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:fc56a2b260d38836ff8e067a76e704083949cc3caea9852edde0bcdb9236cb37
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d2af545a50f8d90703aa2473cb920faa92364009c6929e2aa513a9b113acc60
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f38568f5cf9941ee8073b342cb4436c3167a88ea41e31ea6cf9a97e882e1c68
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e30a23382d1c3f3490cc1e1f088c2f2971d1287a074a7d4c74d0aa42218ce72
+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": 8.443065671641791e-07, "epoch": 0.004491858506457047, "percentage": 0.15, "elapsed_time": "0:03:00", "remaining_time": "1 day, 9:25:37"}
+{"current_steps": 2, "total_steps": 666, "loss": 0.8731, "lr": 1.6886131343283583e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:05:51", "remaining_time": "1 day, 8:23:14"}
+{"current_steps": 3, "total_steps": 666, "loss": 0.8539, "lr": 2.532919701492537e-06, "epoch": 0.01347557551937114, "percentage": 0.45, "elapsed_time": "0:08:50", "remaining_time": "1 day, 8:35:50"}
+{"current_steps": 4, "total_steps": 666, "loss": 0.8525, "lr": 3.3772262686567165e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:11:43", "remaining_time": "1 day, 8:20:37"}
+{"current_steps": 5, "total_steps": 666, "loss": 0.8241, "lr": 4.221532835820895e-06, "epoch": 0.022459292532285232, "percentage": 0.75, "elapsed_time": "0:14:22", "remaining_time": "1 day, 7:40:26"}
+{"current_steps": 6, "total_steps": 666, "loss": 0.7623, "lr": 5.065839402985074e-06, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:17:12", "remaining_time": "1 day, 7:32:27"}
+{"current_steps": 7, "total_steps": 666, "loss": 0.7558, "lr": 5.910145970149254e-06, "epoch": 0.031443009545199324, "percentage": 1.05, "elapsed_time": "0:20:05", "remaining_time": "1 day, 7:31:24"}
+{"current_steps": 8, "total_steps": 666, "loss": 0.7472, "lr": 6.754452537313433e-06, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:22:53", "remaining_time": "1 day, 7:22:40"}
+{"current_steps": 9, "total_steps": 666, "loss": 0.7507, "lr": 7.598759104477612e-06, "epoch": 0.04042672655811342, "percentage": 1.35, "elapsed_time": "0:25:40", "remaining_time": "1 day, 7:14:41"}
+{"current_steps": 10, "total_steps": 666, "loss": 0.7386, "lr": 8.44306567164179e-06, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:28:31", "remaining_time": "1 day, 7:11:12"}
+{"current_steps": 11, "total_steps": 666, "loss": 0.7097, "lr": 9.287372238805971e-06, "epoch": 0.049410443571027515, "percentage": 1.65, "elapsed_time": "0:31:29", "remaining_time": "1 day, 7:15:24"}
+{"current_steps": 12, "total_steps": 666, "loss": 0.6956, "lr": 1.0131678805970148e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:34:05", "remaining_time": "1 day, 6:57:55"}
+{"current_steps": 13, "total_steps": 666, "loss": 0.6712, "lr": 1.0975985373134329e-05, "epoch": 0.058394160583941604, "percentage": 1.95, "elapsed_time": "0:36:59", "remaining_time": "1 day, 6:58:12"}
+{"current_steps": 14, "total_steps": 666, "loss": 0.6589, "lr": 1.1820291940298508e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:40:04", "remaining_time": "1 day, 7:06:32"}
+{"current_steps": 15, "total_steps": 666, "loss": 0.6446, "lr": 1.2664598507462687e-05, "epoch": 0.06737787759685569, "percentage": 2.25, "elapsed_time": "0:42:55", "remaining_time": "1 day, 7:03:03"}
+{"current_steps": 16, "total_steps": 666, "loss": 0.6383, "lr": 1.3508905074626866e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:45:38", "remaining_time": "1 day, 6:54:00"}
+{"current_steps": 17, "total_steps": 666, "loss": 0.6404, "lr": 1.4353211641791045e-05, "epoch": 0.0763615946097698, "percentage": 2.55, "elapsed_time": "0:48:25", "remaining_time": "1 day, 6:48:46"}
+{"current_steps": 18, "total_steps": 666, "loss": 0.6213, "lr": 1.5197518208955224e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:51:18", "remaining_time": "1 day, 6:47:14"}
+{"current_steps": 19, "total_steps": 666, "loss": 0.6102, "lr": 1.60418247761194e-05, "epoch": 0.08534531162268388, "percentage": 2.85, "elapsed_time": "0:53:57", "remaining_time": "1 day, 6:37:11"}
+{"current_steps": 20, "total_steps": 666, "loss": 0.6132, "lr": 1.688613134328358e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:56:51", "remaining_time": "1 day, 6:36:35"}
+{"current_steps": 21, "total_steps": 666, "loss": 0.5945, "lr": 1.7730437910447763e-05, "epoch": 0.09432902863559797, "percentage": 3.15, "elapsed_time": "0:59:39", "remaining_time": "1 day, 6:32:24"}
+{"current_steps": 22, "total_steps": 666, "loss": 0.5901, "lr": 1.8574744477611942e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:02:33", "remaining_time": "1 day, 6:31:15"}
+{"current_steps": 23, "total_steps": 666, "loss": 0.5878, "lr": 1.941905104477612e-05, "epoch": 0.10331274564851207, "percentage": 3.45, "elapsed_time": "1:05:40", "remaining_time": "1 day, 6:35:59"}
+{"current_steps": 24, "total_steps": 666, "loss": 0.5775, "lr": 2.0263357611940297e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:08:32", "remaining_time": "1 day, 6:33:26"}
+{"current_steps": 25, "total_steps": 666, "loss": 0.578, "lr": 2.110766417910448e-05, "epoch": 0.11229646266142616, "percentage": 3.75, "elapsed_time": "1:11:23", "remaining_time": "1 day, 6:30:41"}
+{"current_steps": 26, "total_steps": 666, "loss": 0.557, "lr": 2.1951970746268658e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:13:58", "remaining_time": "1 day, 6:20:44"}
+{"current_steps": 27, "total_steps": 666, "loss": 0.5658, "lr": 2.2796277313432837e-05, "epoch": 0.12128017967434025, "percentage": 4.05, "elapsed_time": "1:16:42", "remaining_time": "1 day, 6:15:28"}
+{"current_steps": 28, "total_steps": 666, "loss": 0.5643, "lr": 2.3640583880597016e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:19:32", "remaining_time": "1 day, 6:12:33"}
+{"current_steps": 29, "total_steps": 666, "loss": 0.5617, "lr": 2.4484890447761192e-05, "epoch": 0.13026389668725435, "percentage": 4.35, "elapsed_time": "1:22:21", "remaining_time": "1 day, 6:09:05"}
+{"current_steps": 30, "total_steps": 666, "loss": 0.561, "lr": 2.5329197014925374e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:25:11", "remaining_time": "1 day, 6:06:14"}
+{"current_steps": 31, "total_steps": 666, "loss": 0.5606, "lr": 2.6173503582089553e-05, "epoch": 0.13924761370016844, "percentage": 4.65, "elapsed_time": "1:28:06", "remaining_time": "1 day, 6:04:56"}
+{"current_steps": 32, "total_steps": 666, "loss": 0.5518, "lr": 2.7017810149253732e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:30:57", "remaining_time": "1 day, 6:02:00"}
+{"current_steps": 33, "total_steps": 666, "loss": 0.5387, "lr": 2.786211671641791e-05, "epoch": 0.14823133071308253, "percentage": 4.95, "elapsed_time": "1:33:50", "remaining_time": "1 day, 6:00:06"}
+{"current_steps": 34, "total_steps": 666, "loss": 0.5465, "lr": 2.870642328358209e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:36:40", "remaining_time": "1 day, 5:57:03"}
+{"current_steps": 35, "total_steps": 666, "loss": 0.5418, "lr": 2.9550729850746266e-05, "epoch": 0.15721504772599662, "percentage": 5.26, "elapsed_time": "1:39:22", "remaining_time": "1 day, 5:51:44"}
+{"current_steps": 36, "total_steps": 666, "loss": 0.5326, "lr": 3.039503641791045e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:42:16", "remaining_time": "1 day, 5:49:53"}
+{"current_steps": 37, "total_steps": 666, "loss": 0.5317, "lr": 3.123934298507463e-05, "epoch": 0.16619876473891074, "percentage": 5.56, "elapsed_time": "1:45:03", "remaining_time": "1 day, 5:46:00"}
+{"current_steps": 38, "total_steps": 666, "loss": 0.5391, "lr": 3.20836495522388e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:48:01", "remaining_time": "1 day, 5:45:19"}
+{"current_steps": 39, "total_steps": 666, "loss": 0.5369, "lr": 3.292795611940299e-05, "epoch": 0.17518248175182483, "percentage": 5.86, "elapsed_time": "1:50:46", "remaining_time": "1 day, 5:40:50"}
+{"current_steps": 40, "total_steps": 666, "loss": 0.5412, "lr": 3.377226268656716e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:53:39", "remaining_time": "1 day, 5:38:45"}
+{"current_steps": 41, "total_steps": 666, "loss": 0.5357, "lr": 3.461656925373135e-05, "epoch": 0.18416619876473891, "percentage": 6.16, "elapsed_time": "1:56:41", "remaining_time": "1 day, 5:38:50"}
+{"current_steps": 42, "total_steps": 666, "loss": 0.525, "lr": 3.5460875820895526e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "1:59:31", "remaining_time": "1 day, 5:35:43"}
+{"current_steps": 43, "total_steps": 666, "loss": 0.5248, "lr": 3.63051823880597e-05, "epoch": 0.193149915777653, "percentage": 6.46, "elapsed_time": "2:02:22", "remaining_time": "1 day, 5:32:54"}
+{"current_steps": 44, "total_steps": 666, "loss": 0.5286, "lr": 3.7149488955223884e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:05:17", "remaining_time": "1 day, 5:31:03"}
+{"current_steps": 45, "total_steps": 666, "loss": 0.5178, "lr": 3.799379552238806e-05, "epoch": 0.2021336327905671, "percentage": 6.76, "elapsed_time": "2:07:57", "remaining_time": "1 day, 5:25:42"}
+{"current_steps": 46, "total_steps": 666, "loss": 0.5231, "lr": 3.883810208955224e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:10:39", "remaining_time": "1 day, 5:20:58"}
+{"current_steps": 47, "total_steps": 666, "loss": 0.5157, "lr": 3.968240865671642e-05, "epoch": 0.21111734980348118, "percentage": 7.06, "elapsed_time": "2:13:28", "remaining_time": "1 day, 5:17:50"}
+{"current_steps": 48, "total_steps": 666, "loss": 0.5213, "lr": 4.052671522388059e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:16:23", "remaining_time": "1 day, 5:16:07"}
+{"current_steps": 49, "total_steps": 666, "loss": 0.5092, "lr": 4.137102179104478e-05, "epoch": 0.2201010668163953, "percentage": 7.36, "elapsed_time": "2:19:07", "remaining_time": "1 day, 5:11:50"}
+{"current_steps": 50, "total_steps": 666, "loss": 0.5294, "lr": 4.221532835820896e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:21:49", "remaining_time": "1 day, 5:07:12"}
+{"current_steps": 51, "total_steps": 666, "loss": 0.5179, "lr": 4.305963492537314e-05, "epoch": 0.22908478382930939, "percentage": 7.66, "elapsed_time": "2:24:45", "remaining_time": "1 day, 5:05:34"}
+{"current_steps": 52, "total_steps": 666, "loss": 0.5201, "lr": 4.3903941492537316e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:27:18", "remaining_time": "1 day, 4:59:27"}
+{"current_steps": 53, "total_steps": 666, "loss": 0.5157, "lr": 4.474824805970149e-05, "epoch": 0.23806850084222347, "percentage": 7.96, "elapsed_time": "2:29:54", "remaining_time": "1 day, 4:53:45"}
+{"current_steps": 54, "total_steps": 666, "loss": 0.5171, "lr": 4.5592554626865674e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:32:37", "remaining_time": "1 day, 4:49:42"}
+{"current_steps": 55, "total_steps": 666, "loss": 0.504, "lr": 4.643686119402985e-05, "epoch": 0.24705221785513756, "percentage": 8.26, "elapsed_time": "2:35:25", "remaining_time": "1 day, 4:46:43"}
+{"current_steps": 56, "total_steps": 666, "loss": 0.513, "lr": 4.728116776119403e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:38:02", "remaining_time": "1 day, 4:41:33"}
+{"current_steps": 57, "total_steps": 666, "loss": 0.5156, "lr": 4.812547432835821e-05, "epoch": 0.25603593486805165, "percentage": 8.56, "elapsed_time": "2:40:52", "remaining_time": "1 day, 4:38:54"}
+{"current_steps": 58, "total_steps": 666, "loss": 0.5113, "lr": 4.8969780895522384e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:43:43", "remaining_time": "1 day, 4:36:22"}
+{"current_steps": 59, "total_steps": 666, "loss": 0.5175, "lr": 4.981408746268657e-05, "epoch": 0.26501965188096577, "percentage": 8.86, "elapsed_time": "2:46:37", "remaining_time": "1 day, 4:34:15"}
+{"current_steps": 60, "total_steps": 666, "loss": 0.5126, "lr": 5.065839402985075e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:49:25", "remaining_time": "1 day, 4:31:07"}
+{"current_steps": 61, "total_steps": 666, "loss": 0.5056, "lr": 5.150270059701493e-05, "epoch": 0.27400336889387983, "percentage": 9.16, "elapsed_time": "2:52:09", "remaining_time": "1 day, 4:27:27"}
+{"current_steps": 62, "total_steps": 666, "loss": 0.509, "lr": 5.2347007164179107e-05, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:54:49", "remaining_time": "1 day, 4:23:12"}
+{"current_steps": 63, "total_steps": 666, "loss": 0.5229, "lr": 5.3191313731343286e-05, "epoch": 0.28298708590679394, "percentage": 9.46, "elapsed_time": "2:57:39", "remaining_time": "1 day, 4:20:28"}
+{"current_steps": 64, "total_steps": 666, "loss": 0.5035, "lr": 5.4035620298507465e-05, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "3:00:21", "remaining_time": "1 day, 4:16:30"}
+{"current_steps": 65, "total_steps": 666, "loss": 0.5073, "lr": 5.4879926865671644e-05, "epoch": 0.291970802919708, "percentage": 9.76, "elapsed_time": "3:03:03", "remaining_time": "1 day, 4:12:34"}
+{"current_steps": 66, "total_steps": 666, "loss": 0.4948, "lr": 5.572423343283582e-05, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:05:56", "remaining_time": "1 day, 4:10:23"}
+{"current_steps": 67, "total_steps": 666, "loss": 0.5059, "lr": 5.656854e-05, "epoch": 0.3009545199326221, "percentage": 10.06, "elapsed_time": "3:08:51", "remaining_time": "1 day, 4:08:25"}
+{"current_steps": 68, "total_steps": 666, "loss": 0.4964, "lr": 5.6568150990610705e-05, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:11:42", "remaining_time": "1 day, 4:05:57"}
+{"current_steps": 69, "total_steps": 666, "loss": 0.5007, "lr": 5.656698397314335e-05, "epoch": 0.30993823694553624, "percentage": 10.36, "elapsed_time": "3:14:31", "remaining_time": "1 day, 4:03:03"}
+{"current_steps": 70, "total_steps": 666, "loss": 0.4989, "lr": 5.656503897969921e-05, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:17:20", "remaining_time": "1 day, 4:00:14"}
+{"current_steps": 71, "total_steps": 666, "loss": 0.4983, "lr": 5.656231606377945e-05, "epoch": 0.3189219539584503, "percentage": 10.66, "elapsed_time": "3:20:14", "remaining_time": "1 day, 3:58:03"}
+{"current_steps": 72, "total_steps": 666, "loss": 0.5145, "lr": 5.655881530028367e-05, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:23:00", "remaining_time": "1 day, 3:54:50"}
+{"current_steps": 73, "total_steps": 666, "loss": 0.4988, "lr": 5.655453678550775e-05, "epoch": 0.3279056709713644, "percentage": 10.96, "elapsed_time": "3:25:56", "remaining_time": "1 day, 3:52:59"}
+{"current_steps": 74, "total_steps": 666, "loss": 0.4985, "lr": 5.654948063714134e-05, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:28:47", "remaining_time": "1 day, 3:50:17"}
+{"current_steps": 75, "total_steps": 666, "loss": 0.5072, "lr": 5.654364699426449e-05, "epoch": 0.3368893879842785, "percentage": 11.26, "elapsed_time": "3:31:35", "remaining_time": "1 day, 3:47:21"}
+{"current_steps": 76, "total_steps": 666, "loss": 0.4932, "lr": 5.653703601734391e-05, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:34:10", "remaining_time": "1 day, 3:42:39"}
+{"current_steps": 77, "total_steps": 666, "loss": 0.5239, "lr": 5.652964788822855e-05, "epoch": 0.3458731049971926, "percentage": 11.56, "elapsed_time": "3:37:00", "remaining_time": "1 day, 3:40:00"}
+{"current_steps": 78, "total_steps": 666, "loss": 0.4971, "lr": 5.652148281014452e-05, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:39:54", "remaining_time": "1 day, 3:37:46"}
+{"current_steps": 79, "total_steps": 666, "loss": 0.5127, "lr": 5.651254100768964e-05, "epoch": 0.35485682201010665, "percentage": 11.86, "elapsed_time": "3:42:40", "remaining_time": "1 day, 3:34:35"}
+{"current_steps": 80, "total_steps": 666, "loss": 0.5057, "lr": 5.6502822726827084e-05, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:45:27", "remaining_time": "1 day, 3:31:30"}
+{"current_steps": 81, "total_steps": 666, "loss": 0.5066, "lr": 5.6492328234878805e-05, "epoch": 0.36384053902302077, "percentage": 12.16, "elapsed_time": "3:48:08", "remaining_time": "1 day, 3:27:41"}
+{"current_steps": 82, "total_steps": 666, "loss": 0.5107, "lr": 5.6481057820518e-05, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:50:50", "remaining_time": "1 day, 3:24:05"}
+{"current_steps": 83, "total_steps": 666, "loss": 0.502, "lr": 5.646901179376134e-05, "epoch": 0.3728242560359349, "percentage": 12.46, "elapsed_time": "3:53:46", "remaining_time": "1 day, 3:22:04"}
+{"current_steps": 84, "total_steps": 666, "loss": 0.5024, "lr": 5.6456190485960274e-05, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "3:56:34", "remaining_time": "1 day, 3:19:05"}
+{"current_steps": 85, "total_steps": 666, "loss": 0.5137, "lr": 5.644259424979206e-05, "epoch": 0.38180797304884895, "percentage": 12.76, "elapsed_time": "3:59:17", "remaining_time": "1 day, 3:15:36"}
+{"current_steps": 86, "total_steps": 666, "loss": 0.5151, "lr": 5.642822345924999e-05, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "4:01:54", "remaining_time": "1 day, 3:11:29"}
+{"current_steps": 87, "total_steps": 666, "loss": 0.5017, "lr": 5.641307850963309e-05, "epoch": 0.39079169006176306, "percentage": 13.06, "elapsed_time": "4:04:45", "remaining_time": "1 day, 3:08:57"}
+{"current_steps": 88, "total_steps": 666, "loss": 0.5043, "lr": 5.6397159817535313e-05, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:07:43", "remaining_time": "1 day, 3:07:04"}
+{"current_steps": 89, "total_steps": 666, "loss": 0.5084, "lr": 5.638046782083399e-05, "epoch": 0.3997754070746771, "percentage": 13.36, "elapsed_time": "4:10:34", "remaining_time": "1 day, 3:04:32"}
+{"current_steps": 90, "total_steps": 666, "loss": 0.5031, "lr": 5.636300297867789e-05, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:13:28", "remaining_time": "1 day, 3:02:14"}
+{"current_steps": 91, "total_steps": 666, "loss": 0.501, "lr": 5.634476577147447e-05, "epoch": 0.40875912408759124, "percentage": 13.66, "elapsed_time": "4:16:13", "remaining_time": "1 day, 2:58:58"}
+{"current_steps": 92, "total_steps": 666, "loss": 0.4931, "lr": 5.6325756700876784e-05, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:19:00", "remaining_time": "1 day, 2:56:01"}
+{"current_steps": 93, "total_steps": 666, "loss": 0.4968, "lr": 5.6305976289769585e-05, "epoch": 0.41774284110050536, "percentage": 13.96, "elapsed_time": "4:21:46", "remaining_time": "1 day, 2:52:55"}
+{"current_steps": 94, "total_steps": 666, "loss": 0.5003, "lr": 5.628542508225499e-05, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:24:43", "remaining_time": "1 day, 2:50:55"}
+{"current_steps": 95, "total_steps": 666, "loss": 0.4983, "lr": 5.626410364363752e-05, "epoch": 0.4267265581134194, "percentage": 14.26, "elapsed_time": "4:27:32", "remaining_time": "1 day, 2:48:05"}
+{"current_steps": 96, "total_steps": 666, "loss": 0.48, "lr": 5.624201256040852e-05, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:30:13", "remaining_time": "1 day, 2:44:25"}
+{"current_steps": 97, "total_steps": 666, "loss": 0.5001, "lr": 5.6219152440230034e-05, "epoch": 0.43571027512633353, "percentage": 14.56, "elapsed_time": "4:33:03", "remaining_time": "1 day, 2:41:43"}
+{"current_steps": 98, "total_steps": 666, "loss": 0.5661, "lr": 5.619552391191811e-05, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:35:40", "remaining_time": "1 day, 2:37:46"}
+{"current_steps": 99, "total_steps": 666, "loss": 0.6828, "lr": 5.6171127625425495e-05, "epoch": 0.4446939921392476, "percentage": 14.86, "elapsed_time": "4:38:32", "remaining_time": "1 day, 2:35:15"}
+{"current_steps": 100, "total_steps": 666, "loss": 0.5599, "lr": 5.6145964251823724e-05, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:41:26", "remaining_time": "1 day, 2:32:59"}
+{"current_steps": 101, "total_steps": 666, "loss": 0.5688, "lr": 5.6120034483284736e-05, "epoch": 0.4536777091521617, "percentage": 15.17, "elapsed_time": "4:44:17", "remaining_time": "1 day, 2:30:21"}
+{"current_steps": 102, "total_steps": 666, "loss": 0.5377, "lr": 5.6093339033061736e-05, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:47:03", "remaining_time": "1 day, 2:27:17"}
+{"current_steps": 103, "total_steps": 666, "loss": 0.5176, "lr": 5.606587863546965e-05, "epoch": 0.4626614261650758, "percentage": 15.47, "elapsed_time": "4:49:49", "remaining_time": "1 day, 2:24:09"}
+{"current_steps": 104, "total_steps": 666, "loss": 0.5065, "lr": 5.603765404586491e-05, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "4:52:33", "remaining_time": "1 day, 2:20:57"}
+{"current_steps": 105, "total_steps": 666, "loss": 0.499, "lr": 5.600866604062465e-05, "epoch": 0.4716451431779899, "percentage": 15.77, "elapsed_time": "4:55:23", "remaining_time": "1 day, 2:18:14"}
+{"current_steps": 106, "total_steps": 666, "loss": 0.497, "lr": 5.597891541712538e-05, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "4:58:13", "remaining_time": "1 day, 2:15:31"}
+{"current_steps": 107, "total_steps": 666, "loss": 0.4945, "lr": 5.5948402993721036e-05, "epoch": 0.480628860190904, "percentage": 16.07, "elapsed_time": "5:00:48", "remaining_time": "1 day, 2:11:31"}
+{"current_steps": 108, "total_steps": 666, "loss": 0.5055, "lr": 5.5917129609720485e-05, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "5:03:41", "remaining_time": "1 day, 2:09:03"}
+{"current_steps": 109, "total_steps": 666, "loss": 0.5047, "lr": 5.5885096125364414e-05, "epoch": 0.48961257720381807, "percentage": 16.37, "elapsed_time": "5:06:26", "remaining_time": "1 day, 2:05:55"}
+{"current_steps": 110, "total_steps": 666, "loss": 0.4951, "lr": 5.585230342180169e-05, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:09:14", "remaining_time": "1 day, 2:03:03"}
+{"current_steps": 111, "total_steps": 666, "loss": 0.496, "lr": 5.581875240106511e-05, "epoch": 0.4985962942167322, "percentage": 16.67, "elapsed_time": "5:12:00", "remaining_time": "1 day, 2:00:04"}
+{"current_steps": 112, "total_steps": 666, "loss": 0.4851, "lr": 5.5784443986046583e-05, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:14:47", "remaining_time": "1 day, 1:57:05"}
+{"current_steps": 113, "total_steps": 666, "loss": 0.5025, "lr": 5.574937912047177e-05, "epoch": 0.5075800112296462, "percentage": 16.97, "elapsed_time": "5:17:40", "remaining_time": "1 day, 1:54:37"}
+{"current_steps": 114, "total_steps": 666, "loss": 0.4956, "lr": 5.57135587688741e-05, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:20:33", "remaining_time": "1 day, 1:52:11"}
+{"current_steps": 115, "total_steps": 666, "loss": 0.4825, "lr": 5.5676983916568236e-05, "epoch": 0.5165637282425604, "percentage": 17.27, "elapsed_time": "5:23:09", "remaining_time": "1 day, 1:48:22"}
+{"current_steps": 116, "total_steps": 666, "loss": 0.5059, "lr": 5.5639655569623e-05, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:25:58", "remaining_time": "1 day, 1:45:34"}
+{"current_steps": 117, "total_steps": 666, "loss": 0.4882, "lr": 5.560157475483366e-05, "epoch": 0.5255474452554745, "percentage": 17.57, "elapsed_time": "5:28:45", "remaining_time": "1 day, 1:42:39"}
+{"current_steps": 118, "total_steps": 666, "loss": 0.4983, "lr": 5.5562742519693715e-05, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:31:35", "remaining_time": "1 day, 1:39:58"}
+{"current_steps": 119, "total_steps": 666, "loss": 0.4897, "lr": 5.552315993236609e-05, "epoch": 0.5345311622683886, "percentage": 17.87, "elapsed_time": "5:34:14", "remaining_time": "1 day, 1:36:24"}
+{"current_steps": 120, "total_steps": 666, "loss": 0.496, "lr": 5.548282808165372e-05, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:36:50", "remaining_time": "1 day, 1:32:38"}
+{"current_steps": 121, "total_steps": 666, "loss": 0.5076, "lr": 5.5441748076969605e-05, "epoch": 0.5435148792813026, "percentage": 18.17, "elapsed_time": "5:39:45", "remaining_time": "1 day, 1:30:18"}
+{"current_steps": 122, "total_steps": 666, "loss": 0.4916, "lr": 5.5399921048306325e-05, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:42:33", "remaining_time": "1 day, 1:27:28"}
+{"current_steps": 123, "total_steps": 666, "loss": 0.4779, "lr": 5.535734814620494e-05, "epoch": 0.5524985962942167, "percentage": 18.47, "elapsed_time": "5:45:29", "remaining_time": "1 day, 1:25:15"}
+{"current_steps": 124, "total_steps": 666, "loss": 0.5016, "lr": 5.531403054172332e-05, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:48:11", "remaining_time": "1 day, 1:21:54"}
+{"current_steps": 125, "total_steps": 666, "loss": 0.5029, "lr": 5.526996942640397e-05, "epoch": 0.5614823133071308, "percentage": 18.77, "elapsed_time": "5:51:05", "remaining_time": "1 day, 1:19:30"}
+{"current_steps": 126, "total_steps": 666, "loss": 0.4789, "lr": 5.5225166012241233e-05, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "5:53:43", "remaining_time": "1 day, 1:15:59"}
+{"current_steps": 127, "total_steps": 666, "loss": 0.4789, "lr": 5.517962153164794e-05, "epoch": 0.570466030320045, "percentage": 19.07, "elapsed_time": "5:56:35", "remaining_time": "1 day, 1:13:25"}
+{"current_steps": 128, "total_steps": 666, "loss": 0.4842, "lr": 5.5133337237421544e-05, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "5:59:21", "remaining_time": "1 day, 1:10:23"}
+{"current_steps": 129, "total_steps": 666, "loss": 0.4882, "lr": 5.508631440270962e-05, "epoch": 0.5794497473329591, "percentage": 19.37, "elapsed_time": "6:02:10", "remaining_time": "1 day, 1:07:39"}
+{"current_steps": 130, "total_steps": 666, "loss": 0.4724, "lr": 5.503855432097488e-05, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "6:04:53", "remaining_time": "1 day, 1:04:27"}
+{"current_steps": 131, "total_steps": 666, "loss": 0.4866, "lr": 5.499005830595958e-05, "epoch": 0.5884334643458731, "percentage": 19.67, "elapsed_time": "6:07:48", "remaining_time": "1 day, 1:02:06"}
+{"current_steps": 132, "total_steps": 666, "loss": 0.4705, "lr": 5.494082769164936e-05, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:10:35", "remaining_time": "1 day, 0:59:14"}
+{"current_steps": 133, "total_steps": 666, "loss": 0.4749, "lr": 5.4890863832236595e-05, "epoch": 0.5974171813587872, "percentage": 19.97, "elapsed_time": "6:13:23", "remaining_time": "1 day, 0:56:20"}
+{"current_steps": 134, "total_steps": 666, "loss": 0.4807, "lr": 5.48401681020831e-05, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:15:59", "remaining_time": "1 day, 0:52:44"}
+{"current_steps": 135, "total_steps": 666, "loss": 0.4807, "lr": 5.478874189568235e-05, "epoch": 0.6064008983717013, "percentage": 20.27, "elapsed_time": "6:18:53", "remaining_time": "1 day, 0:50:18"}
+{"current_steps": 136, "total_steps": 666, "loss": 0.4835, "lr": 5.473658662762113e-05, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:21:51", "remaining_time": "1 day, 0:48:06"}
+{"current_steps": 137, "total_steps": 666, "loss": 0.478, "lr": 5.4683703732540596e-05, "epoch": 0.6153846153846154, "percentage": 20.57, "elapsed_time": "6:24:40", "remaining_time": "1 day, 0:45:19"}
+{"current_steps": 138, "total_steps": 666, "loss": 0.4728, "lr": 5.463009466509683e-05, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:27:24", "remaining_time": "1 day, 0:42:16"}
+{"current_steps": 139, "total_steps": 666, "loss": 0.4791, "lr": 5.457576089992082e-05, "epoch": 0.6243683323975294, "percentage": 20.87, "elapsed_time": "6:30:16", "remaining_time": "1 day, 0:39:42"}
+{"current_steps": 140, "total_steps": 666, "loss": 0.4722, "lr": 5.4520703931577924e-05, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:33:08", "remaining_time": "1 day, 0:37:04"}
+{"current_steps": 141, "total_steps": 666, "loss": 0.482, "lr": 5.446492527452671e-05, "epoch": 0.6333520494104435, "percentage": 21.17, "elapsed_time": "6:36:07", "remaining_time": "1 day, 0:34:54"}
+{"current_steps": 142, "total_steps": 666, "loss": 0.4717, "lr": 5.440842646307732e-05, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:38:50", "remaining_time": "1 day, 0:31:47"}
+{"current_steps": 143, "total_steps": 666, "loss": 0.4657, "lr": 5.435120905134929e-05, "epoch": 0.6423357664233577, "percentage": 21.47, "elapsed_time": "6:41:40", "remaining_time": "1 day, 0:29:03"}
+{"current_steps": 144, "total_steps": 666, "loss": 0.467, "lr": 5.429327461322877e-05, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:44:13", "remaining_time": "1 day, 0:25:17"}
+{"current_steps": 145, "total_steps": 666, "loss": 0.4824, "lr": 5.423462474232524e-05, "epoch": 0.6513194834362718, "percentage": 21.77, "elapsed_time": "6:47:09", "remaining_time": "1 day, 0:22:56"}
+{"current_steps": 146, "total_steps": 666, "loss": 0.4753, "lr": 5.417526105192766e-05, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "6:49:47", "remaining_time": "1 day, 0:19:32"}
+{"current_steps": 147, "total_steps": 666, "loss": 0.4734, "lr": 5.4115185174960136e-05, "epoch": 0.6603032004491859, "percentage": 22.07, "elapsed_time": "6:52:18", "remaining_time": "1 day, 0:15:41"}
+{"current_steps": 148, "total_steps": 666, "loss": 0.4725, "lr": 5.405439876393696e-05, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "6:55:04", "remaining_time": "1 day, 0:12:46"}
+{"current_steps": 149, "total_steps": 666, "loss": 0.4756, "lr": 5.3992903490917166e-05, "epoch": 0.6692869174620999, "percentage": 22.37, "elapsed_time": "6:57:50", "remaining_time": "1 day, 0:09:47"}
+{"current_steps": 150, "total_steps": 666, "loss": 0.4691, "lr": 5.393070104745854e-05, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "7:00:42", "remaining_time": "1 day, 0:07:14"}
+{"current_steps": 151, "total_steps": 666, "loss": 0.492, "lr": 5.386779314457109e-05, "epoch": 0.678270634475014, "percentage": 22.67, "elapsed_time": "7:03:37", "remaining_time": "1 day, 0:04:48"}
+{"current_steps": 152, "total_steps": 666, "loss": 0.5055, "lr": 5.380418151266999e-05, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "7:06:24", "remaining_time": "1 day, 0:01:55"}
+{"current_steps": 153, "total_steps": 666, "loss": 0.483, "lr": 5.373986790152796e-05, "epoch": 0.6872543514879281, "percentage": 22.97, "elapsed_time": "7:09:15", "remaining_time": "23:59:17"}
+{"current_steps": 154, "total_steps": 666, "loss": 0.4858, "lr": 5.367485408022714e-05, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:11:57", "remaining_time": "23:56:07"}
+{"current_steps": 155, "total_steps": 666, "loss": 0.4849, "lr": 5.3609141837110465e-05, "epoch": 0.6962380685008422, "percentage": 23.27, "elapsed_time": "7:14:48", "remaining_time": "23:53:27"}
+{"current_steps": 156, "total_steps": 666, "loss": 0.487, "lr": 5.35427329797324e-05, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:17:41", "remaining_time": "23:50:54"}
+{"current_steps": 157, "total_steps": 666, "loss": 0.4819, "lr": 5.34756293348093e-05, "epoch": 0.7052217855137564, "percentage": 23.57, "elapsed_time": "7:20:22", "remaining_time": "23:47:41"}
+{"current_steps": 158, "total_steps": 666, "loss": 0.4803, "lr": 5.340783274816909e-05, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:23:05", "remaining_time": "23:44:36"}
+{"current_steps": 159, "total_steps": 666, "loss": 0.4966, "lr": 5.333934508470055e-05, "epoch": 0.7142055025266704, "percentage": 23.87, "elapsed_time": "7:25:56", "remaining_time": "23:41:56"}
+{"current_steps": 160, "total_steps": 666, "loss": 0.4859, "lr": 5.327016822830199e-05, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:28:38", "remaining_time": "23:38:48"}
+{"current_steps": 161, "total_steps": 666, "loss": 0.4755, "lr": 5.3200304081829424e-05, "epoch": 0.7231892195395845, "percentage": 24.17, "elapsed_time": "7:31:24", "remaining_time": "23:35:54"}
+{"current_steps": 162, "total_steps": 666, "loss": 0.4778, "lr": 5.312975456704423e-05, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:34:16", "remaining_time": "23:33:19"}
+{"current_steps": 163, "total_steps": 666, "loss": 0.4581, "lr": 5.3058521624560304e-05, "epoch": 0.7321729365524986, "percentage": 24.47, "elapsed_time": "7:37:09", "remaining_time": "23:30:42"}
+{"current_steps": 164, "total_steps": 666, "loss": 0.4641, "lr": 5.2986607213790666e-05, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:40:05", "remaining_time": "23:28:21"}
+{"current_steps": 165, "total_steps": 666, "loss": 0.4817, "lr": 5.2914013312893555e-05, "epoch": 0.7411566535654127, "percentage": 24.77, "elapsed_time": "7:43:00", "remaining_time": "23:25:51"}
+{"current_steps": 166, "total_steps": 666, "loss": 0.4791, "lr": 5.284074191871806e-05, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:45:48", "remaining_time": "23:23:02"}
+{"current_steps": 167, "total_steps": 666, "loss": 0.4855, "lr": 5.276679504674912e-05, "epoch": 0.7501403705783268, "percentage": 25.08, "elapsed_time": "7:48:37", "remaining_time": "23:20:14"}
+{"current_steps": 168, "total_steps": 666, "loss": 0.4687, "lr": 5.269217473105214e-05, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "7:51:23", "remaining_time": "23:17:19"}
+{"current_steps": 169, "total_steps": 666, "loss": 0.4705, "lr": 5.261688302421702e-05, "epoch": 0.7591240875912408, "percentage": 25.38, "elapsed_time": "7:54:19", "remaining_time": "23:14:55"}
+{"current_steps": 170, "total_steps": 666, "loss": 0.4716, "lr": 5.2540921997301675e-05, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "7:57:07", "remaining_time": "23:12:05"}
+{"current_steps": 171, "total_steps": 666, "loss": 0.4783, "lr": 5.246429373977513e-05, "epoch": 0.768107804604155, "percentage": 25.68, "elapsed_time": "7:59:59", "remaining_time": "23:09:26"}
+{"current_steps": 172, "total_steps": 666, "loss": 0.4682, "lr": 5.2387000359459964e-05, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "8:02:53", "remaining_time": "23:06:53"}
+{"current_steps": 173, "total_steps": 666, "loss": 0.4582, "lr": 5.230904398247439e-05, "epoch": 0.7770915216170691, "percentage": 25.98, "elapsed_time": "8:05:42", "remaining_time": "23:04:08"}
+{"current_steps": 174, "total_steps": 666, "loss": 0.4727, "lr": 5.2230426753173746e-05, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "8:08:29", "remaining_time": "23:01:15"}
+{"current_steps": 175, "total_steps": 666, "loss": 0.4764, "lr": 5.215115083409149e-05, "epoch": 0.7860752386299832, "percentage": 26.28, "elapsed_time": "8:11:19", "remaining_time": "22:58:30"}
+{"current_steps": 176, "total_steps": 666, "loss": 0.4747, "lr": 5.207121840587976e-05, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:14:11", "remaining_time": "22:55:52"}
+{"current_steps": 177, "total_steps": 666, "loss": 0.4547, "lr": 5.1990631667249386e-05, "epoch": 0.7950589556428973, "percentage": 26.58, "elapsed_time": "8:17:07", "remaining_time": "22:53:24"}
+{"current_steps": 178, "total_steps": 666, "loss": 0.4626, "lr": 5.190939283490934e-05, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:19:57", "remaining_time": "22:50:39"}
+{"current_steps": 179, "total_steps": 666, "loss": 0.4662, "lr": 5.182750414350587e-05, "epoch": 0.8040426726558113, "percentage": 26.88, "elapsed_time": "8:22:56", "remaining_time": "22:48:19"}
+{"current_steps": 180, "total_steps": 666, "loss": 0.4712, "lr": 5.1744967845560936e-05, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:25:50", "remaining_time": "22:45:47"}
+{"current_steps": 181, "total_steps": 666, "loss": 0.4794, "lr": 5.16617862114103e-05, "epoch": 0.8130263896687254, "percentage": 27.18, "elapsed_time": "8:28:42", "remaining_time": "22:43:07"}
+{"current_steps": 182, "total_steps": 666, "loss": 0.4624, "lr": 5.157796152914106e-05, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:31:35", "remaining_time": "22:40:31"}
+{"current_steps": 183, "total_steps": 666, "loss": 0.4673, "lr": 5.1493496104528745e-05, "epoch": 0.8220101066816395, "percentage": 27.48, "elapsed_time": "8:34:17", "remaining_time": "22:37:23"}
+{"current_steps": 184, "total_steps": 666, "loss": 0.4597, "lr": 5.140839226097382e-05, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:37:06", "remaining_time": "22:34:37"}
+{"current_steps": 185, "total_steps": 666, "loss": 0.4588, "lr": 5.132265233943782e-05, "epoch": 0.8309938236945537, "percentage": 27.78, "elapsed_time": "8:39:52", "remaining_time": "22:31:40"}
+{"current_steps": 186, "total_steps": 666, "loss": 0.464, "lr": 5.123627869837897e-05, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:42:38", "remaining_time": "22:28:44"}
+{"current_steps": 187, "total_steps": 666, "loss": 0.466, "lr": 5.1149273713687296e-05, "epoch": 0.8399775407074677, "percentage": 28.08, "elapsed_time": "8:45:31", "remaining_time": "22:26:06"}
+{"current_steps": 188, "total_steps": 666, "loss": 0.4572, "lr": 5.106163977861925e-05, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "8:48:18", "remaining_time": "22:23:14"}
+{"current_steps": 189, "total_steps": 666, "loss": 0.4579, "lr": 5.097337930373192e-05, "epoch": 0.8489612577203818, "percentage": 28.38, "elapsed_time": "8:51:05", "remaining_time": "22:20:22"}
+{"current_steps": 190, "total_steps": 666, "loss": 0.4724, "lr": 5.0884494716816655e-05, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "8:53:55", "remaining_time": "22:17:36"}
+{"current_steps": 191, "total_steps": 666, "loss": 0.4737, "lr": 5.079498846283238e-05, "epoch": 0.8579449747332959, "percentage": 28.68, "elapsed_time": "8:56:43", "remaining_time": "22:14:47"}
+{"current_steps": 192, "total_steps": 666, "loss": 0.4694, "lr": 5.070486300383827e-05, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "8:59:38", "remaining_time": "22:12:13"}
+{"current_steps": 193, "total_steps": 666, "loss": 0.4651, "lr": 5.061412081892603e-05, "epoch": 0.86692869174621, "percentage": 28.98, "elapsed_time": "9:02:28", "remaining_time": "22:09:28"}
+{"current_steps": 194, "total_steps": 666, "loss": 0.4762, "lr": 5.052276440415174e-05, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "9:05:22", "remaining_time": "22:06:54"}
+{"current_steps": 195, "total_steps": 666, "loss": 0.4513, "lr": 5.043079627246717e-05, "epoch": 0.8759124087591241, "percentage": 29.28, "elapsed_time": "9:08:17", "remaining_time": "22:04:20"}
+{"current_steps": 196, "total_steps": 666, "loss": 0.4551, "lr": 5.033821895365065e-05, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "9:11:19", "remaining_time": "22:02:04"}
+{"current_steps": 197, "total_steps": 666, "loss": 0.4633, "lr": 5.02450349942375e-05, "epoch": 0.8848961257720381, "percentage": 29.58, "elapsed_time": "9:14:04", "remaining_time": "21:59:04"}
+{"current_steps": 198, "total_steps": 666, "loss": 0.4721, "lr": 5.015124695744997e-05, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:16:50", "remaining_time": "21:56:09"}
+{"current_steps": 199, "total_steps": 666, "loss": 0.462, "lr": 5.005685742312674e-05, "epoch": 0.8938798427849522, "percentage": 29.88, "elapsed_time": "9:19:44", "remaining_time": "21:53:34"}
+{"current_steps": 200, "total_steps": 666, "loss": 0.4496, "lr": 4.996186898765196e-05, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:22:38", "remaining_time": "21:50:57"}
+{"current_steps": 201, "total_steps": 666, "loss": 0.4615, "lr": 4.9866284263883835e-05, "epoch": 0.9028635597978664, "percentage": 30.18, "elapsed_time": "9:25:25", "remaining_time": "21:48:05"}
+{"current_steps": 202, "total_steps": 666, "loss": 0.477, "lr": 4.97701058810827e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:28:15", "remaining_time": "21:45:17"}
+{"current_steps": 203, "total_steps": 666, "loss": 0.4554, "lr": 4.9673336484838795e-05, "epoch": 0.9118472768107805, "percentage": 30.48, "elapsed_time": "9:31:04", "remaining_time": "21:42:30"}
+{"current_steps": 204, "total_steps": 666, "loss": 0.4554, "lr": 4.95759787369994e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:33:55", "remaining_time": "21:39:45"}
+{"current_steps": 205, "total_steps": 666, "loss": 0.4653, "lr": 4.947803531559565e-05, "epoch": 0.9208309938236946, "percentage": 30.78, "elapsed_time": "9:36:39", "remaining_time": "21:36:47"}
+{"current_steps": 206, "total_steps": 666, "loss": 0.4704, "lr": 4.937950891476891e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:39:23", "remaining_time": "21:33:47"}
+{"current_steps": 207, "total_steps": 666, "loss": 0.459, "lr": 4.9280402244696586e-05, "epoch": 0.9298147108366086, "percentage": 31.08, "elapsed_time": "9:42:13", "remaining_time": "21:31:00"}
+{"current_steps": 208, "total_steps": 666, "loss": 0.4564, "lr": 4.9180718031517646e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "9:44:55", "remaining_time": "21:27:56"}
+{"current_steps": 209, "total_steps": 666, "loss": 0.4662, "lr": 4.90804590172576e-05, "epoch": 0.9387984278495227, "percentage": 31.38, "elapsed_time": "9:47:48", "remaining_time": "21:25:18"}
+{"current_steps": 210, "total_steps": 666, "loss": 0.4697, "lr": 4.8979627959753065e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "9:50:39", "remaining_time": "21:22:35"}
+{"current_steps": 211, "total_steps": 666, "loss": 0.4597, "lr": 4.887822763257594e-05, "epoch": 0.9477821448624368, "percentage": 31.68, "elapsed_time": "9:53:33", "remaining_time": "21:19:57"}
+{"current_steps": 212, "total_steps": 666, "loss": 0.4531, "lr": 4.877626082495709e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "9:56:23", "remaining_time": "21:17:11"}
+{"current_steps": 213, "total_steps": 666, "loss": 0.4525, "lr": 4.867373034170961e-05, "epoch": 0.956765861875351, "percentage": 31.98, "elapsed_time": "9:59:03", "remaining_time": "21:14:03"}
+{"current_steps": 214, "total_steps": 666, "loss": 0.4634, "lr": 4.857063900315169e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "10:01:44", "remaining_time": "21:10:58"}
+{"current_steps": 215, "total_steps": 666, "loss": 0.4418, "lr": 4.8466989645029046e-05, "epoch": 0.9657495788882651, "percentage": 32.28, "elapsed_time": "10:04:30", "remaining_time": "21:08:02"}
+{"current_steps": 216, "total_steps": 666, "loss": 0.4578, "lr": 4.8362785118436906e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "10:07:07", "remaining_time": "21:04:51"}
+{"current_steps": 217, "total_steps": 666, "loss": 0.4535, "lr": 4.8258028289741566e-05, "epoch": 0.9747332959011791, "percentage": 32.58, "elapsed_time": "10:09:47", "remaining_time": "21:01:43"}
+{"current_steps": 218, "total_steps": 666, "loss": 0.4602, "lr": 4.8152722040501576e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "10:12:42", "remaining_time": "20:59:09"}
+{"current_steps": 219, "total_steps": 666, "loss": 0.4593, "lr": 4.804686926738845e-05, "epoch": 0.9837170129140932, "percentage": 32.88, "elapsed_time": "10:15:26", "remaining_time": "20:56:10"}
+{"current_steps": 220, "total_steps": 666, "loss": 0.4732, "lr": 4.794047288210701e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:18:10", "remaining_time": "20:53:13"}
+{"current_steps": 221, "total_steps": 666, "loss": 0.4607, "lr": 4.783353581131529e-05, "epoch": 0.9927007299270073, "percentage": 33.18, "elapsed_time": "10:20:57", "remaining_time": "20:50:21"}
+{"current_steps": 222, "total_steps": 666, "loss": 0.4586, "lr": 4.772606099654399e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:23:47", "remaining_time": "20:47:34"}
+{"current_steps": 223, "total_steps": 666, "loss": 0.7366, "lr": 4.7618051394115645e-05, "epoch": 1.0030881527231892, "percentage": 33.48, "elapsed_time": "10:27:20", "remaining_time": "20:46:13"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dcca4401c9b63f022c84b755f7331af173757dc891b93feed06e3fd74ca4d09
+size 7224