Training in progress, step 93

.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 +1,34 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-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": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "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 sha256:76ab9e55161916b84fd3099d1c1b6656ab7bc6649a1b10c8672f280072740581
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ebcb505715b061282133c32cf3dc8d57917ecc3c1c56827744c0d20559c00d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7db64433badd3b1ab7e072198b80bf67ecf638d0fa09aace32fddcedab4bbf
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f87a0c7a3a2b65f5693eb6784112baa285b5d9aaabf4b6b786fa91ebd8dfc47
+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": "<|im_end|>",
+    "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 +1,209 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 1, "total_steps": 93, "loss": 1.0142, "lr": 1.0000000000000002e-06, "epoch": 0.03208556149732621, "percentage": 1.08, "elapsed_time": "0:02:10", "remaining_time": "3:20:43"}
+{"current_steps": 2, "total_steps": 93, "loss": 1.0111, "lr": 2.0000000000000003e-06, "epoch": 0.06417112299465241, "percentage": 2.15, "elapsed_time": "0:03:53", "remaining_time": "2:57:07"}
+{"current_steps": 3, "total_steps": 93, "loss": 1.0203, "lr": 3e-06, "epoch": 0.0962566844919786, "percentage": 3.23, "elapsed_time": "0:05:57", "remaining_time": "2:58:38"}
+{"current_steps": 4, "total_steps": 93, "loss": 0.9815, "lr": 4.000000000000001e-06, "epoch": 0.12834224598930483, "percentage": 4.3, "elapsed_time": "0:07:54", "remaining_time": "2:55:51"}
+{"current_steps": 5, "total_steps": 93, "loss": 0.9497, "lr": 5e-06, "epoch": 0.16042780748663102, "percentage": 5.38, "elapsed_time": "0:09:43", "remaining_time": "2:51:12"}
+{"current_steps": 6, "total_steps": 93, "loss": 0.9655, "lr": 6e-06, "epoch": 0.1925133689839572, "percentage": 6.45, "elapsed_time": "0:11:39", "remaining_time": "2:48:56"}
+{"current_steps": 7, "total_steps": 93, "loss": 1.0031, "lr": 7e-06, "epoch": 0.22459893048128343, "percentage": 7.53, "elapsed_time": "0:13:16", "remaining_time": "2:43:04"}
+{"current_steps": 8, "total_steps": 93, "loss": 0.8836, "lr": 8.000000000000001e-06, "epoch": 0.25668449197860965, "percentage": 8.6, "elapsed_time": "0:14:54", "remaining_time": "2:38:19"}
+{"current_steps": 9, "total_steps": 93, "loss": 0.904, "lr": 9e-06, "epoch": 0.2887700534759358, "percentage": 9.68, "elapsed_time": "0:16:46", "remaining_time": "2:36:35"}
+{"current_steps": 10, "total_steps": 93, "loss": 0.8347, "lr": 1e-05, "epoch": 0.32085561497326204, "percentage": 10.75, "elapsed_time": "0:18:45", "remaining_time": "2:35:43"}
+{"current_steps": 11, "total_steps": 93, "loss": 0.8767, "lr": 9.996418774081658e-06, "epoch": 0.35294117647058826, "percentage": 11.83, "elapsed_time": "0:20:24", "remaining_time": "2:32:06"}
+{"current_steps": 12, "total_steps": 93, "loss": 0.8649, "lr": 9.985680226398261e-06, "epoch": 0.3850267379679144, "percentage": 12.9, "elapsed_time": "0:22:13", "remaining_time": "2:29:58"}
+{"current_steps": 13, "total_steps": 93, "loss": 0.8318, "lr": 9.967799739815925e-06, "epoch": 0.41711229946524064, "percentage": 13.98, "elapsed_time": "0:24:04", "remaining_time": "2:28:10"}
+{"current_steps": 14, "total_steps": 93, "loss": 0.8099, "lr": 9.942802927959444e-06, "epoch": 0.44919786096256686, "percentage": 15.05, "elapsed_time": "0:25:44", "remaining_time": "2:25:14"}
+{"current_steps": 15, "total_steps": 93, "loss": 0.7997, "lr": 9.910725598521014e-06, "epoch": 0.48128342245989303, "percentage": 16.13, "elapsed_time": "0:27:21", "remaining_time": "2:22:15"}
+{"current_steps": 16, "total_steps": 93, "loss": 0.8052, "lr": 9.871613701966067e-06, "epoch": 0.5133689839572193, "percentage": 17.2, "elapsed_time": "0:29:04", "remaining_time": "2:19:53"}
+{"current_steps": 17, "total_steps": 93, "loss": 0.8383, "lr": 9.825523265709667e-06, "epoch": 0.5454545454545454, "percentage": 18.28, "elapsed_time": "0:30:48", "remaining_time": "2:17:45"}
+{"current_steps": 18, "total_steps": 93, "loss": 0.8014, "lr": 9.772520313857777e-06, "epoch": 0.5775401069518716, "percentage": 19.35, "elapsed_time": "0:32:32", "remaining_time": "2:15:33"}
+{"current_steps": 19, "total_steps": 93, "loss": 0.7716, "lr": 9.712680772628365e-06, "epoch": 0.6096256684491979, "percentage": 20.43, "elapsed_time": "0:34:27", "remaining_time": "2:14:11"}
+{"current_steps": 20, "total_steps": 93, "loss": 0.7857, "lr": 9.646090361587828e-06, "epoch": 0.6417112299465241, "percentage": 21.51, "elapsed_time": "0:36:27", "remaining_time": "2:13:03"}
+{"current_steps": 21, "total_steps": 93, "loss": 0.7589, "lr": 9.572844470858537e-06, "epoch": 0.6737967914438503, "percentage": 22.58, "elapsed_time": "0:38:19", "remaining_time": "2:11:25"}
+{"current_steps": 22, "total_steps": 93, "loss": 0.7776, "lr": 9.493048024473413e-06, "epoch": 0.7058823529411765, "percentage": 23.66, "elapsed_time": "0:40:04", "remaining_time": "2:09:20"}
+{"current_steps": 23, "total_steps": 93, "loss": 0.7594, "lr": 9.406815330073244e-06, "epoch": 0.7379679144385026, "percentage": 24.73, "elapsed_time": "0:41:49", "remaining_time": "2:07:18"}
+{"current_steps": 24, "total_steps": 93, "loss": 0.7548, "lr": 9.314269915162115e-06, "epoch": 0.7700534759358288, "percentage": 25.81, "elapsed_time": "0:43:22", "remaining_time": "2:04:41"}
+{"current_steps": 25, "total_steps": 93, "loss": 0.7432, "lr": 9.215544350155423e-06, "epoch": 0.8021390374331551, "percentage": 26.88, "elapsed_time": "0:45:12", "remaining_time": "2:02:57"}
+{"current_steps": 26, "total_steps": 93, "loss": 0.7391, "lr": 9.110780058474052e-06, "epoch": 0.8342245989304813, "percentage": 27.96, "elapsed_time": "0:46:52", "remaining_time": "2:00:47"}
+{"current_steps": 27, "total_steps": 93, "loss": 0.7673, "lr": 9.000127113956673e-06, "epoch": 0.8663101604278075, "percentage": 29.03, "elapsed_time": "0:48:37", "remaining_time": "1:58:51"}
+{"current_steps": 28, "total_steps": 93, "loss": 0.747, "lr": 8.883744025880429e-06, "epoch": 0.8983957219251337, "percentage": 30.11, "elapsed_time": "0:50:31", "remaining_time": "1:57:16"}
+{"current_steps": 29, "total_steps": 93, "loss": 0.7633, "lr": 8.761797511897907e-06, "epoch": 0.93048128342246, "percentage": 31.18, "elapsed_time": "0:52:21", "remaining_time": "1:55:33"}
+{"current_steps": 30, "total_steps": 93, "loss": 0.7426, "lr": 8.634462259215719e-06, "epoch": 0.9625668449197861, "percentage": 32.26, "elapsed_time": "0:53:52", "remaining_time": "1:53:08"}
+{"current_steps": 31, "total_steps": 93, "loss": 0.7761, "lr": 8.501920674356755e-06, "epoch": 0.9946524064171123, "percentage": 33.33, "elapsed_time": "0:55:50", "remaining_time": "1:51:41"}
+{"current_steps": 32, "total_steps": 93, "loss": 0.7086, "lr": 8.364362621864595e-06, "epoch": 1.0, "percentage": 34.41, "elapsed_time": "0:56:08", "remaining_time": "1:47:01"}
+{"current_steps": 33, "total_steps": 93, "loss": 0.6956, "lr": 8.221985152324385e-06, "epoch": 1.032085561497326, "percentage": 35.48, "elapsed_time": "0:57:52", "remaining_time": "1:45:13"}
+{"current_steps": 34, "total_steps": 93, "loss": 0.6742, "lr": 8.07499222008977e-06, "epoch": 1.0641711229946524, "percentage": 36.56, "elapsed_time": "0:59:49", "remaining_time": "1:43:49"}
+{"current_steps": 35, "total_steps": 93, "loss": 0.6592, "lr": 7.923594391120237e-06, "epoch": 1.0962566844919786, "percentage": 37.63, "elapsed_time": "1:01:28", "remaining_time": "1:41:53"}
+{"current_steps": 36, "total_steps": 93, "loss": 0.6395, "lr": 7.768008541347423e-06, "epoch": 1.1283422459893049, "percentage": 38.71, "elapsed_time": "1:03:18", "remaining_time": "1:40:13"}
+{"current_steps": 37, "total_steps": 93, "loss": 0.6601, "lr": 7.608457546002423e-06, "epoch": 1.160427807486631, "percentage": 39.78, "elapsed_time": "1:05:08", "remaining_time": "1:38:35"}
+{"current_steps": 38, "total_steps": 93, "loss": 0.6438, "lr": 7.445169960349167e-06, "epoch": 1.192513368983957, "percentage": 40.86, "elapsed_time": "1:07:00", "remaining_time": "1:36:59"}
+{"current_steps": 39, "total_steps": 93, "loss": 0.7292, "lr": 7.278379692281209e-06, "epoch": 1.2245989304812834, "percentage": 41.94, "elapsed_time": "1:08:54", "remaining_time": "1:35:24"}
+{"current_steps": 40, "total_steps": 93, "loss": 0.6213, "lr": 7.10832566725092e-06, "epoch": 1.2566844919786098, "percentage": 43.01, "elapsed_time": "1:10:41", "remaining_time": "1:33:39"}
+{"current_steps": 41, "total_steps": 93, "loss": 0.6631, "lr": 6.9352514860110876e-06, "epoch": 1.2887700534759359, "percentage": 44.09, "elapsed_time": "1:12:35", "remaining_time": "1:32:03"}
+{"current_steps": 42, "total_steps": 93, "loss": 0.6472, "lr": 6.759405075659165e-06, "epoch": 1.320855614973262, "percentage": 45.16, "elapsed_time": "1:14:19", "remaining_time": "1:30:14"}
+{"current_steps": 43, "total_steps": 93, "loss": 0.661, "lr": 6.58103833448412e-06, "epoch": 1.3529411764705883, "percentage": 46.24, "elapsed_time": "1:15:55", "remaining_time": "1:28:17"}
+{"current_steps": 44, "total_steps": 93, "loss": 0.6537, "lr": 6.4004067711245366e-06, "epoch": 1.3850267379679144, "percentage": 47.31, "elapsed_time": "1:17:35", "remaining_time": "1:26:24"}
+{"current_steps": 45, "total_steps": 93, "loss": 0.6372, "lr": 6.2177691385549595e-06, "epoch": 1.4171122994652405, "percentage": 48.39, "elapsed_time": "1:19:20", "remaining_time": "1:24:37"}
+{"current_steps": 46, "total_steps": 93, "loss": 0.6449, "lr": 6.033387063424765e-06, "epoch": 1.4491978609625669, "percentage": 49.46, "elapsed_time": "1:21:00", "remaining_time": "1:22:46"}
+{"current_steps": 47, "total_steps": 93, "loss": 0.6532, "lr": 5.8475246712804845e-06, "epoch": 1.481283422459893, "percentage": 50.54, "elapsed_time": "1:22:52", "remaining_time": "1:21:07"}
+{"current_steps": 48, "total_steps": 93, "loss": 0.639, "lr": 5.660448208208513e-06, "epoch": 1.5133689839572193, "percentage": 51.61, "elapsed_time": "1:24:19", "remaining_time": "1:19:03"}
+{"current_steps": 49, "total_steps": 93, "loss": 0.6427, "lr": 5.472425659440157e-06, "epoch": 1.5454545454545454, "percentage": 52.69, "elapsed_time": "1:26:06", "remaining_time": "1:17:18"}
+{"current_steps": 50, "total_steps": 93, "loss": 0.6328, "lr": 5.2837263654653715e-06, "epoch": 1.5775401069518717, "percentage": 53.76, "elapsed_time": "1:27:53", "remaining_time": "1:15:34"}
+{"current_steps": 51, "total_steps": 93, "loss": 0.6267, "lr": 5.094620636205096e-06, "epoch": 1.6096256684491979, "percentage": 54.84, "elapsed_time": "1:29:32", "remaining_time": "1:13:44"}
+{"current_steps": 52, "total_steps": 93, "loss": 0.5955, "lr": 4.905379363794907e-06, "epoch": 1.641711229946524, "percentage": 55.91, "elapsed_time": "1:31:36", "remaining_time": "1:12:13"}
+{"current_steps": 53, "total_steps": 93, "loss": 0.6069, "lr": 4.71627363453463e-06, "epoch": 1.6737967914438503, "percentage": 56.99, "elapsed_time": "1:33:29", "remaining_time": "1:10:33"}
+{"current_steps": 54, "total_steps": 93, "loss": 0.6352, "lr": 4.527574340559844e-06, "epoch": 1.7058823529411766, "percentage": 58.06, "elapsed_time": "1:35:13", "remaining_time": "1:08:46"}
+{"current_steps": 55, "total_steps": 93, "loss": 0.6434, "lr": 4.33955179179149e-06, "epoch": 1.7379679144385025, "percentage": 59.14, "elapsed_time": "1:37:14", "remaining_time": "1:07:11"}
+{"current_steps": 56, "total_steps": 93, "loss": 0.6803, "lr": 4.152475328719517e-06, "epoch": 1.7700534759358288, "percentage": 60.22, "elapsed_time": "1:39:14", "remaining_time": "1:05:34"}
+{"current_steps": 57, "total_steps": 93, "loss": 0.5837, "lr": 3.966612936575235e-06, "epoch": 1.8021390374331552, "percentage": 61.29, "elapsed_time": "1:41:12", "remaining_time": "1:03:55"}
+{"current_steps": 58, "total_steps": 93, "loss": 0.6416, "lr": 3.782230861445041e-06, "epoch": 1.8342245989304813, "percentage": 62.37, "elapsed_time": "1:42:57", "remaining_time": "1:02:07"}
+{"current_steps": 59, "total_steps": 93, "loss": 0.594, "lr": 3.5995932288754655e-06, "epoch": 1.8663101604278074, "percentage": 63.44, "elapsed_time": "1:44:43", "remaining_time": "1:00:20"}
+{"current_steps": 60, "total_steps": 93, "loss": 0.613, "lr": 3.4189616655158803e-06, "epoch": 1.8983957219251337, "percentage": 64.52, "elapsed_time": "1:46:31", "remaining_time": "0:58:35"}
+{"current_steps": 61, "total_steps": 93, "loss": 0.6263, "lr": 3.240594924340835e-06, "epoch": 1.93048128342246, "percentage": 65.59, "elapsed_time": "1:48:13", "remaining_time": "0:56:46"}
+{"current_steps": 62, "total_steps": 93, "loss": 0.6344, "lr": 3.0647485139889145e-06, "epoch": 1.962566844919786, "percentage": 66.67, "elapsed_time": "1:49:49", "remaining_time": "0:54:54"}
+{"current_steps": 63, "total_steps": 93, "loss": 0.5962, "lr": 2.89167433274908e-06, "epoch": 1.9946524064171123, "percentage": 67.74, "elapsed_time": "1:51:29", "remaining_time": "0:53:05"}
+{"current_steps": 64, "total_steps": 93, "loss": 0.6669, "lr": 2.721620307718793e-06, "epoch": 2.0, "percentage": 68.82, "elapsed_time": "1:51:47", "remaining_time": "0:50:39"}
+{"current_steps": 65, "total_steps": 93, "loss": 0.5842, "lr": 2.554830039650834e-06, "epoch": 2.0320855614973263, "percentage": 69.89, "elapsed_time": "1:53:35", "remaining_time": "0:48:55"}
+{"current_steps": 66, "total_steps": 93, "loss": 0.6017, "lr": 2.391542453997578e-06, "epoch": 2.064171122994652, "percentage": 70.97, "elapsed_time": "1:55:05", "remaining_time": "0:47:05"}
+{"current_steps": 67, "total_steps": 93, "loss": 0.5905, "lr": 2.2319914586525776e-06, "epoch": 2.0962566844919786, "percentage": 72.04, "elapsed_time": "1:56:48", "remaining_time": "0:45:19"}
+{"current_steps": 68, "total_steps": 93, "loss": 0.5657, "lr": 2.0764056088797646e-06, "epoch": 2.128342245989305, "percentage": 73.12, "elapsed_time": "1:58:23", "remaining_time": "0:43:31"}
+{"current_steps": 69, "total_steps": 93, "loss": 0.5692, "lr": 1.9250077799102323e-06, "epoch": 2.160427807486631, "percentage": 74.19, "elapsed_time": "2:00:18", "remaining_time": "0:41:50"}
+{"current_steps": 70, "total_steps": 93, "loss": 0.5528, "lr": 1.7780148476756148e-06, "epoch": 2.192513368983957, "percentage": 75.27, "elapsed_time": "2:02:04", "remaining_time": "0:40:06"}
+{"current_steps": 71, "total_steps": 93, "loss": 0.5426, "lr": 1.6356373781354058e-06, "epoch": 2.2245989304812834, "percentage": 76.34, "elapsed_time": "2:03:55", "remaining_time": "0:38:24"}
+{"current_steps": 72, "total_steps": 93, "loss": 0.5578, "lr": 1.4980793256432474e-06, "epoch": 2.2566844919786098, "percentage": 77.42, "elapsed_time": "2:05:40", "remaining_time": "0:36:39"}
+{"current_steps": 73, "total_steps": 93, "loss": 0.5612, "lr": 1.3655377407842813e-06, "epoch": 2.2887700534759357, "percentage": 78.49, "elapsed_time": "2:07:30", "remaining_time": "0:34:55"}
+{"current_steps": 74, "total_steps": 93, "loss": 0.5616, "lr": 1.2382024881020937e-06, "epoch": 2.320855614973262, "percentage": 79.57, "elapsed_time": "2:09:19", "remaining_time": "0:33:12"}
+{"current_steps": 75, "total_steps": 93, "loss": 0.5736, "lr": 1.1162559741195733e-06, "epoch": 2.3529411764705883, "percentage": 80.65, "elapsed_time": "2:11:14", "remaining_time": "0:31:29"}
+{"current_steps": 76, "total_steps": 93, "loss": 0.5565, "lr": 9.998728860433277e-07, "epoch": 2.385026737967914, "percentage": 81.72, "elapsed_time": "2:13:11", "remaining_time": "0:29:47"}
+{"current_steps": 77, "total_steps": 93, "loss": 0.5509, "lr": 8.892199415259501e-07, "epoch": 2.4171122994652405, "percentage": 82.8, "elapsed_time": "2:14:57", "remaining_time": "0:28:02"}
+{"current_steps": 78, "total_steps": 93, "loss": 0.5783, "lr": 7.844556498445788e-07, "epoch": 2.449197860962567, "percentage": 83.87, "elapsed_time": "2:16:42", "remaining_time": "0:26:17"}
+{"current_steps": 79, "total_steps": 93, "loss": 0.553, "lr": 6.857300848378857e-07, "epoch": 2.481283422459893, "percentage": 84.95, "elapsed_time": "2:18:26", "remaining_time": "0:24:32"}
+{"current_steps": 80, "total_steps": 93, "loss": 0.5956, "lr": 5.931846699267558e-07, "epoch": 2.5133689839572195, "percentage": 86.02, "elapsed_time": "2:20:12", "remaining_time": "0:22:47"}
+{"current_steps": 81, "total_steps": 93, "loss": 0.564, "lr": 5.0695197552659e-07, "epoch": 2.5454545454545454, "percentage": 87.1, "elapsed_time": "2:22:10", "remaining_time": "0:21:03"}
+{"current_steps": 82, "total_steps": 93, "loss": 0.5545, "lr": 4.271555291414636e-07, "epoch": 2.5775401069518717, "percentage": 88.17, "elapsed_time": "2:23:48", "remaining_time": "0:19:17"}
+{"current_steps": 83, "total_steps": 93, "loss": 0.5994, "lr": 3.539096384121743e-07, "epoch": 2.6096256684491976, "percentage": 89.25, "elapsed_time": "2:25:42", "remaining_time": "0:17:33"}
+{"current_steps": 84, "total_steps": 93, "loss": 0.5615, "lr": 2.873192273716369e-07, "epoch": 2.641711229946524, "percentage": 90.32, "elapsed_time": "2:27:23", "remaining_time": "0:15:47"}
+{"current_steps": 85, "total_steps": 93, "loss": 0.5494, "lr": 2.274796861422246e-07, "epoch": 2.6737967914438503, "percentage": 91.4, "elapsed_time": "2:29:18", "remaining_time": "0:14:03"}
+{"current_steps": 86, "total_steps": 93, "loss": 0.5975, "lr": 1.7447673429033361e-07, "epoch": 2.7058823529411766, "percentage": 92.47, "elapsed_time": "2:31:04", "remaining_time": "0:12:17"}
+{"current_steps": 87, "total_steps": 93, "loss": 0.5877, "lr": 1.2838629803393343e-07, "epoch": 2.7379679144385025, "percentage": 93.55, "elapsed_time": "2:32:42", "remaining_time": "0:10:31"}
+{"current_steps": 88, "total_steps": 93, "loss": 0.5497, "lr": 8.927440147898703e-08, "epoch": 2.770053475935829, "percentage": 94.62, "elapsed_time": "2:34:39", "remaining_time": "0:08:47"}
+{"current_steps": 89, "total_steps": 93, "loss": 0.552, "lr": 5.7197072040557356e-08, "epoch": 2.802139037433155, "percentage": 95.7, "elapsed_time": "2:36:18", "remaining_time": "0:07:01"}
+{"current_steps": 90, "total_steps": 93, "loss": 0.5543, "lr": 3.220026018407541e-08, "epoch": 2.834224598930481, "percentage": 96.77, "elapsed_time": "2:38:05", "remaining_time": "0:05:16"}
+{"current_steps": 91, "total_steps": 93, "loss": 0.5606, "lr": 1.431977360173975e-08, "epoch": 2.8663101604278074, "percentage": 97.85, "elapsed_time": "2:39:42", "remaining_time": "0:03:30"}
+{"current_steps": 92, "total_steps": 93, "loss": 0.5859, "lr": 3.5812259183426457e-09, "epoch": 2.8983957219251337, "percentage": 98.92, "elapsed_time": "2:41:31", "remaining_time": "0:01:45"}
+{"current_steps": 93, "total_steps": 93, "loss": 0.5555, "lr": 0.0, "epoch": 2.93048128342246, "percentage": 100.0, "elapsed_time": "2:43:07", "remaining_time": "0:00:00"}
+{"current_steps": 93, "total_steps": 93, "epoch": 2.93048128342246, "percentage": 100.0, "elapsed_time": "2:44:32", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151c70b6fb09b0be2e705c26721c9114ed77a86f7f46c1957b9635a6c29b2367
+size 8184