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:b2e93b5d72262ab3351369ae97f8c0046f40c61f3052f4a3a4c7f0d86c9094b5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e71f8e24bb13d5298083fb1e69abd9120534502baffe9d7492d5036f56d15a0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8c85267f240ef73bdd198f53b064737a16b689a9ea0e36e50e13b6adf7a6aee
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55de9e0595e4201963e56cd7a6eafcfdbd33cbb6223b43d6767b7c1723cf18f3
+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 +1,223 @@
+{"current_steps": 1, "total_steps": 666, "loss": 0.8286, "lr": 4e-05, "epoch": 0.004491858506457047, "percentage": 0.15, "elapsed_time": "0:02:54", "remaining_time": "1 day, 8:11:30"}
+{"current_steps": 2, "total_steps": 666, "loss": 1.1828, "lr": 4e-05, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:05:40", "remaining_time": "1 day, 7:25:39"}
+{"current_steps": 3, "total_steps": 666, "loss": 0.9659, "lr": 4e-05, "epoch": 0.01347557551937114, "percentage": 0.45, "elapsed_time": "0:08:36", "remaining_time": "1 day, 7:40:39"}
+{"current_steps": 4, "total_steps": 666, "loss": 0.8547, "lr": 4e-05, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:11:25", "remaining_time": "1 day, 7:29:37"}
+{"current_steps": 5, "total_steps": 666, "loss": 0.783, "lr": 4e-05, "epoch": 0.022459292532285232, "percentage": 0.75, "elapsed_time": "0:14:00", "remaining_time": "1 day, 6:52:50"}
+{"current_steps": 6, "total_steps": 666, "loss": 0.7203, "lr": 4e-05, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:16:46", "remaining_time": "1 day, 6:44:58"}
+{"current_steps": 7, "total_steps": 666, "loss": 0.6916, "lr": 4e-05, "epoch": 0.031443009545199324, "percentage": 1.05, "elapsed_time": "0:19:35", "remaining_time": "1 day, 6:44:17"}
+{"current_steps": 8, "total_steps": 666, "loss": 0.6661, "lr": 4e-05, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:22:20", "remaining_time": "1 day, 6:37:54"}
+{"current_steps": 9, "total_steps": 666, "loss": 0.6438, "lr": 4e-05, "epoch": 0.04042672655811342, "percentage": 1.35, "elapsed_time": "0:25:04", "remaining_time": "1 day, 6:30:35"}
+{"current_steps": 10, "total_steps": 666, "loss": 0.6306, "lr": 4e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:27:51", "remaining_time": "1 day, 6:27:23"}
+{"current_steps": 11, "total_steps": 666, "loss": 0.6285, "lr": 4e-05, "epoch": 0.049410443571027515, "percentage": 1.65, "elapsed_time": "0:30:44", "remaining_time": "1 day, 6:30:47"}
+{"current_steps": 12, "total_steps": 666, "loss": 0.6089, "lr": 4e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:33:17", "remaining_time": "1 day, 6:14:17"}
+{"current_steps": 13, "total_steps": 666, "loss": 0.5951, "lr": 4e-05, "epoch": 0.058394160583941604, "percentage": 1.95, "elapsed_time": "0:36:08", "remaining_time": "1 day, 6:15:41"}
+{"current_steps": 14, "total_steps": 666, "loss": 0.5897, "lr": 4e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:39:09", "remaining_time": "1 day, 6:23:46"}
+{"current_steps": 15, "total_steps": 666, "loss": 0.5786, "lr": 4e-05, "epoch": 0.06737787759685569, "percentage": 2.25, "elapsed_time": "0:41:56", "remaining_time": "1 day, 6:20:18"}
+{"current_steps": 16, "total_steps": 666, "loss": 0.576, "lr": 4e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:44:35", "remaining_time": "1 day, 6:11:40"}
+{"current_steps": 17, "total_steps": 666, "loss": 0.5839, "lr": 4e-05, "epoch": 0.0763615946097698, "percentage": 2.55, "elapsed_time": "0:47:19", "remaining_time": "1 day, 6:06:41"}
+{"current_steps": 18, "total_steps": 666, "loss": 0.5694, "lr": 4e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:50:07", "remaining_time": "1 day, 6:04:45"}
+{"current_steps": 19, "total_steps": 666, "loss": 0.5604, "lr": 4e-05, "epoch": 0.08534531162268388, "percentage": 2.85, "elapsed_time": "0:52:42", "remaining_time": "1 day, 5:55:07"}
+{"current_steps": 20, "total_steps": 666, "loss": 0.566, "lr": 4e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:55:33", "remaining_time": "1 day, 5:54:31"}
+{"current_steps": 21, "total_steps": 666, "loss": 0.551, "lr": 4e-05, "epoch": 0.09432902863559797, "percentage": 3.15, "elapsed_time": "0:58:18", "remaining_time": "1 day, 5:50:49"}
+{"current_steps": 22, "total_steps": 666, "loss": 0.5487, "lr": 4e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:01:09", "remaining_time": "1 day, 5:50:16"}
+{"current_steps": 23, "total_steps": 666, "loss": 0.5502, "lr": 4e-05, "epoch": 0.10331274564851207, "percentage": 3.45, "elapsed_time": "1:04:12", "remaining_time": "1 day, 5:54:50"}
+{"current_steps": 24, "total_steps": 666, "loss": 0.5431, "lr": 4e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:07:00", "remaining_time": "1 day, 5:52:18"}
+{"current_steps": 25, "total_steps": 666, "loss": 0.5441, "lr": 4e-05, "epoch": 0.11229646266142616, "percentage": 3.75, "elapsed_time": "1:09:47", "remaining_time": "1 day, 5:49:36"}
+{"current_steps": 26, "total_steps": 666, "loss": 0.526, "lr": 4e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:12:18", "remaining_time": "1 day, 5:39:53"}
+{"current_steps": 27, "total_steps": 666, "loss": 0.5373, "lr": 4e-05, "epoch": 0.12128017967434025, "percentage": 4.05, "elapsed_time": "1:14:59", "remaining_time": "1 day, 5:34:44"}
+{"current_steps": 28, "total_steps": 666, "loss": 0.536, "lr": 4e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:17:45", "remaining_time": "1 day, 5:31:52"}
+{"current_steps": 29, "total_steps": 666, "loss": 0.5379, "lr": 4e-05, "epoch": 0.13026389668725435, "percentage": 4.35, "elapsed_time": "1:20:30", "remaining_time": "1 day, 5:28:28"}
+{"current_steps": 30, "total_steps": 666, "loss": 0.5363, "lr": 4e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:23:17", "remaining_time": "1 day, 5:25:42"}
+{"current_steps": 31, "total_steps": 666, "loss": 0.5372, "lr": 4e-05, "epoch": 0.13924761370016844, "percentage": 4.65, "elapsed_time": "1:26:08", "remaining_time": "1 day, 5:24:27"}
+{"current_steps": 32, "total_steps": 666, "loss": 0.5299, "lr": 4e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:28:53", "remaining_time": "1 day, 5:21:18"}
+{"current_steps": 33, "total_steps": 666, "loss": 0.5172, "lr": 4e-05, "epoch": 0.14823133071308253, "percentage": 4.95, "elapsed_time": "1:31:44", "remaining_time": "1 day, 5:19:38"}
+{"current_steps": 34, "total_steps": 666, "loss": 0.5248, "lr": 4e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:34:30", "remaining_time": "1 day, 5:16:48"}
+{"current_steps": 35, "total_steps": 666, "loss": 0.5212, "lr": 4e-05, "epoch": 0.15721504772599662, "percentage": 5.26, "elapsed_time": "1:37:09", "remaining_time": "1 day, 5:11:37"}
+{"current_steps": 36, "total_steps": 666, "loss": 0.513, "lr": 4e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:39:58", "remaining_time": "1 day, 5:09:27"}
+{"current_steps": 37, "total_steps": 666, "loss": 0.5121, "lr": 4e-05, "epoch": 0.16619876473891074, "percentage": 5.56, "elapsed_time": "1:42:40", "remaining_time": "1 day, 5:05:26"}
+{"current_steps": 38, "total_steps": 666, "loss": 0.5199, "lr": 4e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:45:34", "remaining_time": "1 day, 5:04:48"}
+{"current_steps": 39, "total_steps": 666, "loss": 0.5171, "lr": 4e-05, "epoch": 0.17518248175182483, "percentage": 5.86, "elapsed_time": "1:48:15", "remaining_time": "1 day, 5:00:23"}
+{"current_steps": 40, "total_steps": 666, "loss": 0.5211, "lr": 4e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:51:04", "remaining_time": "1 day, 4:58:26"}
+{"current_steps": 41, "total_steps": 666, "loss": 0.5186, "lr": 4e-05, "epoch": 0.18416619876473891, "percentage": 6.16, "elapsed_time": "1:54:02", "remaining_time": "1 day, 4:58:29"}
+{"current_steps": 42, "total_steps": 666, "loss": 0.5065, "lr": 4e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "1:56:48", "remaining_time": "1 day, 4:55:29"}
+{"current_steps": 43, "total_steps": 666, "loss": 0.5062, "lr": 4e-05, "epoch": 0.193149915777653, "percentage": 6.46, "elapsed_time": "1:59:34", "remaining_time": "1 day, 4:52:33"}
+{"current_steps": 44, "total_steps": 666, "loss": 0.5137, "lr": 4e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:02:26", "remaining_time": "1 day, 4:50:56"}
+{"current_steps": 45, "total_steps": 666, "loss": 0.5011, "lr": 4e-05, "epoch": 0.2021336327905671, "percentage": 6.76, "elapsed_time": "2:05:03", "remaining_time": "1 day, 4:45:47"}
+{"current_steps": 46, "total_steps": 666, "loss": 0.5083, "lr": 4e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:07:41", "remaining_time": "1 day, 4:41:10"}
+{"current_steps": 47, "total_steps": 666, "loss": 0.5013, "lr": 4e-05, "epoch": 0.21111734980348118, "percentage": 7.06, "elapsed_time": "2:10:27", "remaining_time": "1 day, 4:38:15"}
+{"current_steps": 48, "total_steps": 666, "loss": 0.5073, "lr": 4e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:13:19", "remaining_time": "1 day, 4:36:36"}
+{"current_steps": 49, "total_steps": 666, "loss": 0.4943, "lr": 4e-05, "epoch": 0.2201010668163953, "percentage": 7.36, "elapsed_time": "2:16:00", "remaining_time": "1 day, 4:32:29"}
+{"current_steps": 50, "total_steps": 666, "loss": 0.5158, "lr": 4e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:18:38", "remaining_time": "1 day, 4:28:03"}
+{"current_steps": 51, "total_steps": 666, "loss": 0.5006, "lr": 4e-05, "epoch": 0.22908478382930939, "percentage": 7.66, "elapsed_time": "2:21:30", "remaining_time": "1 day, 4:26:28"}
+{"current_steps": 52, "total_steps": 666, "loss": 0.5066, "lr": 4e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:24:01", "remaining_time": "1 day, 4:20:37"}
+{"current_steps": 53, "total_steps": 666, "loss": 0.5007, "lr": 4e-05, "epoch": 0.23806850084222347, "percentage": 7.96, "elapsed_time": "2:26:33", "remaining_time": "1 day, 4:15:10"}
+{"current_steps": 54, "total_steps": 666, "loss": 0.5045, "lr": 4e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:29:13", "remaining_time": "1 day, 4:11:11"}
+{"current_steps": 55, "total_steps": 666, "loss": 0.4837, "lr": 4e-05, "epoch": 0.24705221785513756, "percentage": 8.26, "elapsed_time": "2:31:58", "remaining_time": "1 day, 4:08:23"}
+{"current_steps": 56, "total_steps": 666, "loss": 0.4989, "lr": 4e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:34:32", "remaining_time": "1 day, 4:03:24"}
+{"current_steps": 57, "total_steps": 666, "loss": 0.4982, "lr": 4e-05, "epoch": 0.25603593486805165, "percentage": 8.56, "elapsed_time": "2:37:18", "remaining_time": "1 day, 4:00:45"}
+{"current_steps": 58, "total_steps": 666, "loss": 0.4893, "lr": 4e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:40:05", "remaining_time": "1 day, 3:58:15"}
+{"current_steps": 59, "total_steps": 666, "loss": 0.5043, "lr": 4e-05, "epoch": 0.26501965188096577, "percentage": 8.86, "elapsed_time": "2:42:54", "remaining_time": "1 day, 3:56:01"}
+{"current_steps": 60, "total_steps": 666, "loss": 0.4973, "lr": 4e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:45:38", "remaining_time": "1 day, 3:53:01"}
+{"current_steps": 61, "total_steps": 666, "loss": 0.4885, "lr": 4e-05, "epoch": 0.27400336889387983, "percentage": 9.16, "elapsed_time": "2:48:19", "remaining_time": "1 day, 3:49:26"}
+{"current_steps": 62, "total_steps": 666, "loss": 0.4952, "lr": 4e-05, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:50:57", "remaining_time": "1 day, 3:45:23"}
+{"current_steps": 63, "total_steps": 666, "loss": 0.5057, "lr": 4e-05, "epoch": 0.28298708590679394, "percentage": 9.46, "elapsed_time": "2:53:43", "remaining_time": "1 day, 3:42:46"}
+{"current_steps": 64, "total_steps": 666, "loss": 0.4914, "lr": 4e-05, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "2:56:21", "remaining_time": "1 day, 3:38:56"}
+{"current_steps": 65, "total_steps": 666, "loss": 0.4952, "lr": 4e-05, "epoch": 0.291970802919708, "percentage": 9.76, "elapsed_time": "2:58:59", "remaining_time": "1 day, 3:35:01"}
+{"current_steps": 66, "total_steps": 666, "loss": 0.4822, "lr": 4e-05, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:01:48", "remaining_time": "1 day, 3:32:49"}
+{"current_steps": 67, "total_steps": 666, "loss": 0.4953, "lr": 4e-05, "epoch": 0.3009545199326221, "percentage": 10.06, "elapsed_time": "3:04:38", "remaining_time": "1 day, 3:30:49"}
+{"current_steps": 68, "total_steps": 666, "loss": 0.4823, "lr": 4e-05, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:07:26", "remaining_time": "1 day, 3:28:25"}
+{"current_steps": 69, "total_steps": 666, "loss": 0.491, "lr": 4e-05, "epoch": 0.30993823694553624, "percentage": 10.36, "elapsed_time": "3:10:11", "remaining_time": "1 day, 3:25:34"}
+{"current_steps": 70, "total_steps": 666, "loss": 0.486, "lr": 4e-05, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:12:56", "remaining_time": "1 day, 3:22:49"}
+{"current_steps": 71, "total_steps": 666, "loss": 0.486, "lr": 4e-05, "epoch": 0.3189219539584503, "percentage": 10.66, "elapsed_time": "3:15:45", "remaining_time": "1 day, 3:20:34"}
+{"current_steps": 72, "total_steps": 666, "loss": 0.5018, "lr": 4e-05, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:18:29", "remaining_time": "1 day, 3:17:29"}
+{"current_steps": 73, "total_steps": 666, "loss": 0.4878, "lr": 4e-05, "epoch": 0.3279056709713644, "percentage": 10.96, "elapsed_time": "3:21:21", "remaining_time": "1 day, 3:15:41"}
+{"current_steps": 74, "total_steps": 666, "loss": 0.4915, "lr": 4e-05, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:24:07", "remaining_time": "1 day, 3:13:02"}
+{"current_steps": 75, "total_steps": 666, "loss": 0.494, "lr": 4e-05, "epoch": 0.3368893879842785, "percentage": 11.26, "elapsed_time": "3:26:52", "remaining_time": "1 day, 3:10:13"}
+{"current_steps": 76, "total_steps": 666, "loss": 0.4833, "lr": 4e-05, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:29:25", "remaining_time": "1 day, 3:05:45"}
+{"current_steps": 77, "total_steps": 666, "loss": 0.4962, "lr": 4e-05, "epoch": 0.3458731049971926, "percentage": 11.56, "elapsed_time": "3:32:11", "remaining_time": "1 day, 3:03:07"}
+{"current_steps": 78, "total_steps": 666, "loss": 0.4783, "lr": 4e-05, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:35:01", "remaining_time": "1 day, 3:00:56"}
+{"current_steps": 79, "total_steps": 666, "loss": 0.49, "lr": 4e-05, "epoch": 0.35485682201010665, "percentage": 11.86, "elapsed_time": "3:37:45", "remaining_time": "1 day, 2:57:59"}
+{"current_steps": 80, "total_steps": 666, "loss": 0.4916, "lr": 4e-05, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:40:29", "remaining_time": "1 day, 2:55:06"}
+{"current_steps": 81, "total_steps": 666, "loss": 0.4921, "lr": 4e-05, "epoch": 0.36384053902302077, "percentage": 12.16, "elapsed_time": "3:43:07", "remaining_time": "1 day, 2:51:28"}
+{"current_steps": 82, "total_steps": 666, "loss": 0.4951, "lr": 4e-05, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:45:46", "remaining_time": "1 day, 2:47:59"}
+{"current_steps": 83, "total_steps": 666, "loss": 0.4869, "lr": 4e-05, "epoch": 0.3728242560359349, "percentage": 12.46, "elapsed_time": "3:48:37", "remaining_time": "1 day, 2:45:55"}
+{"current_steps": 84, "total_steps": 666, "loss": 0.4862, "lr": 4e-05, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "3:51:22", "remaining_time": "1 day, 2:43:05"}
+{"current_steps": 85, "total_steps": 666, "loss": 0.4899, "lr": 4e-05, "epoch": 0.38180797304884895, "percentage": 12.76, "elapsed_time": "3:54:01", "remaining_time": "1 day, 2:39:40"}
+{"current_steps": 86, "total_steps": 666, "loss": 0.4729, "lr": 4e-05, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "3:56:36", "remaining_time": "1 day, 2:35:41"}
+{"current_steps": 87, "total_steps": 666, "loss": 0.4723, "lr": 4e-05, "epoch": 0.39079169006176306, "percentage": 13.06, "elapsed_time": "3:59:23", "remaining_time": "1 day, 2:33:13"}
+{"current_steps": 88, "total_steps": 666, "loss": 0.4773, "lr": 4e-05, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:02:16", "remaining_time": "1 day, 2:31:18"}
+{"current_steps": 89, "total_steps": 666, "loss": 0.4864, "lr": 4e-05, "epoch": 0.3997754070746771, "percentage": 13.36, "elapsed_time": "4:05:05", "remaining_time": "1 day, 2:28:58"}
+{"current_steps": 90, "total_steps": 666, "loss": 0.484, "lr": 4e-05, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:07:55", "remaining_time": "1 day, 2:26:44"}
+{"current_steps": 91, "total_steps": 666, "loss": 0.4845, "lr": 4e-05, "epoch": 0.40875912408759124, "percentage": 13.66, "elapsed_time": "4:10:36", "remaining_time": "1 day, 2:23:31"}
+{"current_steps": 92, "total_steps": 666, "loss": 0.4762, "lr": 4e-05, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:13:20", "remaining_time": "1 day, 2:20:37"}
+{"current_steps": 93, "total_steps": 666, "loss": 0.4785, "lr": 4e-05, "epoch": 0.41774284110050536, "percentage": 13.96, "elapsed_time": "4:16:02", "remaining_time": "1 day, 2:17:32"}
+{"current_steps": 94, "total_steps": 666, "loss": 0.4858, "lr": 4e-05, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:18:55", "remaining_time": "1 day, 2:15:36"}
+{"current_steps": 95, "total_steps": 666, "loss": 0.4853, "lr": 4e-05, "epoch": 0.4267265581134194, "percentage": 14.26, "elapsed_time": "4:21:40", "remaining_time": "1 day, 2:12:49"}
+{"current_steps": 96, "total_steps": 666, "loss": 0.4675, "lr": 4e-05, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:24:18", "remaining_time": "1 day, 2:09:19"}
+{"current_steps": 97, "total_steps": 666, "loss": 0.487, "lr": 4e-05, "epoch": 0.43571027512633353, "percentage": 14.56, "elapsed_time": "4:27:04", "remaining_time": "1 day, 2:06:38"}
+{"current_steps": 98, "total_steps": 666, "loss": 0.481, "lr": 4e-05, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:29:38", "remaining_time": "1 day, 2:02:50"}
+{"current_steps": 99, "total_steps": 666, "loss": 0.4602, "lr": 4e-05, "epoch": 0.4446939921392476, "percentage": 14.86, "elapsed_time": "4:32:26", "remaining_time": "1 day, 2:00:22"}
+{"current_steps": 100, "total_steps": 666, "loss": 0.471, "lr": 4e-05, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:35:17", "remaining_time": "1 day, 1:58:06"}
+{"current_steps": 101, "total_steps": 666, "loss": 0.4832, "lr": 4e-05, "epoch": 0.4536777091521617, "percentage": 15.17, "elapsed_time": "4:38:04", "remaining_time": "1 day, 1:55:35"}
+{"current_steps": 102, "total_steps": 666, "loss": 0.4793, "lr": 4e-05, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:40:47", "remaining_time": "1 day, 1:52:38"}
+{"current_steps": 103, "total_steps": 666, "loss": 0.4797, "lr": 4e-05, "epoch": 0.4626614261650758, "percentage": 15.47, "elapsed_time": "4:43:28", "remaining_time": "1 day, 1:49:30"}
+{"current_steps": 104, "total_steps": 666, "loss": 0.4699, "lr": 4e-05, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "4:46:10", "remaining_time": "1 day, 1:46:26"}
+{"current_steps": 105, "total_steps": 666, "loss": 0.4672, "lr": 4e-05, "epoch": 0.4716451431779899, "percentage": 15.77, "elapsed_time": "4:48:57", "remaining_time": "1 day, 1:43:49"}
+{"current_steps": 106, "total_steps": 666, "loss": 0.4735, "lr": 4e-05, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "4:51:43", "remaining_time": "1 day, 1:41:13"}
+{"current_steps": 107, "total_steps": 666, "loss": 0.4723, "lr": 4e-05, "epoch": 0.480628860190904, "percentage": 16.07, "elapsed_time": "4:54:15", "remaining_time": "1 day, 1:37:16"}
+{"current_steps": 108, "total_steps": 666, "loss": 0.4832, "lr": 4e-05, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "4:57:03", "remaining_time": "1 day, 1:34:49"}
+{"current_steps": 109, "total_steps": 666, "loss": 0.483, "lr": 4e-05, "epoch": 0.48961257720381807, "percentage": 16.37, "elapsed_time": "4:59:45", "remaining_time": "1 day, 1:31:46"}
+{"current_steps": 110, "total_steps": 666, "loss": 0.4769, "lr": 4e-05, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:02:30", "remaining_time": "1 day, 1:29:00"}
+{"current_steps": 111, "total_steps": 666, "loss": 0.4783, "lr": 4e-05, "epoch": 0.4985962942167322, "percentage": 16.67, "elapsed_time": "5:05:13", "remaining_time": "1 day, 1:26:09"}
+{"current_steps": 112, "total_steps": 666, "loss": 0.4686, "lr": 4e-05, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:07:56", "remaining_time": "1 day, 1:23:12"}
+{"current_steps": 113, "total_steps": 666, "loss": 0.4848, "lr": 4e-05, "epoch": 0.5075800112296462, "percentage": 16.97, "elapsed_time": "5:10:46", "remaining_time": "1 day, 1:20:54"}
+{"current_steps": 114, "total_steps": 666, "loss": 0.479, "lr": 4e-05, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:13:36", "remaining_time": "1 day, 1:18:33"}
+{"current_steps": 115, "total_steps": 666, "loss": 0.4662, "lr": 4e-05, "epoch": 0.5165637282425604, "percentage": 17.27, "elapsed_time": "5:16:09", "remaining_time": "1 day, 1:14:49"}
+{"current_steps": 116, "total_steps": 666, "loss": 0.4861, "lr": 4e-05, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:18:54", "remaining_time": "1 day, 1:12:02"}
+{"current_steps": 117, "total_steps": 666, "loss": 0.4718, "lr": 4e-05, "epoch": 0.5255474452554745, "percentage": 17.57, "elapsed_time": "5:21:37", "remaining_time": "1 day, 1:09:11"}
+{"current_steps": 118, "total_steps": 666, "loss": 0.4783, "lr": 4e-05, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:24:24", "remaining_time": "1 day, 1:06:33"}
+{"current_steps": 119, "total_steps": 666, "loss": 0.471, "lr": 4e-05, "epoch": 0.5345311622683886, "percentage": 17.87, "elapsed_time": "5:27:00", "remaining_time": "1 day, 1:03:06"}
+{"current_steps": 120, "total_steps": 666, "loss": 0.4718, "lr": 4e-05, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:29:33", "remaining_time": "1 day, 0:59:29"}
+{"current_steps": 121, "total_steps": 666, "loss": 0.4796, "lr": 4e-05, "epoch": 0.5435148792813026, "percentage": 18.17, "elapsed_time": "5:32:24", "remaining_time": "1 day, 0:57:10"}
+{"current_steps": 122, "total_steps": 666, "loss": 0.4715, "lr": 4e-05, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:35:08", "remaining_time": "1 day, 0:54:23"}
+{"current_steps": 123, "total_steps": 666, "loss": 0.4554, "lr": 4e-05, "epoch": 0.5524985962942167, "percentage": 18.47, "elapsed_time": "5:38:00", "remaining_time": "1 day, 0:52:10"}
+{"current_steps": 124, "total_steps": 666, "loss": 0.4827, "lr": 4e-05, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:40:37", "remaining_time": "1 day, 0:48:52"}
+{"current_steps": 125, "total_steps": 666, "loss": 0.4836, "lr": 4e-05, "epoch": 0.5614823133071308, "percentage": 18.77, "elapsed_time": "5:43:27", "remaining_time": "1 day, 0:46:29"}
+{"current_steps": 126, "total_steps": 666, "loss": 0.4622, "lr": 4e-05, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "5:46:02", "remaining_time": "1 day, 0:43:03"}
+{"current_steps": 127, "total_steps": 666, "loss": 0.4639, "lr": 4e-05, "epoch": 0.570466030320045, "percentage": 19.07, "elapsed_time": "5:48:51", "remaining_time": "1 day, 0:40:35"}
+{"current_steps": 128, "total_steps": 666, "loss": 0.4683, "lr": 4e-05, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "5:51:32", "remaining_time": "1 day, 0:37:34"}
+{"current_steps": 129, "total_steps": 666, "loss": 0.4739, "lr": 4e-05, "epoch": 0.5794497473329591, "percentage": 19.37, "elapsed_time": "5:54:18", "remaining_time": "1 day, 0:34:55"}
+{"current_steps": 130, "total_steps": 666, "loss": 0.4594, "lr": 4e-05, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "5:56:57", "remaining_time": "1 day, 0:31:46"}
+{"current_steps": 131, "total_steps": 666, "loss": 0.4742, "lr": 4e-05, "epoch": 0.5884334643458731, "percentage": 19.67, "elapsed_time": "5:59:49", "remaining_time": "1 day, 0:29:30"}
+{"current_steps": 132, "total_steps": 666, "loss": 0.4576, "lr": 4e-05, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:02:31", "remaining_time": "1 day, 0:26:34"}
+{"current_steps": 133, "total_steps": 666, "loss": 0.4636, "lr": 4e-05, "epoch": 0.5974171813587872, "percentage": 19.97, "elapsed_time": "6:05:15", "remaining_time": "1 day, 0:23:45"}
+{"current_steps": 134, "total_steps": 666, "loss": 0.4701, "lr": 4e-05, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:07:48", "remaining_time": "1 day, 0:20:14"}
+{"current_steps": 135, "total_steps": 666, "loss": 0.4705, "lr": 4e-05, "epoch": 0.6064008983717013, "percentage": 20.27, "elapsed_time": "6:10:37", "remaining_time": "1 day, 0:17:49"}
+{"current_steps": 136, "total_steps": 666, "loss": 0.4742, "lr": 4e-05, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:13:32", "remaining_time": "1 day, 0:15:41"}
+{"current_steps": 137, "total_steps": 666, "loss": 0.4689, "lr": 4e-05, "epoch": 0.6153846153846154, "percentage": 20.57, "elapsed_time": "6:16:16", "remaining_time": "1 day, 0:12:56"}
+{"current_steps": 138, "total_steps": 666, "loss": 0.4665, "lr": 4e-05, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:18:58", "remaining_time": "1 day, 0:09:59"}
+{"current_steps": 139, "total_steps": 666, "loss": 0.4741, "lr": 4e-05, "epoch": 0.6243683323975294, "percentage": 20.87, "elapsed_time": "6:21:46", "remaining_time": "1 day, 0:07:26"}
+{"current_steps": 140, "total_steps": 666, "loss": 0.4633, "lr": 4e-05, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:24:34", "remaining_time": "1 day, 0:04:54"}
+{"current_steps": 141, "total_steps": 666, "loss": 0.4738, "lr": 4e-05, "epoch": 0.6333520494104435, "percentage": 21.17, "elapsed_time": "6:27:29", "remaining_time": "1 day, 0:02:49"}
+{"current_steps": 142, "total_steps": 666, "loss": 0.4665, "lr": 4e-05, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:30:09", "remaining_time": "23:59:45"}
+{"current_steps": 143, "total_steps": 666, "loss": 0.4581, "lr": 4e-05, "epoch": 0.6423357664233577, "percentage": 21.47, "elapsed_time": "6:32:56", "remaining_time": "23:57:05"}
+{"current_steps": 144, "total_steps": 666, "loss": 0.4586, "lr": 4e-05, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:35:25", "remaining_time": "23:53:23"}
+{"current_steps": 145, "total_steps": 666, "loss": 0.4758, "lr": 4e-05, "epoch": 0.6513194834362718, "percentage": 21.77, "elapsed_time": "6:38:15", "remaining_time": "23:50:58"}
+{"current_steps": 146, "total_steps": 666, "loss": 0.47, "lr": 4e-05, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "6:40:51", "remaining_time": "23:47:41"}
+{"current_steps": 147, "total_steps": 666, "loss": 0.467, "lr": 4e-05, "epoch": 0.6603032004491859, "percentage": 22.07, "elapsed_time": "6:43:19", "remaining_time": "23:43:57"}
+{"current_steps": 148, "total_steps": 666, "loss": 0.4667, "lr": 4e-05, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "6:46:02", "remaining_time": "23:41:08"}
+{"current_steps": 149, "total_steps": 666, "loss": 0.4699, "lr": 4e-05, "epoch": 0.6692869174620999, "percentage": 22.37, "elapsed_time": "6:48:44", "remaining_time": "23:38:16"}
+{"current_steps": 150, "total_steps": 666, "loss": 0.4615, "lr": 4e-05, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "6:51:33", "remaining_time": "23:35:44"}
+{"current_steps": 151, "total_steps": 666, "loss": 0.4774, "lr": 4e-05, "epoch": 0.678270634475014, "percentage": 22.67, "elapsed_time": "6:54:23", "remaining_time": "23:33:18"}
+{"current_steps": 152, "total_steps": 666, "loss": 0.4844, "lr": 4e-05, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "6:57:06", "remaining_time": "23:30:30"}
+{"current_steps": 153, "total_steps": 666, "loss": 0.47, "lr": 4e-05, "epoch": 0.6872543514879281, "percentage": 22.97, "elapsed_time": "6:59:55", "remaining_time": "23:27:59"}
+{"current_steps": 154, "total_steps": 666, "loss": 0.4642, "lr": 4e-05, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:02:33", "remaining_time": "23:24:53"}
+{"current_steps": 155, "total_steps": 666, "loss": 0.4689, "lr": 4e-05, "epoch": 0.6962380685008422, "percentage": 23.27, "elapsed_time": "7:05:20", "remaining_time": "23:22:15"}
+{"current_steps": 156, "total_steps": 666, "loss": 0.4662, "lr": 4e-05, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:08:11", "remaining_time": "23:19:50"}
+{"current_steps": 157, "total_steps": 666, "loss": 0.459, "lr": 4e-05, "epoch": 0.7052217855137564, "percentage": 23.57, "elapsed_time": "7:10:48", "remaining_time": "23:16:42"}
+{"current_steps": 158, "total_steps": 666, "loss": 0.4649, "lr": 4e-05, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:13:29", "remaining_time": "23:13:43"}
+{"current_steps": 159, "total_steps": 666, "loss": 0.4776, "lr": 4e-05, "epoch": 0.7142055025266704, "percentage": 23.87, "elapsed_time": "7:16:16", "remaining_time": "23:11:08"}
+{"current_steps": 160, "total_steps": 666, "loss": 0.4717, "lr": 4e-05, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:18:55", "remaining_time": "23:08:07"}
+{"current_steps": 161, "total_steps": 666, "loss": 0.4604, "lr": 4e-05, "epoch": 0.7231892195395845, "percentage": 24.17, "elapsed_time": "7:21:40", "remaining_time": "23:05:24"}
+{"current_steps": 162, "total_steps": 666, "loss": 0.4627, "lr": 4e-05, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:24:29", "remaining_time": "23:02:51"}
+{"current_steps": 163, "total_steps": 666, "loss": 0.4465, "lr": 4e-05, "epoch": 0.7321729365524986, "percentage": 24.47, "elapsed_time": "7:27:17", "remaining_time": "23:00:18"}
+{"current_steps": 164, "total_steps": 666, "loss": 0.4522, "lr": 4e-05, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:30:10", "remaining_time": "22:57:59"}
+{"current_steps": 165, "total_steps": 666, "loss": 0.4684, "lr": 4e-05, "epoch": 0.7411566535654127, "percentage": 24.77, "elapsed_time": "7:33:02", "remaining_time": "22:55:35"}
+{"current_steps": 166, "total_steps": 666, "loss": 0.4689, "lr": 4e-05, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:35:47", "remaining_time": "22:52:51"}
+{"current_steps": 167, "total_steps": 666, "loss": 0.4741, "lr": 4e-05, "epoch": 0.7501403705783268, "percentage": 25.08, "elapsed_time": "7:38:32", "remaining_time": "22:50:07"}
+{"current_steps": 168, "total_steps": 666, "loss": 0.4571, "lr": 4e-05, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "7:41:14", "remaining_time": "22:47:14"}
+{"current_steps": 169, "total_steps": 666, "loss": 0.4625, "lr": 4e-05, "epoch": 0.7591240875912408, "percentage": 25.38, "elapsed_time": "7:44:07", "remaining_time": "22:44:53"}
+{"current_steps": 170, "total_steps": 666, "loss": 0.4613, "lr": 4e-05, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "7:46:51", "remaining_time": "22:42:06"}
+{"current_steps": 171, "total_steps": 666, "loss": 0.4689, "lr": 4e-05, "epoch": 0.768107804604155, "percentage": 25.68, "elapsed_time": "7:49:38", "remaining_time": "22:39:30"}
+{"current_steps": 172, "total_steps": 666, "loss": 0.4605, "lr": 4e-05, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "7:52:28", "remaining_time": "22:36:59"}
+{"current_steps": 173, "total_steps": 666, "loss": 0.4512, "lr": 4e-05, "epoch": 0.7770915216170691, "percentage": 25.98, "elapsed_time": "7:55:14", "remaining_time": "22:34:18"}
+{"current_steps": 174, "total_steps": 666, "loss": 0.4659, "lr": 4e-05, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "7:57:56", "remaining_time": "22:31:26"}
+{"current_steps": 175, "total_steps": 666, "loss": 0.4686, "lr": 4e-05, "epoch": 0.7860752386299832, "percentage": 26.28, "elapsed_time": "8:00:42", "remaining_time": "22:28:44"}
+{"current_steps": 176, "total_steps": 666, "loss": 0.4671, "lr": 4e-05, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:03:31", "remaining_time": "22:26:10"}
+{"current_steps": 177, "total_steps": 666, "loss": 0.448, "lr": 4e-05, "epoch": 0.7950589556428973, "percentage": 26.58, "elapsed_time": "8:06:23", "remaining_time": "22:23:45"}
+{"current_steps": 178, "total_steps": 666, "loss": 0.4562, "lr": 4e-05, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:09:10", "remaining_time": "22:21:05"}
+{"current_steps": 179, "total_steps": 666, "loss": 0.4601, "lr": 4e-05, "epoch": 0.8040426726558113, "percentage": 26.88, "elapsed_time": "8:12:05", "remaining_time": "22:18:50"}
+{"current_steps": 180, "total_steps": 666, "loss": 0.4652, "lr": 4e-05, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:14:57", "remaining_time": "22:16:22"}
+{"current_steps": 181, "total_steps": 666, "loss": 0.4733, "lr": 4e-05, "epoch": 0.8130263896687254, "percentage": 27.18, "elapsed_time": "8:17:45", "remaining_time": "22:13:47"}
+{"current_steps": 182, "total_steps": 666, "loss": 0.4559, "lr": 4e-05, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:20:34", "remaining_time": "22:11:12"}
+{"current_steps": 183, "total_steps": 666, "loss": 0.4618, "lr": 4e-05, "epoch": 0.8220101066816395, "percentage": 27.48, "elapsed_time": "8:23:13", "remaining_time": "22:08:10"}
+{"current_steps": 184, "total_steps": 666, "loss": 0.454, "lr": 4e-05, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:25:58", "remaining_time": "22:05:25"}
+{"current_steps": 185, "total_steps": 666, "loss": 0.4535, "lr": 4e-05, "epoch": 0.8309938236945537, "percentage": 27.78, "elapsed_time": "8:28:40", "remaining_time": "22:02:32"}
+{"current_steps": 186, "total_steps": 666, "loss": 0.4587, "lr": 4e-05, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:31:22", "remaining_time": "21:59:40"}
+{"current_steps": 187, "total_steps": 666, "loss": 0.4614, "lr": 4e-05, "epoch": 0.8399775407074677, "percentage": 28.08, "elapsed_time": "8:34:11", "remaining_time": "21:57:06"}
+{"current_steps": 188, "total_steps": 666, "loss": 0.453, "lr": 4e-05, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "8:36:54", "remaining_time": "21:54:16"}
+{"current_steps": 189, "total_steps": 666, "loss": 0.454, "lr": 4e-05, "epoch": 0.8489612577203818, "percentage": 28.38, "elapsed_time": "8:39:37", "remaining_time": "21:51:27"}
+{"current_steps": 190, "total_steps": 666, "loss": 0.4685, "lr": 4e-05, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "8:42:23", "remaining_time": "21:48:43"}
+{"current_steps": 191, "total_steps": 666, "loss": 0.4689, "lr": 4e-05, "epoch": 0.8579449747332959, "percentage": 28.68, "elapsed_time": "8:45:08", "remaining_time": "21:45:59"}
+{"current_steps": 192, "total_steps": 666, "loss": 0.4655, "lr": 4e-05, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "8:47:59", "remaining_time": "21:43:28"}
+{"current_steps": 193, "total_steps": 666, "loss": 0.4615, "lr": 4e-05, "epoch": 0.86692869174621, "percentage": 28.98, "elapsed_time": "8:50:46", "remaining_time": "21:40:47"}
+{"current_steps": 194, "total_steps": 666, "loss": 0.4729, "lr": 4e-05, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "8:53:37", "remaining_time": "21:38:18"}
+{"current_steps": 195, "total_steps": 666, "loss": 0.4486, "lr": 4e-05, "epoch": 0.8759124087591241, "percentage": 29.28, "elapsed_time": "8:56:28", "remaining_time": "21:35:47"}
+{"current_steps": 196, "total_steps": 666, "loss": 0.4517, "lr": 4e-05, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "8:59:26", "remaining_time": "21:33:34"}
+{"current_steps": 197, "total_steps": 666, "loss": 0.4595, "lr": 4e-05, "epoch": 0.8848961257720381, "percentage": 29.58, "elapsed_time": "9:02:06", "remaining_time": "21:30:35"}
+{"current_steps": 198, "total_steps": 666, "loss": 0.4676, "lr": 4e-05, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:04:48", "remaining_time": "21:27:43"}
+{"current_steps": 199, "total_steps": 666, "loss": 0.4579, "lr": 4e-05, "epoch": 0.8938798427849522, "percentage": 29.88, "elapsed_time": "9:07:39", "remaining_time": "21:25:12"}
+{"current_steps": 200, "total_steps": 666, "loss": 0.445, "lr": 4e-05, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:10:30", "remaining_time": "21:22:40"}
+{"current_steps": 201, "total_steps": 666, "loss": 0.4574, "lr": 4e-05, "epoch": 0.9028635597978664, "percentage": 30.18, "elapsed_time": "9:13:13", "remaining_time": "21:19:50"}
+{"current_steps": 202, "total_steps": 666, "loss": 0.4734, "lr": 4e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:15:59", "remaining_time": "21:17:08"}
+{"current_steps": 203, "total_steps": 666, "loss": 0.4523, "lr": 4e-05, "epoch": 0.9118472768107805, "percentage": 30.48, "elapsed_time": "9:18:46", "remaining_time": "21:14:26"}
+{"current_steps": 204, "total_steps": 666, "loss": 0.4521, "lr": 4e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:21:33", "remaining_time": "21:11:44"}
+{"current_steps": 205, "total_steps": 666, "loss": 0.462, "lr": 4e-05, "epoch": 0.9208309938236946, "percentage": 30.78, "elapsed_time": "9:24:14", "remaining_time": "21:08:51"}
+{"current_steps": 206, "total_steps": 666, "loss": 0.4673, "lr": 4e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:26:54", "remaining_time": "21:05:54"}
+{"current_steps": 207, "total_steps": 666, "loss": 0.4554, "lr": 4e-05, "epoch": 0.9298147108366086, "percentage": 31.08, "elapsed_time": "9:29:39", "remaining_time": "21:03:09"}
+{"current_steps": 208, "total_steps": 666, "loss": 0.4528, "lr": 4e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "9:32:18", "remaining_time": "21:00:10"}
+{"current_steps": 209, "total_steps": 666, "loss": 0.4632, "lr": 4e-05, "epoch": 0.9387984278495227, "percentage": 31.38, "elapsed_time": "9:35:07", "remaining_time": "20:57:34"}
+{"current_steps": 210, "total_steps": 666, "loss": 0.4664, "lr": 4e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "9:37:53", "remaining_time": "20:54:51"}
+{"current_steps": 211, "total_steps": 666, "loss": 0.4565, "lr": 4e-05, "epoch": 0.9477821448624368, "percentage": 31.68, "elapsed_time": "9:40:43", "remaining_time": "20:52:16"}
+{"current_steps": 212, "total_steps": 666, "loss": 0.4501, "lr": 4e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "9:43:30", "remaining_time": "20:49:35"}
+{"current_steps": 213, "total_steps": 666, "loss": 0.4498, "lr": 4e-05, "epoch": 0.956765861875351, "percentage": 31.98, "elapsed_time": "9:46:06", "remaining_time": "20:46:30"}
+{"current_steps": 214, "total_steps": 666, "loss": 0.4609, "lr": 4e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "9:48:44", "remaining_time": "20:43:31"}
+{"current_steps": 215, "total_steps": 666, "loss": 0.4392, "lr": 4e-05, "epoch": 0.9657495788882651, "percentage": 32.28, "elapsed_time": "9:51:26", "remaining_time": "20:40:38"}
+{"current_steps": 216, "total_steps": 666, "loss": 0.4559, "lr": 4e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "9:54:00", "remaining_time": "20:37:31"}
+{"current_steps": 217, "total_steps": 666, "loss": 0.4513, "lr": 4e-05, "epoch": 0.9747332959011791, "percentage": 32.58, "elapsed_time": "9:56:36", "remaining_time": "20:34:27"}
+{"current_steps": 218, "total_steps": 666, "loss": 0.4571, "lr": 4e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "9:59:28", "remaining_time": "20:31:56"}
+{"current_steps": 219, "total_steps": 666, "loss": 0.4561, "lr": 4e-05, "epoch": 0.9837170129140932, "percentage": 32.88, "elapsed_time": "10:02:08", "remaining_time": "20:29:01"}
+{"current_steps": 220, "total_steps": 666, "loss": 0.4699, "lr": 4e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:04:49", "remaining_time": "20:26:08"}
+{"current_steps": 221, "total_steps": 666, "loss": 0.4571, "lr": 4e-05, "epoch": 0.9927007299270073, "percentage": 33.18, "elapsed_time": "10:07:32", "remaining_time": "20:23:20"}
+{"current_steps": 222, "total_steps": 666, "loss": 0.4555, "lr": 4e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:10:19", "remaining_time": "20:20:38"}
+{"current_steps": 223, "total_steps": 666, "loss": 0.73, "lr": 4e-05, "epoch": 1.0030881527231892, "percentage": 33.48, "elapsed_time": "10:13:49", "remaining_time": "20:19:23"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf707fd12d6de40675d251aa4a5dfd46112aced84c48cd983988848baac7de99
+size 7224