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:b2cf01c907a3d53ea4c9e515eaaa53661224fe42199871d30f34466eb1f1b3c8
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fb4a48fcaf234a718c857ae5063f9c3f43a97fb6fe4fc4afc6a9ec1acd9bc9
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e185a690ebe070253c43ff88c54396423b376b3150fcd372613c3dd86ed2b1be
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42641ce1aa455410fa6644e0a7e1e1b937fba1d8faf81a5b33e201ffa972dfea
+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 +1,86 @@
+{"current_steps": 1, "total_steps": 390, "loss": 1.0584, "lr": 1.0256410256410257e-06, "epoch": 0.012779552715654952, "percentage": 0.26, "elapsed_time": "0:00:30", "remaining_time": "3:15:53"}
+{"current_steps": 2, "total_steps": 390, "loss": 1.0359, "lr": 2.0512820512820513e-06, "epoch": 0.025559105431309903, "percentage": 0.51, "elapsed_time": "0:00:52", "remaining_time": "2:50:02"}
+{"current_steps": 3, "total_steps": 390, "loss": 1.0339, "lr": 3.0769230769230774e-06, "epoch": 0.038338658146964855, "percentage": 0.77, "elapsed_time": "0:01:15", "remaining_time": "2:42:47"}
+{"current_steps": 4, "total_steps": 390, "loss": 1.0326, "lr": 4.102564102564103e-06, "epoch": 0.051118210862619806, "percentage": 1.03, "elapsed_time": "0:01:39", "remaining_time": "2:39:33"}
+{"current_steps": 5, "total_steps": 390, "loss": 0.9829, "lr": 5.128205128205128e-06, "epoch": 0.06389776357827476, "percentage": 1.28, "elapsed_time": "0:02:03", "remaining_time": "2:38:55"}
+{"current_steps": 6, "total_steps": 390, "loss": 0.9442, "lr": 6.153846153846155e-06, "epoch": 0.07667731629392971, "percentage": 1.54, "elapsed_time": "0:02:27", "remaining_time": "2:37:49"}
+{"current_steps": 7, "total_steps": 390, "loss": 0.9341, "lr": 7.17948717948718e-06, "epoch": 0.08945686900958466, "percentage": 1.79, "elapsed_time": "0:02:50", "remaining_time": "2:35:53"}
+{"current_steps": 8, "total_steps": 390, "loss": 0.9597, "lr": 8.205128205128205e-06, "epoch": 0.10223642172523961, "percentage": 2.05, "elapsed_time": "0:03:14", "remaining_time": "2:34:57"}
+{"current_steps": 9, "total_steps": 390, "loss": 0.9411, "lr": 9.230769230769232e-06, "epoch": 0.11501597444089456, "percentage": 2.31, "elapsed_time": "0:03:37", "remaining_time": "2:33:45"}
+{"current_steps": 10, "total_steps": 390, "loss": 0.8849, "lr": 1.0256410256410256e-05, "epoch": 0.12779552715654952, "percentage": 2.56, "elapsed_time": "0:04:00", "remaining_time": "2:32:35"}
+{"current_steps": 11, "total_steps": 390, "loss": 0.8685, "lr": 1.1282051282051283e-05, "epoch": 0.14057507987220447, "percentage": 2.82, "elapsed_time": "0:04:22", "remaining_time": "2:30:59"}
+{"current_steps": 12, "total_steps": 390, "loss": 0.8425, "lr": 1.230769230769231e-05, "epoch": 0.15335463258785942, "percentage": 3.08, "elapsed_time": "0:04:45", "remaining_time": "2:30:02"}
+{"current_steps": 13, "total_steps": 390, "loss": 0.8044, "lr": 1.3333333333333333e-05, "epoch": 0.16613418530351437, "percentage": 3.33, "elapsed_time": "0:05:09", "remaining_time": "2:29:26"}
+{"current_steps": 14, "total_steps": 390, "loss": 0.7956, "lr": 1.435897435897436e-05, "epoch": 0.17891373801916932, "percentage": 3.59, "elapsed_time": "0:05:30", "remaining_time": "2:27:44"}
+{"current_steps": 15, "total_steps": 390, "loss": 0.7928, "lr": 1.5384615384615387e-05, "epoch": 0.19169329073482427, "percentage": 3.85, "elapsed_time": "0:05:52", "remaining_time": "2:26:49"}
+{"current_steps": 16, "total_steps": 390, "loss": 0.7647, "lr": 1.641025641025641e-05, "epoch": 0.20447284345047922, "percentage": 4.1, "elapsed_time": "0:06:15", "remaining_time": "2:26:17"}
+{"current_steps": 17, "total_steps": 390, "loss": 0.7418, "lr": 1.7435897435897438e-05, "epoch": 0.21725239616613418, "percentage": 4.36, "elapsed_time": "0:06:37", "remaining_time": "2:25:30"}
+{"current_steps": 18, "total_steps": 390, "loss": 0.7388, "lr": 1.8461538461538465e-05, "epoch": 0.23003194888178913, "percentage": 4.62, "elapsed_time": "0:07:00", "remaining_time": "2:24:59"}
+{"current_steps": 19, "total_steps": 390, "loss": 0.7342, "lr": 1.9487179487179488e-05, "epoch": 0.24281150159744408, "percentage": 4.87, "elapsed_time": "0:07:22", "remaining_time": "2:24:08"}
+{"current_steps": 20, "total_steps": 390, "loss": 0.7153, "lr": 2.0512820512820512e-05, "epoch": 0.25559105431309903, "percentage": 5.13, "elapsed_time": "0:07:45", "remaining_time": "2:23:40"}
+{"current_steps": 21, "total_steps": 390, "loss": 0.7131, "lr": 2.153846153846154e-05, "epoch": 0.268370607028754, "percentage": 5.38, "elapsed_time": "0:08:09", "remaining_time": "2:23:19"}
+{"current_steps": 22, "total_steps": 390, "loss": 0.7218, "lr": 2.2564102564102566e-05, "epoch": 0.28115015974440893, "percentage": 5.64, "elapsed_time": "0:08:32", "remaining_time": "2:22:54"}
+{"current_steps": 23, "total_steps": 390, "loss": 0.6969, "lr": 2.3589743589743593e-05, "epoch": 0.2939297124600639, "percentage": 5.9, "elapsed_time": "0:08:56", "remaining_time": "2:22:37"}
+{"current_steps": 24, "total_steps": 390, "loss": 0.6896, "lr": 2.461538461538462e-05, "epoch": 0.30670926517571884, "percentage": 6.15, "elapsed_time": "0:09:19", "remaining_time": "2:22:18"}
+{"current_steps": 25, "total_steps": 390, "loss": 0.6908, "lr": 2.5641025641025646e-05, "epoch": 0.3194888178913738, "percentage": 6.41, "elapsed_time": "0:09:44", "remaining_time": "2:22:09"}
+{"current_steps": 26, "total_steps": 390, "loss": 0.6939, "lr": 2.6666666666666667e-05, "epoch": 0.33226837060702874, "percentage": 6.67, "elapsed_time": "0:10:08", "remaining_time": "2:21:59"}
+{"current_steps": 27, "total_steps": 390, "loss": 0.6917, "lr": 2.7692307692307694e-05, "epoch": 0.3450479233226837, "percentage": 6.92, "elapsed_time": "0:10:32", "remaining_time": "2:21:40"}
+{"current_steps": 28, "total_steps": 390, "loss": 0.6728, "lr": 2.871794871794872e-05, "epoch": 0.35782747603833864, "percentage": 7.18, "elapsed_time": "0:10:53", "remaining_time": "2:20:53"}
+{"current_steps": 29, "total_steps": 390, "loss": 0.6775, "lr": 2.9743589743589747e-05, "epoch": 0.3706070287539936, "percentage": 7.44, "elapsed_time": "0:11:16", "remaining_time": "2:20:17"}
+{"current_steps": 30, "total_steps": 390, "loss": 0.6652, "lr": 3.0769230769230774e-05, "epoch": 0.38338658146964855, "percentage": 7.69, "elapsed_time": "0:11:38", "remaining_time": "2:19:44"}
+{"current_steps": 31, "total_steps": 390, "loss": 0.6837, "lr": 3.1794871794871795e-05, "epoch": 0.3961661341853035, "percentage": 7.95, "elapsed_time": "0:12:01", "remaining_time": "2:19:17"}
+{"current_steps": 32, "total_steps": 390, "loss": 0.6619, "lr": 3.282051282051282e-05, "epoch": 0.40894568690095845, "percentage": 8.21, "elapsed_time": "0:12:25", "remaining_time": "2:18:57"}
+{"current_steps": 33, "total_steps": 390, "loss": 0.6668, "lr": 3.384615384615385e-05, "epoch": 0.4217252396166134, "percentage": 8.46, "elapsed_time": "0:12:48", "remaining_time": "2:18:37"}
+{"current_steps": 34, "total_steps": 390, "loss": 0.652, "lr": 3.4871794871794875e-05, "epoch": 0.43450479233226835, "percentage": 8.72, "elapsed_time": "0:13:11", "remaining_time": "2:18:07"}
+{"current_steps": 35, "total_steps": 390, "loss": 0.6807, "lr": 3.58974358974359e-05, "epoch": 0.4472843450479233, "percentage": 8.97, "elapsed_time": "0:13:34", "remaining_time": "2:17:39"}
+{"current_steps": 36, "total_steps": 390, "loss": 0.6571, "lr": 3.692307692307693e-05, "epoch": 0.46006389776357826, "percentage": 9.23, "elapsed_time": "0:13:57", "remaining_time": "2:17:10"}
+{"current_steps": 37, "total_steps": 390, "loss": 0.6422, "lr": 3.794871794871795e-05, "epoch": 0.4728434504792332, "percentage": 9.49, "elapsed_time": "0:14:21", "remaining_time": "2:16:56"}
+{"current_steps": 38, "total_steps": 390, "loss": 0.6506, "lr": 3.8974358974358976e-05, "epoch": 0.48562300319488816, "percentage": 9.74, "elapsed_time": "0:14:43", "remaining_time": "2:16:28"}
+{"current_steps": 39, "total_steps": 390, "loss": 0.6565, "lr": 4e-05, "epoch": 0.4984025559105431, "percentage": 10.0, "elapsed_time": "0:15:07", "remaining_time": "2:16:11"}
+{"current_steps": 40, "total_steps": 390, "loss": 0.6511, "lr": 3.9999198907597046e-05, "epoch": 0.5111821086261981, "percentage": 10.26, "elapsed_time": "0:15:31", "remaining_time": "2:15:51"}
+{"current_steps": 41, "total_steps": 390, "loss": 0.6595, "lr": 3.9996795694563096e-05, "epoch": 0.5239616613418531, "percentage": 10.51, "elapsed_time": "0:15:54", "remaining_time": "2:15:26"}
+{"current_steps": 42, "total_steps": 390, "loss": 0.6603, "lr": 3.999279055341771e-05, "epoch": 0.536741214057508, "percentage": 10.77, "elapsed_time": "0:16:18", "remaining_time": "2:15:05"}
+{"current_steps": 43, "total_steps": 390, "loss": 0.6348, "lr": 3.998718380500971e-05, "epoch": 0.549520766773163, "percentage": 11.03, "elapsed_time": "0:16:39", "remaining_time": "2:14:28"}
+{"current_steps": 44, "total_steps": 390, "loss": 0.6476, "lr": 3.997997589849145e-05, "epoch": 0.5623003194888179, "percentage": 11.28, "elapsed_time": "0:17:03", "remaining_time": "2:14:10"}
+{"current_steps": 45, "total_steps": 390, "loss": 0.6378, "lr": 3.9971167411282835e-05, "epoch": 0.5750798722044729, "percentage": 11.54, "elapsed_time": "0:17:26", "remaining_time": "2:13:46"}
+{"current_steps": 46, "total_steps": 390, "loss": 0.6354, "lr": 3.99607590490251e-05, "epoch": 0.5878594249201278, "percentage": 11.79, "elapsed_time": "0:17:49", "remaining_time": "2:13:18"}
+{"current_steps": 47, "total_steps": 390, "loss": 0.6383, "lr": 3.9948751645524235e-05, "epoch": 0.6006389776357828, "percentage": 12.05, "elapsed_time": "0:18:12", "remaining_time": "2:12:55"}
+{"current_steps": 48, "total_steps": 390, "loss": 0.634, "lr": 3.9935146162684206e-05, "epoch": 0.6134185303514377, "percentage": 12.31, "elapsed_time": "0:18:36", "remaining_time": "2:12:34"}
+{"current_steps": 49, "total_steps": 390, "loss": 0.6288, "lr": 3.9919943690429906e-05, "epoch": 0.6261980830670927, "percentage": 12.56, "elapsed_time": "0:18:59", "remaining_time": "2:12:13"}
+{"current_steps": 50, "total_steps": 390, "loss": 0.6279, "lr": 3.9903145446619837e-05, "epoch": 0.6389776357827476, "percentage": 12.82, "elapsed_time": "0:19:23", "remaining_time": "2:11:51"}
+{"current_steps": 51, "total_steps": 390, "loss": 0.6214, "lr": 3.9884752776948564e-05, "epoch": 0.6517571884984026, "percentage": 13.08, "elapsed_time": "0:19:46", "remaining_time": "2:11:24"}
+{"current_steps": 52, "total_steps": 390, "loss": 0.6183, "lr": 3.9864767154838864e-05, "epoch": 0.6645367412140575, "percentage": 13.33, "elapsed_time": "0:20:08", "remaining_time": "2:10:54"}
+{"current_steps": 53, "total_steps": 390, "loss": 0.6471, "lr": 3.9843190181323744e-05, "epoch": 0.6773162939297125, "percentage": 13.59, "elapsed_time": "0:20:31", "remaining_time": "2:10:32"}
+{"current_steps": 54, "total_steps": 390, "loss": 0.6251, "lr": 3.982002358491817e-05, "epoch": 0.6900958466453674, "percentage": 13.85, "elapsed_time": "0:20:55", "remaining_time": "2:10:08"}
+{"current_steps": 55, "total_steps": 390, "loss": 0.6225, "lr": 3.979526922148058e-05, "epoch": 0.7028753993610224, "percentage": 14.1, "elapsed_time": "0:21:17", "remaining_time": "2:09:40"}
+{"current_steps": 56, "total_steps": 390, "loss": 0.6463, "lr": 3.9768929074064206e-05, "epoch": 0.7156549520766773, "percentage": 14.36, "elapsed_time": "0:21:40", "remaining_time": "2:09:17"}
+{"current_steps": 57, "total_steps": 390, "loss": 0.6225, "lr": 3.9741005252758255e-05, "epoch": 0.7284345047923323, "percentage": 14.62, "elapsed_time": "0:22:04", "remaining_time": "2:08:57"}
+{"current_steps": 58, "total_steps": 390, "loss": 0.6057, "lr": 3.971149999451886e-05, "epoch": 0.7412140575079872, "percentage": 14.87, "elapsed_time": "0:22:27", "remaining_time": "2:08:31"}
+{"current_steps": 59, "total_steps": 390, "loss": 0.6191, "lr": 3.9680415662989806e-05, "epoch": 0.7539936102236422, "percentage": 15.13, "elapsed_time": "0:22:49", "remaining_time": "2:08:05"}
+{"current_steps": 60, "total_steps": 390, "loss": 0.623, "lr": 3.9647754748313294e-05, "epoch": 0.7667731629392971, "percentage": 15.38, "elapsed_time": "0:23:12", "remaining_time": "2:07:39"}
+{"current_steps": 61, "total_steps": 390, "loss": 0.6167, "lr": 3.96135198669304e-05, "epoch": 0.7795527156549521, "percentage": 15.64, "elapsed_time": "0:23:36", "remaining_time": "2:07:19"}
+{"current_steps": 62, "total_steps": 390, "loss": 0.6227, "lr": 3.957771376137144e-05, "epoch": 0.792332268370607, "percentage": 15.9, "elapsed_time": "0:23:59", "remaining_time": "2:06:57"}
+{"current_steps": 63, "total_steps": 390, "loss": 0.6239, "lr": 3.954033930003634e-05, "epoch": 0.805111821086262, "percentage": 16.15, "elapsed_time": "0:24:22", "remaining_time": "2:06:30"}
+{"current_steps": 64, "total_steps": 390, "loss": 0.6117, "lr": 3.9501399476964806e-05, "epoch": 0.8178913738019169, "percentage": 16.41, "elapsed_time": "0:24:45", "remaining_time": "2:06:05"}
+{"current_steps": 65, "total_steps": 390, "loss": 0.6174, "lr": 3.946089741159648e-05, "epoch": 0.8306709265175719, "percentage": 16.67, "elapsed_time": "0:25:07", "remaining_time": "2:05:38"}
+{"current_steps": 66, "total_steps": 390, "loss": 0.6155, "lr": 3.9418836348521045e-05, "epoch": 0.8434504792332268, "percentage": 16.92, "elapsed_time": "0:25:30", "remaining_time": "2:05:11"}
+{"current_steps": 67, "total_steps": 390, "loss": 0.6208, "lr": 3.937521965721831e-05, "epoch": 0.8562300319488818, "percentage": 17.18, "elapsed_time": "0:25:53", "remaining_time": "2:04:46"}
+{"current_steps": 68, "total_steps": 390, "loss": 0.5886, "lr": 3.933005083178828e-05, "epoch": 0.8690095846645367, "percentage": 17.44, "elapsed_time": "0:26:15", "remaining_time": "2:04:22"}
+{"current_steps": 69, "total_steps": 390, "loss": 0.6167, "lr": 3.928333349067125e-05, "epoch": 0.8817891373801917, "percentage": 17.69, "elapsed_time": "0:26:39", "remaining_time": "2:03:59"}
+{"current_steps": 70, "total_steps": 390, "loss": 0.6064, "lr": 3.923507137635792e-05, "epoch": 0.8945686900958466, "percentage": 17.95, "elapsed_time": "0:27:02", "remaining_time": "2:03:36"}
+{"current_steps": 71, "total_steps": 390, "loss": 0.5933, "lr": 3.9185268355089606e-05, "epoch": 0.9073482428115016, "percentage": 18.21, "elapsed_time": "0:27:25", "remaining_time": "2:03:12"}
+{"current_steps": 72, "total_steps": 390, "loss": 0.6008, "lr": 3.913392841654851e-05, "epoch": 0.9201277955271565, "percentage": 18.46, "elapsed_time": "0:27:48", "remaining_time": "2:02:50"}
+{"current_steps": 73, "total_steps": 390, "loss": 0.6211, "lr": 3.9081055673538093e-05, "epoch": 0.9329073482428115, "percentage": 18.72, "elapsed_time": "0:28:11", "remaining_time": "2:02:27"}
+{"current_steps": 74, "total_steps": 390, "loss": 0.6029, "lr": 3.902665436165364e-05, "epoch": 0.9456869009584664, "percentage": 18.97, "elapsed_time": "0:28:34", "remaining_time": "2:02:02"}
+{"current_steps": 75, "total_steps": 390, "loss": 0.6023, "lr": 3.897072883894291e-05, "epoch": 0.9584664536741214, "percentage": 19.23, "elapsed_time": "0:28:56", "remaining_time": "2:01:33"}
+{"current_steps": 76, "total_steps": 390, "loss": 0.6085, "lr": 3.8913283585557054e-05, "epoch": 0.9712460063897763, "percentage": 19.49, "elapsed_time": "0:29:20", "remaining_time": "2:01:12"}
+{"current_steps": 77, "total_steps": 390, "loss": 0.6035, "lr": 3.885432320339167e-05, "epoch": 0.9840255591054313, "percentage": 19.74, "elapsed_time": "0:29:42", "remaining_time": "2:00:47"}
+{"current_steps": 78, "total_steps": 390, "loss": 0.6017, "lr": 3.879385241571817e-05, "epoch": 0.9968051118210862, "percentage": 20.0, "elapsed_time": "0:30:06", "remaining_time": "2:00:25"}
+{"current_steps": 79, "total_steps": 390, "loss": 0.5699, "lr": 3.873187606680543e-05, "epoch": 1.0095846645367412, "percentage": 20.26, "elapsed_time": "0:32:28", "remaining_time": "2:07:50"}
+{"current_steps": 80, "total_steps": 390, "loss": 0.5432, "lr": 3.866839912153168e-05, "epoch": 1.0223642172523961, "percentage": 20.51, "elapsed_time": "0:32:51", "remaining_time": "2:07:20"}
+{"current_steps": 81, "total_steps": 390, "loss": 0.5442, "lr": 3.860342666498677e-05, "epoch": 1.035143769968051, "percentage": 20.77, "elapsed_time": "0:33:13", "remaining_time": "2:06:44"}
+{"current_steps": 82, "total_steps": 390, "loss": 0.5384, "lr": 3.853696390206484e-05, "epoch": 1.0479233226837061, "percentage": 21.03, "elapsed_time": "0:33:36", "remaining_time": "2:06:13"}
+{"current_steps": 83, "total_steps": 390, "loss": 0.5649, "lr": 3.846901615704734e-05, "epoch": 1.060702875399361, "percentage": 21.28, "elapsed_time": "0:33:59", "remaining_time": "2:05:44"}
+{"current_steps": 84, "total_steps": 390, "loss": 0.5498, "lr": 3.839958887317649e-05, "epoch": 1.073482428115016, "percentage": 21.54, "elapsed_time": "0:34:23", "remaining_time": "2:05:15"}
+{"current_steps": 85, "total_steps": 390, "loss": 0.5283, "lr": 3.832868761221926e-05, "epoch": 1.0862619808306708, "percentage": 21.79, "elapsed_time": "0:34:46", "remaining_time": "2:04:46"}
+{"current_steps": 86, "total_steps": 390, "loss": 0.5429, "lr": 3.825631805402182e-05, "epoch": 1.099041533546326, "percentage": 22.05, "elapsed_time": "0:35:09", "remaining_time": "2:04:15"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84f391c4332a72597fd62d46f9f3fc5402d50acb0d020bd9670ec9a7e1855ce
+size 7288