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 sha256:4b6bc99e934eff4fdcc7af1d95c9ec3e2115bcade9ab597b27ce6b9caa176c20
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be672463b4229f2c0c94658b853bf44fe678359727a81c8f33e9b49291c3b7ff
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f5d9f4c8a23aa6aae06cd2939f25ce745776128d3d70d19001edec67cd5e98
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159058a1140980df75be1991b6af1d316ceb30691ba55e100b7e5d947affa4e7
+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 +1,105 @@
+{"current_steps": 1, "total_steps": 312, "loss": 0.9061, "lr": 3.125e-07, "epoch": 0.0096, "percentage": 0.32, "elapsed_time": "0:01:52", "remaining_time": "9:43:43"}
+{"current_steps": 2, "total_steps": 312, "loss": 0.9105, "lr": 6.25e-07, "epoch": 0.0192, "percentage": 0.64, "elapsed_time": "0:03:37", "remaining_time": "9:22:14"}
+{"current_steps": 3, "total_steps": 312, "loss": 0.9029, "lr": 9.375000000000001e-07, "epoch": 0.0288, "percentage": 0.96, "elapsed_time": "0:05:41", "remaining_time": "9:46:32"}
+{"current_steps": 4, "total_steps": 312, "loss": 0.9133, "lr": 1.25e-06, "epoch": 0.0384, "percentage": 1.28, "elapsed_time": "0:07:34", "remaining_time": "9:43:21"}
+{"current_steps": 5, "total_steps": 312, "loss": 0.8816, "lr": 1.5625e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:09:24", "remaining_time": "9:37:40"}
+{"current_steps": 6, "total_steps": 312, "loss": 0.8616, "lr": 1.8750000000000003e-06, "epoch": 0.0576, "percentage": 1.92, "elapsed_time": "0:11:09", "remaining_time": "9:29:27"}
+{"current_steps": 7, "total_steps": 312, "loss": 0.8717, "lr": 2.1875000000000002e-06, "epoch": 0.0672, "percentage": 2.24, "elapsed_time": "0:13:05", "remaining_time": "9:30:06"}
+{"current_steps": 8, "total_steps": 312, "loss": 0.8967, "lr": 2.5e-06, "epoch": 0.0768, "percentage": 2.56, "elapsed_time": "0:14:51", "remaining_time": "9:24:37"}
+{"current_steps": 9, "total_steps": 312, "loss": 0.8247, "lr": 2.8125e-06, "epoch": 0.0864, "percentage": 2.88, "elapsed_time": "0:16:27", "remaining_time": "9:14:06"}
+{"current_steps": 10, "total_steps": 312, "loss": 0.8194, "lr": 3.125e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:18:24", "remaining_time": "9:15:50"}
+{"current_steps": 11, "total_steps": 312, "loss": 0.8173, "lr": 3.4375e-06, "epoch": 0.1056, "percentage": 3.53, "elapsed_time": "0:20:05", "remaining_time": "9:09:49"}
+{"current_steps": 12, "total_steps": 312, "loss": 0.8072, "lr": 3.7500000000000005e-06, "epoch": 0.1152, "percentage": 3.85, "elapsed_time": "0:21:44", "remaining_time": "9:03:28"}
+{"current_steps": 13, "total_steps": 312, "loss": 0.7925, "lr": 4.0625000000000005e-06, "epoch": 0.1248, "percentage": 4.17, "elapsed_time": "0:23:32", "remaining_time": "9:01:24"}
+{"current_steps": 14, "total_steps": 312, "loss": 0.7964, "lr": 4.3750000000000005e-06, "epoch": 0.1344, "percentage": 4.49, "elapsed_time": "0:25:27", "remaining_time": "9:01:51"}
+{"current_steps": 15, "total_steps": 312, "loss": 0.7774, "lr": 4.6875000000000004e-06, "epoch": 0.144, "percentage": 4.81, "elapsed_time": "0:27:17", "remaining_time": "9:00:25"}
+{"current_steps": 16, "total_steps": 312, "loss": 0.757, "lr": 5e-06, "epoch": 0.1536, "percentage": 5.13, "elapsed_time": "0:28:59", "remaining_time": "8:56:25"}
+{"current_steps": 17, "total_steps": 312, "loss": 0.7718, "lr": 5.3125e-06, "epoch": 0.1632, "percentage": 5.45, "elapsed_time": "0:30:55", "remaining_time": "8:56:45"}
+{"current_steps": 18, "total_steps": 312, "loss": 0.7582, "lr": 5.625e-06, "epoch": 0.1728, "percentage": 5.77, "elapsed_time": "0:32:46", "remaining_time": "8:55:24"}
+{"current_steps": 19, "total_steps": 312, "loss": 0.7192, "lr": 5.9375e-06, "epoch": 0.1824, "percentage": 6.09, "elapsed_time": "0:34:33", "remaining_time": "8:53:02"}
+{"current_steps": 20, "total_steps": 312, "loss": 0.7072, "lr": 6.25e-06, "epoch": 0.192, "percentage": 6.41, "elapsed_time": "0:36:23", "remaining_time": "8:51:15"}
+{"current_steps": 21, "total_steps": 312, "loss": 0.7075, "lr": 6.5625e-06, "epoch": 0.2016, "percentage": 6.73, "elapsed_time": "0:38:23", "remaining_time": "8:52:06"}
+{"current_steps": 22, "total_steps": 312, "loss": 0.7336, "lr": 6.875e-06, "epoch": 0.2112, "percentage": 7.05, "elapsed_time": "0:40:22", "remaining_time": "8:52:16"}
+{"current_steps": 23, "total_steps": 312, "loss": 0.6851, "lr": 7.1875e-06, "epoch": 0.2208, "percentage": 7.37, "elapsed_time": "0:42:03", "remaining_time": "8:48:22"}
+{"current_steps": 24, "total_steps": 312, "loss": 0.6955, "lr": 7.500000000000001e-06, "epoch": 0.2304, "percentage": 7.69, "elapsed_time": "0:43:49", "remaining_time": "8:45:50"}
+{"current_steps": 25, "total_steps": 312, "loss": 0.6746, "lr": 7.8125e-06, "epoch": 0.24, "percentage": 8.01, "elapsed_time": "0:45:32", "remaining_time": "8:42:51"}
+{"current_steps": 26, "total_steps": 312, "loss": 0.6963, "lr": 8.125000000000001e-06, "epoch": 0.2496, "percentage": 8.33, "elapsed_time": "0:47:15", "remaining_time": "8:39:50"}
+{"current_steps": 27, "total_steps": 312, "loss": 0.6886, "lr": 8.4375e-06, "epoch": 0.2592, "percentage": 8.65, "elapsed_time": "0:49:03", "remaining_time": "8:37:50"}
+{"current_steps": 28, "total_steps": 312, "loss": 0.6746, "lr": 8.750000000000001e-06, "epoch": 0.2688, "percentage": 8.97, "elapsed_time": "0:50:51", "remaining_time": "8:35:53"}
+{"current_steps": 29, "total_steps": 312, "loss": 0.6852, "lr": 9.0625e-06, "epoch": 0.2784, "percentage": 9.29, "elapsed_time": "0:52:29", "remaining_time": "8:32:18"}
+{"current_steps": 30, "total_steps": 312, "loss": 0.6524, "lr": 9.375000000000001e-06, "epoch": 0.288, "percentage": 9.62, "elapsed_time": "0:54:04", "remaining_time": "8:28:18"}
+{"current_steps": 31, "total_steps": 312, "loss": 0.6993, "lr": 9.6875e-06, "epoch": 0.2976, "percentage": 9.94, "elapsed_time": "0:55:57", "remaining_time": "8:27:11"}
+{"current_steps": 32, "total_steps": 312, "loss": 0.6839, "lr": 1e-05, "epoch": 0.3072, "percentage": 10.26, "elapsed_time": "0:57:35", "remaining_time": "8:23:56"}
+{"current_steps": 33, "total_steps": 312, "loss": 0.6732, "lr": 9.999685283773504e-06, "epoch": 0.3168, "percentage": 10.58, "elapsed_time": "0:59:16", "remaining_time": "8:21:08"}
+{"current_steps": 34, "total_steps": 312, "loss": 0.6645, "lr": 9.998741174712534e-06, "epoch": 0.3264, "percentage": 10.9, "elapsed_time": "1:00:43", "remaining_time": "8:16:33"}
+{"current_steps": 35, "total_steps": 312, "loss": 0.6251, "lr": 9.997167791667668e-06, "epoch": 0.336, "percentage": 11.22, "elapsed_time": "1:02:46", "remaining_time": "8:16:49"}
+{"current_steps": 36, "total_steps": 312, "loss": 0.6305, "lr": 9.994965332706574e-06, "epoch": 0.3456, "percentage": 11.54, "elapsed_time": "1:04:35", "remaining_time": "8:15:11"}
+{"current_steps": 37, "total_steps": 312, "loss": 0.6501, "lr": 9.992134075089085e-06, "epoch": 0.3552, "percentage": 11.86, "elapsed_time": "1:06:30", "remaining_time": "8:14:21"}
+{"current_steps": 38, "total_steps": 312, "loss": 0.6473, "lr": 9.98867437523228e-06, "epoch": 0.3648, "percentage": 12.18, "elapsed_time": "1:08:26", "remaining_time": "8:13:32"}
+{"current_steps": 39, "total_steps": 312, "loss": 0.6267, "lr": 9.984586668665641e-06, "epoch": 0.3744, "percentage": 12.5, "elapsed_time": "1:10:06", "remaining_time": "8:10:45"}
+{"current_steps": 40, "total_steps": 312, "loss": 0.6353, "lr": 9.979871469976197e-06, "epoch": 0.384, "percentage": 12.82, "elapsed_time": "1:11:47", "remaining_time": "8:08:08"}
+{"current_steps": 41, "total_steps": 312, "loss": 0.6697, "lr": 9.974529372743762e-06, "epoch": 0.3936, "percentage": 13.14, "elapsed_time": "1:13:30", "remaining_time": "8:05:50"}
+{"current_steps": 42, "total_steps": 312, "loss": 0.6229, "lr": 9.968561049466214e-06, "epoch": 0.4032, "percentage": 13.46, "elapsed_time": "1:15:12", "remaining_time": "8:03:28"}
+{"current_steps": 43, "total_steps": 312, "loss": 0.6199, "lr": 9.961967251474823e-06, "epoch": 0.4128, "percentage": 13.78, "elapsed_time": "1:17:08", "remaining_time": "8:02:32"}
+{"current_steps": 44, "total_steps": 312, "loss": 0.6642, "lr": 9.954748808839675e-06, "epoch": 0.4224, "percentage": 14.1, "elapsed_time": "1:19:11", "remaining_time": "8:02:20"}
+{"current_steps": 45, "total_steps": 312, "loss": 0.6415, "lr": 9.946906630265184e-06, "epoch": 0.432, "percentage": 14.42, "elapsed_time": "1:20:54", "remaining_time": "8:00:05"}
+{"current_steps": 46, "total_steps": 312, "loss": 0.6498, "lr": 9.938441702975689e-06, "epoch": 0.4416, "percentage": 14.74, "elapsed_time": "1:22:31", "remaining_time": "7:57:13"}
+{"current_steps": 47, "total_steps": 312, "loss": 0.6146, "lr": 9.92935509259118e-06, "epoch": 0.4512, "percentage": 15.06, "elapsed_time": "1:24:17", "remaining_time": "7:55:15"}
+{"current_steps": 48, "total_steps": 312, "loss": 0.6323, "lr": 9.91964794299315e-06, "epoch": 0.4608, "percentage": 15.38, "elapsed_time": "1:26:07", "remaining_time": "7:53:39"}
+{"current_steps": 49, "total_steps": 312, "loss": 0.6343, "lr": 9.909321476180594e-06, "epoch": 0.4704, "percentage": 15.71, "elapsed_time": "1:27:59", "remaining_time": "7:52:14"}
+{"current_steps": 50, "total_steps": 312, "loss": 0.6362, "lr": 9.898376992116179e-06, "epoch": 0.48, "percentage": 16.03, "elapsed_time": "1:29:39", "remaining_time": "7:49:46"}
+{"current_steps": 51, "total_steps": 312, "loss": 0.6336, "lr": 9.886815868562596e-06, "epoch": 0.4896, "percentage": 16.35, "elapsed_time": "1:31:34", "remaining_time": "7:48:38"}
+{"current_steps": 52, "total_steps": 312, "loss": 0.6389, "lr": 9.874639560909118e-06, "epoch": 0.4992, "percentage": 16.67, "elapsed_time": "1:33:36", "remaining_time": "7:48:01"}
+{"current_steps": 53, "total_steps": 312, "loss": 0.6277, "lr": 9.861849601988384e-06, "epoch": 0.5088, "percentage": 16.99, "elapsed_time": "1:35:26", "remaining_time": "7:46:25"}
+{"current_steps": 54, "total_steps": 312, "loss": 0.6166, "lr": 9.848447601883436e-06, "epoch": 0.5184, "percentage": 17.31, "elapsed_time": "1:37:29", "remaining_time": "7:45:49"}
+{"current_steps": 55, "total_steps": 312, "loss": 0.6193, "lr": 9.834435247725032e-06, "epoch": 0.528, "percentage": 17.63, "elapsed_time": "1:39:10", "remaining_time": "7:43:25"}
+{"current_steps": 56, "total_steps": 312, "loss": 0.6277, "lr": 9.819814303479268e-06, "epoch": 0.5376, "percentage": 17.95, "elapsed_time": "1:40:48", "remaining_time": "7:40:49"}
+{"current_steps": 57, "total_steps": 312, "loss": 0.5966, "lr": 9.804586609725499e-06, "epoch": 0.5472, "percentage": 18.27, "elapsed_time": "1:42:28", "remaining_time": "7:38:25"}
+{"current_steps": 58, "total_steps": 312, "loss": 0.6435, "lr": 9.788754083424654e-06, "epoch": 0.5568, "percentage": 18.59, "elapsed_time": "1:44:10", "remaining_time": "7:36:14"}
+{"current_steps": 59, "total_steps": 312, "loss": 0.653, "lr": 9.772318717677905e-06, "epoch": 0.5664, "percentage": 18.91, "elapsed_time": "1:46:07", "remaining_time": "7:35:03"}
+{"current_steps": 60, "total_steps": 312, "loss": 0.621, "lr": 9.755282581475769e-06, "epoch": 0.576, "percentage": 19.23, "elapsed_time": "1:47:43", "remaining_time": "7:32:26"}
+{"current_steps": 61, "total_steps": 312, "loss": 0.6077, "lr": 9.737647819437645e-06, "epoch": 0.5856, "percentage": 19.55, "elapsed_time": "1:49:29", "remaining_time": "7:30:30"}
+{"current_steps": 62, "total_steps": 312, "loss": 0.6279, "lr": 9.719416651541839e-06, "epoch": 0.5952, "percentage": 19.87, "elapsed_time": "1:51:15", "remaining_time": "7:28:36"}
+{"current_steps": 63, "total_steps": 312, "loss": 0.6158, "lr": 9.700591372846096e-06, "epoch": 0.6048, "percentage": 20.19, "elapsed_time": "1:53:01", "remaining_time": "7:26:41"}
+{"current_steps": 64, "total_steps": 312, "loss": 0.5928, "lr": 9.681174353198687e-06, "epoch": 0.6144, "percentage": 20.51, "elapsed_time": "1:54:46", "remaining_time": "7:24:44"}
+{"current_steps": 65, "total_steps": 312, "loss": 0.6023, "lr": 9.661168036940071e-06, "epoch": 0.624, "percentage": 20.83, "elapsed_time": "1:56:47", "remaining_time": "7:23:49"}
+{"current_steps": 66, "total_steps": 312, "loss": 0.6342, "lr": 9.640574942595195e-06, "epoch": 0.6336, "percentage": 21.15, "elapsed_time": "1:58:38", "remaining_time": "7:22:12"}
+{"current_steps": 67, "total_steps": 312, "loss": 0.5781, "lr": 9.619397662556434e-06, "epoch": 0.6432, "percentage": 21.47, "elapsed_time": "2:00:23", "remaining_time": "7:20:13"}
+{"current_steps": 68, "total_steps": 312, "loss": 0.5852, "lr": 9.597638862757255e-06, "epoch": 0.6528, "percentage": 21.79, "elapsed_time": "2:01:58", "remaining_time": "7:17:41"}
+{"current_steps": 69, "total_steps": 312, "loss": 0.5965, "lr": 9.5753012823366e-06, "epoch": 0.6624, "percentage": 22.12, "elapsed_time": "2:03:51", "remaining_time": "7:16:13"}
+{"current_steps": 70, "total_steps": 312, "loss": 0.5982, "lr": 9.552387733294081e-06, "epoch": 0.672, "percentage": 22.44, "elapsed_time": "2:05:52", "remaining_time": "7:15:08"}
+{"current_steps": 71, "total_steps": 312, "loss": 0.6152, "lr": 9.528901100135971e-06, "epoch": 0.6816, "percentage": 22.76, "elapsed_time": "2:07:31", "remaining_time": "7:12:51"}
+{"current_steps": 72, "total_steps": 312, "loss": 0.5856, "lr": 9.504844339512096e-06, "epoch": 0.6912, "percentage": 23.08, "elapsed_time": "2:09:30", "remaining_time": "7:11:42"}
+{"current_steps": 73, "total_steps": 312, "loss": 0.6151, "lr": 9.480220479843627e-06, "epoch": 0.7008, "percentage": 23.4, "elapsed_time": "2:11:25", "remaining_time": "7:10:16"}
+{"current_steps": 74, "total_steps": 312, "loss": 0.6251, "lr": 9.45503262094184e-06, "epoch": 0.7104, "percentage": 23.72, "elapsed_time": "2:13:08", "remaining_time": "7:08:12"}
+{"current_steps": 75, "total_steps": 312, "loss": 0.6015, "lr": 9.4292839336179e-06, "epoch": 0.72, "percentage": 24.04, "elapsed_time": "2:14:58", "remaining_time": "7:06:30"}
+{"current_steps": 76, "total_steps": 312, "loss": 0.5881, "lr": 9.40297765928369e-06, "epoch": 0.7296, "percentage": 24.36, "elapsed_time": "2:16:49", "remaining_time": "7:04:52"}
+{"current_steps": 77, "total_steps": 312, "loss": 0.5908, "lr": 9.376117109543769e-06, "epoch": 0.7392, "percentage": 24.68, "elapsed_time": "2:18:41", "remaining_time": "7:03:17"}
+{"current_steps": 78, "total_steps": 312, "loss": 0.6226, "lr": 9.348705665778479e-06, "epoch": 0.7488, "percentage": 25.0, "elapsed_time": "2:20:31", "remaining_time": "7:01:34"}
+{"current_steps": 79, "total_steps": 312, "loss": 0.6182, "lr": 9.320746778718274e-06, "epoch": 0.7584, "percentage": 25.32, "elapsed_time": "2:22:39", "remaining_time": "7:00:45"}
+{"current_steps": 80, "total_steps": 312, "loss": 0.6044, "lr": 9.292243968009332e-06, "epoch": 0.768, "percentage": 25.64, "elapsed_time": "2:24:25", "remaining_time": "6:58:49"}
+{"current_steps": 81, "total_steps": 312, "loss": 0.6141, "lr": 9.263200821770462e-06, "epoch": 0.7776, "percentage": 25.96, "elapsed_time": "2:26:08", "remaining_time": "6:56:46"}
+{"current_steps": 82, "total_steps": 312, "loss": 0.6298, "lr": 9.233620996141421e-06, "epoch": 0.7872, "percentage": 26.28, "elapsed_time": "2:28:03", "remaining_time": "6:55:17"}
+{"current_steps": 83, "total_steps": 312, "loss": 0.5925, "lr": 9.203508214822652e-06, "epoch": 0.7968, "percentage": 26.6, "elapsed_time": "2:29:43", "remaining_time": "6:53:04"}
+{"current_steps": 84, "total_steps": 312, "loss": 0.5883, "lr": 9.172866268606514e-06, "epoch": 0.8064, "percentage": 26.92, "elapsed_time": "2:31:30", "remaining_time": "6:51:14"}
+{"current_steps": 85, "total_steps": 312, "loss": 0.6336, "lr": 9.141699014900084e-06, "epoch": 0.816, "percentage": 27.24, "elapsed_time": "2:33:04", "remaining_time": "6:48:49"}
+{"current_steps": 86, "total_steps": 312, "loss": 0.6144, "lr": 9.110010377239552e-06, "epoch": 0.8256, "percentage": 27.56, "elapsed_time": "2:34:59", "remaining_time": "6:47:16"}
+{"current_steps": 87, "total_steps": 312, "loss": 0.5838, "lr": 9.077804344796302e-06, "epoch": 0.8352, "percentage": 27.88, "elapsed_time": "2:36:57", "remaining_time": "6:45:56"}
+{"current_steps": 88, "total_steps": 312, "loss": 0.6099, "lr": 9.045084971874738e-06, "epoch": 0.8448, "percentage": 28.21, "elapsed_time": "2:38:37", "remaining_time": "6:43:45"}
+{"current_steps": 89, "total_steps": 312, "loss": 0.6068, "lr": 9.011856377401891e-06, "epoch": 0.8544, "percentage": 28.53, "elapsed_time": "2:40:20", "remaining_time": "6:41:45"}
+{"current_steps": 90, "total_steps": 312, "loss": 0.5969, "lr": 8.978122744408905e-06, "epoch": 0.864, "percentage": 28.85, "elapsed_time": "2:42:07", "remaining_time": "6:39:54"}
+{"current_steps": 91, "total_steps": 312, "loss": 0.6134, "lr": 8.943888319504456e-06, "epoch": 0.8736, "percentage": 29.17, "elapsed_time": "2:43:57", "remaining_time": "6:38:11"}
+{"current_steps": 92, "total_steps": 312, "loss": 0.6013, "lr": 8.90915741234015e-06, "epoch": 0.8832, "percentage": 29.49, "elapsed_time": "2:45:35", "remaining_time": "6:35:59"}
+{"current_steps": 93, "total_steps": 312, "loss": 0.5696, "lr": 8.873934395068006e-06, "epoch": 0.8928, "percentage": 29.81, "elapsed_time": "2:47:35", "remaining_time": "6:34:39"}
+{"current_steps": 94, "total_steps": 312, "loss": 0.5992, "lr": 8.838223701790057e-06, "epoch": 0.9024, "percentage": 30.13, "elapsed_time": "2:49:20", "remaining_time": "6:32:43"}
+{"current_steps": 95, "total_steps": 312, "loss": 0.5747, "lr": 8.802029828000157e-06, "epoch": 0.912, "percentage": 30.45, "elapsed_time": "2:51:10", "remaining_time": "6:30:59"}
+{"current_steps": 96, "total_steps": 312, "loss": 0.5639, "lr": 8.765357330018056e-06, "epoch": 0.9216, "percentage": 30.77, "elapsed_time": "2:52:48", "remaining_time": "6:28:48"}
+{"current_steps": 97, "total_steps": 312, "loss": 0.5801, "lr": 8.728210824415829e-06, "epoch": 0.9312, "percentage": 31.09, "elapsed_time": "2:54:46", "remaining_time": "6:27:22"}
+{"current_steps": 98, "total_steps": 312, "loss": 0.6, "lr": 8.690594987436705e-06, "epoch": 0.9408, "percentage": 31.41, "elapsed_time": "2:56:12", "remaining_time": "6:24:46"}
+{"current_steps": 99, "total_steps": 312, "loss": 0.5812, "lr": 8.652514554406388e-06, "epoch": 0.9504, "percentage": 31.73, "elapsed_time": "2:58:03", "remaining_time": "6:23:06"}
+{"current_steps": 100, "total_steps": 312, "loss": 0.5749, "lr": 8.613974319136959e-06, "epoch": 0.96, "percentage": 32.05, "elapsed_time": "2:59:39", "remaining_time": "6:20:52"}
+{"current_steps": 101, "total_steps": 312, "loss": 0.583, "lr": 8.574979133323378e-06, "epoch": 0.9696, "percentage": 32.37, "elapsed_time": "3:01:29", "remaining_time": "6:19:09"}
+{"current_steps": 102, "total_steps": 312, "loss": 0.6007, "lr": 8.535533905932739e-06, "epoch": 0.9792, "percentage": 32.69, "elapsed_time": "3:03:25", "remaining_time": "6:17:37"}
+{"current_steps": 103, "total_steps": 312, "loss": 0.5838, "lr": 8.495643602586287e-06, "epoch": 0.9888, "percentage": 33.01, "elapsed_time": "3:04:56", "remaining_time": "6:15:16"}
+{"current_steps": 104, "total_steps": 312, "loss": 0.6134, "lr": 8.455313244934324e-06, "epoch": 0.9984, "percentage": 33.33, "elapsed_time": "3:06:24", "remaining_time": "6:12:49"}
+{"current_steps": 105, "total_steps": 312, "loss": 1.0593, "lr": 8.414547910024035e-06, "epoch": 1.008, "percentage": 33.65, "elapsed_time": "3:09:08", "remaining_time": "6:12:52"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a3e9445af99945b2fed54ca8cd24a2c9492a296c6fe29ed085fd548e022d9b
+size 7416