      "learning_rate": 1.3953488372093025e-05,
+      "loss": 0.8642,
+      "step": 30
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 1.6320397546760788,
+      "learning_rate": 1.6279069767441862e-05,
+      "loss": 0.8257,
+      "step": 35
+    },
+    {
+      "epoch": 0.09329446064139942,
+      "grad_norm": 1.5592567483272015,
+      "learning_rate": 1.86046511627907e-05,
+      "loss": 0.8176,
+      "step": 40
+    },
+    {
+      "epoch": 0.10495626822157435,
+      "grad_norm": 1.3951663860271262,
+      "learning_rate": 1.9998668323785298e-05,
+      "loss": 0.7741,
+      "step": 45
+    },
+    {
+      "epoch": 0.11661807580174927,
+      "grad_norm": 1.4635616498654132,
+      "learning_rate": 1.9983691039261358e-05,
+      "loss": 0.7657,
+      "step": 50
+    },
+    {
+      "epoch": 0.1282798833819242,
+      "grad_norm": 1.3897367328931463,
+      "learning_rate": 1.995209688628471e-05,
+      "loss": 0.764,
+      "step": 55
+    },
+    {
+      "epoch": 0.13994169096209913,
+      "grad_norm": 1.4677519579642233,
+      "learning_rate": 1.9903938450204972e-05,
+      "loss": 0.7532,
+      "step": 60
+    },
+    {
+      "epoch": 0.15160349854227406,
+      "grad_norm": 1.3525843889582088,
+      "learning_rate": 1.98392958859863e-05,
+      "loss": 0.7677,
+      "step": 65
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 1.2810082328753933,
+      "learning_rate": 1.97582767847973e-05,
+      "loss": 0.7866,
+      "step": 70
+    },
+    {
+      "epoch": 0.1749271137026239,
+      "grad_norm": 1.410365708483155,
+      "learning_rate": 1.9661015994936204e-05,
+      "loss": 0.7319,
+      "step": 75
+    },
+    {
+      "epoch": 0.18658892128279883,
+      "grad_norm": 1.338394460274712,
+      "learning_rate": 1.9547675397389144e-05,
+      "loss": 0.7557,
+      "step": 80
+    },
+    {
+      "epoch": 0.19825072886297376,
+      "grad_norm": 1.261244065429889,
+      "learning_rate": 1.941844363639525e-05,
+      "loss": 0.7175,
+      "step": 85
+    },
+    {
+      "epoch": 0.2099125364431487,
+      "grad_norm": 1.215164653032661,
+      "learning_rate": 1.927353580546692e-05,
+      "loss": 0.7294,
+      "step": 90
+    },
+    {
+      "epoch": 0.22157434402332363,
+      "grad_norm": 1.2443591542748973,
+      "learning_rate": 1.91131930893879e-05,
+      "loss": 0.7206,
+      "step": 95
+    },
+    {
+      "epoch": 0.23323615160349853,
+      "grad_norm": 1.2086200909117264,
+      "learning_rate": 1.8937682362785025e-05,
+      "loss": 0.6945,
+      "step": 100
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 1.213051298160692,
+      "learning_rate": 1.8747295745941705e-05,
+      "loss": 0.7326,
+      "step": 105
+    },
+    {
+      "epoch": 0.2565597667638484,
+      "grad_norm": 1.137971799158331,
+      "learning_rate": 1.8542350118592585e-05,
+      "loss": 0.6812,
+      "step": 110
+    },
+    {
+      "epoch": 0.26822157434402333,
+      "grad_norm": 1.1585761159361583,
+      "learning_rate": 1.8323186592508474e-05,
+      "loss": 0.6969,
+      "step": 115
+    },
+    {
+      "epoch": 0.27988338192419826,
+      "grad_norm": 1.1515560595866825,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.7011,
+      "step": 120
+    },
+    {
+      "epoch": 0.2915451895043732,
+      "grad_norm": 1.0997734319206522,
+      "learning_rate": 1.7843688005531227e-05,
+      "loss": 0.6838,
+      "step": 125
+    },
+    {
+      "epoch": 0.3032069970845481,
+      "grad_norm": 1.2764056795227468,
+      "learning_rate": 1.75841510227148e-05,
+      "loss": 0.7043,
+      "step": 130
+    },
+    {
+      "epoch": 0.31486880466472306,
+      "grad_norm": 1.0377127791698006,
+      "learning_rate": 1.7311990968994598e-05,
+      "loss": 0.6669,
+      "step": 135
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 1.1053908039020601,
+      "learning_rate": 1.7027660827920798e-05,
+      "loss": 0.6718,
+      "step": 140
+    },
+    {
+      "epoch": 0.33819241982507287,
+      "grad_norm": 1.1551534904797163,
+      "learning_rate": 1.6731633838952905e-05,
+      "loss": 0.6482,
+      "step": 145
+    },
+    {
+      "epoch": 0.3498542274052478,
+      "grad_norm": 1.034352399420296,
+      "learning_rate": 1.6424402709799404e-05,
+      "loss": 0.638,
+      "step": 150
+    },
+    {
+      "epoch": 0.36151603498542273,
+      "grad_norm": 1.1059243078762329,
+      "learning_rate": 1.6106478796354382e-05,
+      "loss": 0.6584,
+      "step": 155
+    },
+    {
+      "epoch": 0.37317784256559766,
+      "grad_norm": 1.095922771947225,
+      "learning_rate": 1.577839125159613e-05,
+      "loss": 0.6764,
+      "step": 160
+    },
+    {
+      "epoch": 0.3848396501457726,
+      "grad_norm": 1.0466369154137758,
+      "learning_rate": 1.5440686144864207e-05,
+      "loss": 0.6636,
+      "step": 165
+    },
+    {
+      "epoch": 0.3965014577259475,
+      "grad_norm": 1.0771241734155246,
+      "learning_rate": 1.5093925552980934e-05,
+      "loss": 0.6294,
+      "step": 170
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 1.0682948938211811,
+      "learning_rate": 1.4738686624729987e-05,
+      "loss": 0.7022,
+      "step": 175
+    },
+    {
+      "epoch": 0.4198250728862974,
+      "grad_norm": 1.1643012419599077,
+      "learning_rate": 1.4375560620249209e-05,
+      "loss": 0.671,
+      "step": 180
+    },
+    {
+      "epoch": 0.4314868804664723,
+      "grad_norm": 1.0755879990816233,
+      "learning_rate": 1.400515192693645e-05,
+      "loss": 0.6511,
+      "step": 185
+    },
+    {
+      "epoch": 0.44314868804664725,
+      "grad_norm": 1.085934296396749,
+      "learning_rate": 1.362807705350641e-05,
+      "loss": 0.6539,
+      "step": 190
+    },
+    {
+      "epoch": 0.45481049562682213,
+      "grad_norm": 1.1260377838932638,
+      "learning_rate": 1.3244963603872707e-05,
+      "loss": 0.6797,
+      "step": 195
+    },
+    {
+      "epoch": 0.46647230320699706,
+      "grad_norm": 1.0915272500557975,
+      "learning_rate": 1.285644923256311e-05,
+      "loss": 0.6193,
+      "step": 200
+    },
+    {
+      "epoch": 0.478134110787172,
+      "grad_norm": 1.154696911676013,
+      "learning_rate": 1.24631805834065e-05,
+      "loss": 0.6511,
+      "step": 205
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.9929399462013461,
+      "learning_rate": 1.2065812213258051e-05,
+      "loss": 0.6545,
+      "step": 210
+    },
+    {
+      "epoch": 0.5014577259475219,
+      "grad_norm": 0.9894872780096761,
+      "learning_rate": 1.1665005502553912e-05,
+      "loss": 0.6284,
+      "step": 215
+    },
+    {
+      "epoch": 0.5131195335276968,
+      "grad_norm": 0.96208327378256,
+      "learning_rate": 1.126142755450878e-05,
+      "loss": 0.6575,
+      "step": 220
+    },
+    {
+      "epoch": 0.5247813411078717,
+      "grad_norm": 1.1452854935261283,
+      "learning_rate": 1.08557500847884e-05,
+      "loss": 0.6303,
+      "step": 225
+    },
+    {
+      "epoch": 0.5364431486880467,
+      "grad_norm": 1.0957404862495375,
+      "learning_rate": 1.044864830350515e-05,
+      "loss": 0.6735,
+      "step": 230
+    },
+    {
+      "epoch": 0.5481049562682215,
+      "grad_norm": 1.093675863371594,
+      "learning_rate": 1.0040799791397444e-05,
+      "loss": 0.635,
+      "step": 235
+    },
+    {
+      "epoch": 0.5597667638483965,
+      "grad_norm": 1.0282574359077061,
+      "learning_rate": 9.632883372063458e-06,
+      "loss": 0.6605,
+      "step": 240
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 1.0467764161760484,
+      "learning_rate": 9.225577982126234e-06,
+      "loss": 0.603,
+      "step": 245
+    },
+    {
+      "epoch": 0.5830903790087464,
+      "grad_norm": 1.045793488921542,
+      "learning_rate": 8.819561541210698e-06,
+      "loss": 0.6462,
+      "step": 250
+    },
+    {
+      "epoch": 0.5947521865889213,
+      "grad_norm": 1.09312551012188,
+      "learning_rate": 8.415509823613332e-06,
+      "loss": 0.613,
+      "step": 255
+    },
+    {
+      "epoch": 0.6064139941690962,
+      "grad_norm": 1.0469491212049562,
+      "learning_rate": 8.014095333542548e-06,
+      "loss": 0.5981,
+      "step": 260
+    },
+    {
+      "epoch": 0.6180758017492711,
+      "grad_norm": 1.119981963772929,
+      "learning_rate": 7.615986185801807e-06,
+      "loss": 0.6576,
+      "step": 265
+    },
+    {
+      "epoch": 0.6297376093294461,
+      "grad_norm": 1.0388608369041863,
+      "learning_rate": 7.221844993778464e-06,
+      "loss": 0.635,
+      "step": 270
+    },
+    {
+      "epoch": 0.641399416909621,
+      "grad_norm": 1.050724550953437,
+      "learning_rate": 6.832327766589177e-06,
+      "loss": 0.6432,
+      "step": 275
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 1.054149353336804,
+      "learning_rate": 6.4480828172174714e-06,
+      "loss": 0.5894,
+      "step": 280
+    },
+    {
+      "epoch": 0.6647230320699709,
+      "grad_norm": 1.1070920843455114,
+      "learning_rate": 6.069749683460765e-06,
+      "loss": 0.6227,
+      "step": 285
+    },
+    {
+      "epoch": 0.6763848396501457,
+      "grad_norm": 1.0893681833824727,
+      "learning_rate": 5.6979580634828125e-06,
+      "loss": 0.6112,
+      "step": 290
+    },
+    {
+      "epoch": 0.6880466472303207,
+      "grad_norm": 1.0859059130677133,
+      "learning_rate": 5.333326767743263e-06,
+      "loss": 0.5984,
+      "step": 295
+    },
+    {
+      "epoch": 0.6997084548104956,
+      "grad_norm": 1.0697474803677252,
+      "learning_rate": 4.976462689048718e-06,
+      "loss": 0.6488,
+      "step": 300
+    },
+    {
+      "epoch": 0.7113702623906706,
+      "grad_norm": 1.052526565910687,
+      "learning_rate": 4.6279597924395434e-06,
+      "loss": 0.6115,
+      "step": 305
+    },
+    {
+      "epoch": 0.7230320699708455,
+      "grad_norm": 0.9878751278043086,
+      "learning_rate": 4.2883981265936884e-06,
+      "loss": 0.5879,
+      "step": 310
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 1.059931660103588,
+      "learning_rate": 3.958342858392893e-06,
+      "loss": 0.6543,
+      "step": 315
+    },
+    {
+      "epoch": 0.7463556851311953,
+      "grad_norm": 1.0586083735874494,
+      "learning_rate": 3.6383433322582028e-06,
+      "loss": 0.6271,
+      "step": 320
+    },
+    {
+      "epoch": 0.7580174927113703,
+      "grad_norm": 0.975773551141294,
+      "learning_rate": 3.3289321558203767e-06,
+      "loss": 0.5902,
+      "step": 325
+    },
+    {
+      "epoch": 0.7696793002915452,
+      "grad_norm": 0.9876800637973334,
+      "learning_rate": 3.0306243134470668e-06,
+      "loss": 0.596,
+      "step": 330
+    },
+    {
+      "epoch": 0.7813411078717201,
+      "grad_norm": 1.0515614916924696,
+      "learning_rate": 2.7439163091021525e-06,
+      "loss": 0.6302,
+      "step": 335
+    },
+    {
+      "epoch": 0.793002915451895,
+      "grad_norm": 1.0474370957948071,
+      "learning_rate": 2.469285339963892e-06,
+      "loss": 0.6528,
+      "step": 340
+    },
+    {
+      "epoch": 0.8046647230320699,
+      "grad_norm": 0.9264240929000849,
+      "learning_rate": 2.207188502177313e-06,
+      "loss": 0.6451,
+      "step": 345
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.949110672628745,
+      "learning_rate": 1.958062030062795e-06,
+      "loss": 0.5829,
+      "step": 350
+    },
+    {
+      "epoch": 0.8279883381924198,
+      "grad_norm": 1.0405418200779821,
+      "learning_rate": 1.722320570047089e-06,
+      "loss": 0.5753,
+      "step": 355
+    },
+    {
+      "epoch": 0.8396501457725948,
+      "grad_norm": 1.0819407655076494,
+      "learning_rate": 1.500356490525261e-06,
+      "loss": 0.5827,
+      "step": 360
+    },
+    {
+      "epoch": 0.8513119533527697,
+      "grad_norm": 1.0138846350573034,
+      "learning_rate": 1.2925392288022299e-06,
+      "loss": 0.5756,
+      "step": 365
+    },
+    {
+      "epoch": 0.8629737609329446,
+      "grad_norm": 1.0532845992055002,
+      "learning_rate": 1.099214676200816e-06,
+      "loss": 0.5825,
+      "step": 370
+    },
+    {
+      "epoch": 0.8746355685131195,
+      "grad_norm": 1.1028582402610156,
+      "learning_rate": 9.207046023597866e-07,
+      "loss": 0.6418,
+      "step": 375
+    },
+    {
+      "epoch": 0.8862973760932945,
+      "grad_norm": 0.9947622550770129,
+      "learning_rate": 7.573061196800414e-07,
+      "loss": 0.5721,
+      "step": 380
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 1.0958725426754459,
+      "learning_rate": 6.092911888103404e-07,
+      "loss": 0.6572,
+      "step": 385
+    },
+    {
+      "epoch": 0.9096209912536443,
+      "grad_norm": 1.0469141740178454,
+      "learning_rate": 4.769061659956464e-07,
+      "loss": 0.6094,
+      "step": 390
+    },
+    {
+      "epoch": 0.9212827988338192,
+      "grad_norm": 0.952138107523841,
+      "learning_rate": 3.603713930414676e-07,
+      "loss": 0.5784,
+      "step": 395
+    },
+    {
+      "epoch": 0.9329446064139941,
+      "grad_norm": 0.9484948053834679,
+      "learning_rate": 2.5988083057666534e-07,
+      "loss": 0.5697,
+      "step": 400
+    },
+    {
+      "epoch": 0.9446064139941691,
+      "grad_norm": 0.9890722384698073,
+      "learning_rate": 1.7560173522513268e-07,
+      "loss": 0.5972,
+      "step": 405
+    },
+    {
+      "epoch": 0.956268221574344,
+      "grad_norm": 0.9895097594935042,
+      "learning_rate": 1.0767438122364914e-07,
+      "loss": 0.5693,
+      "step": 410
+    },
+    {
+      "epoch": 0.967930029154519,
+      "grad_norm": 1.071764554251202,
+      "learning_rate": 5.621182694925731e-08,
+      "loss": 0.5734,
+      "step": 415
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 1.129723164194212,
+      "learning_rate": 2.1299726744747896e-08,
+      "loss": 0.5945,
+      "step": 420
+    },
+    {
+      "epoch": 0.9912536443148688,
+      "grad_norm": 1.0525792994619305,
+      "learning_rate": 2.9961883554674443e-09,
+      "loss": 0.605,
+      "step": 425
+    },
+    {
+      "epoch": 0.9982507288629737,
+      "eval_loss": 0.5850064158439636,
+      "eval_runtime": 50.604,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.692,
+      "step": 428
+    },
+    {
+      "epoch": 0.9982507288629737,
+      "step": 428,
+      "total_flos": 21976597397504.0,
+      "train_loss": 0.7188172000590886,
+      "train_runtime": 7093.9262,
+      "train_samples_per_second": 1.934,
+      "train_steps_per_second": 0.06
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 428,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 21976597397504.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd769b3c9e1e79ad9cd61a9567ca320e444fe40463e8b9cef3c473ccde2e2a1f
+size 7160