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 sha256:6305513ba8997c918e5d2aa8d2c2e77cdbd4f09d79d94597a3fc5cb99f64a4e5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c655259e61ce861ae60764081c36999f335a76c75b067717fd200c7908dedbf4
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49187663d2b09091bba30ad94564bc67d97c74b26eb34aa709c87562ebf82ada
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53de2519ee48c2100e1b6ebe263a2477e986eab984f5e7f014997509643153f5
+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 +1,92 @@
+{"current_steps": 1, "total_steps": 460, "loss": 0.8566, "lr": 1.7391304347826088e-06, "epoch": 0.010825439783491205, "percentage": 0.22, "elapsed_time": "0:04:30", "remaining_time": "1 day, 10:28:24"}
+{"current_steps": 2, "total_steps": 460, "loss": 0.8603, "lr": 3.4782608695652175e-06, "epoch": 0.02165087956698241, "percentage": 0.43, "elapsed_time": "0:08:10", "remaining_time": "1 day, 7:13:02"}
+{"current_steps": 3, "total_steps": 460, "loss": 0.8631, "lr": 5.2173913043478265e-06, "epoch": 0.03247631935047361, "percentage": 0.65, "elapsed_time": "0:11:50", "remaining_time": "1 day, 6:04:40"}
+{"current_steps": 4, "total_steps": 460, "loss": 0.8176, "lr": 6.956521739130435e-06, "epoch": 0.04330175913396482, "percentage": 0.87, "elapsed_time": "0:15:30", "remaining_time": "1 day, 5:28:26"}
+{"current_steps": 5, "total_steps": 460, "loss": 0.7658, "lr": 8.695652173913044e-06, "epoch": 0.05412719891745602, "percentage": 1.09, "elapsed_time": "0:19:10", "remaining_time": "1 day, 5:04:59"}
+{"current_steps": 6, "total_steps": 460, "loss": 0.7574, "lr": 1.0434782608695653e-05, "epoch": 0.06495263870094722, "percentage": 1.3, "elapsed_time": "0:22:50", "remaining_time": "1 day, 4:48:47"}
+{"current_steps": 7, "total_steps": 460, "loss": 0.7776, "lr": 1.2173913043478263e-05, "epoch": 0.07577807848443843, "percentage": 1.52, "elapsed_time": "0:26:31", "remaining_time": "1 day, 4:36:32"}
+{"current_steps": 8, "total_steps": 460, "loss": 0.7457, "lr": 1.391304347826087e-05, "epoch": 0.08660351826792964, "percentage": 1.74, "elapsed_time": "0:30:11", "remaining_time": "1 day, 4:25:59"}
+{"current_steps": 9, "total_steps": 460, "loss": 0.7141, "lr": 1.565217391304348e-05, "epoch": 0.09742895805142084, "percentage": 1.96, "elapsed_time": "0:33:51", "remaining_time": "1 day, 4:16:49"}
+{"current_steps": 10, "total_steps": 460, "loss": 0.6986, "lr": 1.739130434782609e-05, "epoch": 0.10825439783491204, "percentage": 2.17, "elapsed_time": "0:37:31", "remaining_time": "1 day, 4:08:44"}
+{"current_steps": 11, "total_steps": 460, "loss": 0.6642, "lr": 1.9130434782608697e-05, "epoch": 0.11907983761840325, "percentage": 2.39, "elapsed_time": "0:41:11", "remaining_time": "1 day, 4:01:26"}
+{"current_steps": 12, "total_steps": 460, "loss": 0.6566, "lr": 2.0869565217391306e-05, "epoch": 0.12990527740189445, "percentage": 2.61, "elapsed_time": "0:44:51", "remaining_time": "1 day, 3:54:38"}
+{"current_steps": 13, "total_steps": 460, "loss": 0.636, "lr": 2.2608695652173914e-05, "epoch": 0.14073071718538566, "percentage": 2.83, "elapsed_time": "0:48:31", "remaining_time": "1 day, 3:48:33"}
+{"current_steps": 14, "total_steps": 460, "loss": 0.6427, "lr": 2.4347826086956526e-05, "epoch": 0.15155615696887687, "percentage": 3.04, "elapsed_time": "0:52:11", "remaining_time": "1 day, 3:42:43"}
+{"current_steps": 15, "total_steps": 460, "loss": 0.6195, "lr": 2.608695652173913e-05, "epoch": 0.16238159675236807, "percentage": 3.26, "elapsed_time": "0:55:51", "remaining_time": "1 day, 3:37:04"}
+{"current_steps": 16, "total_steps": 460, "loss": 0.6092, "lr": 2.782608695652174e-05, "epoch": 0.17320703653585928, "percentage": 3.48, "elapsed_time": "0:59:31", "remaining_time": "1 day, 3:31:37"}
+{"current_steps": 17, "total_steps": 460, "loss": 0.6006, "lr": 2.956521739130435e-05, "epoch": 0.18403247631935046, "percentage": 3.7, "elapsed_time": "1:03:11", "remaining_time": "1 day, 3:26:53"}
+{"current_steps": 18, "total_steps": 460, "loss": 0.5868, "lr": 3.130434782608696e-05, "epoch": 0.19485791610284167, "percentage": 3.91, "elapsed_time": "1:06:51", "remaining_time": "1 day, 3:21:52"}
+{"current_steps": 19, "total_steps": 460, "loss": 0.5769, "lr": 3.304347826086957e-05, "epoch": 0.20568335588633288, "percentage": 4.13, "elapsed_time": "1:10:31", "remaining_time": "1 day, 3:16:56"}
+{"current_steps": 20, "total_steps": 460, "loss": 0.5798, "lr": 3.478260869565218e-05, "epoch": 0.2165087956698241, "percentage": 4.35, "elapsed_time": "1:14:11", "remaining_time": "1 day, 3:12:17"}
+{"current_steps": 21, "total_steps": 460, "loss": 0.5738, "lr": 3.6521739130434786e-05, "epoch": 0.2273342354533153, "percentage": 4.57, "elapsed_time": "1:17:51", "remaining_time": "1 day, 3:07:38"}
+{"current_steps": 22, "total_steps": 460, "loss": 0.5713, "lr": 3.8260869565217395e-05, "epoch": 0.2381596752368065, "percentage": 4.78, "elapsed_time": "1:21:31", "remaining_time": "1 day, 3:03:01"}
+{"current_steps": 23, "total_steps": 460, "loss": 0.5636, "lr": 4e-05, "epoch": 0.2489851150202977, "percentage": 5.0, "elapsed_time": "1:25:11", "remaining_time": "1 day, 2:58:34"}
+{"current_steps": 24, "total_steps": 460, "loss": 0.5703, "lr": 4.173913043478261e-05, "epoch": 0.2598105548037889, "percentage": 5.22, "elapsed_time": "1:28:51", "remaining_time": "1 day, 2:54:14"}
+{"current_steps": 25, "total_steps": 460, "loss": 0.5608, "lr": 4.347826086956522e-05, "epoch": 0.2706359945872801, "percentage": 5.43, "elapsed_time": "1:32:31", "remaining_time": "1 day, 2:49:50"}
+{"current_steps": 26, "total_steps": 460, "loss": 0.5383, "lr": 4.521739130434783e-05, "epoch": 0.2814614343707713, "percentage": 5.65, "elapsed_time": "1:36:10", "remaining_time": "1 day, 2:45:26"}
+{"current_steps": 27, "total_steps": 460, "loss": 0.5481, "lr": 4.6956521739130444e-05, "epoch": 0.2922868741542625, "percentage": 5.87, "elapsed_time": "1:39:50", "remaining_time": "1 day, 2:41:16"}
+{"current_steps": 28, "total_steps": 460, "loss": 0.5463, "lr": 4.869565217391305e-05, "epoch": 0.30311231393775373, "percentage": 6.09, "elapsed_time": "1:43:30", "remaining_time": "1 day, 2:36:58"}
+{"current_steps": 29, "total_steps": 460, "loss": 0.5542, "lr": 5.043478260869566e-05, "epoch": 0.31393775372124494, "percentage": 6.3, "elapsed_time": "1:47:10", "remaining_time": "1 day, 2:32:48"}
+{"current_steps": 30, "total_steps": 460, "loss": 0.5401, "lr": 5.217391304347826e-05, "epoch": 0.32476319350473615, "percentage": 6.52, "elapsed_time": "1:50:50", "remaining_time": "1 day, 2:28:37"}
+{"current_steps": 31, "total_steps": 460, "loss": 0.5552, "lr": 5.391304347826087e-05, "epoch": 0.33558863328822736, "percentage": 6.74, "elapsed_time": "1:54:30", "remaining_time": "1 day, 2:24:39"}
+{"current_steps": 32, "total_steps": 460, "loss": 0.5547, "lr": 5.565217391304348e-05, "epoch": 0.34641407307171856, "percentage": 6.96, "elapsed_time": "1:58:10", "remaining_time": "1 day, 2:20:33"}
+{"current_steps": 33, "total_steps": 460, "loss": 0.5499, "lr": 5.739130434782609e-05, "epoch": 0.3572395128552097, "percentage": 7.17, "elapsed_time": "2:01:50", "remaining_time": "1 day, 2:16:32"}
+{"current_steps": 34, "total_steps": 460, "loss": 0.55, "lr": 5.91304347826087e-05, "epoch": 0.3680649526387009, "percentage": 7.39, "elapsed_time": "2:05:29", "remaining_time": "1 day, 2:12:22"}
+{"current_steps": 35, "total_steps": 460, "loss": 0.5347, "lr": 6.086956521739131e-05, "epoch": 0.37889039242219213, "percentage": 7.61, "elapsed_time": "2:09:09", "remaining_time": "1 day, 2:08:20"}
+{"current_steps": 36, "total_steps": 460, "loss": 0.5264, "lr": 6.260869565217392e-05, "epoch": 0.38971583220568334, "percentage": 7.83, "elapsed_time": "2:12:49", "remaining_time": "1 day, 2:04:27"}
+{"current_steps": 37, "total_steps": 460, "loss": 0.5362, "lr": 6.434782608695653e-05, "epoch": 0.40054127198917455, "percentage": 8.04, "elapsed_time": "2:16:30", "remaining_time": "1 day, 2:00:33"}
+{"current_steps": 38, "total_steps": 460, "loss": 0.5238, "lr": 6.608695652173914e-05, "epoch": 0.41136671177266576, "percentage": 8.26, "elapsed_time": "2:20:10", "remaining_time": "1 day, 1:56:36"}
+{"current_steps": 39, "total_steps": 460, "loss": 0.5311, "lr": 6.782608695652175e-05, "epoch": 0.42219215155615697, "percentage": 8.48, "elapsed_time": "2:23:50", "remaining_time": "1 day, 1:52:42"}
+{"current_steps": 40, "total_steps": 460, "loss": 0.523, "lr": 6.956521739130436e-05, "epoch": 0.4330175913396482, "percentage": 8.7, "elapsed_time": "2:27:30", "remaining_time": "1 day, 1:48:49"}
+{"current_steps": 41, "total_steps": 460, "loss": 0.5188, "lr": 7.130434782608696e-05, "epoch": 0.4438430311231394, "percentage": 8.91, "elapsed_time": "2:31:10", "remaining_time": "1 day, 1:44:58"}
+{"current_steps": 42, "total_steps": 460, "loss": 0.5239, "lr": 7.304347826086957e-05, "epoch": 0.4546684709066306, "percentage": 9.13, "elapsed_time": "2:34:50", "remaining_time": "1 day, 1:41:02"}
+{"current_steps": 43, "total_steps": 460, "loss": 0.5174, "lr": 7.478260869565218e-05, "epoch": 0.4654939106901218, "percentage": 9.35, "elapsed_time": "2:38:30", "remaining_time": "1 day, 1:37:09"}
+{"current_steps": 44, "total_steps": 460, "loss": 0.5147, "lr": 7.652173913043479e-05, "epoch": 0.476319350473613, "percentage": 9.57, "elapsed_time": "2:42:10", "remaining_time": "1 day, 1:33:20"}
+{"current_steps": 45, "total_steps": 460, "loss": 0.5243, "lr": 7.82608695652174e-05, "epoch": 0.4871447902571042, "percentage": 9.78, "elapsed_time": "2:45:50", "remaining_time": "1 day, 1:29:29"}
+{"current_steps": 46, "total_steps": 460, "loss": 0.5176, "lr": 8e-05, "epoch": 0.4979702300405954, "percentage": 10.0, "elapsed_time": "2:49:31", "remaining_time": "1 day, 1:25:39"}
+{"current_steps": 47, "total_steps": 460, "loss": 0.5124, "lr": 7.999884833286186e-05, "epoch": 0.5087956698240866, "percentage": 10.22, "elapsed_time": "2:53:11", "remaining_time": "1 day, 1:21:48"}
+{"current_steps": 48, "total_steps": 460, "loss": 0.5211, "lr": 7.999539339776424e-05, "epoch": 0.5196211096075778, "percentage": 10.43, "elapsed_time": "2:56:50", "remaining_time": "1 day, 1:17:57"}
+{"current_steps": 49, "total_steps": 460, "loss": 0.5144, "lr": 7.998963539365397e-05, "epoch": 0.530446549391069, "percentage": 10.65, "elapsed_time": "3:00:30", "remaining_time": "1 day, 1:14:07"}
+{"current_steps": 50, "total_steps": 460, "loss": 0.5084, "lr": 7.998157465209622e-05, "epoch": 0.5412719891745602, "percentage": 10.87, "elapsed_time": "3:04:10", "remaining_time": "1 day, 1:10:17"}
+{"current_steps": 51, "total_steps": 460, "loss": 0.52, "lr": 7.997121163725553e-05, "epoch": 0.5520974289580515, "percentage": 11.09, "elapsed_time": "3:07:51", "remaining_time": "1 day, 1:06:29"}
+{"current_steps": 52, "total_steps": 460, "loss": 0.527, "lr": 7.995854694586911e-05, "epoch": 0.5629228687415426, "percentage": 11.3, "elapsed_time": "3:11:31", "remaining_time": "1 day, 1:02:42"}
+{"current_steps": 53, "total_steps": 460, "loss": 0.5125, "lr": 7.994358130721238e-05, "epoch": 0.5737483085250338, "percentage": 11.52, "elapsed_time": "3:15:11", "remaining_time": "1 day, 0:58:54"}
+{"current_steps": 54, "total_steps": 460, "loss": 0.5239, "lr": 7.992631558305709e-05, "epoch": 0.584573748308525, "percentage": 11.74, "elapsed_time": "3:18:51", "remaining_time": "1 day, 0:55:06"}
+{"current_steps": 55, "total_steps": 460, "loss": 0.5054, "lr": 7.990675076762158e-05, "epoch": 0.5953991880920162, "percentage": 11.96, "elapsed_time": "3:22:31", "remaining_time": "1 day, 0:51:18"}
+{"current_steps": 56, "total_steps": 460, "loss": 0.5106, "lr": 7.988488798751358e-05, "epoch": 0.6062246278755075, "percentage": 12.17, "elapsed_time": "3:26:11", "remaining_time": "1 day, 0:47:29"}
+{"current_steps": 57, "total_steps": 460, "loss": 0.5065, "lr": 7.986072850166538e-05, "epoch": 0.6170500676589986, "percentage": 12.39, "elapsed_time": "3:29:51", "remaining_time": "1 day, 0:43:43"}
+{"current_steps": 58, "total_steps": 460, "loss": 0.5062, "lr": 7.983427370126126e-05, "epoch": 0.6278755074424899, "percentage": 12.61, "elapsed_time": "3:33:31", "remaining_time": "1 day, 0:39:55"}
+{"current_steps": 59, "total_steps": 460, "loss": 0.4905, "lr": 7.980552510965744e-05, "epoch": 0.638700947225981, "percentage": 12.83, "elapsed_time": "3:37:11", "remaining_time": "1 day, 0:36:07"}
+{"current_steps": 60, "total_steps": 460, "loss": 0.5013, "lr": 7.977448438229435e-05, "epoch": 0.6495263870094723, "percentage": 13.04, "elapsed_time": "3:40:50", "remaining_time": "1 day, 0:32:19"}
+{"current_steps": 61, "total_steps": 460, "loss": 0.5107, "lr": 7.974115330660125e-05, "epoch": 0.6603518267929634, "percentage": 13.26, "elapsed_time": "3:44:30", "remaining_time": "1 day, 0:28:32"}
+{"current_steps": 62, "total_steps": 460, "loss": 0.5004, "lr": 7.970553380189338e-05, "epoch": 0.6711772665764547, "percentage": 13.48, "elapsed_time": "3:48:10", "remaining_time": "1 day, 0:24:43"}
+{"current_steps": 63, "total_steps": 460, "loss": 0.5112, "lr": 7.966762791926138e-05, "epoch": 0.6820027063599459, "percentage": 13.7, "elapsed_time": "3:51:50", "remaining_time": "1 day, 0:20:56"}
+{"current_steps": 64, "total_steps": 460, "loss": 0.5033, "lr": 7.962743784145323e-05, "epoch": 0.6928281461434371, "percentage": 13.91, "elapsed_time": "3:55:30", "remaining_time": "1 day, 0:17:10"}
+{"current_steps": 65, "total_steps": 460, "loss": 0.4994, "lr": 7.958496588274853e-05, "epoch": 0.7036535859269283, "percentage": 14.13, "elapsed_time": "3:59:09", "remaining_time": "1 day, 0:13:22"}
+{"current_steps": 66, "total_steps": 460, "loss": 0.5014, "lr": 7.954021448882522e-05, "epoch": 0.7144790257104194, "percentage": 14.35, "elapsed_time": "4:02:49", "remaining_time": "1 day, 0:09:36"}
+{"current_steps": 67, "total_steps": 460, "loss": 0.4988, "lr": 7.94931862366188e-05, "epoch": 0.7253044654939107, "percentage": 14.57, "elapsed_time": "4:06:29", "remaining_time": "1 day, 0:05:49"}
+{"current_steps": 68, "total_steps": 460, "loss": 0.5078, "lr": 7.944388383417388e-05, "epoch": 0.7361299052774019, "percentage": 14.78, "elapsed_time": "4:10:09", "remaining_time": "1 day, 0:02:02"}
+{"current_steps": 69, "total_steps": 460, "loss": 0.497, "lr": 7.939231012048833e-05, "epoch": 0.7469553450608931, "percentage": 15.0, "elapsed_time": "4:13:48", "remaining_time": "23:58:17"}
+{"current_steps": 70, "total_steps": 460, "loss": 0.4826, "lr": 7.93384680653497e-05, "epoch": 0.7577807848443843, "percentage": 15.22, "elapsed_time": "4:17:28", "remaining_time": "23:54:30"}
+{"current_steps": 71, "total_steps": 460, "loss": 0.4856, "lr": 7.928236076916423e-05, "epoch": 0.7686062246278755, "percentage": 15.43, "elapsed_time": "4:21:08", "remaining_time": "23:50:47"}
+{"current_steps": 72, "total_steps": 460, "loss": 0.4953, "lr": 7.922399146277846e-05, "epoch": 0.7794316644113667, "percentage": 15.65, "elapsed_time": "4:24:48", "remaining_time": "23:47:02"}
+{"current_steps": 73, "total_steps": 460, "loss": 0.5043, "lr": 7.916336350729293e-05, "epoch": 0.790257104194858, "percentage": 15.87, "elapsed_time": "4:28:28", "remaining_time": "23:43:16"}
+{"current_steps": 74, "total_steps": 460, "loss": 0.4982, "lr": 7.910048039386885e-05, "epoch": 0.8010825439783491, "percentage": 16.09, "elapsed_time": "4:32:08", "remaining_time": "23:39:31"}
+{"current_steps": 75, "total_steps": 460, "loss": 0.4924, "lr": 7.903534574352698e-05, "epoch": 0.8119079837618404, "percentage": 16.3, "elapsed_time": "4:35:48", "remaining_time": "23:35:47"}
+{"current_steps": 76, "total_steps": 460, "loss": 0.4941, "lr": 7.896796330693917e-05, "epoch": 0.8227334235453315, "percentage": 16.52, "elapsed_time": "4:39:27", "remaining_time": "23:32:01"}
+{"current_steps": 77, "total_steps": 460, "loss": 0.4905, "lr": 7.889833696421229e-05, "epoch": 0.8335588633288228, "percentage": 16.74, "elapsed_time": "4:43:08", "remaining_time": "23:28:20"}
+{"current_steps": 78, "total_steps": 460, "loss": 0.4949, "lr": 7.882647072466488e-05, "epoch": 0.8443843031123139, "percentage": 16.96, "elapsed_time": "4:46:48", "remaining_time": "23:24:37"}
+{"current_steps": 79, "total_steps": 460, "loss": 0.4956, "lr": 7.875236872659626e-05, "epoch": 0.8552097428958051, "percentage": 17.17, "elapsed_time": "4:50:28", "remaining_time": "23:20:52"}
+{"current_steps": 80, "total_steps": 460, "loss": 0.4891, "lr": 7.867603523704825e-05, "epoch": 0.8660351826792964, "percentage": 17.39, "elapsed_time": "4:54:08", "remaining_time": "23:17:09"}
+{"current_steps": 81, "total_steps": 460, "loss": 0.4983, "lr": 7.859747465155941e-05, "epoch": 0.8768606224627875, "percentage": 17.61, "elapsed_time": "4:57:47", "remaining_time": "23:13:23"}
+{"current_steps": 82, "total_steps": 460, "loss": 0.4853, "lr": 7.851669149391198e-05, "epoch": 0.8876860622462788, "percentage": 17.83, "elapsed_time": "5:01:27", "remaining_time": "23:09:39"}
+{"current_steps": 83, "total_steps": 460, "loss": 0.4899, "lr": 7.843369041587135e-05, "epoch": 0.8985115020297699, "percentage": 18.04, "elapsed_time": "5:05:07", "remaining_time": "23:05:55"}
+{"current_steps": 84, "total_steps": 460, "loss": 0.4921, "lr": 7.834847619691823e-05, "epoch": 0.9093369418132612, "percentage": 18.26, "elapsed_time": "5:08:47", "remaining_time": "23:02:13"}
+{"current_steps": 85, "total_steps": 460, "loss": 0.491, "lr": 7.82610537439734e-05, "epoch": 0.9201623815967523, "percentage": 18.48, "elapsed_time": "5:12:27", "remaining_time": "22:58:30"}
+{"current_steps": 86, "total_steps": 460, "loss": 0.4927, "lr": 7.817142809111516e-05, "epoch": 0.9309878213802436, "percentage": 18.7, "elapsed_time": "5:16:07", "remaining_time": "22:54:45"}
+{"current_steps": 87, "total_steps": 460, "loss": 0.4901, "lr": 7.807960439928948e-05, "epoch": 0.9418132611637348, "percentage": 18.91, "elapsed_time": "5:19:47", "remaining_time": "22:51:01"}
+{"current_steps": 88, "total_steps": 460, "loss": 0.4727, "lr": 7.798558795601278e-05, "epoch": 0.952638700947226, "percentage": 19.13, "elapsed_time": "5:23:27", "remaining_time": "22:47:20"}
+{"current_steps": 89, "total_steps": 460, "loss": 0.4909, "lr": 7.788938417506746e-05, "epoch": 0.9634641407307172, "percentage": 19.35, "elapsed_time": "5:27:07", "remaining_time": "22:43:36"}
+{"current_steps": 90, "total_steps": 460, "loss": 0.486, "lr": 7.779099859619017e-05, "epoch": 0.9742895805142084, "percentage": 19.57, "elapsed_time": "5:30:46", "remaining_time": "22:39:51"}
+{"current_steps": 91, "total_steps": 460, "loss": 0.4874, "lr": 7.769043688475283e-05, "epoch": 0.9851150202976996, "percentage": 19.78, "elapsed_time": "5:34:26", "remaining_time": "22:36:08"}
+{"current_steps": 92, "total_steps": 460, "loss": 0.4911, "lr": 7.758770483143634e-05, "epoch": 0.9959404600811907, "percentage": 20.0, "elapsed_time": "5:38:07", "remaining_time": "22:32:28"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4348cbb524918cd53f7b145e5dfa32b19fa8e2a9140acdb2ca2657465512df0
+size 7160