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 sha256:2bd51b5b2ad4e088fa46a43be088a5b087fb002ace122ed7940e307bd5dfdc90
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a321df940364d3062620ac1d54c04773a2f96adbe4bf75d2692828289cb708
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7463019e2b09248de5a8ddd0cf053920b4f1ecd1e918a8fc55eeeb72fe10e9
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38541c915a5e6c6dbc72d2e4b11faa12621e56e1dbc531e8d5ce25518bec7628
+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 +1,113 @@
+{"current_steps": 1, "total_steps": 555, "loss": 1.0353, "lr": 1.4285714285714286e-06, "epoch": 0.0090001406271973, "percentage": 0.18, "elapsed_time": "0:07:15", "remaining_time": "2 days, 19:00:55"}
+{"current_steps": 1, "total_steps": 555, "loss": 1.0356, "lr": 1.4285714285714286e-06, "epoch": 0.008998875140607425, "percentage": 0.18, "elapsed_time": "0:02:06", "remaining_time": "19:25:00"}
+{"current_steps": 2, "total_steps": 555, "loss": 1.0356, "lr": 2.8571428571428573e-06, "epoch": 0.01799775028121485, "percentage": 0.36, "elapsed_time": "0:04:05", "remaining_time": "18:50:30"}
+{"current_steps": 3, "total_steps": 555, "loss": 1.0346, "lr": 4.2857142857142855e-06, "epoch": 0.02699662542182227, "percentage": 0.54, "elapsed_time": "0:06:04", "remaining_time": "18:37:30"}
+{"current_steps": 4, "total_steps": 555, "loss": 0.9945, "lr": 5.7142857142857145e-06, "epoch": 0.0359955005624297, "percentage": 0.72, "elapsed_time": "0:08:02", "remaining_time": "18:28:29"}
+{"current_steps": 5, "total_steps": 555, "loss": 0.9512, "lr": 7.1428571428571436e-06, "epoch": 0.04499437570303712, "percentage": 0.9, "elapsed_time": "0:10:02", "remaining_time": "18:24:26"}
+{"current_steps": 6, "total_steps": 555, "loss": 0.9632, "lr": 8.571428571428571e-06, "epoch": 0.05399325084364454, "percentage": 1.08, "elapsed_time": "0:12:01", "remaining_time": "18:20:53"}
+{"current_steps": 7, "total_steps": 555, "loss": 0.9478, "lr": 1e-05, "epoch": 0.06299212598425197, "percentage": 1.26, "elapsed_time": "0:14:01", "remaining_time": "18:17:42"}
+{"current_steps": 8, "total_steps": 555, "loss": 0.9316, "lr": 1.1428571428571429e-05, "epoch": 0.0719910011248594, "percentage": 1.44, "elapsed_time": "0:16:00", "remaining_time": "18:14:33"}
+{"current_steps": 9, "total_steps": 555, "loss": 0.9182, "lr": 1.2857142857142859e-05, "epoch": 0.08098987626546682, "percentage": 1.62, "elapsed_time": "0:17:59", "remaining_time": "18:11:24"}
+{"current_steps": 10, "total_steps": 555, "loss": 0.9052, "lr": 1.4285714285714287e-05, "epoch": 0.08998875140607424, "percentage": 1.8, "elapsed_time": "0:19:58", "remaining_time": "18:08:53"}
+{"current_steps": 11, "total_steps": 555, "loss": 0.8738, "lr": 1.5714285714285715e-05, "epoch": 0.09898762654668167, "percentage": 1.98, "elapsed_time": "0:21:57", "remaining_time": "18:05:38"}
+{"current_steps": 12, "total_steps": 555, "loss": 0.8448, "lr": 1.7142857142857142e-05, "epoch": 0.10798650168728909, "percentage": 2.16, "elapsed_time": "0:23:56", "remaining_time": "18:03:21"}
+{"current_steps": 13, "total_steps": 555, "loss": 0.8214, "lr": 1.8571428571428575e-05, "epoch": 0.11698537682789652, "percentage": 2.34, "elapsed_time": "0:25:55", "remaining_time": "18:01:02"}
+{"current_steps": 14, "total_steps": 555, "loss": 0.8118, "lr": 2e-05, "epoch": 0.12598425196850394, "percentage": 2.52, "elapsed_time": "0:27:55", "remaining_time": "17:58:53"}
+{"current_steps": 15, "total_steps": 555, "loss": 0.7967, "lr": 2.1428571428571428e-05, "epoch": 0.13498312710911137, "percentage": 2.7, "elapsed_time": "0:29:53", "remaining_time": "17:56:12"}
+{"current_steps": 16, "total_steps": 555, "loss": 0.7817, "lr": 2.2857142857142858e-05, "epoch": 0.1439820022497188, "percentage": 2.88, "elapsed_time": "0:31:51", "remaining_time": "17:53:10"}
+{"current_steps": 17, "total_steps": 555, "loss": 0.7702, "lr": 2.4285714285714285e-05, "epoch": 0.1529808773903262, "percentage": 3.06, "elapsed_time": "0:33:49", "remaining_time": "17:50:36"}
+{"current_steps": 18, "total_steps": 555, "loss": 0.7625, "lr": 2.5714285714285718e-05, "epoch": 0.16197975253093364, "percentage": 3.24, "elapsed_time": "0:35:49", "remaining_time": "17:48:40"}
+{"current_steps": 19, "total_steps": 555, "loss": 0.7552, "lr": 2.7142857142857148e-05, "epoch": 0.17097862767154107, "percentage": 3.42, "elapsed_time": "0:37:48", "remaining_time": "17:46:26"}
+{"current_steps": 20, "total_steps": 555, "loss": 0.748, "lr": 2.8571428571428574e-05, "epoch": 0.17997750281214847, "percentage": 3.6, "elapsed_time": "0:39:45", "remaining_time": "17:43:26"}
+{"current_steps": 21, "total_steps": 555, "loss": 0.7319, "lr": 3.0000000000000004e-05, "epoch": 0.1889763779527559, "percentage": 3.78, "elapsed_time": "0:41:42", "remaining_time": "17:40:29"}
+{"current_steps": 22, "total_steps": 555, "loss": 0.7376, "lr": 3.142857142857143e-05, "epoch": 0.19797525309336333, "percentage": 3.96, "elapsed_time": "0:43:41", "remaining_time": "17:38:24"}
+{"current_steps": 23, "total_steps": 555, "loss": 0.7225, "lr": 3.285714285714286e-05, "epoch": 0.20697412823397077, "percentage": 4.14, "elapsed_time": "0:45:40", "remaining_time": "17:36:21"}
+{"current_steps": 24, "total_steps": 555, "loss": 0.7232, "lr": 3.4285714285714284e-05, "epoch": 0.21597300337457817, "percentage": 4.32, "elapsed_time": "0:47:39", "remaining_time": "17:34:28"}
+{"current_steps": 25, "total_steps": 555, "loss": 0.7235, "lr": 3.571428571428572e-05, "epoch": 0.2249718785151856, "percentage": 4.5, "elapsed_time": "0:49:37", "remaining_time": "17:32:08"}
+{"current_steps": 26, "total_steps": 555, "loss": 0.7136, "lr": 3.714285714285715e-05, "epoch": 0.23397075365579303, "percentage": 4.68, "elapsed_time": "0:51:35", "remaining_time": "17:29:49"}
+{"current_steps": 27, "total_steps": 555, "loss": 0.7138, "lr": 3.857142857142858e-05, "epoch": 0.24296962879640044, "percentage": 4.86, "elapsed_time": "0:53:34", "remaining_time": "17:27:33"}
+{"current_steps": 28, "total_steps": 555, "loss": 0.7106, "lr": 4e-05, "epoch": 0.25196850393700787, "percentage": 5.05, "elapsed_time": "0:55:31", "remaining_time": "17:25:11"}
+{"current_steps": 29, "total_steps": 555, "loss": 0.7056, "lr": 4.1428571428571437e-05, "epoch": 0.2609673790776153, "percentage": 5.23, "elapsed_time": "0:57:30", "remaining_time": "17:23:02"}
+{"current_steps": 30, "total_steps": 555, "loss": 0.6906, "lr": 4.2857142857142856e-05, "epoch": 0.26996625421822273, "percentage": 5.41, "elapsed_time": "0:59:30", "remaining_time": "17:21:16"}
+{"current_steps": 31, "total_steps": 555, "loss": 0.7022, "lr": 4.428571428571429e-05, "epoch": 0.27896512935883017, "percentage": 5.59, "elapsed_time": "1:01:29", "remaining_time": "17:19:20"}
+{"current_steps": 32, "total_steps": 555, "loss": 0.6925, "lr": 4.5714285714285716e-05, "epoch": 0.2879640044994376, "percentage": 5.77, "elapsed_time": "1:03:27", "remaining_time": "17:17:09"}
+{"current_steps": 33, "total_steps": 555, "loss": 0.6894, "lr": 4.714285714285715e-05, "epoch": 0.296962879640045, "percentage": 5.95, "elapsed_time": "1:05:24", "remaining_time": "17:14:46"}
+{"current_steps": 34, "total_steps": 555, "loss": 0.6924, "lr": 4.857142857142857e-05, "epoch": 0.3059617547806524, "percentage": 6.13, "elapsed_time": "1:07:23", "remaining_time": "17:12:46"}
+{"current_steps": 35, "total_steps": 555, "loss": 0.6856, "lr": 5e-05, "epoch": 0.31496062992125984, "percentage": 6.31, "elapsed_time": "1:09:22", "remaining_time": "17:10:39"}
+{"current_steps": 36, "total_steps": 555, "loss": 0.6882, "lr": 5.1428571428571436e-05, "epoch": 0.32395950506186727, "percentage": 6.49, "elapsed_time": "1:11:20", "remaining_time": "17:08:33"}
+{"current_steps": 37, "total_steps": 555, "loss": 0.6827, "lr": 5.285714285714286e-05, "epoch": 0.3329583802024747, "percentage": 6.67, "elapsed_time": "1:13:18", "remaining_time": "17:06:25"}
+{"current_steps": 38, "total_steps": 555, "loss": 0.6804, "lr": 5.4285714285714295e-05, "epoch": 0.34195725534308213, "percentage": 6.85, "elapsed_time": "1:15:18", "remaining_time": "17:04:30"}
+{"current_steps": 39, "total_steps": 555, "loss": 0.675, "lr": 5.5714285714285715e-05, "epoch": 0.35095613048368957, "percentage": 7.03, "elapsed_time": "1:17:17", "remaining_time": "17:02:34"}
+{"current_steps": 40, "total_steps": 555, "loss": 0.6714, "lr": 5.714285714285715e-05, "epoch": 0.35995500562429694, "percentage": 7.21, "elapsed_time": "1:19:14", "remaining_time": "17:00:10"}
+{"current_steps": 41, "total_steps": 555, "loss": 0.666, "lr": 5.8571428571428575e-05, "epoch": 0.3689538807649044, "percentage": 7.39, "elapsed_time": "1:21:12", "remaining_time": "16:58:00"}
+{"current_steps": 42, "total_steps": 555, "loss": 0.6716, "lr": 6.000000000000001e-05, "epoch": 0.3779527559055118, "percentage": 7.57, "elapsed_time": "1:23:10", "remaining_time": "16:55:54"}
+{"current_steps": 43, "total_steps": 555, "loss": 0.6668, "lr": 6.142857142857143e-05, "epoch": 0.38695163104611924, "percentage": 7.75, "elapsed_time": "1:25:09", "remaining_time": "16:54:00"}
+{"current_steps": 44, "total_steps": 555, "loss": 0.6706, "lr": 6.285714285714286e-05, "epoch": 0.39595050618672667, "percentage": 7.93, "elapsed_time": "1:27:08", "remaining_time": "16:52:01"}
+{"current_steps": 45, "total_steps": 555, "loss": 0.6666, "lr": 6.428571428571429e-05, "epoch": 0.4049493813273341, "percentage": 8.11, "elapsed_time": "1:29:06", "remaining_time": "16:49:51"}
+{"current_steps": 46, "total_steps": 555, "loss": 0.6611, "lr": 6.571428571428571e-05, "epoch": 0.41394825646794153, "percentage": 8.29, "elapsed_time": "1:31:04", "remaining_time": "16:47:42"}
+{"current_steps": 47, "total_steps": 555, "loss": 0.6654, "lr": 6.714285714285715e-05, "epoch": 0.4229471316085489, "percentage": 8.47, "elapsed_time": "1:33:01", "remaining_time": "16:45:30"}
+{"current_steps": 48, "total_steps": 555, "loss": 0.666, "lr": 6.857142857142857e-05, "epoch": 0.43194600674915634, "percentage": 8.65, "elapsed_time": "1:34:59", "remaining_time": "16:43:20"}
+{"current_steps": 49, "total_steps": 555, "loss": 0.6525, "lr": 7.000000000000001e-05, "epoch": 0.4409448818897638, "percentage": 8.83, "elapsed_time": "1:36:57", "remaining_time": "16:41:12"}
+{"current_steps": 50, "total_steps": 555, "loss": 0.6706, "lr": 7.142857142857143e-05, "epoch": 0.4499437570303712, "percentage": 9.01, "elapsed_time": "1:38:55", "remaining_time": "16:39:04"}
+{"current_steps": 51, "total_steps": 555, "loss": 0.6578, "lr": 7.285714285714286e-05, "epoch": 0.45894263217097864, "percentage": 9.19, "elapsed_time": "1:40:53", "remaining_time": "16:37:02"}
+{"current_steps": 52, "total_steps": 555, "loss": 0.6659, "lr": 7.42857142857143e-05, "epoch": 0.46794150731158607, "percentage": 9.37, "elapsed_time": "1:42:51", "remaining_time": "16:34:55"}
+{"current_steps": 53, "total_steps": 555, "loss": 0.6555, "lr": 7.571428571428571e-05, "epoch": 0.4769403824521935, "percentage": 9.55, "elapsed_time": "1:44:49", "remaining_time": "16:32:54"}
+{"current_steps": 54, "total_steps": 555, "loss": 0.6655, "lr": 7.714285714285715e-05, "epoch": 0.4859392575928009, "percentage": 9.73, "elapsed_time": "1:46:47", "remaining_time": "16:30:50"}
+{"current_steps": 55, "total_steps": 555, "loss": 0.6593, "lr": 7.857142857142858e-05, "epoch": 0.4949381327334083, "percentage": 9.91, "elapsed_time": "1:48:46", "remaining_time": "16:28:55"}
+{"current_steps": 56, "total_steps": 555, "loss": 0.6541, "lr": 8e-05, "epoch": 0.5039370078740157, "percentage": 10.09, "elapsed_time": "1:50:45", "remaining_time": "16:26:55"}
+{"current_steps": 57, "total_steps": 555, "loss": 0.6421, "lr": 7.999920726649282e-05, "epoch": 0.5129358830146231, "percentage": 10.27, "elapsed_time": "1:52:42", "remaining_time": "16:24:44"}
+{"current_steps": 58, "total_steps": 555, "loss": 0.6416, "lr": 7.999682909739257e-05, "epoch": 0.5219347581552306, "percentage": 10.45, "elapsed_time": "1:54:39", "remaining_time": "16:22:30"}
+{"current_steps": 59, "total_steps": 555, "loss": 0.6427, "lr": 7.999286558696199e-05, "epoch": 0.530933633295838, "percentage": 10.63, "elapsed_time": "1:56:38", "remaining_time": "16:20:35"}
+{"current_steps": 60, "total_steps": 555, "loss": 0.6535, "lr": 7.998731689230145e-05, "epoch": 0.5399325084364455, "percentage": 10.81, "elapsed_time": "1:58:37", "remaining_time": "16:18:36"}
+{"current_steps": 61, "total_steps": 555, "loss": 0.6496, "lr": 7.998018323334275e-05, "epoch": 0.5489313835770528, "percentage": 10.99, "elapsed_time": "2:00:37", "remaining_time": "16:16:52"}
+{"current_steps": 62, "total_steps": 555, "loss": 0.6437, "lr": 7.997146489284042e-05, "epoch": 0.5579302587176603, "percentage": 11.17, "elapsed_time": "2:02:36", "remaining_time": "16:14:57"}
+{"current_steps": 63, "total_steps": 555, "loss": 0.6478, "lr": 7.996116221636049e-05, "epoch": 0.5669291338582677, "percentage": 11.35, "elapsed_time": "2:04:34", "remaining_time": "16:12:55"}
+{"current_steps": 64, "total_steps": 555, "loss": 0.641, "lr": 7.994927561226682e-05, "epoch": 0.5759280089988752, "percentage": 11.53, "elapsed_time": "2:06:33", "remaining_time": "16:10:58"}
+{"current_steps": 65, "total_steps": 555, "loss": 0.6483, "lr": 7.993580555170486e-05, "epoch": 0.5849268841394826, "percentage": 11.71, "elapsed_time": "2:08:32", "remaining_time": "16:08:58"}
+{"current_steps": 66, "total_steps": 555, "loss": 0.639, "lr": 7.992075256858302e-05, "epoch": 0.59392575928009, "percentage": 11.89, "elapsed_time": "2:10:30", "remaining_time": "16:06:55"}
+{"current_steps": 67, "total_steps": 555, "loss": 0.6469, "lr": 7.990411725955153e-05, "epoch": 0.6029246344206974, "percentage": 12.07, "elapsed_time": "2:12:26", "remaining_time": "16:04:41"}
+{"current_steps": 68, "total_steps": 555, "loss": 0.6403, "lr": 7.98859002839787e-05, "epoch": 0.6119235095613048, "percentage": 12.25, "elapsed_time": "2:14:24", "remaining_time": "16:02:37"}
+{"current_steps": 69, "total_steps": 555, "loss": 0.6436, "lr": 7.986610236392491e-05, "epoch": 0.6209223847019123, "percentage": 12.43, "elapsed_time": "2:16:23", "remaining_time": "16:00:37"}
+{"current_steps": 70, "total_steps": 555, "loss": 0.6541, "lr": 7.984472428411388e-05, "epoch": 0.6299212598425197, "percentage": 12.61, "elapsed_time": "2:18:22", "remaining_time": "15:58:42"}
+{"current_steps": 71, "total_steps": 555, "loss": 0.6408, "lr": 7.98217668919016e-05, "epoch": 0.6389201349831272, "percentage": 12.79, "elapsed_time": "2:20:20", "remaining_time": "15:56:39"}
+{"current_steps": 72, "total_steps": 555, "loss": 0.6462, "lr": 7.97972310972428e-05, "epoch": 0.6479190101237345, "percentage": 12.97, "elapsed_time": "2:22:20", "remaining_time": "15:54:49"}
+{"current_steps": 73, "total_steps": 555, "loss": 0.6348, "lr": 7.977111787265479e-05, "epoch": 0.6569178852643419, "percentage": 13.15, "elapsed_time": "2:24:18", "remaining_time": "15:52:48"}
+{"current_steps": 74, "total_steps": 555, "loss": 0.6398, "lr": 7.9743428253179e-05, "epoch": 0.6659167604049494, "percentage": 13.33, "elapsed_time": "2:26:16", "remaining_time": "15:50:45"}
+{"current_steps": 75, "total_steps": 555, "loss": 0.633, "lr": 7.971416333633984e-05, "epoch": 0.6749156355455568, "percentage": 13.51, "elapsed_time": "2:28:15", "remaining_time": "15:48:48"}
+{"current_steps": 76, "total_steps": 555, "loss": 0.6344, "lr": 7.968332428210136e-05, "epoch": 0.6839145106861643, "percentage": 13.69, "elapsed_time": "2:30:13", "remaining_time": "15:46:46"}
+{"current_steps": 77, "total_steps": 555, "loss": 0.6316, "lr": 7.965091231282114e-05, "epoch": 0.6929133858267716, "percentage": 13.87, "elapsed_time": "2:32:09", "remaining_time": "15:44:32"}
+{"current_steps": 78, "total_steps": 555, "loss": 0.6384, "lr": 7.961692871320186e-05, "epoch": 0.7019122609673791, "percentage": 14.05, "elapsed_time": "2:34:07", "remaining_time": "15:42:31"}
+{"current_steps": 79, "total_steps": 555, "loss": 0.6348, "lr": 7.958137483024044e-05, "epoch": 0.7109111361079865, "percentage": 14.23, "elapsed_time": "2:36:06", "remaining_time": "15:40:35"}
+{"current_steps": 80, "total_steps": 555, "loss": 0.6319, "lr": 7.95442520731746e-05, "epoch": 0.7199100112485939, "percentage": 14.41, "elapsed_time": "2:38:04", "remaining_time": "15:38:35"}
+{"current_steps": 81, "total_steps": 555, "loss": 0.6255, "lr": 7.9505561913427e-05, "epoch": 0.7289088863892014, "percentage": 14.59, "elapsed_time": "2:40:02", "remaining_time": "15:36:31"}
+{"current_steps": 82, "total_steps": 555, "loss": 0.6324, "lr": 7.946530588454695e-05, "epoch": 0.7379077615298087, "percentage": 14.77, "elapsed_time": "2:42:00", "remaining_time": "15:34:30"}
+{"current_steps": 83, "total_steps": 555, "loss": 0.6326, "lr": 7.942348558214958e-05, "epoch": 0.7469066366704162, "percentage": 14.95, "elapsed_time": "2:43:59", "remaining_time": "15:32:34"}
+{"current_steps": 84, "total_steps": 555, "loss": 0.6362, "lr": 7.938010266385268e-05, "epoch": 0.7559055118110236, "percentage": 15.14, "elapsed_time": "2:45:58", "remaining_time": "15:30:37"}
+{"current_steps": 85, "total_steps": 555, "loss": 0.6274, "lr": 7.933515884921086e-05, "epoch": 0.7649043869516311, "percentage": 15.32, "elapsed_time": "2:47:56", "remaining_time": "15:28:36"}
+{"current_steps": 86, "total_steps": 555, "loss": 0.6356, "lr": 7.928865591964751e-05, "epoch": 0.7739032620922385, "percentage": 15.5, "elapsed_time": "2:49:53", "remaining_time": "15:26:32"}
+{"current_steps": 87, "total_steps": 555, "loss": 0.6239, "lr": 7.924059571838419e-05, "epoch": 0.7829021372328459, "percentage": 15.68, "elapsed_time": "2:51:51", "remaining_time": "15:24:29"}
+{"current_steps": 88, "total_steps": 555, "loss": 0.6254, "lr": 7.919098015036746e-05, "epoch": 0.7919010123734533, "percentage": 15.86, "elapsed_time": "2:53:50", "remaining_time": "15:22:32"}
+{"current_steps": 89, "total_steps": 555, "loss": 0.6386, "lr": 7.91398111821935e-05, "epoch": 0.8008998875140607, "percentage": 16.04, "elapsed_time": "2:55:48", "remaining_time": "15:20:33"}
+{"current_steps": 90, "total_steps": 555, "loss": 0.6433, "lr": 7.908709084203006e-05, "epoch": 0.8098987626546682, "percentage": 16.22, "elapsed_time": "2:57:47", "remaining_time": "15:18:34"}
+{"current_steps": 91, "total_steps": 555, "loss": 0.6274, "lr": 7.903282121953619e-05, "epoch": 0.8188976377952756, "percentage": 16.4, "elapsed_time": "2:59:44", "remaining_time": "15:16:27"}
+{"current_steps": 92, "total_steps": 555, "loss": 0.6395, "lr": 7.897700446577928e-05, "epoch": 0.8278965129358831, "percentage": 16.58, "elapsed_time": "3:01:43", "remaining_time": "15:14:30"}
+{"current_steps": 93, "total_steps": 555, "loss": 0.6304, "lr": 7.891964279314988e-05, "epoch": 0.8368953880764904, "percentage": 16.76, "elapsed_time": "3:03:40", "remaining_time": "15:12:26"}
+{"current_steps": 94, "total_steps": 555, "loss": 0.634, "lr": 7.886073847527397e-05, "epoch": 0.8458942632170978, "percentage": 16.94, "elapsed_time": "3:05:38", "remaining_time": "15:10:25"}
+{"current_steps": 95, "total_steps": 555, "loss": 0.6187, "lr": 7.88002938469229e-05, "epoch": 0.8548931383577053, "percentage": 17.12, "elapsed_time": "3:07:37", "remaining_time": "15:08:28"}
+{"current_steps": 96, "total_steps": 555, "loss": 0.6224, "lr": 7.873831130392077e-05, "epoch": 0.8638920134983127, "percentage": 17.3, "elapsed_time": "3:09:35", "remaining_time": "15:06:27"}
+{"current_steps": 97, "total_steps": 555, "loss": 0.6129, "lr": 7.867479330304951e-05, "epoch": 0.8728908886389202, "percentage": 17.48, "elapsed_time": "3:11:32", "remaining_time": "15:04:25"}
+{"current_steps": 98, "total_steps": 555, "loss": 0.6133, "lr": 7.860974236195151e-05, "epoch": 0.8818897637795275, "percentage": 17.66, "elapsed_time": "3:13:31", "remaining_time": "15:02:29"}
+{"current_steps": 99, "total_steps": 555, "loss": 0.6212, "lr": 7.85431610590298e-05, "epoch": 0.890888638920135, "percentage": 17.84, "elapsed_time": "3:15:30", "remaining_time": "15:00:31"}
+{"current_steps": 100, "total_steps": 555, "loss": 0.6162, "lr": 7.847505203334588e-05, "epoch": 0.8998875140607424, "percentage": 18.02, "elapsed_time": "3:17:29", "remaining_time": "14:58:32"}
+{"current_steps": 101, "total_steps": 555, "loss": 0.6105, "lr": 7.840541798451506e-05, "epoch": 0.9088863892013498, "percentage": 18.2, "elapsed_time": "3:19:26", "remaining_time": "14:56:28"}
+{"current_steps": 102, "total_steps": 555, "loss": 0.6091, "lr": 7.833426167259955e-05, "epoch": 0.9178852643419573, "percentage": 18.38, "elapsed_time": "3:21:23", "remaining_time": "14:54:25"}
+{"current_steps": 103, "total_steps": 555, "loss": 0.6124, "lr": 7.826158591799898e-05, "epoch": 0.9268841394825647, "percentage": 18.56, "elapsed_time": "3:23:20", "remaining_time": "14:52:19"}
+{"current_steps": 104, "total_steps": 555, "loss": 0.6093, "lr": 7.818739360133863e-05, "epoch": 0.9358830146231721, "percentage": 18.74, "elapsed_time": "3:25:17", "remaining_time": "14:50:14"}
+{"current_steps": 105, "total_steps": 555, "loss": 0.6152, "lr": 7.811168766335531e-05, "epoch": 0.9448818897637795, "percentage": 18.92, "elapsed_time": "3:27:16", "remaining_time": "14:48:17"}
+{"current_steps": 106, "total_steps": 555, "loss": 0.6183, "lr": 7.803447110478067e-05, "epoch": 0.953880764904387, "percentage": 19.1, "elapsed_time": "3:29:14", "remaining_time": "14:46:18"}
+{"current_steps": 107, "total_steps": 555, "loss": 0.6176, "lr": 7.795574698622237e-05, "epoch": 0.9628796400449944, "percentage": 19.28, "elapsed_time": "3:31:10", "remaining_time": "14:44:10"}
+{"current_steps": 108, "total_steps": 555, "loss": 0.6099, "lr": 7.787551842804276e-05, "epoch": 0.9718785151856018, "percentage": 19.46, "elapsed_time": "3:33:05", "remaining_time": "14:41:59"}
+{"current_steps": 109, "total_steps": 555, "loss": 0.6063, "lr": 7.779378861023516e-05, "epoch": 0.9808773903262092, "percentage": 19.64, "elapsed_time": "3:35:03", "remaining_time": "14:39:56"}
+{"current_steps": 110, "total_steps": 555, "loss": 0.6088, "lr": 7.77105607722978e-05, "epoch": 0.9898762654668166, "percentage": 19.82, "elapsed_time": "3:37:01", "remaining_time": "14:37:56"}
+{"current_steps": 111, "total_steps": 555, "loss": 0.6027, "lr": 7.762583821310548e-05, "epoch": 0.9988751406074241, "percentage": 20.0, "elapsed_time": "3:38:58", "remaining_time": "14:35:53"}
+{"current_steps": 112, "total_steps": 555, "loss": 1.109, "lr": 7.753962429077881e-05, "epoch": 1.0078740157480315, "percentage": 20.18, "elapsed_time": "3:42:50", "remaining_time": "14:41:23"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523668d083d1f21209f2f2795e24c7f99dcfd814b22ed59d36959deb5b49832a
+size 7288