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 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": 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 sha256:4720924a33e0feb43b34bb220cdd1aed6354f1d5e71c399fc0e81c766854ee08
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4e519fedf61a7b75a7fc89f3c58d3d30f5ad5e4c8b0f38d21eeeb3c669d48c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3582868b80b7b57302349c3a13df1986fc0cd51957a4394ed8324a088ebd79b2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fea9b5f57509acdb3c3891afedceaed1bb092876acf6e54ea8af536405aa4b5
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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 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 a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "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 +1,89 @@
+{"current_steps": 10, "total_steps": 2631, "loss": 0.7552, "learning_rate": 5e-06, "epoch": 0.011396011396011397, "percentage": 0.38, "elapsed_time": "0:04:26", "remaining_time": "19:26:07"}
+{"current_steps": 20, "total_steps": 2631, "loss": 0.7051, "learning_rate": 5e-06, "epoch": 0.022792022792022793, "percentage": 0.76, "elapsed_time": "0:08:48", "remaining_time": "19:10:45"}
+{"current_steps": 30, "total_steps": 2631, "loss": 0.6821, "learning_rate": 5e-06, "epoch": 0.03418803418803419, "percentage": 1.14, "elapsed_time": "0:13:11", "remaining_time": "19:03:46"}
+{"current_steps": 40, "total_steps": 2631, "loss": 0.6856, "learning_rate": 5e-06, "epoch": 0.045584045584045586, "percentage": 1.52, "elapsed_time": "0:17:34", "remaining_time": "18:58:14"}
+{"current_steps": 50, "total_steps": 2631, "loss": 0.6637, "learning_rate": 5e-06, "epoch": 0.05698005698005698, "percentage": 1.9, "elapsed_time": "0:21:57", "remaining_time": "18:53:22"}
+{"current_steps": 60, "total_steps": 2631, "loss": 0.6622, "learning_rate": 5e-06, "epoch": 0.06837606837606838, "percentage": 2.28, "elapsed_time": "0:26:20", "remaining_time": "18:48:23"}
+{"current_steps": 70, "total_steps": 2631, "loss": 0.6663, "learning_rate": 5e-06, "epoch": 0.07977207977207977, "percentage": 2.66, "elapsed_time": "0:30:42", "remaining_time": "18:43:35"}
+{"current_steps": 80, "total_steps": 2631, "loss": 0.6571, "learning_rate": 5e-06, "epoch": 0.09116809116809117, "percentage": 3.04, "elapsed_time": "0:35:06", "remaining_time": "18:39:25"}
+{"current_steps": 90, "total_steps": 2631, "loss": 0.6638, "learning_rate": 5e-06, "epoch": 0.10256410256410256, "percentage": 3.42, "elapsed_time": "0:39:28", "remaining_time": "18:34:43"}
+{"current_steps": 100, "total_steps": 2631, "loss": 0.6579, "learning_rate": 5e-06, "epoch": 0.11396011396011396, "percentage": 3.8, "elapsed_time": "0:43:52", "remaining_time": "18:30:26"}
+{"current_steps": 110, "total_steps": 2631, "loss": 0.6526, "learning_rate": 5e-06, "epoch": 0.12535612535612536, "percentage": 4.18, "elapsed_time": "0:48:15", "remaining_time": "18:26:10"}
+{"current_steps": 120, "total_steps": 2631, "loss": 0.6369, "learning_rate": 5e-06, "epoch": 0.13675213675213677, "percentage": 4.56, "elapsed_time": "0:52:38", "remaining_time": "18:21:37"}
+{"current_steps": 130, "total_steps": 2631, "loss": 0.6341, "learning_rate": 5e-06, "epoch": 0.14814814814814814, "percentage": 4.94, "elapsed_time": "0:57:01", "remaining_time": "18:16:58"}
+{"current_steps": 140, "total_steps": 2631, "loss": 0.6573, "learning_rate": 5e-06, "epoch": 0.15954415954415954, "percentage": 5.32, "elapsed_time": "1:01:23", "remaining_time": "18:12:27"}
+{"current_steps": 150, "total_steps": 2631, "loss": 0.6449, "learning_rate": 5e-06, "epoch": 0.17094017094017094, "percentage": 5.7, "elapsed_time": "1:05:46", "remaining_time": "18:08:00"}
+{"current_steps": 160, "total_steps": 2631, "loss": 0.6558, "learning_rate": 5e-06, "epoch": 0.18233618233618235, "percentage": 6.08, "elapsed_time": "1:10:09", "remaining_time": "18:03:34"}
+{"current_steps": 170, "total_steps": 2631, "loss": 0.6287, "learning_rate": 5e-06, "epoch": 0.19373219373219372, "percentage": 6.46, "elapsed_time": "1:14:32", "remaining_time": "17:59:07"}
+{"current_steps": 180, "total_steps": 2631, "loss": 0.6439, "learning_rate": 5e-06, "epoch": 0.20512820512820512, "percentage": 6.84, "elapsed_time": "1:18:55", "remaining_time": "17:54:43"}
+{"current_steps": 190, "total_steps": 2631, "loss": 0.6396, "learning_rate": 5e-06, "epoch": 0.21652421652421652, "percentage": 7.22, "elapsed_time": "1:23:18", "remaining_time": "17:50:18"}
+{"current_steps": 200, "total_steps": 2631, "loss": 0.6356, "learning_rate": 5e-06, "epoch": 0.22792022792022792, "percentage": 7.6, "elapsed_time": "1:27:41", "remaining_time": "17:45:56"}
+{"current_steps": 210, "total_steps": 2631, "loss": 0.6306, "learning_rate": 5e-06, "epoch": 0.23931623931623933, "percentage": 7.98, "elapsed_time": "1:32:04", "remaining_time": "17:41:34"}
+{"current_steps": 220, "total_steps": 2631, "loss": 0.6277, "learning_rate": 5e-06, "epoch": 0.25071225071225073, "percentage": 8.36, "elapsed_time": "1:36:27", "remaining_time": "17:37:06"}
+{"current_steps": 230, "total_steps": 2631, "loss": 0.6339, "learning_rate": 5e-06, "epoch": 0.2621082621082621, "percentage": 8.74, "elapsed_time": "1:40:50", "remaining_time": "17:32:41"}
+{"current_steps": 240, "total_steps": 2631, "loss": 0.641, "learning_rate": 5e-06, "epoch": 0.27350427350427353, "percentage": 9.12, "elapsed_time": "1:45:13", "remaining_time": "17:28:17"}
+{"current_steps": 250, "total_steps": 2631, "loss": 0.6372, "learning_rate": 5e-06, "epoch": 0.2849002849002849, "percentage": 9.5, "elapsed_time": "1:49:36", "remaining_time": "17:23:53"}
+{"current_steps": 260, "total_steps": 2631, "loss": 0.6403, "learning_rate": 5e-06, "epoch": 0.2962962962962963, "percentage": 9.88, "elapsed_time": "1:53:58", "remaining_time": "17:19:25"}
+{"current_steps": 270, "total_steps": 2631, "loss": 0.6415, "learning_rate": 5e-06, "epoch": 0.3076923076923077, "percentage": 10.26, "elapsed_time": "1:58:21", "remaining_time": "17:15:01"}
+{"current_steps": 280, "total_steps": 2631, "loss": 0.6399, "learning_rate": 5e-06, "epoch": 0.3190883190883191, "percentage": 10.64, "elapsed_time": "2:02:43", "remaining_time": "17:10:30"}
+{"current_steps": 290, "total_steps": 2631, "loss": 0.6336, "learning_rate": 5e-06, "epoch": 0.33048433048433046, "percentage": 11.02, "elapsed_time": "2:07:06", "remaining_time": "17:06:02"}
+{"current_steps": 300, "total_steps": 2631, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 0.3418803418803419, "percentage": 11.4, "elapsed_time": "2:11:29", "remaining_time": "17:01:40"}
+{"current_steps": 310, "total_steps": 2631, "loss": 0.637, "learning_rate": 5e-06, "epoch": 0.35327635327635326, "percentage": 11.78, "elapsed_time": "2:15:51", "remaining_time": "16:57:14"}
+{"current_steps": 320, "total_steps": 2631, "loss": 0.64, "learning_rate": 5e-06, "epoch": 0.3646723646723647, "percentage": 12.16, "elapsed_time": "2:20:15", "remaining_time": "16:52:52"}
+{"current_steps": 330, "total_steps": 2631, "loss": 0.6252, "learning_rate": 5e-06, "epoch": 0.37606837606837606, "percentage": 12.54, "elapsed_time": "2:24:37", "remaining_time": "16:48:28"}
+{"current_steps": 340, "total_steps": 2631, "loss": 0.636, "learning_rate": 5e-06, "epoch": 0.38746438746438744, "percentage": 12.92, "elapsed_time": "2:29:00", "remaining_time": "16:44:05"}
+{"current_steps": 350, "total_steps": 2631, "loss": 0.6387, "learning_rate": 5e-06, "epoch": 0.39886039886039887, "percentage": 13.3, "elapsed_time": "2:33:23", "remaining_time": "16:39:41"}
+{"current_steps": 360, "total_steps": 2631, "loss": 0.6338, "learning_rate": 5e-06, "epoch": 0.41025641025641024, "percentage": 13.68, "elapsed_time": "2:37:46", "remaining_time": "16:35:20"}
+{"current_steps": 370, "total_steps": 2631, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 0.42165242165242167, "percentage": 14.06, "elapsed_time": "2:42:10", "remaining_time": "16:30:59"}
+{"current_steps": 380, "total_steps": 2631, "loss": 0.6235, "learning_rate": 5e-06, "epoch": 0.43304843304843305, "percentage": 14.44, "elapsed_time": "2:46:33", "remaining_time": "16:26:38"}
+{"current_steps": 390, "total_steps": 2631, "loss": 0.6305, "learning_rate": 5e-06, "epoch": 0.4444444444444444, "percentage": 14.82, "elapsed_time": "2:50:56", "remaining_time": "16:22:16"}
+{"current_steps": 400, "total_steps": 2631, "loss": 0.6424, "learning_rate": 5e-06, "epoch": 0.45584045584045585, "percentage": 15.2, "elapsed_time": "2:55:19", "remaining_time": "16:17:50"}
+{"current_steps": 410, "total_steps": 2631, "loss": 0.6319, "learning_rate": 5e-06, "epoch": 0.4672364672364672, "percentage": 15.58, "elapsed_time": "2:59:42", "remaining_time": "16:13:27"}
+{"current_steps": 420, "total_steps": 2631, "loss": 0.6332, "learning_rate": 5e-06, "epoch": 0.47863247863247865, "percentage": 15.96, "elapsed_time": "3:04:05", "remaining_time": "16:09:04"}
+{"current_steps": 430, "total_steps": 2631, "loss": 0.6328, "learning_rate": 5e-06, "epoch": 0.49002849002849, "percentage": 16.34, "elapsed_time": "3:08:27", "remaining_time": "16:04:41"}
+{"current_steps": 440, "total_steps": 2631, "loss": 0.6402, "learning_rate": 5e-06, "epoch": 0.5014245014245015, "percentage": 16.72, "elapsed_time": "3:12:50", "remaining_time": "16:00:18"}
+{"current_steps": 450, "total_steps": 2631, "loss": 0.6306, "learning_rate": 5e-06, "epoch": 0.5128205128205128, "percentage": 17.1, "elapsed_time": "3:17:13", "remaining_time": "15:55:54"}
+{"current_steps": 460, "total_steps": 2631, "loss": 0.6344, "learning_rate": 5e-06, "epoch": 0.5242165242165242, "percentage": 17.48, "elapsed_time": "3:21:36", "remaining_time": "15:51:31"}
+{"current_steps": 470, "total_steps": 2631, "loss": 0.6231, "learning_rate": 5e-06, "epoch": 0.5356125356125356, "percentage": 17.86, "elapsed_time": "3:25:59", "remaining_time": "15:47:08"}
+{"current_steps": 480, "total_steps": 2631, "loss": 0.6341, "learning_rate": 5e-06, "epoch": 0.5470085470085471, "percentage": 18.24, "elapsed_time": "3:30:22", "remaining_time": "15:42:44"}
+{"current_steps": 490, "total_steps": 2631, "loss": 0.6351, "learning_rate": 5e-06, "epoch": 0.5584045584045584, "percentage": 18.62, "elapsed_time": "3:34:44", "remaining_time": "15:38:18"}
+{"current_steps": 500, "total_steps": 2631, "loss": 0.6309, "learning_rate": 5e-06, "epoch": 0.5698005698005698, "percentage": 19.0, "elapsed_time": "3:39:07", "remaining_time": "15:33:54"}
+{"current_steps": 510, "total_steps": 2631, "loss": 0.6331, "learning_rate": 5e-06, "epoch": 0.5811965811965812, "percentage": 19.38, "elapsed_time": "3:43:30", "remaining_time": "15:29:30"}
+{"current_steps": 520, "total_steps": 2631, "loss": 0.6303, "learning_rate": 5e-06, "epoch": 0.5925925925925926, "percentage": 19.76, "elapsed_time": "3:47:53", "remaining_time": "15:25:08"}
+{"current_steps": 530, "total_steps": 2631, "loss": 0.6295, "learning_rate": 5e-06, "epoch": 0.603988603988604, "percentage": 20.14, "elapsed_time": "3:52:16", "remaining_time": "15:20:45"}
+{"current_steps": 540, "total_steps": 2631, "loss": 0.629, "learning_rate": 5e-06, "epoch": 0.6153846153846154, "percentage": 20.52, "elapsed_time": "3:56:39", "remaining_time": "15:16:23"}
+{"current_steps": 550, "total_steps": 2631, "loss": 0.6418, "learning_rate": 5e-06, "epoch": 0.6267806267806267, "percentage": 20.9, "elapsed_time": "4:01:02", "remaining_time": "15:12:00"}
+{"current_steps": 560, "total_steps": 2631, "loss": 0.6365, "learning_rate": 5e-06, "epoch": 0.6381766381766382, "percentage": 21.28, "elapsed_time": "4:05:25", "remaining_time": "15:07:38"}
+{"current_steps": 570, "total_steps": 2631, "loss": 0.6298, "learning_rate": 5e-06, "epoch": 0.6495726495726496, "percentage": 21.66, "elapsed_time": "4:09:48", "remaining_time": "15:03:16"}
+{"current_steps": 580, "total_steps": 2631, "loss": 0.6264, "learning_rate": 5e-06, "epoch": 0.6609686609686609, "percentage": 22.04, "elapsed_time": "4:14:11", "remaining_time": "14:58:54"}
+{"current_steps": 590, "total_steps": 2631, "loss": 0.6338, "learning_rate": 5e-06, "epoch": 0.6723646723646723, "percentage": 22.42, "elapsed_time": "4:18:34", "remaining_time": "14:54:29"}
+{"current_steps": 600, "total_steps": 2631, "loss": 0.6185, "learning_rate": 5e-06, "epoch": 0.6837606837606838, "percentage": 22.81, "elapsed_time": "4:22:57", "remaining_time": "14:50:07"}
+{"current_steps": 610, "total_steps": 2631, "loss": 0.6285, "learning_rate": 5e-06, "epoch": 0.6951566951566952, "percentage": 23.19, "elapsed_time": "4:27:20", "remaining_time": "14:45:45"}
+{"current_steps": 620, "total_steps": 2631, "loss": 0.6249, "learning_rate": 5e-06, "epoch": 0.7065527065527065, "percentage": 23.57, "elapsed_time": "4:31:44", "remaining_time": "14:41:23"}
+{"current_steps": 630, "total_steps": 2631, "loss": 0.6297, "learning_rate": 5e-06, "epoch": 0.717948717948718, "percentage": 23.95, "elapsed_time": "4:36:06", "remaining_time": "14:36:59"}
+{"current_steps": 640, "total_steps": 2631, "loss": 0.624, "learning_rate": 5e-06, "epoch": 0.7293447293447294, "percentage": 24.33, "elapsed_time": "4:40:29", "remaining_time": "14:32:37"}
+{"current_steps": 650, "total_steps": 2631, "loss": 0.629, "learning_rate": 5e-06, "epoch": 0.7407407407407407, "percentage": 24.71, "elapsed_time": "4:44:53", "remaining_time": "14:28:15"}
+{"current_steps": 660, "total_steps": 2631, "loss": 0.6177, "learning_rate": 5e-06, "epoch": 0.7521367521367521, "percentage": 25.09, "elapsed_time": "4:49:16", "remaining_time": "14:23:52"}
+{"current_steps": 670, "total_steps": 2631, "loss": 0.6261, "learning_rate": 5e-06, "epoch": 0.7635327635327636, "percentage": 25.47, "elapsed_time": "4:53:38", "remaining_time": "14:19:28"}
+{"current_steps": 680, "total_steps": 2631, "loss": 0.6304, "learning_rate": 5e-06, "epoch": 0.7749287749287749, "percentage": 25.85, "elapsed_time": "4:58:02", "remaining_time": "14:15:05"}
+{"current_steps": 690, "total_steps": 2631, "loss": 0.6398, "learning_rate": 5e-06, "epoch": 0.7863247863247863, "percentage": 26.23, "elapsed_time": "5:02:25", "remaining_time": "14:10:42"}
+{"current_steps": 700, "total_steps": 2631, "loss": 0.6319, "learning_rate": 5e-06, "epoch": 0.7977207977207977, "percentage": 26.61, "elapsed_time": "5:06:47", "remaining_time": "14:06:18"}
+{"current_steps": 710, "total_steps": 2631, "loss": 0.6314, "learning_rate": 5e-06, "epoch": 0.8091168091168092, "percentage": 26.99, "elapsed_time": "5:11:11", "remaining_time": "14:01:57"}
+{"current_steps": 720, "total_steps": 2631, "loss": 0.6243, "learning_rate": 5e-06, "epoch": 0.8205128205128205, "percentage": 27.37, "elapsed_time": "5:15:34", "remaining_time": "13:57:34"}
+{"current_steps": 730, "total_steps": 2631, "loss": 0.6226, "learning_rate": 5e-06, "epoch": 0.8319088319088319, "percentage": 27.75, "elapsed_time": "5:19:57", "remaining_time": "13:53:11"}
+{"current_steps": 740, "total_steps": 2631, "loss": 0.6208, "learning_rate": 5e-06, "epoch": 0.8433048433048433, "percentage": 28.13, "elapsed_time": "5:24:20", "remaining_time": "13:48:48"}
+{"current_steps": 750, "total_steps": 2631, "loss": 0.6338, "learning_rate": 5e-06, "epoch": 0.8547008547008547, "percentage": 28.51, "elapsed_time": "5:28:43", "remaining_time": "13:44:26"}
+{"current_steps": 760, "total_steps": 2631, "loss": 0.6337, "learning_rate": 5e-06, "epoch": 0.8660968660968661, "percentage": 28.89, "elapsed_time": "5:33:06", "remaining_time": "13:40:03"}
+{"current_steps": 770, "total_steps": 2631, "loss": 0.6296, "learning_rate": 5e-06, "epoch": 0.8774928774928775, "percentage": 29.27, "elapsed_time": "5:37:28", "remaining_time": "13:35:38"}
+{"current_steps": 780, "total_steps": 2631, "loss": 0.6357, "learning_rate": 5e-06, "epoch": 0.8888888888888888, "percentage": 29.65, "elapsed_time": "5:41:51", "remaining_time": "13:31:14"}
+{"current_steps": 790, "total_steps": 2631, "loss": 0.6333, "learning_rate": 5e-06, "epoch": 0.9002849002849003, "percentage": 30.03, "elapsed_time": "5:46:14", "remaining_time": "13:26:51"}
+{"current_steps": 800, "total_steps": 2631, "loss": 0.6384, "learning_rate": 5e-06, "epoch": 0.9116809116809117, "percentage": 30.41, "elapsed_time": "5:50:36", "remaining_time": "13:22:27"}
+{"current_steps": 810, "total_steps": 2631, "loss": 0.6309, "learning_rate": 5e-06, "epoch": 0.9230769230769231, "percentage": 30.79, "elapsed_time": "5:54:59", "remaining_time": "13:18:04"}
+{"current_steps": 820, "total_steps": 2631, "loss": 0.6323, "learning_rate": 5e-06, "epoch": 0.9344729344729344, "percentage": 31.17, "elapsed_time": "5:59:23", "remaining_time": "13:13:42"}
+{"current_steps": 830, "total_steps": 2631, "loss": 0.6117, "learning_rate": 5e-06, "epoch": 0.9458689458689459, "percentage": 31.55, "elapsed_time": "6:03:46", "remaining_time": "13:09:20"}
+{"current_steps": 840, "total_steps": 2631, "loss": 0.6258, "learning_rate": 5e-06, "epoch": 0.9572649572649573, "percentage": 31.93, "elapsed_time": "6:08:09", "remaining_time": "13:04:58"}
+{"current_steps": 850, "total_steps": 2631, "loss": 0.6334, "learning_rate": 5e-06, "epoch": 0.9686609686609686, "percentage": 32.31, "elapsed_time": "6:12:32", "remaining_time": "13:00:34"}
+{"current_steps": 860, "total_steps": 2631, "loss": 0.6299, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.69, "elapsed_time": "6:16:55", "remaining_time": "12:56:12"}
+{"current_steps": 870, "total_steps": 2631, "loss": 0.6134, "learning_rate": 5e-06, "epoch": 0.9914529914529915, "percentage": 33.07, "elapsed_time": "6:21:18", "remaining_time": "12:51:49"}
+{"current_steps": 877, "total_steps": 2631, "eval_loss": 0.622437059879303, "epoch": 0.9994301994301994, "percentage": 33.33, "elapsed_time": "6:31:57", "remaining_time": "13:03:55"}
+{"current_steps": 880, "total_steps": 2631, "loss": 0.6384, "learning_rate": 5e-06, "epoch": 1.002849002849003, "percentage": 33.45, "elapsed_time": "6:34:09", "remaining_time": "13:04:17"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986eb4052af367007073a5d51bd61d3c829c14374d72b179bfe772bb1fe811fe
+size 7160