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 sha256:7df587f9b27900e80c724f54f24be5001279fe9a5b548c5d0397955aba950b1d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5b68159d1f8f0a69b7884d39e4a440292b6d9486879e39ae2eddd1c1676cd5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73aa434b405be5c5de0c66774499298ea7ef3a1ea9b8f0edbd938faf1e4c2f4a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df07a88306c1f935b398c3da93e18634d6b7979f40e2d4ecbd944d2a62683174
+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 +1,85 @@
+{"current_steps": 1, "total_steps": 249, "loss": 1.2874, "lr": 4.0000000000000003e-07, "epoch": 0.012, "percentage": 0.4, "elapsed_time": "0:01:13", "remaining_time": "5:02:49"}
+{"current_steps": 2, "total_steps": 249, "loss": 1.3379, "lr": 8.000000000000001e-07, "epoch": 0.024, "percentage": 0.8, "elapsed_time": "0:02:06", "remaining_time": "4:20:21"}
+{"current_steps": 3, "total_steps": 249, "loss": 1.2253, "lr": 1.2000000000000002e-06, "epoch": 0.036, "percentage": 1.2, "elapsed_time": "0:02:56", "remaining_time": "4:00:38"}
+{"current_steps": 4, "total_steps": 249, "loss": 1.2606, "lr": 1.6000000000000001e-06, "epoch": 0.048, "percentage": 1.61, "elapsed_time": "0:03:52", "remaining_time": "3:57:26"}
+{"current_steps": 5, "total_steps": 249, "loss": 1.2299, "lr": 2.0000000000000003e-06, "epoch": 0.06, "percentage": 2.01, "elapsed_time": "0:04:47", "remaining_time": "3:53:58"}
+{"current_steps": 6, "total_steps": 249, "loss": 1.1999, "lr": 2.4000000000000003e-06, "epoch": 0.072, "percentage": 2.41, "elapsed_time": "0:05:42", "remaining_time": "3:51:27"}
+{"current_steps": 7, "total_steps": 249, "loss": 1.2123, "lr": 2.8000000000000003e-06, "epoch": 0.084, "percentage": 2.81, "elapsed_time": "0:06:33", "remaining_time": "3:46:44"}
+{"current_steps": 8, "total_steps": 249, "loss": 1.2145, "lr": 3.2000000000000003e-06, "epoch": 0.096, "percentage": 3.21, "elapsed_time": "0:07:31", "remaining_time": "3:46:28"}
+{"current_steps": 9, "total_steps": 249, "loss": 1.1699, "lr": 3.6000000000000003e-06, "epoch": 0.108, "percentage": 3.61, "elapsed_time": "0:08:29", "remaining_time": "3:46:15"}
+{"current_steps": 10, "total_steps": 249, "loss": 1.1446, "lr": 4.000000000000001e-06, "epoch": 0.12, "percentage": 4.02, "elapsed_time": "0:09:21", "remaining_time": "3:43:32"}
+{"current_steps": 11, "total_steps": 249, "loss": 1.1619, "lr": 4.4e-06, "epoch": 0.132, "percentage": 4.42, "elapsed_time": "0:10:17", "remaining_time": "3:42:48"}
+{"current_steps": 12, "total_steps": 249, "loss": 1.1448, "lr": 4.800000000000001e-06, "epoch": 0.144, "percentage": 4.82, "elapsed_time": "0:11:18", "remaining_time": "3:43:24"}
+{"current_steps": 13, "total_steps": 249, "loss": 1.1301, "lr": 5.2e-06, "epoch": 0.156, "percentage": 5.22, "elapsed_time": "0:12:17", "remaining_time": "3:43:10"}
+{"current_steps": 14, "total_steps": 249, "loss": 1.1112, "lr": 5.600000000000001e-06, "epoch": 0.168, "percentage": 5.62, "elapsed_time": "0:13:20", "remaining_time": "3:43:48"}
+{"current_steps": 15, "total_steps": 249, "loss": 1.1117, "lr": 6e-06, "epoch": 0.18, "percentage": 6.02, "elapsed_time": "0:14:23", "remaining_time": "3:44:36"}
+{"current_steps": 16, "total_steps": 249, "loss": 1.0957, "lr": 6.4000000000000006e-06, "epoch": 0.192, "percentage": 6.43, "elapsed_time": "0:15:22", "remaining_time": "3:43:54"}
+{"current_steps": 17, "total_steps": 249, "loss": 1.0306, "lr": 6.800000000000001e-06, "epoch": 0.204, "percentage": 6.83, "elapsed_time": "0:16:14", "remaining_time": "3:41:39"}
+{"current_steps": 18, "total_steps": 249, "loss": 1.069, "lr": 7.2000000000000005e-06, "epoch": 0.216, "percentage": 7.23, "elapsed_time": "0:17:16", "remaining_time": "3:41:46"}
+{"current_steps": 19, "total_steps": 249, "loss": 1.0052, "lr": 7.600000000000001e-06, "epoch": 0.228, "percentage": 7.63, "elapsed_time": "0:18:13", "remaining_time": "3:40:32"}
+{"current_steps": 20, "total_steps": 249, "loss": 1.0323, "lr": 8.000000000000001e-06, "epoch": 0.24, "percentage": 8.03, "elapsed_time": "0:19:12", "remaining_time": "3:39:51"}
+{"current_steps": 21, "total_steps": 249, "loss": 1.0235, "lr": 8.400000000000001e-06, "epoch": 0.252, "percentage": 8.43, "elapsed_time": "0:20:03", "remaining_time": "3:37:51"}
+{"current_steps": 22, "total_steps": 249, "loss": 1.0052, "lr": 8.8e-06, "epoch": 0.264, "percentage": 8.84, "elapsed_time": "0:20:52", "remaining_time": "3:35:25"}
+{"current_steps": 23, "total_steps": 249, "loss": 0.9629, "lr": 9.200000000000002e-06, "epoch": 0.276, "percentage": 9.24, "elapsed_time": "0:21:43", "remaining_time": "3:33:26"}
+{"current_steps": 24, "total_steps": 249, "loss": 0.9827, "lr": 9.600000000000001e-06, "epoch": 0.288, "percentage": 9.64, "elapsed_time": "0:22:36", "remaining_time": "3:31:58"}
+{"current_steps": 25, "total_steps": 249, "loss": 0.9396, "lr": 1e-05, "epoch": 0.3, "percentage": 10.04, "elapsed_time": "0:23:18", "remaining_time": "3:28:54"}
+{"current_steps": 26, "total_steps": 249, "loss": 0.9898, "lr": 9.999508258797876e-06, "epoch": 0.312, "percentage": 10.44, "elapsed_time": "0:24:23", "remaining_time": "3:29:16"}
+{"current_steps": 27, "total_steps": 249, "loss": 0.9925, "lr": 9.998033131915266e-06, "epoch": 0.324, "percentage": 10.84, "elapsed_time": "0:25:21", "remaining_time": "3:28:32"}
+{"current_steps": 28, "total_steps": 249, "loss": 0.9736, "lr": 9.995574909504434e-06, "epoch": 0.336, "percentage": 11.24, "elapsed_time": "0:26:17", "remaining_time": "3:27:29"}
+{"current_steps": 29, "total_steps": 249, "loss": 0.946, "lr": 9.992134075089085e-06, "epoch": 0.348, "percentage": 11.65, "elapsed_time": "0:27:01", "remaining_time": "3:25:00"}
+{"current_steps": 30, "total_steps": 249, "loss": 0.9901, "lr": 9.987711305469232e-06, "epoch": 0.36, "percentage": 12.05, "elapsed_time": "0:28:04", "remaining_time": "3:24:55"}
+{"current_steps": 31, "total_steps": 249, "loss": 0.9884, "lr": 9.982307470588097e-06, "epoch": 0.372, "percentage": 12.45, "elapsed_time": "0:29:09", "remaining_time": "3:25:01"}
+{"current_steps": 32, "total_steps": 249, "loss": 0.9645, "lr": 9.975923633360985e-06, "epoch": 0.384, "percentage": 12.85, "elapsed_time": "0:30:11", "remaining_time": "3:24:42"}
+{"current_steps": 33, "total_steps": 249, "loss": 0.9543, "lr": 9.968561049466214e-06, "epoch": 0.396, "percentage": 13.25, "elapsed_time": "0:31:09", "remaining_time": "3:23:55"}
+{"current_steps": 34, "total_steps": 249, "loss": 0.9672, "lr": 9.960221167098124e-06, "epoch": 0.408, "percentage": 13.65, "elapsed_time": "0:32:16", "remaining_time": "3:24:07"}
+{"current_steps": 35, "total_steps": 249, "loss": 0.9399, "lr": 9.950905626682229e-06, "epoch": 0.42, "percentage": 14.06, "elapsed_time": "0:33:05", "remaining_time": "3:22:18"}
+{"current_steps": 36, "total_steps": 249, "loss": 0.9548, "lr": 9.940616260552545e-06, "epoch": 0.432, "percentage": 14.46, "elapsed_time": "0:34:07", "remaining_time": "3:21:54"}
+{"current_steps": 37, "total_steps": 249, "loss": 0.959, "lr": 9.92935509259118e-06, "epoch": 0.444, "percentage": 14.86, "elapsed_time": "0:35:02", "remaining_time": "3:20:46"}
+{"current_steps": 38, "total_steps": 249, "loss": 0.9314, "lr": 9.917124337830242e-06, "epoch": 0.456, "percentage": 15.26, "elapsed_time": "0:35:55", "remaining_time": "3:19:28"}
+{"current_steps": 39, "total_steps": 249, "loss": 0.9564, "lr": 9.903926402016153e-06, "epoch": 0.468, "percentage": 15.66, "elapsed_time": "0:36:51", "remaining_time": "3:18:27"}
+{"current_steps": 40, "total_steps": 249, "loss": 0.958, "lr": 9.889763881136439e-06, "epoch": 0.48, "percentage": 16.06, "elapsed_time": "0:37:49", "remaining_time": "3:17:38"}
+{"current_steps": 41, "total_steps": 249, "loss": 0.9135, "lr": 9.874639560909118e-06, "epoch": 0.492, "percentage": 16.47, "elapsed_time": "0:38:42", "remaining_time": "3:16:23"}
+{"current_steps": 42, "total_steps": 249, "loss": 0.9224, "lr": 9.858556416234755e-06, "epoch": 0.504, "percentage": 16.87, "elapsed_time": "0:39:40", "remaining_time": "3:15:30"}
+{"current_steps": 43, "total_steps": 249, "loss": 0.9147, "lr": 9.841517610611309e-06, "epoch": 0.516, "percentage": 17.27, "elapsed_time": "0:40:35", "remaining_time": "3:14:26"}
+{"current_steps": 44, "total_steps": 249, "loss": 0.9471, "lr": 9.82352649551188e-06, "epoch": 0.528, "percentage": 17.67, "elapsed_time": "0:41:41", "remaining_time": "3:14:13"}
+{"current_steps": 45, "total_steps": 249, "loss": 0.9136, "lr": 9.804586609725499e-06, "epoch": 0.54, "percentage": 18.07, "elapsed_time": "0:42:29", "remaining_time": "3:12:35"}
+{"current_steps": 46, "total_steps": 249, "loss": 0.9142, "lr": 9.784701678661045e-06, "epoch": 0.552, "percentage": 18.47, "elapsed_time": "0:43:24", "remaining_time": "3:11:34"}
+{"current_steps": 47, "total_steps": 249, "loss": 0.887, "lr": 9.763875613614482e-06, "epoch": 0.564, "percentage": 18.88, "elapsed_time": "0:44:12", "remaining_time": "3:10:01"}
+{"current_steps": 48, "total_steps": 249, "loss": 0.9138, "lr": 9.742112510999516e-06, "epoch": 0.576, "percentage": 19.28, "elapsed_time": "0:45:10", "remaining_time": "3:09:09"}
+{"current_steps": 49, "total_steps": 249, "loss": 0.9335, "lr": 9.719416651541839e-06, "epoch": 0.588, "percentage": 19.68, "elapsed_time": "0:46:06", "remaining_time": "3:08:10"}
+{"current_steps": 50, "total_steps": 249, "loss": 0.9457, "lr": 9.69579249943714e-06, "epoch": 0.6, "percentage": 20.08, "elapsed_time": "0:47:12", "remaining_time": "3:07:52"}
+{"current_steps": 51, "total_steps": 249, "loss": 0.9146, "lr": 9.671244701472999e-06, "epoch": 0.612, "percentage": 20.48, "elapsed_time": "0:48:12", "remaining_time": "3:07:11"}
+{"current_steps": 52, "total_steps": 249, "loss": 0.9178, "lr": 9.645778086114892e-06, "epoch": 0.624, "percentage": 20.88, "elapsed_time": "0:49:04", "remaining_time": "3:05:56"}
+{"current_steps": 53, "total_steps": 249, "loss": 0.908, "lr": 9.619397662556434e-06, "epoch": 0.636, "percentage": 21.29, "elapsed_time": "0:49:59", "remaining_time": "3:04:53"}
+{"current_steps": 54, "total_steps": 249, "loss": 0.953, "lr": 9.592108619734107e-06, "epoch": 0.648, "percentage": 21.69, "elapsed_time": "0:51:01", "remaining_time": "3:04:16"}
+{"current_steps": 55, "total_steps": 249, "loss": 0.8592, "lr": 9.563916325306595e-06, "epoch": 0.66, "percentage": 22.09, "elapsed_time": "0:51:50", "remaining_time": "3:02:51"}
+{"current_steps": 56, "total_steps": 249, "loss": 0.9176, "lr": 9.534826324599002e-06, "epoch": 0.672, "percentage": 22.49, "elapsed_time": "0:52:46", "remaining_time": "3:01:53"}
+{"current_steps": 57, "total_steps": 249, "loss": 0.9613, "lr": 9.504844339512096e-06, "epoch": 0.684, "percentage": 22.89, "elapsed_time": "0:53:45", "remaining_time": "3:01:06"}
+{"current_steps": 58, "total_steps": 249, "loss": 0.9182, "lr": 9.473976267396831e-06, "epoch": 0.696, "percentage": 23.29, "elapsed_time": "0:54:37", "remaining_time": "2:59:54"}
+{"current_steps": 59, "total_steps": 249, "loss": 0.9183, "lr": 9.442228179894362e-06, "epoch": 0.708, "percentage": 23.69, "elapsed_time": "0:55:37", "remaining_time": "2:59:07"}
+{"current_steps": 60, "total_steps": 249, "loss": 0.9708, "lr": 9.409606321741776e-06, "epoch": 0.72, "percentage": 24.1, "elapsed_time": "0:56:34", "remaining_time": "2:58:12"}
+{"current_steps": 61, "total_steps": 249, "loss": 0.9074, "lr": 9.376117109543769e-06, "epoch": 0.732, "percentage": 24.5, "elapsed_time": "0:57:22", "remaining_time": "2:56:49"}
+{"current_steps": 62, "total_steps": 249, "loss": 0.8991, "lr": 9.341767130510529e-06, "epoch": 0.744, "percentage": 24.9, "elapsed_time": "0:58:21", "remaining_time": "2:55:59"}
+{"current_steps": 63, "total_steps": 249, "loss": 0.8979, "lr": 9.306563141162046e-06, "epoch": 0.756, "percentage": 25.3, "elapsed_time": "0:59:06", "remaining_time": "2:54:30"}
+{"current_steps": 64, "total_steps": 249, "loss": 0.8945, "lr": 9.270512065999139e-06, "epoch": 0.768, "percentage": 25.7, "elapsed_time": "0:59:57", "remaining_time": "2:53:18"}
+{"current_steps": 65, "total_steps": 249, "loss": 0.9179, "lr": 9.233620996141421e-06, "epoch": 0.78, "percentage": 26.1, "elapsed_time": "1:00:57", "remaining_time": "2:52:33"}
+{"current_steps": 66, "total_steps": 249, "loss": 0.8887, "lr": 9.195897187932513e-06, "epoch": 0.792, "percentage": 26.51, "elapsed_time": "1:01:47", "remaining_time": "2:51:19"}
+{"current_steps": 67, "total_steps": 249, "loss": 0.8882, "lr": 9.157348061512728e-06, "epoch": 0.804, "percentage": 26.91, "elapsed_time": "1:02:40", "remaining_time": "2:50:14"}
+{"current_steps": 68, "total_steps": 249, "loss": 0.9022, "lr": 9.117981199359575e-06, "epoch": 0.816, "percentage": 27.31, "elapsed_time": "1:03:30", "remaining_time": "2:49:03"}
+{"current_steps": 69, "total_steps": 249, "loss": 0.8962, "lr": 9.077804344796302e-06, "epoch": 0.828, "percentage": 27.71, "elapsed_time": "1:04:31", "remaining_time": "2:48:20"}
+{"current_steps": 70, "total_steps": 249, "loss": 0.8789, "lr": 9.036825400468814e-06, "epoch": 0.84, "percentage": 28.11, "elapsed_time": "1:05:20", "remaining_time": "2:47:04"}
+{"current_steps": 71, "total_steps": 249, "loss": 0.8723, "lr": 8.995052426791247e-06, "epoch": 0.852, "percentage": 28.51, "elapsed_time": "1:06:07", "remaining_time": "2:45:47"}
+{"current_steps": 72, "total_steps": 249, "loss": 0.9267, "lr": 8.952493640360518e-06, "epoch": 0.864, "percentage": 28.92, "elapsed_time": "1:07:09", "remaining_time": "2:45:05"}
+{"current_steps": 73, "total_steps": 249, "loss": 0.8762, "lr": 8.90915741234015e-06, "epoch": 0.876, "percentage": 29.32, "elapsed_time": "1:08:05", "remaining_time": "2:44:10"}
+{"current_steps": 74, "total_steps": 249, "loss": 0.9348, "lr": 8.865052266813686e-06, "epoch": 0.888, "percentage": 29.72, "elapsed_time": "1:09:08", "remaining_time": "2:43:29"}
+{"current_steps": 75, "total_steps": 249, "loss": 0.9024, "lr": 8.820186879108038e-06, "epoch": 0.9, "percentage": 30.12, "elapsed_time": "1:10:02", "remaining_time": "2:42:28"}
+{"current_steps": 76, "total_steps": 249, "loss": 0.8927, "lr": 8.77457007408708e-06, "epoch": 0.912, "percentage": 30.52, "elapsed_time": "1:10:53", "remaining_time": "2:41:21"}
+{"current_steps": 77, "total_steps": 249, "loss": 0.9414, "lr": 8.728210824415829e-06, "epoch": 0.924, "percentage": 30.92, "elapsed_time": "1:11:42", "remaining_time": "2:40:11"}
+{"current_steps": 78, "total_steps": 249, "loss": 0.9135, "lr": 8.681118248795548e-06, "epoch": 0.936, "percentage": 31.33, "elapsed_time": "1:12:42", "remaining_time": "2:39:22"}
+{"current_steps": 79, "total_steps": 249, "loss": 0.9005, "lr": 8.633301610170136e-06, "epoch": 0.948, "percentage": 31.73, "elapsed_time": "1:13:29", "remaining_time": "2:38:09"}
+{"current_steps": 80, "total_steps": 249, "loss": 0.8882, "lr": 8.584770313904138e-06, "epoch": 0.96, "percentage": 32.13, "elapsed_time": "1:14:24", "remaining_time": "2:37:10"}
+{"current_steps": 81, "total_steps": 249, "loss": 0.8829, "lr": 8.535533905932739e-06, "epoch": 0.972, "percentage": 32.53, "elapsed_time": "1:15:15", "remaining_time": "2:36:06"}
+{"current_steps": 82, "total_steps": 249, "loss": 0.9358, "lr": 8.485602070884118e-06, "epoch": 0.984, "percentage": 32.93, "elapsed_time": "1:16:12", "remaining_time": "2:35:12"}
+{"current_steps": 83, "total_steps": 249, "loss": 0.9051, "lr": 8.43498463017451e-06, "epoch": 0.996, "percentage": 33.33, "elapsed_time": "1:17:08", "remaining_time": "2:34:17"}
+{"current_steps": 84, "total_steps": 249, "loss": 1.5002, "lr": 8.383691540076372e-06, "epoch": 1.008, "percentage": 33.73, "elapsed_time": "1:19:10", "remaining_time": "2:35:30"}
+{"current_steps": 85, "total_steps": 249, "loss": 0.826, "lr": 8.331732889760021e-06, "epoch": 1.02, "percentage": 34.14, "elapsed_time": "1:20:13", "remaining_time": "2:34:47"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d701af24f4f140248c25da1dd3fbaf991a8f5403c25a35764bdaaa6ec9e6c5
+size 7416