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 sha256:71bd76154665ef2792cc766e23972ac07b2f9b7dd2c7aef375428ee756716ae4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16526c55b9a5392e483e6a27c35c33a0a735f4b807f8bb77b5a778e961393ddf
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d014a85aa83fb6942f6011a434818058c9abee1aff0347c265d8f240655d6075
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5a60bb9367b7356b0ade7c809aeab589844dabf52fddf31fb3d6317921da1bb
+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 +1,111 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.851, "lr": 2.3529411764705885e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:06:04", "remaining_time": "1 day, 9:34:44"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8589, "lr": 4.705882352941177e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:12:09", "remaining_time": "1 day, 9:32:09"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.851, "lr": 7.058823529411766e-06, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:43", "remaining_time": "1 day, 8:30:10"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.8013, "lr": 9.411764705882354e-06, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:23:32", "remaining_time": "1 day, 8:16:41"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.7675, "lr": 1.1764705882352942e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:29:18", "remaining_time": "1 day, 8:03:09"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.8021, "lr": 1.4117647058823532e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:35:01", "remaining_time": "1 day, 7:49:17"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.7729, "lr": 1.647058823529412e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:41:10", "remaining_time": "1 day, 7:57:41"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.7895, "lr": 1.8823529411764708e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:46:53", "remaining_time": "1 day, 7:45:06"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.7502, "lr": 2.1176470588235296e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:52:42", "remaining_time": "1 day, 7:37:14"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.7085, "lr": 2.3529411764705884e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:58:23", "remaining_time": "1 day, 7:25:46"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.68, "lr": 2.5882352941176475e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:04:15", "remaining_time": "1 day, 7:20:57"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.6579, "lr": 2.8235294117647063e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:10:21", "remaining_time": "1 day, 7:22:14"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6348, "lr": 3.0588235294117644e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:15:56", "remaining_time": "1 day, 7:09:10"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.6259, "lr": 3.294117647058824e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:21:38", "remaining_time": "1 day, 7:00:15"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6217, "lr": 3.529411764705883e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:27:27", "remaining_time": "1 day, 6:54:10"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.6117, "lr": 3.7647058823529415e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:33:19", "remaining_time": "1 day, 6:49:09"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.5951, "lr": 4e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:39:12", "remaining_time": "1 day, 6:44:00"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.5873, "lr": 4.235294117647059e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:44:54", "remaining_time": "1 day, 6:35:56"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.5855, "lr": 4.470588235294118e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:50:48", "remaining_time": "1 day, 6:31:20"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.5855, "lr": 4.705882352941177e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:56:37", "remaining_time": "1 day, 6:25:13"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.5834, "lr": 4.941176470588236e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "2:02:40", "remaining_time": "1 day, 6:22:39"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.573, "lr": 5.176470588235295e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:08:36", "remaining_time": "1 day, 6:18:00"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.5687, "lr": 5.411764705882354e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:14:06", "remaining_time": "1 day, 6:07:28"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.5629, "lr": 5.6470588235294126e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:19:59", "remaining_time": "1 day, 6:02:29"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.5644, "lr": 5.8823529411764714e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:25:34", "remaining_time": "1 day, 5:53:31"}
+{"current_steps": 26, "total_steps": 333, "loss": 0.561, "lr": 6.117647058823529e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:31:15", "remaining_time": "1 day, 5:45:58"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.5581, "lr": 6.352941176470589e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:36:42", "remaining_time": "1 day, 5:35:57"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.5497, "lr": 6.588235294117648e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:42:15", "remaining_time": "1 day, 5:27:31"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.5405, "lr": 6.823529411764707e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:48:05", "remaining_time": "1 day, 5:22:03"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.5489, "lr": 7.058823529411765e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:53:55", "remaining_time": "1 day, 5:16:35"}
+{"current_steps": 31, "total_steps": 333, "loss": 0.5429, "lr": 7.294117647058824e-05, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:59:27", "remaining_time": "1 day, 5:08:18"}
+{"current_steps": 32, "total_steps": 333, "loss": 0.5439, "lr": 7.529411764705883e-05, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:05:07", "remaining_time": "1 day, 5:01:16"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.5409, "lr": 7.764705882352942e-05, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:10:50", "remaining_time": "1 day, 4:54:55"}
+{"current_steps": 34, "total_steps": 333, "loss": 0.5448, "lr": 8e-05, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:16:45", "remaining_time": "1 day, 4:50:21"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.5376, "lr": 7.999779207981935e-05, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:22:31", "remaining_time": "1 day, 4:44:25"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.5429, "lr": 7.999116856302298e-05, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:28:21", "remaining_time": "1 day, 4:38:56"}
+{"current_steps": 37, "total_steps": 333, "loss": 0.5372, "lr": 7.998013018082072e-05, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:34:15", "remaining_time": "1 day, 4:34:03"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.5306, "lr": 7.996467815180588e-05, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:39:49", "remaining_time": "1 day, 4:26:32"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.5309, "lr": 7.994481418182082e-05, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:45:41", "remaining_time": "1 day, 4:21:23"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.5301, "lr": 7.992054046376854e-05, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:51:25", "remaining_time": "1 day, 4:15:10"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.534, "lr": 7.989185967737066e-05, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:56:57", "remaining_time": "1 day, 4:07:37"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.526, "lr": 7.985877498887149e-05, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "4:02:50", "remaining_time": "1 day, 4:02:32"}
+{"current_steps": 43, "total_steps": 333, "loss": 0.5169, "lr": 7.982129005068865e-05, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:08:20", "remaining_time": "1 day, 3:54:53"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.5086, "lr": 7.977940900100967e-05, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:14:17", "remaining_time": "1 day, 3:50:12"}
+{"current_steps": 45, "total_steps": 333, "loss": 0.5214, "lr": 7.973313646333532e-05, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:20:13", "remaining_time": "1 day, 3:45:23"}
+{"current_steps": 46, "total_steps": 333, "loss": 0.5143, "lr": 7.968247754596908e-05, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:25:53", "remaining_time": "1 day, 3:38:55"}
+{"current_steps": 47, "total_steps": 333, "loss": 0.5207, "lr": 7.962743784145323e-05, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:31:44", "remaining_time": "1 day, 3:33:36"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.5069, "lr": 7.956802342595152e-05, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:37:22", "remaining_time": "1 day, 3:26:55"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.5145, "lr": 7.950424085857827e-05, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:42:57", "remaining_time": "1 day, 3:19:58"}
+{"current_steps": 50, "total_steps": 333, "loss": 0.5034, "lr": 7.943609718067437e-05, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:48:50", "remaining_time": "1 day, 3:14:51"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.5139, "lr": 7.936359991502993e-05, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:54:37", "remaining_time": "1 day, 3:09:06"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.5024, "lr": 7.92867570650537e-05, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "5:00:15", "remaining_time": "1 day, 3:02:34"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.5024, "lr": 7.920557711388967e-05, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "5:06:07", "remaining_time": "1 day, 2:57:14"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.5087, "lr": 7.912006902348045e-05, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:11:42", "remaining_time": "1 day, 2:50:32"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.5059, "lr": 7.903024223357797e-05, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:17:24", "remaining_time": "1 day, 2:44:21"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.5025, "lr": 7.893610666070134e-05, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:23:08", "remaining_time": "1 day, 2:38:24"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.5166, "lr": 7.883767269704209e-05, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:29:04", "remaining_time": "1 day, 2:33:25"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.5053, "lr": 7.873495120931697e-05, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:34:35", "remaining_time": "1 day, 2:26:25"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.506, "lr": 7.86279535375683e-05, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:40:21", "remaining_time": "1 day, 2:20:39"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.4972, "lr": 7.851669149391198e-05, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:45:45", "remaining_time": "1 day, 2:13:10"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.503, "lr": 7.84011773612336e-05, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:51:38", "remaining_time": "1 day, 2:07:58"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.5002, "lr": 7.828142389183239e-05, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:57:23", "remaining_time": "1 day, 2:02:10"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.5056, "lr": 7.815744430601344e-05, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "6:03:04", "remaining_time": "1 day, 1:56:02"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.4918, "lr": 7.802925229062823e-05, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "6:08:49", "remaining_time": "1 day, 1:50:13"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.4969, "lr": 7.789686199756365e-05, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:14:30", "remaining_time": "1 day, 1:44:07"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.5026, "lr": 7.776028804217968e-05, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:20:20", "remaining_time": "1 day, 1:38:39"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.4932, "lr": 7.761954550169593e-05, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:25:53", "remaining_time": "1 day, 1:32:02"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.5172, "lr": 7.74746499135272e-05, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:31:53", "remaining_time": "1 day, 1:27:11"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.5039, "lr": 7.732561727356811e-05, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:37:34", "remaining_time": "1 day, 1:21:10"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.4973, "lr": 7.717246403442735e-05, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:43:28", "remaining_time": "1 day, 1:15:53"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.4988, "lr": 7.701520710361129e-05, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:49:19", "remaining_time": "1 day, 1:10:28"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.4874, "lr": 7.685386384165748e-05, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:54:50", "remaining_time": "1 day, 1:03:48"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.5035, "lr": 7.668845206021812e-05, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "7:00:32", "remaining_time": "1 day, 0:57:48"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.4926, "lr": 7.651899002009375e-05, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "7:05:58", "remaining_time": "1 day, 0:50:54"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.4939, "lr": 7.634549642921725e-05, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:11:44", "remaining_time": "1 day, 0:45:12"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.5067, "lr": 7.616799044058867e-05, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:17:34", "remaining_time": "1 day, 0:39:42"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.4915, "lr": 7.598649165016073e-05, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:23:18", "remaining_time": "1 day, 0:33:50"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.4934, "lr": 7.58010200946755e-05, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:29:11", "remaining_time": "1 day, 0:28:29"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.4823, "lr": 7.561159624945257e-05, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:34:44", "remaining_time": "1 day, 0:22:05"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.5005, "lr": 7.541824102612839e-05, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:40:27", "remaining_time": "1 day, 0:16:12"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.4846, "lr": 7.5220975770348e-05, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:46:15", "remaining_time": "1 day, 0:10:34"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.4716, "lr": 7.501982225940833e-05, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:52:13", "remaining_time": "1 day, 0:05:27"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.4912, "lr": 7.48148026998542e-05, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:58:04", "remaining_time": "23:59:57"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.4857, "lr": 7.460593972502674e-05, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "8:03:47", "remaining_time": "23:54:06"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.4815, "lr": 7.439325639256483e-05, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "8:09:40", "remaining_time": "23:48:41"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.4837, "lr": 7.417677618185955e-05, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:15:33", "remaining_time": "23:43:15"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.4765, "lr": 7.39565229914622e-05, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:21:17", "remaining_time": "23:37:26"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.4879, "lr": 7.373252113644596e-05, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:27:08", "remaining_time": "23:31:55"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4705, "lr": 7.350479534572166e-05, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:33:04", "remaining_time": "23:26:37"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.4806, "lr": 7.327337075930775e-05, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:39:08", "remaining_time": "23:21:41"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.481, "lr": 7.303827292555495e-05, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:45:02", "remaining_time": "23:16:16"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.4759, "lr": 7.279952779832584e-05, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:50:42", "remaining_time": "23:10:12"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.4736, "lr": 7.255716173412966e-05, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:56:21", "remaining_time": "23:04:09"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.4754, "lr": 7.23112014892126e-05, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "9:02:10", "remaining_time": "22:58:30"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.4801, "lr": 7.20616742166041e-05, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "9:07:55", "remaining_time": "22:52:42"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.4904, "lr": 7.180860746311917e-05, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "9:13:49", "remaining_time": "22:47:14"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.4824, "lr": 7.155202916631743e-05, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:19:43", "remaining_time": "22:41:48"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.4679, "lr": 7.129196765141886e-05, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:25:49", "remaining_time": "22:36:49"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.4786, "lr": 7.10284516281768e-05, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:31:26", "remaining_time": "22:30:39"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.4669, "lr": 7.076151018770854e-05, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:37:24", "remaining_time": "22:25:21"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.4801, "lr": 7.049117279928374e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:43:10", "remaining_time": "22:19:33"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.4674, "lr": 7.021746930707117e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:48:58", "remaining_time": "22:13:50"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.4788, "lr": 6.994042992684406e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:54:34", "remaining_time": "22:07:41"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.4679, "lr": 6.966008524264429e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "10:00:14", "remaining_time": "22:01:40"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4792, "lr": 6.937646620340618e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "10:06:05", "remaining_time": "21:56:04"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4683, "lr": 6.908960411953973e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "10:11:58", "remaining_time": "21:50:33"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.4678, "lr": 6.879953065947416e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:17:28", "remaining_time": "21:44:12"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4601, "lr": 6.850627784616178e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:23:00", "remaining_time": "21:37:55"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4681, "lr": 6.82098780535428e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:28:44", "remaining_time": "21:32:05"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4761, "lr": 6.791036400297142e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:34:20", "remaining_time": "21:25:59"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4689, "lr": 6.760776875960347e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:40:06", "remaining_time": "21:20:12"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988c7d01f8af588226778b6f68460e315af51bb2c7487fe3feab44fcfb8cf749
+size 7224