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 sha256:4424dcc0f0fba2014b0cbf275c4e3c34d7114b44e0b3b9ad33e68da9c27fd16b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b2ecdef60cf8444d430aeb45ac57e8e59d5e7c7b03f19960f71631243d5ed0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc38f6b035c3a871355946db1f0a862790b8035581e9c20d8630687984803fe
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df00978a2aa4d1083f32e3428c2ff4efee5c6beaf0e907b1e8f5561ba809ea13
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,93 @@
+{"current_steps": 1, "total_steps": 276, "loss": 0.8567, "lr": 4.04061e-06, "epoch": 0.010825439783491205, "percentage": 0.36, "elapsed_time": "0:02:32", "remaining_time": "11:38:03"}
+{"current_steps": 2, "total_steps": 276, "loss": 0.8604, "lr": 8.08122e-06, "epoch": 0.02165087956698241, "percentage": 0.72, "elapsed_time": "0:04:10", "remaining_time": "9:32:37"}
+{"current_steps": 3, "total_steps": 276, "loss": 0.8206, "lr": 1.212183e-05, "epoch": 0.03247631935047361, "percentage": 1.09, "elapsed_time": "0:05:49", "remaining_time": "8:49:50"}
+{"current_steps": 4, "total_steps": 276, "loss": 0.7738, "lr": 1.616244e-05, "epoch": 0.04330175913396482, "percentage": 1.45, "elapsed_time": "0:07:27", "remaining_time": "8:27:23"}
+{"current_steps": 5, "total_steps": 276, "loss": 0.7833, "lr": 2.020305e-05, "epoch": 0.05412719891745602, "percentage": 1.81, "elapsed_time": "0:09:06", "remaining_time": "8:13:27"}
+{"current_steps": 6, "total_steps": 276, "loss": 0.7883, "lr": 2.424366e-05, "epoch": 0.06495263870094722, "percentage": 2.17, "elapsed_time": "0:10:45", "remaining_time": "8:03:53"}
+{"current_steps": 7, "total_steps": 276, "loss": 0.7834, "lr": 2.828427e-05, "epoch": 0.07577807848443843, "percentage": 2.54, "elapsed_time": "0:12:24", "remaining_time": "7:56:40"}
+{"current_steps": 8, "total_steps": 276, "loss": 0.7479, "lr": 3.232488e-05, "epoch": 0.08660351826792964, "percentage": 2.9, "elapsed_time": "0:14:02", "remaining_time": "7:50:27"}
+{"current_steps": 9, "total_steps": 276, "loss": 0.6909, "lr": 3.636549e-05, "epoch": 0.09742895805142084, "percentage": 3.26, "elapsed_time": "0:15:41", "remaining_time": "7:45:16"}
+{"current_steps": 10, "total_steps": 276, "loss": 0.6719, "lr": 4.04061e-05, "epoch": 0.10825439783491204, "percentage": 3.62, "elapsed_time": "0:17:19", "remaining_time": "7:40:45"}
+{"current_steps": 11, "total_steps": 276, "loss": 0.6462, "lr": 4.444671e-05, "epoch": 0.11907983761840325, "percentage": 3.99, "elapsed_time": "0:18:57", "remaining_time": "7:36:48"}
+{"current_steps": 12, "total_steps": 276, "loss": 0.6351, "lr": 4.848732e-05, "epoch": 0.12990527740189445, "percentage": 4.35, "elapsed_time": "0:20:35", "remaining_time": "7:33:09"}
+{"current_steps": 13, "total_steps": 276, "loss": 0.6228, "lr": 5.2527930000000004e-05, "epoch": 0.14073071718538566, "percentage": 4.71, "elapsed_time": "0:22:14", "remaining_time": "7:29:50"}
+{"current_steps": 14, "total_steps": 276, "loss": 0.6311, "lr": 5.656854e-05, "epoch": 0.15155615696887687, "percentage": 5.07, "elapsed_time": "0:23:52", "remaining_time": "7:26:47"}
+{"current_steps": 15, "total_steps": 276, "loss": 0.6178, "lr": 6.060915e-05, "epoch": 0.16238159675236807, "percentage": 5.43, "elapsed_time": "0:25:30", "remaining_time": "7:23:57"}
+{"current_steps": 16, "total_steps": 276, "loss": 0.604, "lr": 6.464976e-05, "epoch": 0.17320703653585928, "percentage": 5.8, "elapsed_time": "0:27:09", "remaining_time": "7:21:17"}
+{"current_steps": 17, "total_steps": 276, "loss": 0.6064, "lr": 6.869037e-05, "epoch": 0.18403247631935046, "percentage": 6.16, "elapsed_time": "0:28:47", "remaining_time": "7:18:44"}
+{"current_steps": 18, "total_steps": 276, "loss": 0.5883, "lr": 7.273098e-05, "epoch": 0.19485791610284167, "percentage": 6.52, "elapsed_time": "0:30:26", "remaining_time": "7:16:21"}
+{"current_steps": 19, "total_steps": 276, "loss": 0.5875, "lr": 7.677159e-05, "epoch": 0.20568335588633288, "percentage": 6.88, "elapsed_time": "0:32:05", "remaining_time": "7:13:59"}
+{"current_steps": 20, "total_steps": 276, "loss": 0.5996, "lr": 8.08122e-05, "epoch": 0.2165087956698241, "percentage": 7.25, "elapsed_time": "0:33:43", "remaining_time": "7:11:39"}
+{"current_steps": 21, "total_steps": 276, "loss": 0.5792, "lr": 8.485281e-05, "epoch": 0.2273342354533153, "percentage": 7.61, "elapsed_time": "0:35:21", "remaining_time": "7:09:26"}
+{"current_steps": 22, "total_steps": 276, "loss": 0.5806, "lr": 8.889342e-05, "epoch": 0.2381596752368065, "percentage": 7.97, "elapsed_time": "0:37:00", "remaining_time": "7:07:16"}
+{"current_steps": 23, "total_steps": 276, "loss": 0.573, "lr": 9.293403e-05, "epoch": 0.2489851150202977, "percentage": 8.33, "elapsed_time": "0:38:38", "remaining_time": "7:05:08"}
+{"current_steps": 24, "total_steps": 276, "loss": 0.5753, "lr": 9.697464e-05, "epoch": 0.2598105548037889, "percentage": 8.7, "elapsed_time": "0:40:17", "remaining_time": "7:03:02"}
+{"current_steps": 25, "total_steps": 276, "loss": 0.564, "lr": 0.00010101525000000001, "epoch": 0.2706359945872801, "percentage": 9.06, "elapsed_time": "0:41:55", "remaining_time": "7:00:59"}
+{"current_steps": 26, "total_steps": 276, "loss": 0.5529, "lr": 0.00010505586000000001, "epoch": 0.2814614343707713, "percentage": 9.42, "elapsed_time": "0:43:34", "remaining_time": "6:58:57"}
+{"current_steps": 27, "total_steps": 276, "loss": 0.5578, "lr": 0.00010909647, "epoch": 0.2922868741542625, "percentage": 9.78, "elapsed_time": "0:45:13", "remaining_time": "6:57:04"}
+{"current_steps": 28, "total_steps": 276, "loss": 0.5725, "lr": 0.00011313708, "epoch": 0.30311231393775373, "percentage": 10.14, "elapsed_time": "0:46:51", "remaining_time": "6:55:06"}
+{"current_steps": 29, "total_steps": 276, "loss": 0.5751, "lr": 0.00011313254125743567, "epoch": 0.31393775372124494, "percentage": 10.51, "elapsed_time": "0:48:30", "remaining_time": "6:53:09"}
+{"current_steps": 30, "total_steps": 276, "loss": 0.5513, "lr": 0.00011311892575806915, "epoch": 0.32476319350473615, "percentage": 10.87, "elapsed_time": "0:50:08", "remaining_time": "6:51:12"}
+{"current_steps": 31, "total_steps": 276, "loss": 0.5561, "lr": 0.00011309623568676317, "epoch": 0.33558863328822736, "percentage": 11.23, "elapsed_time": "0:51:47", "remaining_time": "6:49:22"}
+{"current_steps": 32, "total_steps": 276, "loss": 0.5524, "lr": 0.00011306447468456599, "epoch": 0.34641407307171856, "percentage": 11.59, "elapsed_time": "0:53:26", "remaining_time": "6:47:31"}
+{"current_steps": 33, "total_steps": 276, "loss": 0.56, "lr": 0.0001130236478481272, "epoch": 0.3572395128552097, "percentage": 11.96, "elapsed_time": "0:55:05", "remaining_time": "6:45:37"}
+{"current_steps": 34, "total_steps": 276, "loss": 0.5715, "lr": 0.00011297376172887978, "epoch": 0.3680649526387009, "percentage": 12.32, "elapsed_time": "0:56:43", "remaining_time": "6:43:45"}
+{"current_steps": 35, "total_steps": 276, "loss": 0.5509, "lr": 0.00011291482433198894, "epoch": 0.37889039242219213, "percentage": 12.68, "elapsed_time": "0:58:22", "remaining_time": "6:41:54"}
+{"current_steps": 36, "total_steps": 276, "loss": 0.5394, "lr": 0.00011284684511506735, "epoch": 0.38971583220568334, "percentage": 13.04, "elapsed_time": "1:00:00", "remaining_time": "6:40:01"}
+{"current_steps": 37, "total_steps": 276, "loss": 0.5478, "lr": 0.00011276983498665771, "epoch": 0.40054127198917455, "percentage": 13.41, "elapsed_time": "1:01:38", "remaining_time": "6:38:11"}
+{"current_steps": 38, "total_steps": 276, "loss": 0.535, "lr": 0.00011268380630448204, "epoch": 0.41136671177266576, "percentage": 13.77, "elapsed_time": "1:03:17", "remaining_time": "6:36:23"}
+{"current_steps": 39, "total_steps": 276, "loss": 0.6342, "lr": 0.00011258877287345884, "epoch": 0.42219215155615697, "percentage": 14.13, "elapsed_time": "1:04:55", "remaining_time": "6:34:34"}
+{"current_steps": 40, "total_steps": 276, "loss": 0.9216, "lr": 0.00011248474994348775, "epoch": 0.4330175913396482, "percentage": 14.49, "elapsed_time": "1:06:34", "remaining_time": "6:32:46"}
+{"current_steps": 41, "total_steps": 276, "loss": 0.6257, "lr": 0.00011237175420700238, "epoch": 0.4438430311231394, "percentage": 14.86, "elapsed_time": "1:08:12", "remaining_time": "6:30:58"}
+{"current_steps": 42, "total_steps": 276, "loss": 0.5676, "lr": 0.00011224980379629178, "epoch": 0.4546684709066306, "percentage": 15.22, "elapsed_time": "1:09:51", "remaining_time": "6:29:11"}
+{"current_steps": 43, "total_steps": 276, "loss": 0.5571, "lr": 0.0001121189182805907, "epoch": 0.4654939106901218, "percentage": 15.58, "elapsed_time": "1:11:29", "remaining_time": "6:27:24"}
+{"current_steps": 44, "total_steps": 276, "loss": 0.5752, "lr": 0.00011197911866293939, "epoch": 0.476319350473613, "percentage": 15.94, "elapsed_time": "1:13:07", "remaining_time": "6:25:36"}
+{"current_steps": 45, "total_steps": 276, "loss": 0.5675, "lr": 0.00011183042737681327, "epoch": 0.4871447902571042, "percentage": 16.3, "elapsed_time": "1:14:46", "remaining_time": "6:23:49"}
+{"current_steps": 46, "total_steps": 276, "loss": 0.5509, "lr": 0.00011167286828252297, "epoch": 0.4979702300405954, "percentage": 16.67, "elapsed_time": "1:16:24", "remaining_time": "6:22:02"}
+{"current_steps": 47, "total_steps": 276, "loss": 0.5437, "lr": 0.00011150646666338564, "epoch": 0.5087956698240866, "percentage": 17.03, "elapsed_time": "1:18:02", "remaining_time": "6:20:16"}
+{"current_steps": 48, "total_steps": 276, "loss": 0.5353, "lr": 0.00011133124922166763, "epoch": 0.5196211096075778, "percentage": 17.39, "elapsed_time": "1:19:41", "remaining_time": "6:18:30"}
+{"current_steps": 49, "total_steps": 276, "loss": 0.532, "lr": 0.00011114724407429968, "epoch": 0.530446549391069, "percentage": 17.75, "elapsed_time": "1:21:19", "remaining_time": "6:16:46"}
+{"current_steps": 50, "total_steps": 276, "loss": 0.5445, "lr": 0.00011095448074836505, "epoch": 0.5412719891745602, "percentage": 18.12, "elapsed_time": "1:22:58", "remaining_time": "6:15:01"}
+{"current_steps": 51, "total_steps": 276, "loss": 0.5331, "lr": 0.00011075299017636123, "epoch": 0.5520974289580515, "percentage": 18.48, "elapsed_time": "1:24:36", "remaining_time": "6:13:16"}
+{"current_steps": 52, "total_steps": 276, "loss": 0.5243, "lr": 0.00011054280469123641, "epoch": 0.5629228687415426, "percentage": 18.84, "elapsed_time": "1:26:14", "remaining_time": "6:11:31"}
+{"current_steps": 53, "total_steps": 276, "loss": 0.5243, "lr": 0.00011032395802120092, "epoch": 0.5737483085250338, "percentage": 19.2, "elapsed_time": "1:27:53", "remaining_time": "6:09:48"}
+{"current_steps": 54, "total_steps": 276, "loss": 0.5345, "lr": 0.00011009648528431498, "epoch": 0.584573748308525, "percentage": 19.57, "elapsed_time": "1:29:31", "remaining_time": "6:08:04"}
+{"current_steps": 55, "total_steps": 276, "loss": 0.5178, "lr": 0.00010986042298285322, "epoch": 0.5953991880920162, "percentage": 19.93, "elapsed_time": "1:31:10", "remaining_time": "6:06:21"}
+{"current_steps": 56, "total_steps": 276, "loss": 0.5246, "lr": 0.00010961580899744742, "epoch": 0.6062246278755075, "percentage": 20.29, "elapsed_time": "1:32:48", "remaining_time": "6:04:37"}
+{"current_steps": 57, "total_steps": 276, "loss": 0.5218, "lr": 0.00010936268258100764, "epoch": 0.6170500676589986, "percentage": 20.65, "elapsed_time": "1:34:27", "remaining_time": "6:02:53"}
+{"current_steps": 58, "total_steps": 276, "loss": 0.5221, "lr": 0.00010910108435242351, "epoch": 0.6278755074424899, "percentage": 21.01, "elapsed_time": "1:36:05", "remaining_time": "6:01:10"}
+{"current_steps": 59, "total_steps": 276, "loss": 0.5022, "lr": 0.00010883105629004603, "epoch": 0.638700947225981, "percentage": 21.38, "elapsed_time": "1:37:44", "remaining_time": "5:59:28"}
+{"current_steps": 60, "total_steps": 276, "loss": 0.5053, "lr": 0.00010855264172495148, "epoch": 0.6495263870094723, "percentage": 21.74, "elapsed_time": "1:39:22", "remaining_time": "5:57:45"}
+{"current_steps": 61, "total_steps": 276, "loss": 0.5204, "lr": 0.00010826588533398805, "epoch": 0.6603518267929634, "percentage": 22.1, "elapsed_time": "1:41:01", "remaining_time": "5:56:02"}
+{"current_steps": 62, "total_steps": 276, "loss": 0.5043, "lr": 0.00010797083313260666, "epoch": 0.6711772665764547, "percentage": 22.46, "elapsed_time": "1:42:39", "remaining_time": "5:54:20"}
+{"current_steps": 63, "total_steps": 276, "loss": 0.5159, "lr": 0.0001076675324674768, "epoch": 0.6820027063599459, "percentage": 22.83, "elapsed_time": "1:44:17", "remaining_time": "5:52:37"}
+{"current_steps": 64, "total_steps": 276, "loss": 0.5075, "lr": 0.00010735603200888909, "epoch": 0.6928281461434371, "percentage": 23.19, "elapsed_time": "1:45:56", "remaining_time": "5:50:54"}
+{"current_steps": 65, "total_steps": 276, "loss": 0.5008, "lr": 0.00010703638174294492, "epoch": 0.7036535859269283, "percentage": 23.55, "elapsed_time": "1:47:34", "remaining_time": "5:49:12"}
+{"current_steps": 66, "total_steps": 276, "loss": 0.5041, "lr": 0.00010670863296353553, "epoch": 0.7144790257104194, "percentage": 23.91, "elapsed_time": "1:49:13", "remaining_time": "5:47:30"}
+{"current_steps": 67, "total_steps": 276, "loss": 0.5023, "lr": 0.00010637283826411074, "epoch": 0.7253044654939107, "percentage": 24.28, "elapsed_time": "1:50:51", "remaining_time": "5:45:48"}
+{"current_steps": 68, "total_steps": 276, "loss": 0.5114, "lr": 0.00010602905152923944, "epoch": 0.7361299052774019, "percentage": 24.64, "elapsed_time": "1:52:29", "remaining_time": "5:44:06"}
+{"current_steps": 69, "total_steps": 276, "loss": 0.5007, "lr": 0.00010567732792596276, "epoch": 0.7469553450608931, "percentage": 25.0, "elapsed_time": "1:54:08", "remaining_time": "5:42:24"}
+{"current_steps": 70, "total_steps": 276, "loss": 0.4829, "lr": 0.00010531772389494152, "epoch": 0.7577807848443843, "percentage": 25.36, "elapsed_time": "1:55:46", "remaining_time": "5:40:41"}
+{"current_steps": 71, "total_steps": 276, "loss": 0.4843, "lr": 0.0001049502971413992, "epoch": 0.7686062246278755, "percentage": 25.72, "elapsed_time": "1:57:24", "remaining_time": "5:38:59"}
+{"current_steps": 72, "total_steps": 276, "loss": 0.4952, "lr": 0.00010457510662586213, "epoch": 0.7794316644113667, "percentage": 26.09, "elapsed_time": "1:59:02", "remaining_time": "5:37:17"}
+{"current_steps": 73, "total_steps": 276, "loss": 0.4991, "lr": 0.00010419221255469808, "epoch": 0.790257104194858, "percentage": 26.45, "elapsed_time": "2:00:41", "remaining_time": "5:35:36"}
+{"current_steps": 74, "total_steps": 276, "loss": 0.4934, "lr": 0.00010380167637045515, "epoch": 0.8010825439783491, "percentage": 26.81, "elapsed_time": "2:02:19", "remaining_time": "5:33:55"}
+{"current_steps": 75, "total_steps": 276, "loss": 0.488, "lr": 0.00010340356074200197, "epoch": 0.8119079837618404, "percentage": 27.17, "elapsed_time": "2:03:58", "remaining_time": "5:32:14"}
+{"current_steps": 76, "total_steps": 276, "loss": 0.4813, "lr": 0.00010299792955447147, "epoch": 0.8227334235453315, "percentage": 27.54, "elapsed_time": "2:05:36", "remaining_time": "5:30:33"}
+{"current_steps": 77, "total_steps": 276, "loss": 0.4793, "lr": 0.00010258484789900923, "epoch": 0.8335588633288228, "percentage": 27.9, "elapsed_time": "2:07:15", "remaining_time": "5:28:53"}
+{"current_steps": 78, "total_steps": 276, "loss": 0.4868, "lr": 0.00010216438206232844, "epoch": 0.8443843031123139, "percentage": 28.26, "elapsed_time": "2:08:53", "remaining_time": "5:27:12"}
+{"current_steps": 79, "total_steps": 276, "loss": 0.4896, "lr": 0.00010173659951607282, "epoch": 0.8552097428958051, "percentage": 28.62, "elapsed_time": "2:10:32", "remaining_time": "5:25:31"}
+{"current_steps": 80, "total_steps": 276, "loss": 0.484, "lr": 0.00010130156890598967, "epoch": 0.8660351826792964, "percentage": 28.99, "elapsed_time": "2:12:10", "remaining_time": "5:23:50"}
+{"current_steps": 81, "total_steps": 276, "loss": 0.491, "lr": 0.00010085936004091438, "epoch": 0.8768606224627875, "percentage": 29.35, "elapsed_time": "2:13:49", "remaining_time": "5:22:10"}
+{"current_steps": 82, "total_steps": 276, "loss": 0.4779, "lr": 0.0001004100438815681, "epoch": 0.8876860622462788, "percentage": 29.71, "elapsed_time": "2:15:27", "remaining_time": "5:20:29"}
+{"current_steps": 83, "total_steps": 276, "loss": 0.4851, "lr": 9.995369252917098e-05, "epoch": 0.8985115020297699, "percentage": 30.07, "elapsed_time": "2:17:06", "remaining_time": "5:18:49"}
+{"current_steps": 84, "total_steps": 276, "loss": 0.4854, "lr": 9.949037921387205e-05, "epoch": 0.9093369418132612, "percentage": 30.43, "elapsed_time": "2:18:44", "remaining_time": "5:17:08"}
+{"current_steps": 85, "total_steps": 276, "loss": 0.477, "lr": 9.902017828299812e-05, "epoch": 0.9201623815967523, "percentage": 30.8, "elapsed_time": "2:20:23", "remaining_time": "5:15:27"}
+{"current_steps": 86, "total_steps": 276, "loss": 0.4856, "lr": 9.854316518912328e-05, "epoch": 0.9309878213802436, "percentage": 31.16, "elapsed_time": "2:22:01", "remaining_time": "5:13:47"}
+{"current_steps": 87, "total_steps": 276, "loss": 0.4813, "lr": 9.805941647796121e-05, "epoch": 0.9418132611637348, "percentage": 31.52, "elapsed_time": "2:23:40", "remaining_time": "5:12:07"}
+{"current_steps": 88, "total_steps": 276, "loss": 0.4655, "lr": 9.756900977608196e-05, "epoch": 0.952638700947226, "percentage": 31.88, "elapsed_time": "2:25:18", "remaining_time": "5:10:26"}
+{"current_steps": 89, "total_steps": 276, "loss": 0.4848, "lr": 9.707202377845526e-05, "epoch": 0.9634641407307172, "percentage": 32.25, "elapsed_time": "2:26:57", "remaining_time": "5:08:45"}
+{"current_steps": 90, "total_steps": 276, "loss": 0.4783, "lr": 9.656853823582246e-05, "epoch": 0.9742895805142084, "percentage": 32.61, "elapsed_time": "2:28:35", "remaining_time": "5:07:04"}
+{"current_steps": 91, "total_steps": 276, "loss": 0.4808, "lr": 9.605863394189905e-05, "epoch": 0.9851150202976996, "percentage": 32.97, "elapsed_time": "2:30:13", "remaining_time": "5:05:24"}
+{"current_steps": 92, "total_steps": 276, "loss": 0.4794, "lr": 9.554239272040974e-05, "epoch": 0.9959404600811907, "percentage": 33.33, "elapsed_time": "2:31:51", "remaining_time": "5:03:43"}
+{"current_steps": 93, "total_steps": 276, "loss": 0.7428, "lr": 9.501989741195838e-05, "epoch": 1.006765899864682, "percentage": 33.7, "elapsed_time": "2:35:00", "remaining_time": "5:05:01"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f730f47936c2cc911831916319d3062cac91f93b0677e6c9cc1a5860a46e4b
+size 7224