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 sha256:83828bf8a9500ba3a372edbcf9b3ba5811ac69c888b5aff937f2da128cd3a44d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefa598355af6d4934d9a31c7105bcf864a7967649be7144c095eb1b0890a079
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36a3ea3a4b815e7278f3b4019f479e9aac0b706ae4c40584244d7995b6966a5
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a3714d1376200dc6ef2aa55aa6ac6b0742aa88592b5b3c37e9039f55ba7119
+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 +1,112 @@
+{"current_steps": 1, "total_steps": 333, "loss": 0.8925, "lr": 2.3529411764705885e-06, "epoch": 0.008988764044943821, "percentage": 0.3, "elapsed_time": "0:02:29", "remaining_time": "13:49:56"}
+{"current_steps": 2, "total_steps": 333, "loss": 0.8908, "lr": 4.705882352941177e-06, "epoch": 0.017977528089887642, "percentage": 0.6, "elapsed_time": "0:04:06", "remaining_time": "11:19:50"}
+{"current_steps": 3, "total_steps": 333, "loss": 0.8716, "lr": 7.058823529411766e-06, "epoch": 0.02696629213483146, "percentage": 0.9, "elapsed_time": "0:05:44", "remaining_time": "10:30:42"}
+{"current_steps": 4, "total_steps": 333, "loss": 0.8395, "lr": 9.411764705882354e-06, "epoch": 0.035955056179775284, "percentage": 1.2, "elapsed_time": "0:07:21", "remaining_time": "10:04:53"}
+{"current_steps": 5, "total_steps": 333, "loss": 0.7954, "lr": 1.1764705882352942e-05, "epoch": 0.0449438202247191, "percentage": 1.5, "elapsed_time": "0:08:58", "remaining_time": "9:48:19"}
+{"current_steps": 6, "total_steps": 333, "loss": 0.8391, "lr": 1.4117647058823532e-05, "epoch": 0.05393258426966292, "percentage": 1.8, "elapsed_time": "0:10:34", "remaining_time": "9:36:32"}
+{"current_steps": 7, "total_steps": 333, "loss": 0.8077, "lr": 1.647058823529412e-05, "epoch": 0.06292134831460675, "percentage": 2.1, "elapsed_time": "0:12:11", "remaining_time": "9:28:10"}
+{"current_steps": 8, "total_steps": 333, "loss": 0.8269, "lr": 1.8823529411764708e-05, "epoch": 0.07191011235955057, "percentage": 2.4, "elapsed_time": "0:13:48", "remaining_time": "9:21:10"}
+{"current_steps": 9, "total_steps": 333, "loss": 0.7655, "lr": 2.1176470588235296e-05, "epoch": 0.08089887640449438, "percentage": 2.7, "elapsed_time": "0:15:26", "remaining_time": "9:15:43"}
+{"current_steps": 10, "total_steps": 333, "loss": 0.7356, "lr": 2.3529411764705884e-05, "epoch": 0.0898876404494382, "percentage": 3.0, "elapsed_time": "0:17:03", "remaining_time": "9:10:46"}
+{"current_steps": 11, "total_steps": 333, "loss": 0.7015, "lr": 2.5882352941176475e-05, "epoch": 0.09887640449438202, "percentage": 3.3, "elapsed_time": "0:18:40", "remaining_time": "9:06:28"}
+{"current_steps": 12, "total_steps": 333, "loss": 0.6907, "lr": 2.8235294117647063e-05, "epoch": 0.10786516853932585, "percentage": 3.6, "elapsed_time": "0:20:16", "remaining_time": "9:02:30"}
+{"current_steps": 13, "total_steps": 333, "loss": 0.6657, "lr": 3.0588235294117644e-05, "epoch": 0.11685393258426967, "percentage": 3.9, "elapsed_time": "0:21:53", "remaining_time": "8:58:57"}
+{"current_steps": 14, "total_steps": 333, "loss": 0.6501, "lr": 3.294117647058824e-05, "epoch": 0.1258426966292135, "percentage": 4.2, "elapsed_time": "0:23:30", "remaining_time": "8:55:38"}
+{"current_steps": 15, "total_steps": 333, "loss": 0.6431, "lr": 3.529411764705883e-05, "epoch": 0.1348314606741573, "percentage": 4.5, "elapsed_time": "0:25:07", "remaining_time": "8:52:37"}
+{"current_steps": 16, "total_steps": 333, "loss": 0.6305, "lr": 3.7647058823529415e-05, "epoch": 0.14382022471910114, "percentage": 4.8, "elapsed_time": "0:26:44", "remaining_time": "8:49:43"}
+{"current_steps": 17, "total_steps": 333, "loss": 0.6239, "lr": 4e-05, "epoch": 0.15280898876404495, "percentage": 5.11, "elapsed_time": "0:28:21", "remaining_time": "8:46:59"}
+{"current_steps": 18, "total_steps": 333, "loss": 0.6169, "lr": 4.235294117647059e-05, "epoch": 0.16179775280898875, "percentage": 5.41, "elapsed_time": "0:29:57", "remaining_time": "8:44:22"}
+{"current_steps": 19, "total_steps": 333, "loss": 0.6097, "lr": 4.470588235294118e-05, "epoch": 0.1707865168539326, "percentage": 5.71, "elapsed_time": "0:31:34", "remaining_time": "8:41:54"}
+{"current_steps": 20, "total_steps": 333, "loss": 0.6134, "lr": 4.705882352941177e-05, "epoch": 0.1797752808988764, "percentage": 6.01, "elapsed_time": "0:33:11", "remaining_time": "8:39:30"}
+{"current_steps": 21, "total_steps": 333, "loss": 0.6007, "lr": 4.941176470588236e-05, "epoch": 0.18876404494382024, "percentage": 6.31, "elapsed_time": "0:34:48", "remaining_time": "8:37:12"}
+{"current_steps": 22, "total_steps": 333, "loss": 0.5961, "lr": 5.176470588235295e-05, "epoch": 0.19775280898876405, "percentage": 6.61, "elapsed_time": "0:36:25", "remaining_time": "8:34:56"}
+{"current_steps": 23, "total_steps": 333, "loss": 0.5872, "lr": 5.411764705882354e-05, "epoch": 0.20674157303370785, "percentage": 6.91, "elapsed_time": "0:38:02", "remaining_time": "8:32:45"}
+{"current_steps": 24, "total_steps": 333, "loss": 0.5779, "lr": 5.6470588235294126e-05, "epoch": 0.2157303370786517, "percentage": 7.21, "elapsed_time": "0:39:39", "remaining_time": "8:30:34"}
+{"current_steps": 25, "total_steps": 333, "loss": 0.5728, "lr": 5.8823529411764714e-05, "epoch": 0.2247191011235955, "percentage": 7.51, "elapsed_time": "0:41:15", "remaining_time": "8:28:24"}
+{"current_steps": 26, "total_steps": 333, "loss": 0.5948, "lr": 6.117647058823529e-05, "epoch": 0.23370786516853934, "percentage": 7.81, "elapsed_time": "0:42:52", "remaining_time": "8:26:18"}
+{"current_steps": 27, "total_steps": 333, "loss": 0.5869, "lr": 6.352941176470589e-05, "epoch": 0.24269662921348314, "percentage": 8.11, "elapsed_time": "0:44:29", "remaining_time": "8:24:15"}
+{"current_steps": 28, "total_steps": 333, "loss": 0.5816, "lr": 6.588235294117648e-05, "epoch": 0.251685393258427, "percentage": 8.41, "elapsed_time": "0:46:06", "remaining_time": "8:22:17"}
+{"current_steps": 29, "total_steps": 333, "loss": 0.5674, "lr": 6.823529411764707e-05, "epoch": 0.2606741573033708, "percentage": 8.71, "elapsed_time": "0:47:43", "remaining_time": "8:20:18"}
+{"current_steps": 30, "total_steps": 333, "loss": 0.5801, "lr": 7.058823529411765e-05, "epoch": 0.2696629213483146, "percentage": 9.01, "elapsed_time": "0:49:20", "remaining_time": "8:18:21"}
+{"current_steps": 31, "total_steps": 333, "loss": 0.5622, "lr": 7.294117647058824e-05, "epoch": 0.2786516853932584, "percentage": 9.31, "elapsed_time": "0:50:57", "remaining_time": "8:16:26"}
+{"current_steps": 32, "total_steps": 333, "loss": 0.5628, "lr": 7.529411764705883e-05, "epoch": 0.2876404494382023, "percentage": 9.61, "elapsed_time": "0:52:34", "remaining_time": "8:14:30"}
+{"current_steps": 33, "total_steps": 333, "loss": 0.569, "lr": 7.764705882352942e-05, "epoch": 0.2966292134831461, "percentage": 9.91, "elapsed_time": "0:54:11", "remaining_time": "8:12:39"}
+{"current_steps": 34, "total_steps": 333, "loss": 0.5559, "lr": 8e-05, "epoch": 0.3056179775280899, "percentage": 10.21, "elapsed_time": "0:55:48", "remaining_time": "8:10:45"}
+{"current_steps": 35, "total_steps": 333, "loss": 0.5578, "lr": 7.999779207981935e-05, "epoch": 0.3146067415730337, "percentage": 10.51, "elapsed_time": "0:57:25", "remaining_time": "8:08:54"}
+{"current_steps": 36, "total_steps": 333, "loss": 0.5553, "lr": 7.999116856302298e-05, "epoch": 0.3235955056179775, "percentage": 10.81, "elapsed_time": "0:59:02", "remaining_time": "8:07:03"}
+{"current_steps": 37, "total_steps": 333, "loss": 0.5518, "lr": 7.998013018082072e-05, "epoch": 0.3325842696629214, "percentage": 11.11, "elapsed_time": "1:00:39", "remaining_time": "8:05:13"}
+{"current_steps": 38, "total_steps": 333, "loss": 0.5587, "lr": 7.996467815180588e-05, "epoch": 0.3415730337078652, "percentage": 11.41, "elapsed_time": "1:02:16", "remaining_time": "8:03:24"}
+{"current_steps": 39, "total_steps": 333, "loss": 0.5394, "lr": 7.994481418182082e-05, "epoch": 0.350561797752809, "percentage": 11.71, "elapsed_time": "1:03:53", "remaining_time": "8:01:36"}
+{"current_steps": 40, "total_steps": 333, "loss": 0.5602, "lr": 7.992054046376854e-05, "epoch": 0.3595505617977528, "percentage": 12.01, "elapsed_time": "1:05:29", "remaining_time": "7:59:47"}
+{"current_steps": 41, "total_steps": 333, "loss": 0.5489, "lr": 7.989185967737066e-05, "epoch": 0.3685393258426966, "percentage": 12.31, "elapsed_time": "1:07:06", "remaining_time": "7:57:59"}
+{"current_steps": 42, "total_steps": 333, "loss": 0.554, "lr": 7.985877498887149e-05, "epoch": 0.3775280898876405, "percentage": 12.61, "elapsed_time": "1:08:43", "remaining_time": "7:56:12"}
+{"current_steps": 43, "total_steps": 333, "loss": 0.5432, "lr": 7.982129005068865e-05, "epoch": 0.3865168539325843, "percentage": 12.91, "elapsed_time": "1:10:20", "remaining_time": "7:54:24"}
+{"current_steps": 44, "total_steps": 333, "loss": 0.5476, "lr": 7.977940900100967e-05, "epoch": 0.3955056179775281, "percentage": 13.21, "elapsed_time": "1:11:57", "remaining_time": "7:52:36"}
+{"current_steps": 45, "total_steps": 333, "loss": 0.535, "lr": 7.973313646333532e-05, "epoch": 0.4044943820224719, "percentage": 13.51, "elapsed_time": "1:13:34", "remaining_time": "7:50:49"}
+{"current_steps": 46, "total_steps": 333, "loss": 0.5339, "lr": 7.968247754596908e-05, "epoch": 0.4134831460674157, "percentage": 13.81, "elapsed_time": "1:15:10", "remaining_time": "7:49:02"}
+{"current_steps": 47, "total_steps": 333, "loss": 0.5381, "lr": 7.962743784145323e-05, "epoch": 0.42247191011235957, "percentage": 14.11, "elapsed_time": "1:16:47", "remaining_time": "7:47:18"}
+{"current_steps": 48, "total_steps": 333, "loss": 0.5328, "lr": 7.956802342595152e-05, "epoch": 0.4314606741573034, "percentage": 14.41, "elapsed_time": "1:18:24", "remaining_time": "7:45:32"}
+{"current_steps": 49, "total_steps": 333, "loss": 0.5265, "lr": 7.950424085857827e-05, "epoch": 0.4404494382022472, "percentage": 14.71, "elapsed_time": "1:20:01", "remaining_time": "7:43:48"}
+{"current_steps": 50, "total_steps": 333, "loss": 0.5245, "lr": 7.943609718067437e-05, "epoch": 0.449438202247191, "percentage": 15.02, "elapsed_time": "1:21:38", "remaining_time": "7:42:02"}
+{"current_steps": 51, "total_steps": 333, "loss": 0.5167, "lr": 7.936359991502993e-05, "epoch": 0.4584269662921348, "percentage": 15.32, "elapsed_time": "1:23:15", "remaining_time": "7:40:19"}
+{"current_steps": 52, "total_steps": 333, "loss": 0.5325, "lr": 7.92867570650537e-05, "epoch": 0.46741573033707867, "percentage": 15.62, "elapsed_time": "1:24:51", "remaining_time": "7:38:36"}
+{"current_steps": 53, "total_steps": 333, "loss": 0.5371, "lr": 7.920557711388967e-05, "epoch": 0.4764044943820225, "percentage": 15.92, "elapsed_time": "1:26:28", "remaining_time": "7:36:52"}
+{"current_steps": 54, "total_steps": 333, "loss": 0.5245, "lr": 7.912006902348045e-05, "epoch": 0.4853932584269663, "percentage": 16.22, "elapsed_time": "1:28:05", "remaining_time": "7:35:07"}
+{"current_steps": 55, "total_steps": 333, "loss": 0.5289, "lr": 7.903024223357797e-05, "epoch": 0.4943820224719101, "percentage": 16.52, "elapsed_time": "1:29:42", "remaining_time": "7:33:25"}
+{"current_steps": 56, "total_steps": 333, "loss": 0.5346, "lr": 7.893610666070134e-05, "epoch": 0.503370786516854, "percentage": 16.82, "elapsed_time": "1:31:19", "remaining_time": "7:31:42"}
+{"current_steps": 57, "total_steps": 333, "loss": 0.5251, "lr": 7.883767269704209e-05, "epoch": 0.5123595505617977, "percentage": 17.12, "elapsed_time": "1:32:56", "remaining_time": "7:29:59"}
+{"current_steps": 58, "total_steps": 333, "loss": 0.5242, "lr": 7.873495120931697e-05, "epoch": 0.5213483146067416, "percentage": 17.42, "elapsed_time": "1:34:32", "remaining_time": "7:28:16"}
+{"current_steps": 59, "total_steps": 333, "loss": 0.5266, "lr": 7.86279535375683e-05, "epoch": 0.5303370786516854, "percentage": 17.72, "elapsed_time": "1:36:09", "remaining_time": "7:26:34"}
+{"current_steps": 60, "total_steps": 333, "loss": 0.5228, "lr": 7.851669149391198e-05, "epoch": 0.5393258426966292, "percentage": 18.02, "elapsed_time": "1:37:46", "remaining_time": "7:24:51"}
+{"current_steps": 61, "total_steps": 333, "loss": 0.5231, "lr": 7.84011773612336e-05, "epoch": 0.5483146067415731, "percentage": 18.32, "elapsed_time": "1:39:22", "remaining_time": "7:23:08"}
+{"current_steps": 62, "total_steps": 333, "loss": 0.5195, "lr": 7.828142389183239e-05, "epoch": 0.5573033707865168, "percentage": 18.62, "elapsed_time": "1:40:59", "remaining_time": "7:21:26"}
+{"current_steps": 63, "total_steps": 333, "loss": 0.5129, "lr": 7.815744430601344e-05, "epoch": 0.5662921348314607, "percentage": 18.92, "elapsed_time": "1:42:36", "remaining_time": "7:19:45"}
+{"current_steps": 64, "total_steps": 333, "loss": 0.521, "lr": 7.802925229062823e-05, "epoch": 0.5752808988764045, "percentage": 19.22, "elapsed_time": "1:44:13", "remaining_time": "7:18:03"}
+{"current_steps": 65, "total_steps": 333, "loss": 0.5172, "lr": 7.789686199756365e-05, "epoch": 0.5842696629213483, "percentage": 19.52, "elapsed_time": "1:45:50", "remaining_time": "7:16:22"}
+{"current_steps": 66, "total_steps": 333, "loss": 0.5134, "lr": 7.776028804217968e-05, "epoch": 0.5932584269662922, "percentage": 19.82, "elapsed_time": "1:47:26", "remaining_time": "7:14:40"}
+{"current_steps": 67, "total_steps": 333, "loss": 0.5161, "lr": 7.761954550169593e-05, "epoch": 0.6022471910112359, "percentage": 20.12, "elapsed_time": "1:49:03", "remaining_time": "7:13:00"}
+{"current_steps": 68, "total_steps": 333, "loss": 0.5153, "lr": 7.74746499135272e-05, "epoch": 0.6112359550561798, "percentage": 20.42, "elapsed_time": "1:50:40", "remaining_time": "7:11:19"}
+{"current_steps": 69, "total_steps": 333, "loss": 0.5086, "lr": 7.732561727356811e-05, "epoch": 0.6202247191011236, "percentage": 20.72, "elapsed_time": "1:52:17", "remaining_time": "7:09:39"}
+{"current_steps": 70, "total_steps": 333, "loss": 0.5137, "lr": 7.717246403442735e-05, "epoch": 0.6292134831460674, "percentage": 21.02, "elapsed_time": "1:53:54", "remaining_time": "7:07:58"}
+{"current_steps": 71, "total_steps": 333, "loss": 0.4999, "lr": 7.701520710361129e-05, "epoch": 0.6382022471910113, "percentage": 21.32, "elapsed_time": "1:55:31", "remaining_time": "7:06:18"}
+{"current_steps": 72, "total_steps": 333, "loss": 0.5036, "lr": 7.685386384165748e-05, "epoch": 0.647191011235955, "percentage": 21.62, "elapsed_time": "1:57:08", "remaining_time": "7:04:38"}
+{"current_steps": 73, "total_steps": 333, "loss": 0.5132, "lr": 7.668845206021812e-05, "epoch": 0.6561797752808989, "percentage": 21.92, "elapsed_time": "1:58:45", "remaining_time": "7:02:58"}
+{"current_steps": 74, "total_steps": 333, "loss": 0.5044, "lr": 7.651899002009375e-05, "epoch": 0.6651685393258427, "percentage": 22.22, "elapsed_time": "2:00:22", "remaining_time": "7:01:18"}
+{"current_steps": 75, "total_steps": 333, "loss": 0.5158, "lr": 7.634549642921725e-05, "epoch": 0.6741573033707865, "percentage": 22.52, "elapsed_time": "2:01:59", "remaining_time": "6:59:39"}
+{"current_steps": 76, "total_steps": 333, "loss": 0.5132, "lr": 7.616799044058867e-05, "epoch": 0.6831460674157304, "percentage": 22.82, "elapsed_time": "2:03:36", "remaining_time": "6:57:59"}
+{"current_steps": 77, "total_steps": 333, "loss": 0.5051, "lr": 7.598649165016073e-05, "epoch": 0.6921348314606741, "percentage": 23.12, "elapsed_time": "2:05:13", "remaining_time": "6:56:20"}
+{"current_steps": 78, "total_steps": 333, "loss": 0.5, "lr": 7.58010200946755e-05, "epoch": 0.701123595505618, "percentage": 23.42, "elapsed_time": "2:06:50", "remaining_time": "6:54:40"}
+{"current_steps": 79, "total_steps": 333, "loss": 0.5094, "lr": 7.561159624945257e-05, "epoch": 0.7101123595505618, "percentage": 23.72, "elapsed_time": "2:08:27", "remaining_time": "6:53:01"}
+{"current_steps": 80, "total_steps": 333, "loss": 0.5009, "lr": 7.541824102612839e-05, "epoch": 0.7191011235955056, "percentage": 24.02, "elapsed_time": "2:10:04", "remaining_time": "6:51:21"}
+{"current_steps": 81, "total_steps": 333, "loss": 0.501, "lr": 7.5220975770348e-05, "epoch": 0.7280898876404495, "percentage": 24.32, "elapsed_time": "2:11:41", "remaining_time": "6:49:41"}
+{"current_steps": 82, "total_steps": 333, "loss": 0.5009, "lr": 7.501982225940833e-05, "epoch": 0.7370786516853932, "percentage": 24.62, "elapsed_time": "2:13:18", "remaining_time": "6:48:02"}
+{"current_steps": 83, "total_steps": 333, "loss": 0.503, "lr": 7.48148026998542e-05, "epoch": 0.7460674157303371, "percentage": 24.92, "elapsed_time": "2:14:55", "remaining_time": "6:46:23"}
+{"current_steps": 84, "total_steps": 333, "loss": 0.4953, "lr": 7.460593972502674e-05, "epoch": 0.755056179775281, "percentage": 25.23, "elapsed_time": "2:16:31", "remaining_time": "6:44:43"}
+{"current_steps": 85, "total_steps": 333, "loss": 0.4897, "lr": 7.439325639256483e-05, "epoch": 0.7640449438202247, "percentage": 25.53, "elapsed_time": "2:18:08", "remaining_time": "6:43:03"}
+{"current_steps": 86, "total_steps": 333, "loss": 0.4969, "lr": 7.417677618185955e-05, "epoch": 0.7730337078651686, "percentage": 25.83, "elapsed_time": "2:19:45", "remaining_time": "6:41:24"}
+{"current_steps": 87, "total_steps": 333, "loss": 0.5046, "lr": 7.39565229914622e-05, "epoch": 0.7820224719101123, "percentage": 26.13, "elapsed_time": "2:21:22", "remaining_time": "6:39:45"}
+{"current_steps": 88, "total_steps": 333, "loss": 0.5006, "lr": 7.373252113644596e-05, "epoch": 0.7910112359550562, "percentage": 26.43, "elapsed_time": "2:22:59", "remaining_time": "6:38:06"}
+{"current_steps": 89, "total_steps": 333, "loss": 0.4949, "lr": 7.350479534572166e-05, "epoch": 0.8, "percentage": 26.73, "elapsed_time": "2:24:36", "remaining_time": "6:36:27"}
+{"current_steps": 90, "total_steps": 333, "loss": 0.5003, "lr": 7.327337075930775e-05, "epoch": 0.8089887640449438, "percentage": 27.03, "elapsed_time": "2:26:13", "remaining_time": "6:34:48"}
+{"current_steps": 91, "total_steps": 333, "loss": 0.4907, "lr": 7.303827292555495e-05, "epoch": 0.8179775280898877, "percentage": 27.33, "elapsed_time": "2:27:50", "remaining_time": "6:33:10"}
+{"current_steps": 92, "total_steps": 333, "loss": 0.5043, "lr": 7.279952779832584e-05, "epoch": 0.8269662921348314, "percentage": 27.63, "elapsed_time": "2:29:27", "remaining_time": "6:31:32"}
+{"current_steps": 93, "total_steps": 333, "loss": 0.486, "lr": 7.255716173412966e-05, "epoch": 0.8359550561797753, "percentage": 27.93, "elapsed_time": "2:31:04", "remaining_time": "6:29:53"}
+{"current_steps": 94, "total_steps": 333, "loss": 0.4932, "lr": 7.23112014892126e-05, "epoch": 0.8449438202247191, "percentage": 28.23, "elapsed_time": "2:32:42", "remaining_time": "6:28:16"}
+{"current_steps": 95, "total_steps": 333, "loss": 0.49, "lr": 7.20616742166041e-05, "epoch": 0.8539325842696629, "percentage": 28.53, "elapsed_time": "2:34:20", "remaining_time": "6:26:40"}
+{"current_steps": 96, "total_steps": 333, "loss": 0.4911, "lr": 7.180860746311917e-05, "epoch": 0.8629213483146068, "percentage": 28.83, "elapsed_time": "2:35:57", "remaining_time": "6:25:01"}
+{"current_steps": 97, "total_steps": 333, "loss": 0.4922, "lr": 7.155202916631743e-05, "epoch": 0.8719101123595505, "percentage": 29.13, "elapsed_time": "2:37:34", "remaining_time": "6:23:23"}
+{"current_steps": 98, "total_steps": 333, "loss": 0.4899, "lr": 7.129196765141886e-05, "epoch": 0.8808988764044944, "percentage": 29.43, "elapsed_time": "2:39:11", "remaining_time": "6:21:44"}
+{"current_steps": 99, "total_steps": 333, "loss": 0.4935, "lr": 7.10284516281768e-05, "epoch": 0.8898876404494382, "percentage": 29.73, "elapsed_time": "2:40:49", "remaining_time": "6:20:07"}
+{"current_steps": 100, "total_steps": 333, "loss": 0.4933, "lr": 7.076151018770854e-05, "epoch": 0.898876404494382, "percentage": 30.03, "elapsed_time": "2:42:26", "remaining_time": "6:18:28"}
+{"current_steps": 101, "total_steps": 333, "loss": 0.4941, "lr": 7.049117279928374e-05, "epoch": 0.9078651685393259, "percentage": 30.33, "elapsed_time": "2:44:03", "remaining_time": "6:16:50"}
+{"current_steps": 102, "total_steps": 333, "loss": 0.4878, "lr": 7.021746930707117e-05, "epoch": 0.9168539325842696, "percentage": 30.63, "elapsed_time": "2:45:40", "remaining_time": "6:15:11"}
+{"current_steps": 103, "total_steps": 333, "loss": 0.478, "lr": 6.994042992684406e-05, "epoch": 0.9258426966292135, "percentage": 30.93, "elapsed_time": "2:47:17", "remaining_time": "6:13:33"}
+{"current_steps": 104, "total_steps": 333, "loss": 0.4868, "lr": 6.966008524264429e-05, "epoch": 0.9348314606741573, "percentage": 31.23, "elapsed_time": "2:48:54", "remaining_time": "6:11:55"}
+{"current_steps": 105, "total_steps": 333, "loss": 0.4921, "lr": 6.937646620340618e-05, "epoch": 0.9438202247191011, "percentage": 31.53, "elapsed_time": "2:50:31", "remaining_time": "6:10:17"}
+{"current_steps": 106, "total_steps": 333, "loss": 0.4871, "lr": 6.908960411953973e-05, "epoch": 0.952808988764045, "percentage": 31.83, "elapsed_time": "2:52:09", "remaining_time": "6:08:40"}
+{"current_steps": 107, "total_steps": 333, "loss": 0.4856, "lr": 6.879953065947416e-05, "epoch": 0.9617977528089887, "percentage": 32.13, "elapsed_time": "2:53:46", "remaining_time": "6:07:02"}
+{"current_steps": 108, "total_steps": 333, "loss": 0.4884, "lr": 6.850627784616178e-05, "epoch": 0.9707865168539326, "percentage": 32.43, "elapsed_time": "2:55:23", "remaining_time": "6:05:23"}
+{"current_steps": 109, "total_steps": 333, "loss": 0.4844, "lr": 6.82098780535428e-05, "epoch": 0.9797752808988764, "percentage": 32.73, "elapsed_time": "2:57:01", "remaining_time": "6:03:47"}
+{"current_steps": 110, "total_steps": 333, "loss": 0.4766, "lr": 6.791036400297142e-05, "epoch": 0.9887640449438202, "percentage": 33.03, "elapsed_time": "2:58:38", "remaining_time": "6:02:08"}
+{"current_steps": 111, "total_steps": 333, "loss": 0.4796, "lr": 6.760776875960347e-05, "epoch": 0.9977528089887641, "percentage": 33.33, "elapsed_time": "3:00:14", "remaining_time": "6:00:29"}
+{"current_steps": 112, "total_steps": 333, "loss": 0.8205, "lr": 6.730212572874618e-05, "epoch": 1.006741573033708, "percentage": 33.63, "elapsed_time": "3:03:21", "remaining_time": "6:01:47"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bd0f38d541ccf601a1d3cb3ae8da75b49cd763b1dd35bdbce9b6871d86834e
+size 7224