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:d49870e3c49499c252bb25c1c9d798e3e0a5882248e49ac180ea01c00c05813f
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8e621550b4fcca6f18f1854161f38ae4ea5c728db7c154da234421cffb2784
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed90a70c38d81b6aa0a3a7d8d4470c5079089c1b640bc0f42febd617a9eef63
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396a294eb1bc596cfd2168913bf1908a92ff702e1292575209011e02fe5f8257
+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": 1.1764705882352942e-06, "epoch": 0.004491858506457047, "percentage": 0.15, "elapsed_time": "0:02:54", "remaining_time": "1 day, 8:10:09"}
+{"current_steps": 2, "total_steps": 666, "loss": 0.8731, "lr": 2.3529411764705885e-06, "epoch": 0.008983717012914094, "percentage": 0.3, "elapsed_time": "0:05:40", "remaining_time": "1 day, 7:23:19"}
+{"current_steps": 3, "total_steps": 666, "loss": 0.8513, "lr": 3.529411764705883e-06, "epoch": 0.01347557551937114, "percentage": 0.45, "elapsed_time": "0:08:35", "remaining_time": "1 day, 7:39:36"}
+{"current_steps": 4, "total_steps": 666, "loss": 0.8491, "lr": 4.705882352941177e-06, "epoch": 0.017967434025828188, "percentage": 0.6, "elapsed_time": "0:11:24", "remaining_time": "1 day, 7:29:12"}
+{"current_steps": 5, "total_steps": 666, "loss": 0.8159, "lr": 5.882352941176471e-06, "epoch": 0.022459292532285232, "percentage": 0.75, "elapsed_time": "0:14:00", "remaining_time": "1 day, 6:52:25"}
+{"current_steps": 6, "total_steps": 666, "loss": 0.7612, "lr": 7.058823529411766e-06, "epoch": 0.02695115103874228, "percentage": 0.9, "elapsed_time": "0:16:45", "remaining_time": "1 day, 6:43:59"}
+{"current_steps": 7, "total_steps": 666, "loss": 0.7665, "lr": 8.23529411764706e-06, "epoch": 0.031443009545199324, "percentage": 1.05, "elapsed_time": "0:19:34", "remaining_time": "1 day, 6:43:05"}
+{"current_steps": 8, "total_steps": 666, "loss": 0.7725, "lr": 9.411764705882354e-06, "epoch": 0.035934868051656375, "percentage": 1.2, "elapsed_time": "0:22:19", "remaining_time": "1 day, 6:36:25"}
+{"current_steps": 9, "total_steps": 666, "loss": 0.728, "lr": 1.0588235294117648e-05, "epoch": 0.04042672655811342, "percentage": 1.35, "elapsed_time": "0:25:04", "remaining_time": "1 day, 6:29:53"}
+{"current_steps": 10, "total_steps": 666, "loss": 0.7155, "lr": 1.1764705882352942e-05, "epoch": 0.044918585064570464, "percentage": 1.5, "elapsed_time": "0:27:50", "remaining_time": "1 day, 6:26:28"}
+{"current_steps": 11, "total_steps": 666, "loss": 0.7075, "lr": 1.2941176470588238e-05, "epoch": 0.049410443571027515, "percentage": 1.65, "elapsed_time": "0:30:43", "remaining_time": "1 day, 6:29:36"}
+{"current_steps": 12, "total_steps": 666, "loss": 0.6782, "lr": 1.4117647058823532e-05, "epoch": 0.05390230207748456, "percentage": 1.8, "elapsed_time": "0:33:16", "remaining_time": "1 day, 6:13:12"}
+{"current_steps": 13, "total_steps": 666, "loss": 0.6527, "lr": 1.5294117647058822e-05, "epoch": 0.058394160583941604, "percentage": 1.95, "elapsed_time": "0:36:07", "remaining_time": "1 day, 6:14:32"}
+{"current_steps": 14, "total_steps": 666, "loss": 0.6456, "lr": 1.647058823529412e-05, "epoch": 0.06288601909039865, "percentage": 2.1, "elapsed_time": "0:39:07", "remaining_time": "1 day, 6:22:19"}
+{"current_steps": 15, "total_steps": 666, "loss": 0.6262, "lr": 1.7647058823529414e-05, "epoch": 0.06737787759685569, "percentage": 2.25, "elapsed_time": "0:41:54", "remaining_time": "1 day, 6:18:57"}
+{"current_steps": 16, "total_steps": 666, "loss": 0.6198, "lr": 1.8823529411764708e-05, "epoch": 0.07186973610331275, "percentage": 2.4, "elapsed_time": "0:44:33", "remaining_time": "1 day, 6:10:22"}
+{"current_steps": 17, "total_steps": 666, "loss": 0.623, "lr": 2e-05, "epoch": 0.0763615946097698, "percentage": 2.55, "elapsed_time": "0:47:17", "remaining_time": "1 day, 6:05:37"}
+{"current_steps": 18, "total_steps": 666, "loss": 0.6044, "lr": 2.1176470588235296e-05, "epoch": 0.08085345311622684, "percentage": 2.7, "elapsed_time": "0:50:07", "remaining_time": "1 day, 6:04:21"}
+{"current_steps": 19, "total_steps": 666, "loss": 0.5933, "lr": 2.235294117647059e-05, "epoch": 0.08534531162268388, "percentage": 2.85, "elapsed_time": "0:52:41", "remaining_time": "1 day, 5:54:33"}
+{"current_steps": 20, "total_steps": 666, "loss": 0.5979, "lr": 2.3529411764705884e-05, "epoch": 0.08983717012914093, "percentage": 3.0, "elapsed_time": "0:55:32", "remaining_time": "1 day, 5:53:53"}
+{"current_steps": 21, "total_steps": 666, "loss": 0.5798, "lr": 2.470588235294118e-05, "epoch": 0.09432902863559797, "percentage": 3.15, "elapsed_time": "0:58:16", "remaining_time": "1 day, 5:49:57"}
+{"current_steps": 22, "total_steps": 666, "loss": 0.5774, "lr": 2.5882352941176475e-05, "epoch": 0.09882088714205503, "percentage": 3.3, "elapsed_time": "1:01:06", "remaining_time": "1 day, 5:48:58"}
+{"current_steps": 23, "total_steps": 666, "loss": 0.5748, "lr": 2.705882352941177e-05, "epoch": 0.10331274564851207, "percentage": 3.45, "elapsed_time": "1:04:09", "remaining_time": "1 day, 5:53:29"}
+{"current_steps": 24, "total_steps": 666, "loss": 0.5648, "lr": 2.8235294117647063e-05, "epoch": 0.10780460415496912, "percentage": 3.6, "elapsed_time": "1:06:56", "remaining_time": "1 day, 5:50:40"}
+{"current_steps": 25, "total_steps": 666, "loss": 0.5667, "lr": 2.9411764705882357e-05, "epoch": 0.11229646266142616, "percentage": 3.75, "elapsed_time": "1:09:43", "remaining_time": "1 day, 5:47:56"}
+{"current_steps": 26, "total_steps": 666, "loss": 0.5459, "lr": 3.0588235294117644e-05, "epoch": 0.11678832116788321, "percentage": 3.9, "elapsed_time": "1:12:14", "remaining_time": "1 day, 5:38:08"}
+{"current_steps": 27, "total_steps": 666, "loss": 0.5563, "lr": 3.1764705882352945e-05, "epoch": 0.12128017967434025, "percentage": 4.05, "elapsed_time": "1:14:54", "remaining_time": "1 day, 5:32:57"}
+{"current_steps": 28, "total_steps": 666, "loss": 0.5542, "lr": 3.294117647058824e-05, "epoch": 0.1257720381807973, "percentage": 4.2, "elapsed_time": "1:17:41", "remaining_time": "1 day, 5:30:20"}
+{"current_steps": 29, "total_steps": 666, "loss": 0.553, "lr": 3.411764705882353e-05, "epoch": 0.13026389668725435, "percentage": 4.35, "elapsed_time": "1:20:26", "remaining_time": "1 day, 5:27:00"}
+{"current_steps": 30, "total_steps": 666, "loss": 0.5545, "lr": 3.529411764705883e-05, "epoch": 0.13475575519371139, "percentage": 4.5, "elapsed_time": "1:23:12", "remaining_time": "1 day, 5:24:07"}
+{"current_steps": 31, "total_steps": 666, "loss": 0.5546, "lr": 3.647058823529412e-05, "epoch": 0.13924761370016844, "percentage": 4.65, "elapsed_time": "1:26:03", "remaining_time": "1 day, 5:22:46"}
+{"current_steps": 32, "total_steps": 666, "loss": 0.5454, "lr": 3.7647058823529415e-05, "epoch": 0.1437394722066255, "percentage": 4.8, "elapsed_time": "1:28:49", "remaining_time": "1 day, 5:19:43"}
+{"current_steps": 33, "total_steps": 666, "loss": 0.5329, "lr": 3.882352941176471e-05, "epoch": 0.14823133071308253, "percentage": 4.95, "elapsed_time": "1:31:39", "remaining_time": "1 day, 5:18:06"}
+{"current_steps": 34, "total_steps": 666, "loss": 0.5394, "lr": 4e-05, "epoch": 0.1527231892195396, "percentage": 5.11, "elapsed_time": "1:34:25", "remaining_time": "1 day, 5:15:11"}
+{"current_steps": 35, "total_steps": 666, "loss": 0.5384, "lr": 3.999975290458064e-05, "epoch": 0.15721504772599662, "percentage": 5.26, "elapsed_time": "1:37:04", "remaining_time": "1 day, 5:09:59"}
+{"current_steps": 36, "total_steps": 666, "loss": 0.5273, "lr": 3.9999011624428174e-05, "epoch": 0.16170690623245368, "percentage": 5.41, "elapsed_time": "1:39:52", "remaining_time": "1 day, 5:07:55"}
+{"current_steps": 37, "total_steps": 666, "loss": 0.5294, "lr": 3.999777617785929e-05, "epoch": 0.16619876473891074, "percentage": 5.56, "elapsed_time": "1:42:35", "remaining_time": "1 day, 5:03:57"}
+{"current_steps": 38, "total_steps": 666, "loss": 0.536, "lr": 3.999604659540131e-05, "epoch": 0.17069062324536777, "percentage": 5.71, "elapsed_time": "1:45:30", "remaining_time": "1 day, 5:03:32"}
+{"current_steps": 39, "total_steps": 666, "loss": 0.5317, "lr": 3.9993822919791434e-05, "epoch": 0.17518248175182483, "percentage": 5.86, "elapsed_time": "1:48:10", "remaining_time": "1 day, 4:59:10"}
+{"current_steps": 40, "total_steps": 666, "loss": 0.5358, "lr": 3.9991105205975656e-05, "epoch": 0.17967434025828186, "percentage": 6.01, "elapsed_time": "1:50:59", "remaining_time": "1 day, 4:57:08"}
+{"current_steps": 41, "total_steps": 666, "loss": 0.5306, "lr": 3.9987893521107434e-05, "epoch": 0.18416619876473891, "percentage": 6.16, "elapsed_time": "1:53:58", "remaining_time": "1 day, 4:57:22"}
+{"current_steps": 42, "total_steps": 666, "loss": 0.5185, "lr": 3.998418794454604e-05, "epoch": 0.18865805727119594, "percentage": 6.31, "elapsed_time": "1:56:44", "remaining_time": "1 day, 4:54:24"}
+{"current_steps": 43, "total_steps": 666, "loss": 0.5204, "lr": 3.9979988567854575e-05, "epoch": 0.193149915777653, "percentage": 6.46, "elapsed_time": "1:59:30", "remaining_time": "1 day, 4:51:23"}
+{"current_steps": 44, "total_steps": 666, "loss": 0.5262, "lr": 3.997529549479771e-05, "epoch": 0.19764177428411006, "percentage": 6.61, "elapsed_time": "2:02:21", "remaining_time": "1 day, 4:49:41"}
+{"current_steps": 45, "total_steps": 666, "loss": 0.5135, "lr": 3.9970108841339125e-05, "epoch": 0.2021336327905671, "percentage": 6.76, "elapsed_time": "2:04:57", "remaining_time": "1 day, 4:44:29"}
+{"current_steps": 46, "total_steps": 666, "loss": 0.5188, "lr": 3.996442873563866e-05, "epoch": 0.20662549129702415, "percentage": 6.91, "elapsed_time": "2:07:35", "remaining_time": "1 day, 4:39:46"}
+{"current_steps": 47, "total_steps": 666, "loss": 0.5143, "lr": 3.9958255318049125e-05, "epoch": 0.21111734980348118, "percentage": 7.06, "elapsed_time": "2:10:21", "remaining_time": "1 day, 4:36:55"}
+{"current_steps": 48, "total_steps": 666, "loss": 0.5191, "lr": 3.995158874111284e-05, "epoch": 0.21560920830993824, "percentage": 7.21, "elapsed_time": "2:13:13", "remaining_time": "1 day, 4:35:19"}
+{"current_steps": 49, "total_steps": 666, "loss": 0.5068, "lr": 3.994442916955786e-05, "epoch": 0.2201010668163953, "percentage": 7.36, "elapsed_time": "2:15:54", "remaining_time": "1 day, 4:31:14"}
+{"current_steps": 50, "total_steps": 666, "loss": 0.5265, "lr": 3.993677678029392e-05, "epoch": 0.22459292532285233, "percentage": 7.51, "elapsed_time": "2:18:32", "remaining_time": "1 day, 4:26:45"}
+{"current_steps": 51, "total_steps": 666, "loss": 0.5099, "lr": 3.992863176240806e-05, "epoch": 0.22908478382930939, "percentage": 7.66, "elapsed_time": "2:21:24", "remaining_time": "1 day, 4:25:08"}
+{"current_steps": 52, "total_steps": 666, "loss": 0.5162, "lr": 3.991999431715994e-05, "epoch": 0.23357664233576642, "percentage": 7.81, "elapsed_time": "2:23:54", "remaining_time": "1 day, 4:19:16"}
+{"current_steps": 53, "total_steps": 666, "loss": 0.5083, "lr": 3.991086465797687e-05, "epoch": 0.23806850084222347, "percentage": 7.96, "elapsed_time": "2:26:26", "remaining_time": "1 day, 4:13:47"}
+{"current_steps": 54, "total_steps": 666, "loss": 0.5134, "lr": 3.990124301044855e-05, "epoch": 0.2425603593486805, "percentage": 8.11, "elapsed_time": "2:29:05", "remaining_time": "1 day, 4:09:47"}
+{"current_steps": 55, "total_steps": 666, "loss": 0.4921, "lr": 3.989112961232149e-05, "epoch": 0.24705221785513756, "percentage": 8.26, "elapsed_time": "2:31:50", "remaining_time": "1 day, 4:06:49"}
+{"current_steps": 56, "total_steps": 666, "loss": 0.5074, "lr": 3.9880524713493105e-05, "epoch": 0.2515440763615946, "percentage": 8.41, "elapsed_time": "2:34:24", "remaining_time": "1 day, 4:01:51"}
+{"current_steps": 57, "total_steps": 666, "loss": 0.5027, "lr": 3.986942857600562e-05, "epoch": 0.25603593486805165, "percentage": 8.56, "elapsed_time": "2:37:10", "remaining_time": "1 day, 3:59:18"}
+{"current_steps": 58, "total_steps": 666, "loss": 0.4958, "lr": 3.985784147403947e-05, "epoch": 0.2605277933745087, "percentage": 8.71, "elapsed_time": "2:39:58", "remaining_time": "1 day, 3:56:54"}
+{"current_steps": 59, "total_steps": 666, "loss": 0.5096, "lr": 3.9845763693906666e-05, "epoch": 0.26501965188096577, "percentage": 8.86, "elapsed_time": "2:42:46", "remaining_time": "1 day, 3:54:42"}
+{"current_steps": 60, "total_steps": 666, "loss": 0.5003, "lr": 3.983319553404362e-05, "epoch": 0.26951151038742277, "percentage": 9.01, "elapsed_time": "2:45:31", "remaining_time": "1 day, 3:51:45"}
+{"current_steps": 61, "total_steps": 666, "loss": 0.494, "lr": 3.982013730500379e-05, "epoch": 0.27400336889387983, "percentage": 9.16, "elapsed_time": "2:48:11", "remaining_time": "1 day, 3:48:07"}
+{"current_steps": 62, "total_steps": 666, "loss": 0.4998, "lr": 3.9806589329450045e-05, "epoch": 0.2784952274003369, "percentage": 9.31, "elapsed_time": "2:50:48", "remaining_time": "1 day, 3:43:59"}
+{"current_steps": 63, "total_steps": 666, "loss": 0.5089, "lr": 3.979255194214665e-05, "epoch": 0.28298708590679394, "percentage": 9.46, "elapsed_time": "2:53:34", "remaining_time": "1 day, 3:41:21"}
+{"current_steps": 64, "total_steps": 666, "loss": 0.4954, "lr": 3.9778025489951015e-05, "epoch": 0.287478944413251, "percentage": 9.61, "elapsed_time": "2:56:12", "remaining_time": "1 day, 3:37:27"}
+{"current_steps": 65, "total_steps": 666, "loss": 0.4997, "lr": 3.976301033180513e-05, "epoch": 0.291970802919708, "percentage": 9.76, "elapsed_time": "2:58:50", "remaining_time": "1 day, 3:33:31"}
+{"current_steps": 66, "total_steps": 666, "loss": 0.4871, "lr": 3.974750683872667e-05, "epoch": 0.29646266142616506, "percentage": 9.91, "elapsed_time": "3:01:38", "remaining_time": "1 day, 3:31:20"}
+{"current_steps": 67, "total_steps": 666, "loss": 0.5006, "lr": 3.973151539379984e-05, "epoch": 0.3009545199326221, "percentage": 10.06, "elapsed_time": "3:04:29", "remaining_time": "1 day, 3:29:20"}
+{"current_steps": 68, "total_steps": 666, "loss": 0.4897, "lr": 3.971503639216593e-05, "epoch": 0.3054463784390792, "percentage": 10.21, "elapsed_time": "3:07:16", "remaining_time": "1 day, 3:26:57"}
+{"current_steps": 69, "total_steps": 666, "loss": 0.4958, "lr": 3.969807024101351e-05, "epoch": 0.30993823694553624, "percentage": 10.36, "elapsed_time": "3:10:01", "remaining_time": "1 day, 3:24:07"}
+{"current_steps": 70, "total_steps": 666, "loss": 0.4911, "lr": 3.9680617359568414e-05, "epoch": 0.31443009545199324, "percentage": 10.51, "elapsed_time": "3:12:46", "remaining_time": "1 day, 3:21:21"}
+{"current_steps": 71, "total_steps": 666, "loss": 0.4908, "lr": 3.966267817908335e-05, "epoch": 0.3189219539584503, "percentage": 10.66, "elapsed_time": "3:15:35", "remaining_time": "1 day, 3:19:07"}
+{"current_steps": 72, "total_steps": 666, "loss": 0.5061, "lr": 3.964425314282723e-05, "epoch": 0.32341381246490736, "percentage": 10.81, "elapsed_time": "3:18:18", "remaining_time": "1 day, 3:16:02"}
+{"current_steps": 73, "total_steps": 666, "loss": 0.4912, "lr": 3.962534270607428e-05, "epoch": 0.3279056709713644, "percentage": 10.96, "elapsed_time": "3:21:09", "remaining_time": "1 day, 3:14:03"}
+{"current_steps": 74, "total_steps": 666, "loss": 0.4928, "lr": 3.960594733609273e-05, "epoch": 0.3323975294778215, "percentage": 11.11, "elapsed_time": "3:23:55", "remaining_time": "1 day, 3:11:25"}
+{"current_steps": 75, "total_steps": 666, "loss": 0.4981, "lr": 3.958606751213327e-05, "epoch": 0.3368893879842785, "percentage": 11.26, "elapsed_time": "3:26:40", "remaining_time": "1 day, 3:08:38"}
+{"current_steps": 76, "total_steps": 666, "loss": 0.4864, "lr": 3.9565703725417266e-05, "epoch": 0.34138124649073553, "percentage": 11.41, "elapsed_time": "3:29:13", "remaining_time": "1 day, 3:04:11"}
+{"current_steps": 77, "total_steps": 666, "loss": 0.4996, "lr": 3.954485647912455e-05, "epoch": 0.3458731049971926, "percentage": 11.56, "elapsed_time": "3:31:59", "remaining_time": "1 day, 3:01:33"}
+{"current_steps": 78, "total_steps": 666, "loss": 0.4818, "lr": 3.952352628838102e-05, "epoch": 0.35036496350364965, "percentage": 11.71, "elapsed_time": "3:34:48", "remaining_time": "1 day, 2:59:22"}
+{"current_steps": 79, "total_steps": 666, "loss": 0.4952, "lr": 3.9501713680245936e-05, "epoch": 0.35485682201010665, "percentage": 11.86, "elapsed_time": "3:37:32", "remaining_time": "1 day, 2:56:22"}
+{"current_steps": 80, "total_steps": 666, "loss": 0.4978, "lr": 3.9479419193698836e-05, "epoch": 0.3593486805165637, "percentage": 12.01, "elapsed_time": "3:40:16", "remaining_time": "1 day, 2:53:29"}
+{"current_steps": 81, "total_steps": 666, "loss": 0.4992, "lr": 3.9456643379626284e-05, "epoch": 0.36384053902302077, "percentage": 12.16, "elapsed_time": "3:42:54", "remaining_time": "1 day, 2:49:52"}
+{"current_steps": 82, "total_steps": 666, "loss": 0.5003, "lr": 3.94333868008082e-05, "epoch": 0.36833239752947783, "percentage": 12.31, "elapsed_time": "3:45:33", "remaining_time": "1 day, 2:46:25"}
+{"current_steps": 83, "total_steps": 666, "loss": 0.4908, "lr": 3.940965003190401e-05, "epoch": 0.3728242560359349, "percentage": 12.46, "elapsed_time": "3:48:24", "remaining_time": "1 day, 2:44:23"}
+{"current_steps": 84, "total_steps": 666, "loss": 0.4908, "lr": 3.938543365943839e-05, "epoch": 0.3773161145423919, "percentage": 12.61, "elapsed_time": "3:51:09", "remaining_time": "1 day, 2:41:34"}
+{"current_steps": 85, "total_steps": 666, "loss": 0.4955, "lr": 3.936073828178681e-05, "epoch": 0.38180797304884895, "percentage": 12.76, "elapsed_time": "3:53:49", "remaining_time": "1 day, 2:38:13"}
+{"current_steps": 86, "total_steps": 666, "loss": 0.4786, "lr": 3.9335564509160746e-05, "epoch": 0.386299831555306, "percentage": 12.91, "elapsed_time": "3:56:23", "remaining_time": "1 day, 2:34:14"}
+{"current_steps": 87, "total_steps": 666, "loss": 0.4769, "lr": 3.930991296359258e-05, "epoch": 0.39079169006176306, "percentage": 13.06, "elapsed_time": "3:59:10", "remaining_time": "1 day, 2:31:43"}
+{"current_steps": 88, "total_steps": 666, "loss": 0.481, "lr": 3.9283784278920266e-05, "epoch": 0.3952835485682201, "percentage": 13.21, "elapsed_time": "4:02:03", "remaining_time": "1 day, 2:29:50"}
+{"current_steps": 89, "total_steps": 666, "loss": 0.4908, "lr": 3.925717910077162e-05, "epoch": 0.3997754070746771, "percentage": 13.36, "elapsed_time": "4:04:51", "remaining_time": "1 day, 2:27:29"}
+{"current_steps": 90, "total_steps": 666, "loss": 0.4881, "lr": 3.9230098086548414e-05, "epoch": 0.4042672655811342, "percentage": 13.51, "elapsed_time": "4:07:41", "remaining_time": "1 day, 2:25:14"}
+{"current_steps": 91, "total_steps": 666, "loss": 0.4888, "lr": 3.92025419054101e-05, "epoch": 0.40875912408759124, "percentage": 13.66, "elapsed_time": "4:10:22", "remaining_time": "1 day, 2:22:02"}
+{"current_steps": 92, "total_steps": 666, "loss": 0.4799, "lr": 3.9174511238257296e-05, "epoch": 0.4132509825940483, "percentage": 13.81, "elapsed_time": "4:13:06", "remaining_time": "1 day, 2:19:08"}
+{"current_steps": 93, "total_steps": 666, "loss": 0.4821, "lr": 3.914600677771495e-05, "epoch": 0.41774284110050536, "percentage": 13.96, "elapsed_time": "4:15:47", "remaining_time": "1 day, 2:16:03"}
+{"current_steps": 94, "total_steps": 666, "loss": 0.4893, "lr": 3.911702922811522e-05, "epoch": 0.42223469960696236, "percentage": 14.11, "elapsed_time": "4:18:41", "remaining_time": "1 day, 2:14:10"}
+{"current_steps": 95, "total_steps": 666, "loss": 0.4885, "lr": 3.9087579305480085e-05, "epoch": 0.4267265581134194, "percentage": 14.26, "elapsed_time": "4:21:26", "remaining_time": "1 day, 2:11:23"}
+{"current_steps": 96, "total_steps": 666, "loss": 0.47, "lr": 3.905765773750364e-05, "epoch": 0.4312184166198765, "percentage": 14.41, "elapsed_time": "4:24:03", "remaining_time": "1 day, 2:07:52"}
+{"current_steps": 97, "total_steps": 666, "loss": 0.489, "lr": 3.9027265263534124e-05, "epoch": 0.43571027512633353, "percentage": 14.56, "elapsed_time": "4:26:50", "remaining_time": "1 day, 2:05:15"}
+{"current_steps": 98, "total_steps": 666, "loss": 0.4838, "lr": 3.899640263455566e-05, "epoch": 0.4402021336327906, "percentage": 14.71, "elapsed_time": "4:29:24", "remaining_time": "1 day, 2:01:28"}
+{"current_steps": 99, "total_steps": 666, "loss": 0.4639, "lr": 3.896507061316965e-05, "epoch": 0.4446939921392476, "percentage": 14.86, "elapsed_time": "4:32:12", "remaining_time": "1 day, 1:59:01"}
+{"current_steps": 100, "total_steps": 666, "loss": 0.4737, "lr": 3.8933269973576014e-05, "epoch": 0.44918585064570465, "percentage": 15.02, "elapsed_time": "4:35:02", "remaining_time": "1 day, 1:56:43"}
+{"current_steps": 101, "total_steps": 666, "loss": 0.4868, "lr": 3.890100150155397e-05, "epoch": 0.4536777091521617, "percentage": 15.17, "elapsed_time": "4:37:50", "remaining_time": "1 day, 1:54:13"}
+{"current_steps": 102, "total_steps": 666, "loss": 0.4838, "lr": 3.8868265994442694e-05, "epoch": 0.45816956765861877, "percentage": 15.32, "elapsed_time": "4:40:32", "remaining_time": "1 day, 1:51:15"}
+{"current_steps": 103, "total_steps": 666, "loss": 0.4835, "lr": 3.883506426112157e-05, "epoch": 0.4626614261650758, "percentage": 15.47, "elapsed_time": "4:43:13", "remaining_time": "1 day, 1:48:07"}
+{"current_steps": 104, "total_steps": 666, "loss": 0.4722, "lr": 3.880139712199021e-05, "epoch": 0.46715328467153283, "percentage": 15.62, "elapsed_time": "4:45:54", "remaining_time": "1 day, 1:45:02"}
+{"current_steps": 105, "total_steps": 666, "loss": 0.4683, "lr": 3.8767265408948206e-05, "epoch": 0.4716451431779899, "percentage": 15.77, "elapsed_time": "4:48:41", "remaining_time": "1 day, 1:42:24"}
+{"current_steps": 106, "total_steps": 666, "loss": 0.4757, "lr": 3.873266996537456e-05, "epoch": 0.47613700168444695, "percentage": 15.92, "elapsed_time": "4:51:28", "remaining_time": "1 day, 1:39:49"}
+{"current_steps": 107, "total_steps": 666, "loss": 0.4746, "lr": 3.869761164610683e-05, "epoch": 0.480628860190904, "percentage": 16.07, "elapsed_time": "4:53:59", "remaining_time": "1 day, 1:35:51"}
+{"current_steps": 108, "total_steps": 666, "loss": 0.4859, "lr": 3.866209131742002e-05, "epoch": 0.485120718697361, "percentage": 16.22, "elapsed_time": "4:56:47", "remaining_time": "1 day, 1:33:25"}
+{"current_steps": 109, "total_steps": 666, "loss": 0.4859, "lr": 3.862610985700519e-05, "epoch": 0.48961257720381807, "percentage": 16.37, "elapsed_time": "4:59:29", "remaining_time": "1 day, 1:30:23"}
+{"current_steps": 110, "total_steps": 666, "loss": 0.4796, "lr": 3.8589668153947743e-05, "epoch": 0.4941044357102751, "percentage": 16.52, "elapsed_time": "5:02:13", "remaining_time": "1 day, 1:27:35"}
+{"current_steps": 111, "total_steps": 666, "loss": 0.4808, "lr": 3.855276710870547e-05, "epoch": 0.4985962942167322, "percentage": 16.67, "elapsed_time": "5:04:57", "remaining_time": "1 day, 1:24:46"}
+{"current_steps": 112, "total_steps": 666, "loss": 0.4708, "lr": 3.851540763308629e-05, "epoch": 0.5030881527231892, "percentage": 16.82, "elapsed_time": "5:07:39", "remaining_time": "1 day, 1:21:49"}
+{"current_steps": 113, "total_steps": 666, "loss": 0.4868, "lr": 3.8477590650225735e-05, "epoch": 0.5075800112296462, "percentage": 16.97, "elapsed_time": "5:10:29", "remaining_time": "1 day, 1:19:30"}
+{"current_steps": 114, "total_steps": 666, "loss": 0.4814, "lr": 3.843931709456414e-05, "epoch": 0.5120718697361033, "percentage": 17.12, "elapsed_time": "5:13:19", "remaining_time": "1 day, 1:17:11"}
+{"current_steps": 115, "total_steps": 666, "loss": 0.4688, "lr": 3.840058791182352e-05, "epoch": 0.5165637282425604, "percentage": 17.27, "elapsed_time": "5:15:52", "remaining_time": "1 day, 1:13:27"}
+{"current_steps": 116, "total_steps": 666, "loss": 0.4891, "lr": 3.8361404058984236e-05, "epoch": 0.5210555867490174, "percentage": 17.42, "elapsed_time": "5:18:37", "remaining_time": "1 day, 1:10:41"}
+{"current_steps": 117, "total_steps": 666, "loss": 0.4748, "lr": 3.8321766504261356e-05, "epoch": 0.5255474452554745, "percentage": 17.57, "elapsed_time": "5:21:20", "remaining_time": "1 day, 1:07:50"}
+{"current_steps": 118, "total_steps": 666, "loss": 0.4813, "lr": 3.8281676227080694e-05, "epoch": 0.5300393037619315, "percentage": 17.72, "elapsed_time": "5:24:07", "remaining_time": "1 day, 1:05:16"}
+{"current_steps": 119, "total_steps": 666, "loss": 0.4742, "lr": 3.824113421805464e-05, "epoch": 0.5345311622683886, "percentage": 17.87, "elapsed_time": "5:26:42", "remaining_time": "1 day, 1:01:47"}
+{"current_steps": 120, "total_steps": 666, "loss": 0.4748, "lr": 3.8200141478957666e-05, "epoch": 0.5390230207748455, "percentage": 18.02, "elapsed_time": "5:29:16", "remaining_time": "1 day, 0:58:10"}
+{"current_steps": 121, "total_steps": 666, "loss": 0.4822, "lr": 3.815869902270157e-05, "epoch": 0.5435148792813026, "percentage": 18.17, "elapsed_time": "5:32:06", "remaining_time": "1 day, 0:55:52"}
+{"current_steps": 122, "total_steps": 666, "loss": 0.4744, "lr": 3.811680787331047e-05, "epoch": 0.5480067377877597, "percentage": 18.32, "elapsed_time": "5:34:50", "remaining_time": "1 day, 0:53:04"}
+{"current_steps": 123, "total_steps": 666, "loss": 0.4581, "lr": 3.8074469065895475e-05, "epoch": 0.5524985962942167, "percentage": 18.47, "elapsed_time": "5:37:42", "remaining_time": "1 day, 0:50:49"}
+{"current_steps": 124, "total_steps": 666, "loss": 0.4854, "lr": 3.803168364662912e-05, "epoch": 0.5569904548006738, "percentage": 18.62, "elapsed_time": "5:40:19", "remaining_time": "1 day, 0:47:34"}
+{"current_steps": 125, "total_steps": 666, "loss": 0.4865, "lr": 3.798845267271952e-05, "epoch": 0.5614823133071308, "percentage": 18.77, "elapsed_time": "5:43:09", "remaining_time": "1 day, 0:45:12"}
+{"current_steps": 126, "total_steps": 666, "loss": 0.4647, "lr": 3.794477721238425e-05, "epoch": 0.5659741718135879, "percentage": 18.92, "elapsed_time": "5:45:44", "remaining_time": "1 day, 0:41:44"}
+{"current_steps": 127, "total_steps": 666, "loss": 0.4672, "lr": 3.790065834482391e-05, "epoch": 0.570466030320045, "percentage": 19.07, "elapsed_time": "5:48:33", "remaining_time": "1 day, 0:39:17"}
+{"current_steps": 128, "total_steps": 666, "loss": 0.4719, "lr": 3.7856097160195516e-05, "epoch": 0.574957888826502, "percentage": 19.22, "elapsed_time": "5:51:14", "remaining_time": "1 day, 0:36:19"}
+{"current_steps": 129, "total_steps": 666, "loss": 0.4776, "lr": 3.781109475958552e-05, "epoch": 0.5794497473329591, "percentage": 19.37, "elapsed_time": "5:54:00", "remaining_time": "1 day, 0:33:38"}
+{"current_steps": 130, "total_steps": 666, "loss": 0.4628, "lr": 3.776565225498264e-05, "epoch": 0.583941605839416, "percentage": 19.52, "elapsed_time": "5:56:39", "remaining_time": "1 day, 0:30:30"}
+{"current_steps": 131, "total_steps": 666, "loss": 0.477, "lr": 3.771977076925034e-05, "epoch": 0.5884334643458731, "percentage": 19.67, "elapsed_time": "5:59:30", "remaining_time": "1 day, 0:28:14"}
+{"current_steps": 132, "total_steps": 666, "loss": 0.46, "lr": 3.7673451436099125e-05, "epoch": 0.5929253228523301, "percentage": 19.82, "elapsed_time": "6:02:12", "remaining_time": "1 day, 0:25:18"}
+{"current_steps": 133, "total_steps": 666, "loss": 0.4659, "lr": 3.762669540005849e-05, "epoch": 0.5974171813587872, "percentage": 19.97, "elapsed_time": "6:04:55", "remaining_time": "1 day, 0:22:28"}
+{"current_steps": 134, "total_steps": 666, "loss": 0.4726, "lr": 3.757950381644868e-05, "epoch": 0.6019090398652442, "percentage": 20.12, "elapsed_time": "6:07:29", "remaining_time": "1 day, 0:18:58"}
+{"current_steps": 135, "total_steps": 666, "loss": 0.4731, "lr": 3.753187785135209e-05, "epoch": 0.6064008983717013, "percentage": 20.27, "elapsed_time": "6:10:18", "remaining_time": "1 day, 0:16:32"}
+{"current_steps": 136, "total_steps": 666, "loss": 0.4768, "lr": 3.748381868158452e-05, "epoch": 0.6108927568781584, "percentage": 20.42, "elapsed_time": "6:13:12", "remaining_time": "1 day, 0:14:24"}
+{"current_steps": 137, "total_steps": 666, "loss": 0.4708, "lr": 3.743532749466604e-05, "epoch": 0.6153846153846154, "percentage": 20.57, "elapsed_time": "6:15:57", "remaining_time": "1 day, 0:11:40"}
+{"current_steps": 138, "total_steps": 666, "loss": 0.467, "lr": 3.738640548879166e-05, "epoch": 0.6198764738910725, "percentage": 20.72, "elapsed_time": "6:18:38", "remaining_time": "1 day, 0:08:43"}
+{"current_steps": 139, "total_steps": 666, "loss": 0.4716, "lr": 3.7337053872801726e-05, "epoch": 0.6243683323975294, "percentage": 20.87, "elapsed_time": "6:21:26", "remaining_time": "1 day, 0:06:11"}
+{"current_steps": 140, "total_steps": 666, "loss": 0.4644, "lr": 3.728727386615208e-05, "epoch": 0.6288601909039865, "percentage": 21.02, "elapsed_time": "6:24:14", "remaining_time": "1 day, 0:03:38"}
+{"current_steps": 141, "total_steps": 666, "loss": 0.4757, "lr": 3.723706669888388e-05, "epoch": 0.6333520494104435, "percentage": 21.17, "elapsed_time": "6:27:10", "remaining_time": "1 day, 0:01:34"}
+{"current_steps": 142, "total_steps": 666, "loss": 0.4665, "lr": 3.7186433611593225e-05, "epoch": 0.6378439079169006, "percentage": 21.32, "elapsed_time": "6:29:49", "remaining_time": "23:58:31"}
+{"current_steps": 143, "total_steps": 666, "loss": 0.4589, "lr": 3.713537585540051e-05, "epoch": 0.6423357664233577, "percentage": 21.47, "elapsed_time": "6:32:35", "remaining_time": "23:55:51"}
+{"current_steps": 144, "total_steps": 666, "loss": 0.4605, "lr": 3.7083894691919506e-05, "epoch": 0.6468276249298147, "percentage": 21.62, "elapsed_time": "6:35:04", "remaining_time": "23:52:09"}
+{"current_steps": 145, "total_steps": 666, "loss": 0.4766, "lr": 3.703199139322619e-05, "epoch": 0.6513194834362718, "percentage": 21.77, "elapsed_time": "6:37:54", "remaining_time": "23:49:44"}
+{"current_steps": 146, "total_steps": 666, "loss": 0.4701, "lr": 3.697966724182729e-05, "epoch": 0.6558113419427288, "percentage": 21.92, "elapsed_time": "6:40:30", "remaining_time": "23:46:28"}
+{"current_steps": 147, "total_steps": 666, "loss": 0.4686, "lr": 3.6926923530628604e-05, "epoch": 0.6603032004491859, "percentage": 22.07, "elapsed_time": "6:42:58", "remaining_time": "23:42:45"}
+{"current_steps": 148, "total_steps": 666, "loss": 0.4672, "lr": 3.687376156290309e-05, "epoch": 0.664795058955643, "percentage": 22.22, "elapsed_time": "6:45:41", "remaining_time": "23:39:56"}
+{"current_steps": 149, "total_steps": 666, "loss": 0.4702, "lr": 3.682018265225862e-05, "epoch": 0.6692869174620999, "percentage": 22.37, "elapsed_time": "6:48:24", "remaining_time": "23:37:04"}
+{"current_steps": 150, "total_steps": 666, "loss": 0.4636, "lr": 3.676618812260553e-05, "epoch": 0.673778775968557, "percentage": 22.52, "elapsed_time": "6:51:12", "remaining_time": "23:34:33"}
+{"current_steps": 151, "total_steps": 666, "loss": 0.4785, "lr": 3.671177930812392e-05, "epoch": 0.678270634475014, "percentage": 22.67, "elapsed_time": "6:54:02", "remaining_time": "23:32:07"}
+{"current_steps": 152, "total_steps": 666, "loss": 0.4851, "lr": 3.665695755323067e-05, "epoch": 0.6827624929814711, "percentage": 22.82, "elapsed_time": "6:56:45", "remaining_time": "23:29:19"}
+{"current_steps": 153, "total_steps": 666, "loss": 0.4717, "lr": 3.6601724212546226e-05, "epoch": 0.6872543514879281, "percentage": 22.97, "elapsed_time": "6:59:34", "remaining_time": "23:26:47"}
+{"current_steps": 154, "total_steps": 666, "loss": 0.4656, "lr": 3.654608065086115e-05, "epoch": 0.6917462099943852, "percentage": 23.12, "elapsed_time": "7:02:12", "remaining_time": "23:23:42"}
+{"current_steps": 155, "total_steps": 666, "loss": 0.4707, "lr": 3.649002824310235e-05, "epoch": 0.6962380685008422, "percentage": 23.27, "elapsed_time": "7:04:59", "remaining_time": "23:21:05"}
+{"current_steps": 156, "total_steps": 666, "loss": 0.4682, "lr": 3.643356837429914e-05, "epoch": 0.7007299270072993, "percentage": 23.42, "elapsed_time": "7:07:49", "remaining_time": "23:18:40"}
+{"current_steps": 157, "total_steps": 666, "loss": 0.4609, "lr": 3.637670243954904e-05, "epoch": 0.7052217855137564, "percentage": 23.57, "elapsed_time": "7:10:27", "remaining_time": "23:15:33"}
+{"current_steps": 158, "total_steps": 666, "loss": 0.4666, "lr": 3.6319431843983223e-05, "epoch": 0.7097136440202133, "percentage": 23.72, "elapsed_time": "7:13:07", "remaining_time": "23:12:34"}
+{"current_steps": 159, "total_steps": 666, "loss": 0.4797, "lr": 3.626175800273189e-05, "epoch": 0.7142055025266704, "percentage": 23.87, "elapsed_time": "7:15:55", "remaining_time": "23:10:01"}
+{"current_steps": 160, "total_steps": 666, "loss": 0.4731, "lr": 3.6203682340889234e-05, "epoch": 0.7186973610331274, "percentage": 24.02, "elapsed_time": "7:18:34", "remaining_time": "23:06:59"}
+{"current_steps": 161, "total_steps": 666, "loss": 0.4623, "lr": 3.614520629347825e-05, "epoch": 0.7231892195395845, "percentage": 24.17, "elapsed_time": "7:21:17", "remaining_time": "23:04:11"}
+{"current_steps": 162, "total_steps": 666, "loss": 0.4645, "lr": 3.60863313054153e-05, "epoch": 0.7276810780460415, "percentage": 24.32, "elapsed_time": "7:24:05", "remaining_time": "23:01:38"}
+{"current_steps": 163, "total_steps": 666, "loss": 0.4484, "lr": 3.602705883147436e-05, "epoch": 0.7321729365524986, "percentage": 24.47, "elapsed_time": "7:26:54", "remaining_time": "22:59:06"}
+{"current_steps": 164, "total_steps": 666, "loss": 0.4541, "lr": 3.5967390336251104e-05, "epoch": 0.7366647950589557, "percentage": 24.62, "elapsed_time": "7:29:47", "remaining_time": "22:56:48"}
+{"current_steps": 165, "total_steps": 666, "loss": 0.4703, "lr": 3.590732729412673e-05, "epoch": 0.7411566535654127, "percentage": 24.77, "elapsed_time": "7:32:38", "remaining_time": "22:54:24"}
+{"current_steps": 166, "total_steps": 666, "loss": 0.4704, "lr": 3.584687118923149e-05, "epoch": 0.7456485120718698, "percentage": 24.92, "elapsed_time": "7:35:23", "remaining_time": "22:51:41"}
+{"current_steps": 167, "total_steps": 666, "loss": 0.4749, "lr": 3.5786023515408045e-05, "epoch": 0.7501403705783268, "percentage": 25.08, "elapsed_time": "7:38:08", "remaining_time": "22:48:56"}
+{"current_steps": 168, "total_steps": 666, "loss": 0.4592, "lr": 3.572478577617454e-05, "epoch": 0.7546322290847838, "percentage": 25.23, "elapsed_time": "7:40:50", "remaining_time": "22:46:04"}
+{"current_steps": 169, "total_steps": 666, "loss": 0.4643, "lr": 3.566315948468746e-05, "epoch": 0.7591240875912408, "percentage": 25.38, "elapsed_time": "7:43:43", "remaining_time": "22:43:43"}
+{"current_steps": 170, "total_steps": 666, "loss": 0.4635, "lr": 3.560114616370425e-05, "epoch": 0.7636159460976979, "percentage": 25.53, "elapsed_time": "7:46:27", "remaining_time": "22:40:56"}
+{"current_steps": 171, "total_steps": 666, "loss": 0.471, "lr": 3.553874734554565e-05, "epoch": 0.768107804604155, "percentage": 25.68, "elapsed_time": "7:49:14", "remaining_time": "22:38:20"}
+{"current_steps": 172, "total_steps": 666, "loss": 0.4616, "lr": 3.5475964572057876e-05, "epoch": 0.772599663110612, "percentage": 25.83, "elapsed_time": "7:52:04", "remaining_time": "22:35:50"}
+{"current_steps": 173, "total_steps": 666, "loss": 0.4521, "lr": 3.541279939457452e-05, "epoch": 0.7770915216170691, "percentage": 25.98, "elapsed_time": "7:54:50", "remaining_time": "22:33:11"}
+{"current_steps": 174, "total_steps": 666, "loss": 0.4666, "lr": 3.534925337387816e-05, "epoch": 0.7815833801235261, "percentage": 26.13, "elapsed_time": "7:57:33", "remaining_time": "22:30:20"}
+{"current_steps": 175, "total_steps": 666, "loss": 0.4701, "lr": 3.528532808016188e-05, "epoch": 0.7860752386299832, "percentage": 26.28, "elapsed_time": "8:00:19", "remaining_time": "22:27:38"}
+{"current_steps": 176, "total_steps": 666, "loss": 0.4692, "lr": 3.522102509299039e-05, "epoch": 0.7905670971364402, "percentage": 26.43, "elapsed_time": "8:03:07", "remaining_time": "22:25:04"}
+{"current_steps": 177, "total_steps": 666, "loss": 0.4497, "lr": 3.5156346001261056e-05, "epoch": 0.7950589556428973, "percentage": 26.58, "elapsed_time": "8:05:59", "remaining_time": "22:22:39"}
+{"current_steps": 178, "total_steps": 666, "loss": 0.4575, "lr": 3.509129240316461e-05, "epoch": 0.7995508141493542, "percentage": 26.73, "elapsed_time": "8:08:45", "remaining_time": "22:19:58"}
+{"current_steps": 179, "total_steps": 666, "loss": 0.4612, "lr": 3.502586590614565e-05, "epoch": 0.8040426726558113, "percentage": 26.88, "elapsed_time": "8:11:41", "remaining_time": "22:17:43"}
+{"current_steps": 180, "total_steps": 666, "loss": 0.4668, "lr": 3.496006812686296e-05, "epoch": 0.8085345311622684, "percentage": 27.03, "elapsed_time": "8:14:32", "remaining_time": "22:15:16"}
+{"current_steps": 181, "total_steps": 666, "loss": 0.4754, "lr": 3.4893900691149525e-05, "epoch": 0.8130263896687254, "percentage": 27.18, "elapsed_time": "8:17:20", "remaining_time": "22:12:40"}
+{"current_steps": 182, "total_steps": 666, "loss": 0.4581, "lr": 3.482736523397237e-05, "epoch": 0.8175182481751825, "percentage": 27.33, "elapsed_time": "8:20:09", "remaining_time": "22:10:06"}
+{"current_steps": 183, "total_steps": 666, "loss": 0.4639, "lr": 3.476046339939216e-05, "epoch": 0.8220101066816395, "percentage": 27.48, "elapsed_time": "8:22:48", "remaining_time": "22:07:03"}
+{"current_steps": 184, "total_steps": 666, "loss": 0.4558, "lr": 3.469319684052259e-05, "epoch": 0.8265019651880966, "percentage": 27.63, "elapsed_time": "8:25:33", "remaining_time": "22:04:19"}
+{"current_steps": 185, "total_steps": 666, "loss": 0.4552, "lr": 3.4625567219489505e-05, "epoch": 0.8309938236945537, "percentage": 27.78, "elapsed_time": "8:28:14", "remaining_time": "22:01:26"}
+{"current_steps": 186, "total_steps": 666, "loss": 0.4601, "lr": 3.455757620738989e-05, "epoch": 0.8354856822010107, "percentage": 27.93, "elapsed_time": "8:30:56", "remaining_time": "21:58:34"}
+{"current_steps": 187, "total_steps": 666, "loss": 0.4624, "lr": 3.4489225484250474e-05, "epoch": 0.8399775407074677, "percentage": 28.08, "elapsed_time": "8:33:45", "remaining_time": "21:56:00"}
+{"current_steps": 188, "total_steps": 666, "loss": 0.4537, "lr": 3.442051673898634e-05, "epoch": 0.8444693992139247, "percentage": 28.23, "elapsed_time": "8:36:28", "remaining_time": "21:53:10"}
+{"current_steps": 189, "total_steps": 666, "loss": 0.4544, "lr": 3.4351451669359103e-05, "epoch": 0.8489612577203818, "percentage": 28.38, "elapsed_time": "8:39:11", "remaining_time": "21:50:21"}
+{"current_steps": 190, "total_steps": 666, "loss": 0.4692, "lr": 3.4282031981935e-05, "epoch": 0.8534531162268388, "percentage": 28.53, "elapsed_time": "8:41:57", "remaining_time": "21:47:37"}
+{"current_steps": 191, "total_steps": 666, "loss": 0.4703, "lr": 3.421225939204271e-05, "epoch": 0.8579449747332959, "percentage": 28.68, "elapsed_time": "8:44:41", "remaining_time": "21:44:52"}
+{"current_steps": 192, "total_steps": 666, "loss": 0.4664, "lr": 3.4142135623730954e-05, "epoch": 0.862436833239753, "percentage": 28.83, "elapsed_time": "8:47:32", "remaining_time": "21:42:22"}
+{"current_steps": 193, "total_steps": 666, "loss": 0.4618, "lr": 3.407166240972594e-05, "epoch": 0.86692869174621, "percentage": 28.98, "elapsed_time": "8:50:19", "remaining_time": "21:39:41"}
+{"current_steps": 194, "total_steps": 666, "loss": 0.4733, "lr": 3.400084149138851e-05, "epoch": 0.8714205502526671, "percentage": 29.13, "elapsed_time": "8:53:10", "remaining_time": "21:37:12"}
+{"current_steps": 195, "total_steps": 666, "loss": 0.4489, "lr": 3.3929674618671107e-05, "epoch": 0.8759124087591241, "percentage": 29.28, "elapsed_time": "8:56:00", "remaining_time": "21:34:40"}
+{"current_steps": 196, "total_steps": 666, "loss": 0.4524, "lr": 3.385816355007455e-05, "epoch": 0.8804042672655812, "percentage": 29.43, "elapsed_time": "8:58:59", "remaining_time": "21:32:28"}
+{"current_steps": 197, "total_steps": 666, "loss": 0.4606, "lr": 3.37863100526046e-05, "epoch": 0.8848961257720381, "percentage": 29.58, "elapsed_time": "9:01:38", "remaining_time": "21:29:29"}
+{"current_steps": 198, "total_steps": 666, "loss": 0.4691, "lr": 3.371411590172827e-05, "epoch": 0.8893879842784952, "percentage": 29.73, "elapsed_time": "9:04:20", "remaining_time": "21:26:36"}
+{"current_steps": 199, "total_steps": 666, "loss": 0.4587, "lr": 3.364158288132994e-05, "epoch": 0.8938798427849522, "percentage": 29.88, "elapsed_time": "9:07:11", "remaining_time": "21:24:06"}
+{"current_steps": 200, "total_steps": 666, "loss": 0.446, "lr": 3.356871278366733e-05, "epoch": 0.8983717012914093, "percentage": 30.03, "elapsed_time": "9:10:02", "remaining_time": "21:21:35"}
+{"current_steps": 201, "total_steps": 666, "loss": 0.4582, "lr": 3.349550740932717e-05, "epoch": 0.9028635597978664, "percentage": 30.18, "elapsed_time": "9:12:45", "remaining_time": "21:18:46"}
+{"current_steps": 202, "total_steps": 666, "loss": 0.4738, "lr": 3.342196856718074e-05, "epoch": 0.9073554183043234, "percentage": 30.33, "elapsed_time": "9:15:32", "remaining_time": "21:16:04"}
+{"current_steps": 203, "total_steps": 666, "loss": 0.4524, "lr": 3.334809807433913e-05, "epoch": 0.9118472768107805, "percentage": 30.48, "elapsed_time": "9:18:18", "remaining_time": "21:13:22"}
+{"current_steps": 204, "total_steps": 666, "loss": 0.4531, "lr": 3.3273897756108384e-05, "epoch": 0.9163391353172375, "percentage": 30.63, "elapsed_time": "9:21:04", "remaining_time": "21:10:41"}
+{"current_steps": 205, "total_steps": 666, "loss": 0.463, "lr": 3.3199369445944376e-05, "epoch": 0.9208309938236946, "percentage": 30.78, "elapsed_time": "9:23:46", "remaining_time": "21:07:47"}
+{"current_steps": 206, "total_steps": 666, "loss": 0.4676, "lr": 3.312451498540751e-05, "epoch": 0.9253228523301515, "percentage": 30.93, "elapsed_time": "9:26:26", "remaining_time": "21:04:51"}
+{"current_steps": 207, "total_steps": 666, "loss": 0.456, "lr": 3.3049336224117234e-05, "epoch": 0.9298147108366086, "percentage": 31.08, "elapsed_time": "9:29:11", "remaining_time": "21:02:06"}
+{"current_steps": 208, "total_steps": 666, "loss": 0.4542, "lr": 3.297383501970628e-05, "epoch": 0.9343065693430657, "percentage": 31.23, "elapsed_time": "9:31:50", "remaining_time": "20:59:08"}
+{"current_steps": 209, "total_steps": 666, "loss": 0.4637, "lr": 3.289801323777484e-05, "epoch": 0.9387984278495227, "percentage": 31.38, "elapsed_time": "9:34:39", "remaining_time": "20:56:32"}
+{"current_steps": 210, "total_steps": 666, "loss": 0.4671, "lr": 3.28218727518444e-05, "epoch": 0.9432902863559798, "percentage": 31.53, "elapsed_time": "9:37:25", "remaining_time": "20:53:50"}
+{"current_steps": 211, "total_steps": 666, "loss": 0.4572, "lr": 3.274541544331151e-05, "epoch": 0.9477821448624368, "percentage": 31.68, "elapsed_time": "9:40:15", "remaining_time": "20:51:16"}
+{"current_steps": 212, "total_steps": 666, "loss": 0.4507, "lr": 3.2668643201401225e-05, "epoch": 0.9522740033688939, "percentage": 31.83, "elapsed_time": "9:43:03", "remaining_time": "20:48:36"}
+{"current_steps": 213, "total_steps": 666, "loss": 0.4503, "lr": 3.2591557923120484e-05, "epoch": 0.956765861875351, "percentage": 31.98, "elapsed_time": "9:45:39", "remaining_time": "20:45:32"}
+{"current_steps": 214, "total_steps": 666, "loss": 0.4608, "lr": 3.25141615132112e-05, "epoch": 0.961257720381808, "percentage": 32.13, "elapsed_time": "9:48:17", "remaining_time": "20:42:34"}
+{"current_steps": 215, "total_steps": 666, "loss": 0.4394, "lr": 3.243645588410321e-05, "epoch": 0.9657495788882651, "percentage": 32.28, "elapsed_time": "9:50:59", "remaining_time": "20:39:42"}
+{"current_steps": 216, "total_steps": 666, "loss": 0.4554, "lr": 3.235844295586702e-05, "epoch": 0.970241437394722, "percentage": 32.43, "elapsed_time": "9:53:33", "remaining_time": "20:36:35"}
+{"current_steps": 217, "total_steps": 666, "loss": 0.451, "lr": 3.228012465616634e-05, "epoch": 0.9747332959011791, "percentage": 32.58, "elapsed_time": "9:56:09", "remaining_time": "20:33:31"}
+{"current_steps": 218, "total_steps": 666, "loss": 0.4581, "lr": 3.220150292021049e-05, "epoch": 0.9792251544076361, "percentage": 32.73, "elapsed_time": "9:59:01", "remaining_time": "20:31:01"}
+{"current_steps": 219, "total_steps": 666, "loss": 0.4571, "lr": 3.212257969070655e-05, "epoch": 0.9837170129140932, "percentage": 32.88, "elapsed_time": "10:01:42", "remaining_time": "20:28:07"}
+{"current_steps": 220, "total_steps": 666, "loss": 0.4708, "lr": 3.204335691781137e-05, "epoch": 0.9882088714205502, "percentage": 33.03, "elapsed_time": "10:04:22", "remaining_time": "20:25:14"}
+{"current_steps": 221, "total_steps": 666, "loss": 0.4584, "lr": 3.196383655908338e-05, "epoch": 0.9927007299270073, "percentage": 33.18, "elapsed_time": "10:07:06", "remaining_time": "20:22:26"}
+{"current_steps": 222, "total_steps": 666, "loss": 0.4564, "lr": 3.1884020579434216e-05, "epoch": 0.9971925884334644, "percentage": 33.33, "elapsed_time": "10:09:52", "remaining_time": "20:19:45"}
+{"current_steps": 223, "total_steps": 666, "loss": 0.7341, "lr": 3.1803910951080174e-05, "epoch": 1.0030881527231892, "percentage": 33.48, "elapsed_time": "10:13:23", "remaining_time": "20:18:31"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbdbf8301c16976d00005a816f28b1b58dee226529e8f3f35ffee086b6dd47a0
+size 7224