Training in progress, epoch 0

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b66f63b2d12355c96336e6aca162892ae1354a9979a2f6d8716008f9bcaa63
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c500e0486294d28584efb789ad3548577a45aa565cc472588edc5e77c8bf22c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52b582cb338ab1b714313572948881c703f41d2e4a858da5e3b6a87f58beac9
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ff5785ee993dee41c6150420cd3ff5865c19e6fcae226d03470ce513e56280
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,93 @@
+{"current_steps": 1, "total_steps": 276, "loss": 0.8567, "lr": 2.8571428571428573e-06, "epoch": 0.010825439783491205, "percentage": 0.36, "elapsed_time": "0:02:31", "remaining_time": "11:32:20"}
+{"current_steps": 2, "total_steps": 276, "loss": 0.8604, "lr": 5.7142857142857145e-06, "epoch": 0.02165087956698241, "percentage": 0.72, "elapsed_time": "0:04:08", "remaining_time": "9:26:49"}
+{"current_steps": 3, "total_steps": 276, "loss": 0.8528, "lr": 8.571428571428571e-06, "epoch": 0.03247631935047361, "percentage": 1.09, "elapsed_time": "0:05:45", "remaining_time": "8:44:16"}
+{"current_steps": 4, "total_steps": 276, "loss": 0.776, "lr": 1.1428571428571429e-05, "epoch": 0.04330175913396482, "percentage": 1.45, "elapsed_time": "0:07:23", "remaining_time": "8:22:11"}
+{"current_steps": 5, "total_steps": 276, "loss": 0.7546, "lr": 1.4285714285714287e-05, "epoch": 0.05412719891745602, "percentage": 1.81, "elapsed_time": "0:09:00", "remaining_time": "8:08:11"}
+{"current_steps": 6, "total_steps": 276, "loss": 0.751, "lr": 1.7142857142857142e-05, "epoch": 0.06495263870094722, "percentage": 2.17, "elapsed_time": "0:10:38", "remaining_time": "7:58:31"}
+{"current_steps": 7, "total_steps": 276, "loss": 0.7344, "lr": 2e-05, "epoch": 0.07577807848443843, "percentage": 2.54, "elapsed_time": "0:12:15", "remaining_time": "7:51:22"}
+{"current_steps": 8, "total_steps": 276, "loss": 0.729, "lr": 2.2857142857142858e-05, "epoch": 0.08660351826792964, "percentage": 2.9, "elapsed_time": "0:13:53", "remaining_time": "7:45:12"}
+{"current_steps": 9, "total_steps": 276, "loss": 0.672, "lr": 2.5714285714285718e-05, "epoch": 0.09742895805142084, "percentage": 3.26, "elapsed_time": "0:15:30", "remaining_time": "7:40:03"}
+{"current_steps": 10, "total_steps": 276, "loss": 0.6659, "lr": 2.8571428571428574e-05, "epoch": 0.10825439783491204, "percentage": 3.62, "elapsed_time": "0:17:07", "remaining_time": "7:35:36"}
+{"current_steps": 11, "total_steps": 276, "loss": 0.6379, "lr": 3.142857142857143e-05, "epoch": 0.11907983761840325, "percentage": 3.99, "elapsed_time": "0:18:45", "remaining_time": "7:31:43"}
+{"current_steps": 12, "total_steps": 276, "loss": 0.6305, "lr": 3.4285714285714284e-05, "epoch": 0.12990527740189445, "percentage": 4.35, "elapsed_time": "0:20:22", "remaining_time": "7:28:07"}
+{"current_steps": 13, "total_steps": 276, "loss": 0.6142, "lr": 3.714285714285715e-05, "epoch": 0.14073071718538566, "percentage": 4.71, "elapsed_time": "0:21:59", "remaining_time": "7:24:55"}
+{"current_steps": 14, "total_steps": 276, "loss": 0.6246, "lr": 4e-05, "epoch": 0.15155615696887687, "percentage": 5.07, "elapsed_time": "0:23:36", "remaining_time": "7:21:53"}
+{"current_steps": 15, "total_steps": 276, "loss": 0.6075, "lr": 4.2857142857142856e-05, "epoch": 0.16238159675236807, "percentage": 5.43, "elapsed_time": "0:25:14", "remaining_time": "7:19:05"}
+{"current_steps": 16, "total_steps": 276, "loss": 0.5986, "lr": 4.5714285714285716e-05, "epoch": 0.17320703653585928, "percentage": 5.8, "elapsed_time": "0:26:51", "remaining_time": "7:16:24"}
+{"current_steps": 17, "total_steps": 276, "loss": 0.5943, "lr": 4.857142857142857e-05, "epoch": 0.18403247631935046, "percentage": 6.16, "elapsed_time": "0:28:28", "remaining_time": "7:13:51"}
+{"current_steps": 18, "total_steps": 276, "loss": 0.577, "lr": 5.1428571428571436e-05, "epoch": 0.19485791610284167, "percentage": 6.52, "elapsed_time": "0:30:06", "remaining_time": "7:11:28"}
+{"current_steps": 19, "total_steps": 276, "loss": 0.5697, "lr": 5.4285714285714295e-05, "epoch": 0.20568335588633288, "percentage": 6.88, "elapsed_time": "0:31:43", "remaining_time": "7:09:06"}
+{"current_steps": 20, "total_steps": 276, "loss": 0.5746, "lr": 5.714285714285715e-05, "epoch": 0.2165087956698241, "percentage": 7.25, "elapsed_time": "0:33:20", "remaining_time": "7:06:48"}
+{"current_steps": 21, "total_steps": 276, "loss": 0.5683, "lr": 6.000000000000001e-05, "epoch": 0.2273342354533153, "percentage": 7.61, "elapsed_time": "0:34:57", "remaining_time": "7:04:35"}
+{"current_steps": 22, "total_steps": 276, "loss": 0.5676, "lr": 6.285714285714286e-05, "epoch": 0.2381596752368065, "percentage": 7.97, "elapsed_time": "0:36:35", "remaining_time": "7:02:22"}
+{"current_steps": 23, "total_steps": 276, "loss": 0.5639, "lr": 6.571428571428571e-05, "epoch": 0.2489851150202977, "percentage": 8.33, "elapsed_time": "0:38:12", "remaining_time": "7:00:17"}
+{"current_steps": 24, "total_steps": 276, "loss": 0.5667, "lr": 6.857142857142857e-05, "epoch": 0.2598105548037889, "percentage": 8.7, "elapsed_time": "0:39:49", "remaining_time": "6:58:11"}
+{"current_steps": 25, "total_steps": 276, "loss": 0.5639, "lr": 7.142857142857143e-05, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:41:26", "remaining_time": "6:56:08"}
+{"current_steps": 26, "total_steps": 276, "loss": 0.5434, "lr": 7.42857142857143e-05, "epoch": 0.2814614343707713, "percentage": 9.42, "elapsed_time": "0:43:04", "remaining_time": "6:54:08"}
+{"current_steps": 27, "total_steps": 276, "loss": 0.5453, "lr": 7.714285714285715e-05, "epoch": 0.2922868741542625, "percentage": 9.78, "elapsed_time": "0:44:42", "remaining_time": "6:52:15"}
+{"current_steps": 28, "total_steps": 276, "loss": 0.5518, "lr": 8e-05, "epoch": 0.30311231393775373, "percentage": 10.14, "elapsed_time": "0:46:19", "remaining_time": "6:50:17"}
+{"current_steps": 29, "total_steps": 276, "loss": 0.5488, "lr": 7.999679062421315e-05, "epoch": 0.31393775372124494, "percentage": 10.51, "elapsed_time": "0:47:56", "remaining_time": "6:48:21"}
+{"current_steps": 30, "total_steps": 276, "loss": 0.5434, "lr": 7.998716301185722e-05, "epoch": 0.32476319350473615, "percentage": 10.87, "elapsed_time": "0:49:33", "remaining_time": "6:46:26"}
+{"current_steps": 31, "total_steps": 276, "loss": 0.543, "lr": 7.997111870786354e-05, "epoch": 0.33558863328822736, "percentage": 11.23, "elapsed_time": "0:51:11", "remaining_time": "6:44:35"}
+{"current_steps": 32, "total_steps": 276, "loss": 0.5386, "lr": 7.994866028684212e-05, "epoch": 0.34641407307171856, "percentage": 11.59, "elapsed_time": "0:52:49", "remaining_time": "6:42:45"}
+{"current_steps": 33, "total_steps": 276, "loss": 0.5426, "lr": 7.991979135266861e-05, "epoch": 0.3572395128552097, "percentage": 11.96, "elapsed_time": "0:54:26", "remaining_time": "6:40:53"}
+{"current_steps": 34, "total_steps": 276, "loss": 0.5419, "lr": 7.98845165379059e-05, "epoch": 0.3680649526387009, "percentage": 12.32, "elapsed_time": "0:56:03", "remaining_time": "6:39:02"}
+{"current_steps": 35, "total_steps": 276, "loss": 0.525, "lr": 7.984284150306085e-05, "epoch": 0.37889039242219213, "percentage": 12.68, "elapsed_time": "0:57:41", "remaining_time": "6:37:12"}
+{"current_steps": 36, "total_steps": 276, "loss": 0.5161, "lr": 7.97947729356758e-05, "epoch": 0.38971583220568334, "percentage": 13.04, "elapsed_time": "0:59:18", "remaining_time": "6:35:21"}
+{"current_steps": 37, "total_steps": 276, "loss": 0.5241, "lr": 7.974031854925562e-05, "epoch": 0.40054127198917455, "percentage": 13.41, "elapsed_time": "1:00:55", "remaining_time": "6:33:33"}
+{"current_steps": 38, "total_steps": 276, "loss": 0.5135, "lr": 7.967948708202972e-05, "epoch": 0.41136671177266576, "percentage": 13.77, "elapsed_time": "1:02:33", "remaining_time": "6:31:46"}
+{"current_steps": 39, "total_steps": 276, "loss": 0.5232, "lr": 7.961228829555003e-05, "epoch": 0.42219215155615697, "percentage": 14.13, "elapsed_time": "1:04:10", "remaining_time": "6:29:58"}
+{"current_steps": 40, "total_steps": 276, "loss": 0.5114, "lr": 7.953873297312447e-05, "epoch": 0.4330175913396482, "percentage": 14.49, "elapsed_time": "1:05:47", "remaining_time": "6:28:10"}
+{"current_steps": 41, "total_steps": 276, "loss": 0.5151, "lr": 7.945883291808655e-05, "epoch": 0.4438430311231394, "percentage": 14.86, "elapsed_time": "1:07:24", "remaining_time": "6:26:22"}
+{"current_steps": 42, "total_steps": 276, "loss": 0.5079, "lr": 7.937260095190137e-05, "epoch": 0.4546684709066306, "percentage": 15.22, "elapsed_time": "1:09:01", "remaining_time": "6:24:36"}
+{"current_steps": 43, "total_steps": 276, "loss": 0.5128, "lr": 7.928005091210817e-05, "epoch": 0.4654939106901218, "percentage": 15.58, "elapsed_time": "1:10:39", "remaining_time": "6:22:51"}
+{"current_steps": 44, "total_steps": 276, "loss": 0.511, "lr": 7.918119765009979e-05, "epoch": 0.476319350473613, "percentage": 15.94, "elapsed_time": "1:12:16", "remaining_time": "6:21:06"}
+{"current_steps": 45, "total_steps": 276, "loss": 0.5101, "lr": 7.907605702873948e-05, "epoch": 0.4871447902571042, "percentage": 16.3, "elapsed_time": "1:13:54", "remaining_time": "6:19:22"}
+{"current_steps": 46, "total_steps": 276, "loss": 0.5086, "lr": 7.896464591981549e-05, "epoch": 0.4979702300405954, "percentage": 16.67, "elapsed_time": "1:15:31", "remaining_time": "6:17:36"}
+{"current_steps": 47, "total_steps": 276, "loss": 0.5163, "lr": 7.884698220133357e-05, "epoch": 0.5087956698240866, "percentage": 17.03, "elapsed_time": "1:17:08", "remaining_time": "6:15:52"}
+{"current_steps": 48, "total_steps": 276, "loss": 0.5086, "lr": 7.872308475464818e-05, "epoch": 0.5196211096075778, "percentage": 17.39, "elapsed_time": "1:18:45", "remaining_time": "6:14:07"}
+{"current_steps": 49, "total_steps": 276, "loss": 0.5051, "lr": 7.859297346143258e-05, "epoch": 0.530446549391069, "percentage": 17.75, "elapsed_time": "1:20:23", "remaining_time": "6:12:23"}
+{"current_steps": 50, "total_steps": 276, "loss": 0.5036, "lr": 7.84566692004885e-05, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "1:22:00", "remaining_time": "6:10:39"}
+{"current_steps": 51, "total_steps": 276, "loss": 0.4979, "lr": 7.831419384439565e-05, "epoch": 0.5520974289580515, "percentage": 18.48, "elapsed_time": "1:23:37", "remaining_time": "6:08:55"}
+{"current_steps": 52, "total_steps": 276, "loss": 0.4954, "lr": 7.816557025600196e-05, "epoch": 0.5629228687415426, "percentage": 18.84, "elapsed_time": "1:25:14", "remaining_time": "6:07:13"}
+{"current_steps": 53, "total_steps": 276, "loss": 0.4935, "lr": 7.80108222847547e-05, "epoch": 0.5737483085250338, "percentage": 19.2, "elapsed_time": "1:26:52", "remaining_time": "6:05:30"}
+{"current_steps": 54, "total_steps": 276, "loss": 0.5029, "lr": 7.784997476287349e-05, "epoch": 0.584573748308525, "percentage": 19.57, "elapsed_time": "1:28:29", "remaining_time": "6:03:47"}
+{"current_steps": 55, "total_steps": 276, "loss": 0.4922, "lr": 7.76830535013654e-05, "epoch": 0.5953991880920162, "percentage": 19.93, "elapsed_time": "1:30:06", "remaining_time": "6:02:05"}
+{"current_steps": 56, "total_steps": 276, "loss": 0.4954, "lr": 7.751008528588322e-05, "epoch": 0.6062246278755075, "percentage": 20.29, "elapsed_time": "1:31:43", "remaining_time": "6:00:22"}
+{"current_steps": 57, "total_steps": 276, "loss": 0.4981, "lr": 7.733109787242708e-05, "epoch": 0.6170500676589986, "percentage": 20.65, "elapsed_time": "1:33:21", "remaining_time": "5:58:40"}
+{"current_steps": 58, "total_steps": 276, "loss": 0.4992, "lr": 7.71461199828905e-05, "epoch": 0.6278755074424899, "percentage": 21.01, "elapsed_time": "1:34:58", "remaining_time": "5:56:58"}
+{"current_steps": 59, "total_steps": 276, "loss": 0.4804, "lr": 7.695518130045147e-05, "epoch": 0.638700947225981, "percentage": 21.38, "elapsed_time": "1:36:35", "remaining_time": "5:55:17"}
+{"current_steps": 60, "total_steps": 276, "loss": 0.4918, "lr": 7.675831246480923e-05, "epoch": 0.6495263870094723, "percentage": 21.74, "elapsed_time": "1:38:13", "remaining_time": "5:53:35"}
+{"current_steps": 61, "total_steps": 276, "loss": 0.5003, "lr": 7.655554506726747e-05, "epoch": 0.6603518267929634, "percentage": 22.1, "elapsed_time": "1:39:50", "remaining_time": "5:51:53"}
+{"current_steps": 62, "total_steps": 276, "loss": 0.4872, "lr": 7.6346911645665e-05, "epoch": 0.6711772665764547, "percentage": 22.46, "elapsed_time": "1:41:27", "remaining_time": "5:50:12"}
+{"current_steps": 63, "total_steps": 276, "loss": 0.4971, "lr": 7.61324456791544e-05, "epoch": 0.6820027063599459, "percentage": 22.83, "elapsed_time": "1:43:04", "remaining_time": "5:48:30"}
+{"current_steps": 64, "total_steps": 276, "loss": 0.4961, "lr": 7.591218158282968e-05, "epoch": 0.6928281461434371, "percentage": 23.19, "elapsed_time": "1:44:42", "remaining_time": "5:46:49"}
+{"current_steps": 65, "total_steps": 276, "loss": 0.4836, "lr": 7.568615470220369e-05, "epoch": 0.7036535859269283, "percentage": 23.55, "elapsed_time": "1:46:19", "remaining_time": "5:45:08"}
+{"current_steps": 66, "total_steps": 276, "loss": 0.4934, "lr": 7.545440130753634e-05, "epoch": 0.7144790257104194, "percentage": 23.91, "elapsed_time": "1:47:56", "remaining_time": "5:43:26"}
+{"current_steps": 67, "total_steps": 276, "loss": 0.492, "lr": 7.52169585880143e-05, "epoch": 0.7253044654939107, "percentage": 24.28, "elapsed_time": "1:49:33", "remaining_time": "5:41:46"}
+{"current_steps": 68, "total_steps": 276, "loss": 0.5004, "lr": 7.497386464578329e-05, "epoch": 0.7361299052774019, "percentage": 24.64, "elapsed_time": "1:51:10", "remaining_time": "5:40:05"}
+{"current_steps": 69, "total_steps": 276, "loss": 0.4927, "lr": 7.472515848983394e-05, "epoch": 0.7469553450608931, "percentage": 25.0, "elapsed_time": "1:52:48", "remaining_time": "5:38:24"}
+{"current_steps": 70, "total_steps": 276, "loss": 0.4735, "lr": 7.447088002974199e-05, "epoch": 0.7577807848443843, "percentage": 25.36, "elapsed_time": "1:54:25", "remaining_time": "5:36:43"}
+{"current_steps": 71, "total_steps": 276, "loss": 0.4776, "lr": 7.421107006926408e-05, "epoch": 0.7686062246278755, "percentage": 25.72, "elapsed_time": "1:56:02", "remaining_time": "5:35:02"}
+{"current_steps": 72, "total_steps": 276, "loss": 0.4878, "lr": 7.394577029979004e-05, "epoch": 0.7794316644113667, "percentage": 26.09, "elapsed_time": "1:57:39", "remaining_time": "5:33:21"}
+{"current_steps": 73, "total_steps": 276, "loss": 0.4949, "lr": 7.367502329365268e-05, "epoch": 0.790257104194858, "percentage": 26.45, "elapsed_time": "1:59:16", "remaining_time": "5:31:41"}
+{"current_steps": 74, "total_steps": 276, "loss": 0.4889, "lr": 7.33988724972963e-05, "epoch": 0.8010825439783491, "percentage": 26.81, "elapsed_time": "2:00:53", "remaining_time": "5:30:00"}
+{"current_steps": 75, "total_steps": 276, "loss": 0.4861, "lr": 7.311736222430487e-05, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "2:02:30", "remaining_time": "5:28:20"}
+{"current_steps": 76, "total_steps": 276, "loss": 0.4783, "lr": 7.283053764829106e-05, "epoch": 0.8227334235453315, "percentage": 27.54, "elapsed_time": "2:04:08", "remaining_time": "5:26:40"}
+{"current_steps": 77, "total_steps": 276, "loss": 0.4764, "lr": 7.253844479564737e-05, "epoch": 0.8335588633288228, "percentage": 27.9, "elapsed_time": "2:05:45", "remaining_time": "5:25:00"}
+{"current_steps": 78, "total_steps": 276, "loss": 0.4817, "lr": 7.224113053816021e-05, "epoch": 0.8443843031123139, "percentage": 28.26, "elapsed_time": "2:07:22", "remaining_time": "5:23:20"}
+{"current_steps": 79, "total_steps": 276, "loss": 0.4853, "lr": 7.193864258548855e-05, "epoch": 0.8552097428958051, "percentage": 28.62, "elapsed_time": "2:08:59", "remaining_time": "5:21:40"}
+{"current_steps": 80, "total_steps": 276, "loss": 0.4796, "lr": 7.163102947750794e-05, "epoch": 0.8660351826792964, "percentage": 28.99, "elapsed_time": "2:10:36", "remaining_time": "5:19:59"}
+{"current_steps": 81, "total_steps": 276, "loss": 0.4863, "lr": 7.131834057652142e-05, "epoch": 0.8768606224627875, "percentage": 29.35, "elapsed_time": "2:12:13", "remaining_time": "5:18:20"}
+{"current_steps": 82, "total_steps": 276, "loss": 0.4762, "lr": 7.100062605933835e-05, "epoch": 0.8876860622462788, "percentage": 29.71, "elapsed_time": "2:13:51", "remaining_time": "5:16:40"}
+{"current_steps": 83, "total_steps": 276, "loss": 0.4853, "lr": 7.067793690922268e-05, "epoch": 0.8985115020297699, "percentage": 30.07, "elapsed_time": "2:15:28", "remaining_time": "5:15:00"}
+{"current_steps": 84, "total_steps": 276, "loss": 0.4794, "lr": 7.035032490771165e-05, "epoch": 0.9093369418132612, "percentage": 30.43, "elapsed_time": "2:17:05", "remaining_time": "5:13:20"}
+{"current_steps": 85, "total_steps": 276, "loss": 0.48, "lr": 7.001784262630652e-05, "epoch": 0.9201623815967523, "percentage": 30.8, "elapsed_time": "2:18:42", "remaining_time": "5:11:41"}
+{"current_steps": 86, "total_steps": 276, "loss": 0.4853, "lr": 6.968054341803644e-05, "epoch": 0.9309878213802436, "percentage": 31.16, "elapsed_time": "2:20:20", "remaining_time": "5:10:02"}
+{"current_steps": 87, "total_steps": 276, "loss": 0.476, "lr": 6.933848140889705e-05, "epoch": 0.9418132611637348, "percentage": 31.52, "elapsed_time": "2:21:57", "remaining_time": "5:08:23"}
+{"current_steps": 88, "total_steps": 276, "loss": 0.4653, "lr": 6.89917114891648e-05, "epoch": 0.952638700947226, "percentage": 31.88, "elapsed_time": "2:23:34", "remaining_time": "5:06:44"}
+{"current_steps": 89, "total_steps": 276, "loss": 0.4788, "lr": 6.864028930458892e-05, "epoch": 0.9634641407307172, "percentage": 32.25, "elapsed_time": "2:25:12", "remaining_time": "5:05:05"}
+{"current_steps": 90, "total_steps": 276, "loss": 0.4776, "lr": 6.828427124746191e-05, "epoch": 0.9742895805142084, "percentage": 32.61, "elapsed_time": "2:26:49", "remaining_time": "5:03:27"}
+{"current_steps": 91, "total_steps": 276, "loss": 0.4803, "lr": 6.792371444757037e-05, "epoch": 0.9851150202976996, "percentage": 32.97, "elapsed_time": "2:28:27", "remaining_time": "5:01:48"}
+{"current_steps": 92, "total_steps": 276, "loss": 0.4798, "lr": 6.755867676302747e-05, "epoch": 0.9959404600811907, "percentage": 33.33, "elapsed_time": "2:30:04", "remaining_time": "5:00:09"}
+{"current_steps": 93, "total_steps": 276, "loss": 0.7491, "lr": 6.718921677098853e-05, "epoch": 1.006765899864682, "percentage": 33.7, "elapsed_time": "2:33:12", "remaining_time": "5:01:27"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8793b162b555177c712736a67e4f3a9413585c6af3fb4b48aa89aec589d8ff5
+size 7224