Training in progress, epoch 1

.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 sha256:88de78996f27988485fc3f6015b58d56ab73cbc9cbd835afb99fa064865e9d9b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7763bf6c4d56f97937584155c20c2ce83d20f5c99855f1d0c9f6d37b00ef71b5
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebcee76a59abe9997eeabfd2673b6b0c7786aa7035ea83d6994e0ba1869aa73
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f648462337060ee436957f67961ebbdbc056bb15ff520cb4becf52f3a181ecb
+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 +1,331 @@
+{"current_steps": 1, "total_steps": 939, "loss": 0.9383, "lr": 2.1276595744680852e-07, "epoch": 0.003194888178913738, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:54:23"}
+{"current_steps": 2, "total_steps": 939, "loss": 0.8501, "lr": 4.2553191489361704e-07, "epoch": 0.006389776357827476, "percentage": 0.21, "elapsed_time": "0:00:29", "remaining_time": "3:49:37"}
+{"current_steps": 3, "total_steps": 939, "loss": 0.8872, "lr": 6.382978723404255e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:29:57"}
+{"current_steps": 4, "total_steps": 939, "loss": 0.8123, "lr": 8.510638297872341e-07, "epoch": 0.012779552715654952, "percentage": 0.43, "elapsed_time": "0:00:52", "remaining_time": "3:26:21"}
+{"current_steps": 5, "total_steps": 939, "loss": 0.8867, "lr": 1.0638297872340427e-06, "epoch": 0.01597444089456869, "percentage": 0.53, "elapsed_time": "0:01:04", "remaining_time": "3:21:49"}
+{"current_steps": 6, "total_steps": 939, "loss": 0.848, "lr": 1.276595744680851e-06, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:15", "remaining_time": "3:15:12"}
+{"current_steps": 7, "total_steps": 939, "loss": 0.8766, "lr": 1.4893617021276596e-06, "epoch": 0.022364217252396165, "percentage": 0.75, "elapsed_time": "0:01:26", "remaining_time": "3:12:50"}
+{"current_steps": 8, "total_steps": 939, "loss": 0.8249, "lr": 1.7021276595744682e-06, "epoch": 0.025559105431309903, "percentage": 0.85, "elapsed_time": "0:01:37", "remaining_time": "3:08:34"}
+{"current_steps": 9, "total_steps": 939, "loss": 0.8056, "lr": 1.9148936170212767e-06, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:49", "remaining_time": "3:08:04"}
+{"current_steps": 10, "total_steps": 939, "loss": 0.7646, "lr": 2.1276595744680853e-06, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:02:00", "remaining_time": "3:06:38"}
+{"current_steps": 11, "total_steps": 939, "loss": 0.7915, "lr": 2.340425531914894e-06, "epoch": 0.03514376996805112, "percentage": 1.17, "elapsed_time": "0:02:12", "remaining_time": "3:06:28"}
+{"current_steps": 12, "total_steps": 939, "loss": 0.8249, "lr": 2.553191489361702e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:24", "remaining_time": "3:06:00"}
+{"current_steps": 13, "total_steps": 939, "loss": 0.767, "lr": 2.765957446808511e-06, "epoch": 0.04153354632587859, "percentage": 1.38, "elapsed_time": "0:02:31", "remaining_time": "3:00:23"}
+{"current_steps": 14, "total_steps": 939, "loss": 0.7684, "lr": 2.978723404255319e-06, "epoch": 0.04472843450479233, "percentage": 1.49, "elapsed_time": "0:02:41", "remaining_time": "2:57:29"}
+{"current_steps": 15, "total_steps": 939, "loss": 0.7301, "lr": 3.191489361702128e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:52", "remaining_time": "2:56:49"}
+{"current_steps": 16, "total_steps": 939, "loss": 0.7483, "lr": 3.4042553191489363e-06, "epoch": 0.051118210862619806, "percentage": 1.7, "elapsed_time": "0:03:01", "remaining_time": "2:54:33"}
+{"current_steps": 17, "total_steps": 939, "loss": 0.7003, "lr": 3.6170212765957453e-06, "epoch": 0.054313099041533544, "percentage": 1.81, "elapsed_time": "0:03:12", "remaining_time": "2:54:17"}
+{"current_steps": 18, "total_steps": 939, "loss": 0.7508, "lr": 3.8297872340425535e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:24", "remaining_time": "2:54:44"}
+{"current_steps": 19, "total_steps": 939, "loss": 0.7397, "lr": 4.042553191489362e-06, "epoch": 0.06070287539936102, "percentage": 2.02, "elapsed_time": "0:03:37", "remaining_time": "2:55:17"}
+{"current_steps": 20, "total_steps": 939, "loss": 0.669, "lr": 4.255319148936171e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:03:46", "remaining_time": "2:53:46"}
+{"current_steps": 21, "total_steps": 939, "loss": 0.6473, "lr": 4.468085106382979e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:58", "remaining_time": "2:53:35"}
+{"current_steps": 22, "total_steps": 939, "loss": 0.5916, "lr": 4.680851063829788e-06, "epoch": 0.07028753993610223, "percentage": 2.34, "elapsed_time": "0:04:07", "remaining_time": "2:51:54"}
+{"current_steps": 23, "total_steps": 939, "loss": 0.7035, "lr": 4.893617021276596e-06, "epoch": 0.07348242811501597, "percentage": 2.45, "elapsed_time": "0:04:18", "remaining_time": "2:51:43"}
+{"current_steps": 24, "total_steps": 939, "loss": 0.6841, "lr": 5.106382978723404e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:27", "remaining_time": "2:49:48"}
+{"current_steps": 25, "total_steps": 939, "loss": 0.608, "lr": 5.319148936170213e-06, "epoch": 0.07987220447284345, "percentage": 2.66, "elapsed_time": "0:04:37", "remaining_time": "2:49:12"}
+{"current_steps": 26, "total_steps": 939, "loss": 0.6812, "lr": 5.531914893617022e-06, "epoch": 0.08306709265175719, "percentage": 2.77, "elapsed_time": "0:04:49", "remaining_time": "2:49:30"}
+{"current_steps": 27, "total_steps": 939, "loss": 0.6243, "lr": 5.744680851063831e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:05:00", "remaining_time": "2:49:17"}
+{"current_steps": 28, "total_steps": 939, "loss": 0.6559, "lr": 5.957446808510638e-06, "epoch": 0.08945686900958466, "percentage": 2.98, "elapsed_time": "0:05:13", "remaining_time": "2:49:47"}
+{"current_steps": 29, "total_steps": 939, "loss": 0.6615, "lr": 6.170212765957447e-06, "epoch": 0.0926517571884984, "percentage": 3.09, "elapsed_time": "0:05:21", "remaining_time": "2:48:18"}
+{"current_steps": 30, "total_steps": 939, "loss": 0.6502, "lr": 6.382978723404256e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:05:31", "remaining_time": "2:47:36"}
+{"current_steps": 31, "total_steps": 939, "loss": 0.6197, "lr": 6.595744680851064e-06, "epoch": 0.09904153354632587, "percentage": 3.3, "elapsed_time": "0:05:43", "remaining_time": "2:47:40"}
+{"current_steps": 32, "total_steps": 939, "loss": 0.648, "lr": 6.808510638297873e-06, "epoch": 0.10223642172523961, "percentage": 3.41, "elapsed_time": "0:05:54", "remaining_time": "2:47:34"}
+{"current_steps": 33, "total_steps": 939, "loss": 0.5946, "lr": 7.021276595744682e-06, "epoch": 0.10543130990415335, "percentage": 3.51, "elapsed_time": "0:06:03", "remaining_time": "2:46:29"}
+{"current_steps": 34, "total_steps": 939, "loss": 0.6183, "lr": 7.234042553191491e-06, "epoch": 0.10862619808306709, "percentage": 3.62, "elapsed_time": "0:06:15", "remaining_time": "2:46:34"}
+{"current_steps": 35, "total_steps": 939, "loss": 0.6104, "lr": 7.446808510638298e-06, "epoch": 0.11182108626198083, "percentage": 3.73, "elapsed_time": "0:06:26", "remaining_time": "2:46:22"}
+{"current_steps": 36, "total_steps": 939, "loss": 0.5497, "lr": 7.659574468085107e-06, "epoch": 0.11501597444089456, "percentage": 3.83, "elapsed_time": "0:06:38", "remaining_time": "2:46:47"}
+{"current_steps": 37, "total_steps": 939, "loss": 0.6082, "lr": 7.872340425531916e-06, "epoch": 0.1182108626198083, "percentage": 3.94, "elapsed_time": "0:06:51", "remaining_time": "2:47:10"}
+{"current_steps": 38, "total_steps": 939, "loss": 0.607, "lr": 8.085106382978723e-06, "epoch": 0.12140575079872204, "percentage": 4.05, "elapsed_time": "0:07:01", "remaining_time": "2:46:38"}
+{"current_steps": 39, "total_steps": 939, "loss": 0.5706, "lr": 8.297872340425532e-06, "epoch": 0.12460063897763578, "percentage": 4.15, "elapsed_time": "0:07:14", "remaining_time": "2:46:58"}
+{"current_steps": 40, "total_steps": 939, "loss": 0.5445, "lr": 8.510638297872341e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:07:24", "remaining_time": "2:46:40"}
+{"current_steps": 41, "total_steps": 939, "loss": 0.5692, "lr": 8.72340425531915e-06, "epoch": 0.13099041533546327, "percentage": 4.37, "elapsed_time": "0:07:37", "remaining_time": "2:46:54"}
+{"current_steps": 42, "total_steps": 939, "loss": 0.5916, "lr": 8.936170212765958e-06, "epoch": 0.134185303514377, "percentage": 4.47, "elapsed_time": "0:07:46", "remaining_time": "2:46:04"}
+{"current_steps": 43, "total_steps": 939, "loss": 0.5842, "lr": 9.148936170212767e-06, "epoch": 0.13738019169329074, "percentage": 4.58, "elapsed_time": "0:07:56", "remaining_time": "2:45:24"}
+{"current_steps": 44, "total_steps": 939, "loss": 0.5588, "lr": 9.361702127659576e-06, "epoch": 0.14057507987220447, "percentage": 4.69, "elapsed_time": "0:08:07", "remaining_time": "2:45:08"}
+{"current_steps": 45, "total_steps": 939, "loss": 0.5985, "lr": 9.574468085106385e-06, "epoch": 0.14376996805111822, "percentage": 4.79, "elapsed_time": "0:08:18", "remaining_time": "2:45:03"}
+{"current_steps": 46, "total_steps": 939, "loss": 0.5751, "lr": 9.787234042553192e-06, "epoch": 0.14696485623003194, "percentage": 4.9, "elapsed_time": "0:08:27", "remaining_time": "2:44:17"}
+{"current_steps": 47, "total_steps": 939, "loss": 0.6098, "lr": 1e-05, "epoch": 0.1501597444089457, "percentage": 5.01, "elapsed_time": "0:08:35", "remaining_time": "2:43:03"}
+{"current_steps": 48, "total_steps": 939, "loss": 0.5898, "lr": 1.0212765957446808e-05, "epoch": 0.15335463258785942, "percentage": 5.11, "elapsed_time": "0:08:47", "remaining_time": "2:43:05"}
+{"current_steps": 49, "total_steps": 939, "loss": 0.5829, "lr": 1.0425531914893619e-05, "epoch": 0.15654952076677317, "percentage": 5.22, "elapsed_time": "0:08:57", "remaining_time": "2:42:43"}
+{"current_steps": 50, "total_steps": 939, "loss": 0.5514, "lr": 1.0638297872340426e-05, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:09:08", "remaining_time": "2:42:38"}
+{"current_steps": 51, "total_steps": 939, "loss": 0.593, "lr": 1.0851063829787233e-05, "epoch": 0.16293929712460065, "percentage": 5.43, "elapsed_time": "0:09:20", "remaining_time": "2:42:31"}
+{"current_steps": 52, "total_steps": 939, "loss": 0.6092, "lr": 1.1063829787234044e-05, "epoch": 0.16613418530351437, "percentage": 5.54, "elapsed_time": "0:09:30", "remaining_time": "2:42:14"}
+{"current_steps": 53, "total_steps": 939, "loss": 0.5577, "lr": 1.1276595744680851e-05, "epoch": 0.16932907348242812, "percentage": 5.64, "elapsed_time": "0:09:37", "remaining_time": "2:40:54"}
+{"current_steps": 54, "total_steps": 939, "loss": 0.551, "lr": 1.1489361702127662e-05, "epoch": 0.17252396166134185, "percentage": 5.75, "elapsed_time": "0:09:49", "remaining_time": "2:41:08"}
+{"current_steps": 55, "total_steps": 939, "loss": 0.5664, "lr": 1.170212765957447e-05, "epoch": 0.1757188498402556, "percentage": 5.86, "elapsed_time": "0:09:57", "remaining_time": "2:40:04"}
+{"current_steps": 56, "total_steps": 939, "loss": 0.5341, "lr": 1.1914893617021277e-05, "epoch": 0.17891373801916932, "percentage": 5.96, "elapsed_time": "0:10:08", "remaining_time": "2:39:47"}
+{"current_steps": 57, "total_steps": 939, "loss": 0.5643, "lr": 1.2127659574468087e-05, "epoch": 0.18210862619808307, "percentage": 6.07, "elapsed_time": "0:10:18", "remaining_time": "2:39:34"}
+{"current_steps": 58, "total_steps": 939, "loss": 0.543, "lr": 1.2340425531914895e-05, "epoch": 0.1853035143769968, "percentage": 6.18, "elapsed_time": "0:10:28", "remaining_time": "2:39:13"}
+{"current_steps": 59, "total_steps": 939, "loss": 0.5653, "lr": 1.2553191489361702e-05, "epoch": 0.18849840255591055, "percentage": 6.28, "elapsed_time": "0:10:36", "remaining_time": "2:38:11"}
+{"current_steps": 60, "total_steps": 939, "loss": 0.5565, "lr": 1.2765957446808513e-05, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:10:48", "remaining_time": "2:38:18"}
+{"current_steps": 61, "total_steps": 939, "loss": 0.5551, "lr": 1.297872340425532e-05, "epoch": 0.19488817891373802, "percentage": 6.5, "elapsed_time": "0:11:00", "remaining_time": "2:38:32"}
+{"current_steps": 62, "total_steps": 939, "loss": 0.5148, "lr": 1.3191489361702127e-05, "epoch": 0.19808306709265175, "percentage": 6.6, "elapsed_time": "0:11:07", "remaining_time": "2:37:28"}
+{"current_steps": 63, "total_steps": 939, "loss": 0.5541, "lr": 1.3404255319148938e-05, "epoch": 0.2012779552715655, "percentage": 6.71, "elapsed_time": "0:11:15", "remaining_time": "2:36:39"}
+{"current_steps": 64, "total_steps": 939, "loss": 0.5484, "lr": 1.3617021276595745e-05, "epoch": 0.20447284345047922, "percentage": 6.82, "elapsed_time": "0:11:26", "remaining_time": "2:36:19"}
+{"current_steps": 65, "total_steps": 939, "loss": 0.5834, "lr": 1.3829787234042556e-05, "epoch": 0.20766773162939298, "percentage": 6.92, "elapsed_time": "0:11:37", "remaining_time": "2:36:12"}
+{"current_steps": 66, "total_steps": 939, "loss": 0.5202, "lr": 1.4042553191489363e-05, "epoch": 0.2108626198083067, "percentage": 7.03, "elapsed_time": "0:11:45", "remaining_time": "2:35:32"}
+{"current_steps": 67, "total_steps": 939, "loss": 0.5276, "lr": 1.425531914893617e-05, "epoch": 0.21405750798722045, "percentage": 7.14, "elapsed_time": "0:11:57", "remaining_time": "2:35:44"}
+{"current_steps": 68, "total_steps": 939, "loss": 0.5184, "lr": 1.4468085106382981e-05, "epoch": 0.21725239616613418, "percentage": 7.24, "elapsed_time": "0:12:03", "remaining_time": "2:34:31"}
+{"current_steps": 69, "total_steps": 939, "loss": 0.5715, "lr": 1.4680851063829789e-05, "epoch": 0.22044728434504793, "percentage": 7.35, "elapsed_time": "0:12:15", "remaining_time": "2:34:37"}
+{"current_steps": 70, "total_steps": 939, "loss": 0.5911, "lr": 1.4893617021276596e-05, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:12:28", "remaining_time": "2:34:48"}
+{"current_steps": 71, "total_steps": 939, "loss": 0.5053, "lr": 1.5106382978723407e-05, "epoch": 0.2268370607028754, "percentage": 7.56, "elapsed_time": "0:12:39", "remaining_time": "2:34:43"}
+{"current_steps": 72, "total_steps": 939, "loss": 0.5301, "lr": 1.5319148936170214e-05, "epoch": 0.23003194888178913, "percentage": 7.67, "elapsed_time": "0:12:48", "remaining_time": "2:34:15"}
+{"current_steps": 73, "total_steps": 939, "loss": 0.5325, "lr": 1.5531914893617023e-05, "epoch": 0.23322683706070288, "percentage": 7.77, "elapsed_time": "0:13:00", "remaining_time": "2:34:14"}
+{"current_steps": 74, "total_steps": 939, "loss": 0.5132, "lr": 1.5744680851063832e-05, "epoch": 0.2364217252396166, "percentage": 7.88, "elapsed_time": "0:13:10", "remaining_time": "2:34:03"}
+{"current_steps": 75, "total_steps": 939, "loss": 0.5175, "lr": 1.595744680851064e-05, "epoch": 0.23961661341853036, "percentage": 7.99, "elapsed_time": "0:13:21", "remaining_time": "2:33:57"}
+{"current_steps": 76, "total_steps": 939, "loss": 0.5411, "lr": 1.6170212765957446e-05, "epoch": 0.24281150159744408, "percentage": 8.09, "elapsed_time": "0:13:32", "remaining_time": "2:33:49"}
+{"current_steps": 77, "total_steps": 939, "loss": 0.4906, "lr": 1.6382978723404255e-05, "epoch": 0.24600638977635783, "percentage": 8.2, "elapsed_time": "0:13:40", "remaining_time": "2:33:07"}
+{"current_steps": 78, "total_steps": 939, "loss": 0.5305, "lr": 1.6595744680851064e-05, "epoch": 0.24920127795527156, "percentage": 8.31, "elapsed_time": "0:13:53", "remaining_time": "2:33:17"}
+{"current_steps": 79, "total_steps": 939, "loss": 0.5442, "lr": 1.6808510638297873e-05, "epoch": 0.2523961661341853, "percentage": 8.41, "elapsed_time": "0:14:05", "remaining_time": "2:33:19"}
+{"current_steps": 80, "total_steps": 939, "loss": 0.5029, "lr": 1.7021276595744682e-05, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:14:13", "remaining_time": "2:32:44"}
+{"current_steps": 81, "total_steps": 939, "loss": 0.5536, "lr": 1.723404255319149e-05, "epoch": 0.25878594249201275, "percentage": 8.63, "elapsed_time": "0:14:24", "remaining_time": "2:32:41"}
+{"current_steps": 82, "total_steps": 939, "loss": 0.5666, "lr": 1.74468085106383e-05, "epoch": 0.26198083067092653, "percentage": 8.73, "elapsed_time": "0:14:31", "remaining_time": "2:31:50"}
+{"current_steps": 83, "total_steps": 939, "loss": 0.5171, "lr": 1.765957446808511e-05, "epoch": 0.26517571884984026, "percentage": 8.84, "elapsed_time": "0:14:42", "remaining_time": "2:31:38"}
+{"current_steps": 84, "total_steps": 939, "loss": 0.4754, "lr": 1.7872340425531915e-05, "epoch": 0.268370607028754, "percentage": 8.95, "elapsed_time": "0:14:49", "remaining_time": "2:30:55"}
+{"current_steps": 85, "total_steps": 939, "loss": 0.5713, "lr": 1.8085106382978724e-05, "epoch": 0.2715654952076677, "percentage": 9.05, "elapsed_time": "0:14:57", "remaining_time": "2:30:21"}
+{"current_steps": 86, "total_steps": 939, "loss": 0.549, "lr": 1.8297872340425533e-05, "epoch": 0.2747603833865815, "percentage": 9.16, "elapsed_time": "0:15:10", "remaining_time": "2:30:26"}
+{"current_steps": 87, "total_steps": 939, "loss": 0.5522, "lr": 1.8510638297872342e-05, "epoch": 0.2779552715654952, "percentage": 9.27, "elapsed_time": "0:15:21", "remaining_time": "2:30:27"}
+{"current_steps": 88, "total_steps": 939, "loss": 0.5825, "lr": 1.872340425531915e-05, "epoch": 0.28115015974440893, "percentage": 9.37, "elapsed_time": "0:15:34", "remaining_time": "2:30:33"}
+{"current_steps": 89, "total_steps": 939, "loss": 0.4851, "lr": 1.893617021276596e-05, "epoch": 0.28434504792332266, "percentage": 9.48, "elapsed_time": "0:15:46", "remaining_time": "2:30:40"}
+{"current_steps": 90, "total_steps": 939, "loss": 0.5195, "lr": 1.914893617021277e-05, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:15:58", "remaining_time": "2:30:38"}
+{"current_steps": 91, "total_steps": 939, "loss": 0.5328, "lr": 1.9361702127659575e-05, "epoch": 0.29073482428115016, "percentage": 9.69, "elapsed_time": "0:16:08", "remaining_time": "2:30:27"}
+{"current_steps": 92, "total_steps": 939, "loss": 0.4985, "lr": 1.9574468085106384e-05, "epoch": 0.2939297124600639, "percentage": 9.8, "elapsed_time": "0:16:19", "remaining_time": "2:30:22"}
+{"current_steps": 93, "total_steps": 939, "loss": 0.5353, "lr": 1.9787234042553193e-05, "epoch": 0.2971246006389776, "percentage": 9.9, "elapsed_time": "0:16:31", "remaining_time": "2:30:23"}
+{"current_steps": 94, "total_steps": 939, "loss": 0.5853, "lr": 2e-05, "epoch": 0.3003194888178914, "percentage": 10.01, "elapsed_time": "0:16:44", "remaining_time": "2:30:25"}
+{"current_steps": 95, "total_steps": 939, "loss": 0.5223, "lr": 1.9999930887622756e-05, "epoch": 0.3035143769968051, "percentage": 10.12, "elapsed_time": "0:16:55", "remaining_time": "2:30:18"}
+{"current_steps": 96, "total_steps": 939, "loss": 0.5499, "lr": 1.9999723551446323e-05, "epoch": 0.30670926517571884, "percentage": 10.22, "elapsed_time": "0:17:07", "remaining_time": "2:30:21"}
+{"current_steps": 97, "total_steps": 939, "loss": 0.5153, "lr": 1.9999377994336602e-05, "epoch": 0.30990415335463256, "percentage": 10.33, "elapsed_time": "0:17:15", "remaining_time": "2:29:46"}
+{"current_steps": 98, "total_steps": 939, "loss": 0.5421, "lr": 1.9998894221070052e-05, "epoch": 0.31309904153354634, "percentage": 10.44, "elapsed_time": "0:17:23", "remaining_time": "2:29:16"}
+{"current_steps": 99, "total_steps": 939, "loss": 0.522, "lr": 1.9998272238333606e-05, "epoch": 0.31629392971246006, "percentage": 10.54, "elapsed_time": "0:17:32", "remaining_time": "2:28:49"}
+{"current_steps": 100, "total_steps": 939, "loss": 0.5768, "lr": 1.9997512054724616e-05, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:17:44", "remaining_time": "2:28:51"}
+{"current_steps": 101, "total_steps": 939, "loss": 0.5366, "lr": 1.99966136807507e-05, "epoch": 0.3226837060702875, "percentage": 10.76, "elapsed_time": "0:17:54", "remaining_time": "2:28:36"}
+{"current_steps": 102, "total_steps": 939, "loss": 0.5629, "lr": 1.99955771288296e-05, "epoch": 0.3258785942492013, "percentage": 10.86, "elapsed_time": "0:18:04", "remaining_time": "2:28:22"}
+{"current_steps": 103, "total_steps": 939, "loss": 0.5057, "lr": 1.9994402413289044e-05, "epoch": 0.329073482428115, "percentage": 10.97, "elapsed_time": "0:18:17", "remaining_time": "2:28:30"}
+{"current_steps": 104, "total_steps": 939, "loss": 0.5436, "lr": 1.99930895503665e-05, "epoch": 0.33226837060702874, "percentage": 11.08, "elapsed_time": "0:18:30", "remaining_time": "2:28:34"}
+{"current_steps": 105, "total_steps": 939, "loss": 0.5043, "lr": 1.9991638558208987e-05, "epoch": 0.3354632587859425, "percentage": 11.18, "elapsed_time": "0:18:41", "remaining_time": "2:28:27"}
+{"current_steps": 106, "total_steps": 939, "loss": 0.4998, "lr": 1.9990049456872805e-05, "epoch": 0.33865814696485624, "percentage": 11.29, "elapsed_time": "0:18:50", "remaining_time": "2:28:00"}
+{"current_steps": 107, "total_steps": 939, "loss": 0.5621, "lr": 1.998832226832327e-05, "epoch": 0.34185303514376997, "percentage": 11.4, "elapsed_time": "0:19:00", "remaining_time": "2:27:45"}
+{"current_steps": 108, "total_steps": 939, "loss": 0.5209, "lr": 1.9986457016434402e-05, "epoch": 0.3450479233226837, "percentage": 11.5, "elapsed_time": "0:19:09", "remaining_time": "2:27:27"}
+{"current_steps": 109, "total_steps": 939, "loss": 0.5304, "lr": 1.99844537269886e-05, "epoch": 0.34824281150159747, "percentage": 11.61, "elapsed_time": "0:19:21", "remaining_time": "2:27:24"}
+{"current_steps": 110, "total_steps": 939, "loss": 0.5295, "lr": 1.9982312427676286e-05, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:19:31", "remaining_time": "2:27:10"}
+{"current_steps": 111, "total_steps": 939, "loss": 0.6233, "lr": 1.9980033148095514e-05, "epoch": 0.3546325878594249, "percentage": 11.82, "elapsed_time": "0:19:41", "remaining_time": "2:26:52"}
+{"current_steps": 112, "total_steps": 939, "loss": 0.5829, "lr": 1.997761591975157e-05, "epoch": 0.35782747603833864, "percentage": 11.93, "elapsed_time": "0:19:50", "remaining_time": "2:26:29"}
+{"current_steps": 113, "total_steps": 939, "loss": 0.5688, "lr": 1.9975060776056538e-05, "epoch": 0.3610223642172524, "percentage": 12.03, "elapsed_time": "0:20:01", "remaining_time": "2:26:21"}
+{"current_steps": 114, "total_steps": 939, "loss": 0.6128, "lr": 1.9972367752328824e-05, "epoch": 0.36421725239616615, "percentage": 12.14, "elapsed_time": "0:20:13", "remaining_time": "2:26:22"}
+{"current_steps": 115, "total_steps": 939, "loss": 0.491, "lr": 1.9969536885792685e-05, "epoch": 0.36741214057507987, "percentage": 12.25, "elapsed_time": "0:20:25", "remaining_time": "2:26:22"}
+{"current_steps": 116, "total_steps": 939, "loss": 0.525, "lr": 1.9966568215577704e-05, "epoch": 0.3706070287539936, "percentage": 12.35, "elapsed_time": "0:20:37", "remaining_time": "2:26:18"}
+{"current_steps": 117, "total_steps": 939, "loss": 0.4981, "lr": 1.9963461782718247e-05, "epoch": 0.3738019169329074, "percentage": 12.46, "elapsed_time": "0:20:46", "remaining_time": "2:25:57"}
+{"current_steps": 118, "total_steps": 939, "loss": 0.5174, "lr": 1.996021763015291e-05, "epoch": 0.3769968051118211, "percentage": 12.57, "elapsed_time": "0:20:57", "remaining_time": "2:25:49"}
+{"current_steps": 119, "total_steps": 939, "loss": 0.5116, "lr": 1.9956835802723916e-05, "epoch": 0.3801916932907348, "percentage": 12.67, "elapsed_time": "0:21:07", "remaining_time": "2:25:36"}
+{"current_steps": 120, "total_steps": 939, "loss": 0.5191, "lr": 1.995331634717649e-05, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:21:19", "remaining_time": "2:25:34"}
+{"current_steps": 121, "total_steps": 939, "loss": 0.5418, "lr": 1.9949659312158212e-05, "epoch": 0.3865814696485623, "percentage": 12.89, "elapsed_time": "0:21:31", "remaining_time": "2:25:28"}
+{"current_steps": 122, "total_steps": 939, "loss": 0.5135, "lr": 1.9945864748218368e-05, "epoch": 0.38977635782747605, "percentage": 12.99, "elapsed_time": "0:21:43", "remaining_time": "2:25:26"}
+{"current_steps": 123, "total_steps": 939, "loss": 0.555, "lr": 1.994193270780722e-05, "epoch": 0.3929712460063898, "percentage": 13.1, "elapsed_time": "0:21:53", "remaining_time": "2:25:16"}
+{"current_steps": 124, "total_steps": 939, "loss": 0.5506, "lr": 1.9937863245275303e-05, "epoch": 0.3961661341853035, "percentage": 13.21, "elapsed_time": "0:22:04", "remaining_time": "2:25:08"}
+{"current_steps": 125, "total_steps": 939, "loss": 0.5404, "lr": 1.9933656416872664e-05, "epoch": 0.3993610223642173, "percentage": 13.31, "elapsed_time": "0:22:17", "remaining_time": "2:25:08"}
+{"current_steps": 126, "total_steps": 939, "loss": 0.6051, "lr": 1.992931228074808e-05, "epoch": 0.402555910543131, "percentage": 13.42, "elapsed_time": "0:22:29", "remaining_time": "2:25:08"}
+{"current_steps": 127, "total_steps": 939, "loss": 0.5515, "lr": 1.9924830896948268e-05, "epoch": 0.4057507987220447, "percentage": 13.53, "elapsed_time": "0:22:39", "remaining_time": "2:24:53"}
+{"current_steps": 128, "total_steps": 939, "loss": 0.5022, "lr": 1.9920212327417044e-05, "epoch": 0.40894568690095845, "percentage": 13.63, "elapsed_time": "0:22:51", "remaining_time": "2:24:51"}
+{"current_steps": 129, "total_steps": 939, "loss": 0.5309, "lr": 1.991545663599448e-05, "epoch": 0.41214057507987223, "percentage": 13.74, "elapsed_time": "0:23:03", "remaining_time": "2:24:44"}
+{"current_steps": 130, "total_steps": 939, "loss": 0.5681, "lr": 1.9910563888415996e-05, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:23:13", "remaining_time": "2:24:32"}
+{"current_steps": 131, "total_steps": 939, "loss": 0.5576, "lr": 1.990553415231148e-05, "epoch": 0.4185303514376997, "percentage": 13.95, "elapsed_time": "0:23:26", "remaining_time": "2:24:37"}
+{"current_steps": 132, "total_steps": 939, "loss": 0.5088, "lr": 1.9900367497204328e-05, "epoch": 0.4217252396166134, "percentage": 14.06, "elapsed_time": "0:23:34", "remaining_time": "2:24:08"}
+{"current_steps": 133, "total_steps": 939, "loss": 0.5269, "lr": 1.9895063994510512e-05, "epoch": 0.4249201277955272, "percentage": 14.16, "elapsed_time": "0:23:45", "remaining_time": "2:23:59"}
+{"current_steps": 134, "total_steps": 939, "loss": 0.5914, "lr": 1.9889623717537564e-05, "epoch": 0.4281150159744409, "percentage": 14.27, "elapsed_time": "0:23:55", "remaining_time": "2:23:44"}
+{"current_steps": 135, "total_steps": 939, "loss": 0.5335, "lr": 1.988404674148358e-05, "epoch": 0.43130990415335463, "percentage": 14.38, "elapsed_time": "0:24:07", "remaining_time": "2:23:38"}
+{"current_steps": 136, "total_steps": 939, "loss": 0.5252, "lr": 1.9878333143436172e-05, "epoch": 0.43450479233226835, "percentage": 14.48, "elapsed_time": "0:24:18", "remaining_time": "2:23:29"}
+{"current_steps": 137, "total_steps": 939, "loss": 0.5289, "lr": 1.987248300237141e-05, "epoch": 0.43769968051118213, "percentage": 14.59, "elapsed_time": "0:24:27", "remaining_time": "2:23:08"}
+{"current_steps": 138, "total_steps": 939, "loss": 0.548, "lr": 1.9866496399152732e-05, "epoch": 0.44089456869009586, "percentage": 14.7, "elapsed_time": "0:24:37", "remaining_time": "2:22:54"}
+{"current_steps": 139, "total_steps": 939, "loss": 0.5533, "lr": 1.9860373416529804e-05, "epoch": 0.4440894568690096, "percentage": 14.8, "elapsed_time": "0:24:48", "remaining_time": "2:22:49"}
+{"current_steps": 140, "total_steps": 939, "loss": 0.5165, "lr": 1.9854114139137408e-05, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:24:58", "remaining_time": "2:22:32"}
+{"current_steps": 141, "total_steps": 939, "loss": 0.5897, "lr": 1.984771865349425e-05, "epoch": 0.4504792332268371, "percentage": 15.02, "elapsed_time": "0:25:10", "remaining_time": "2:22:26"}
+{"current_steps": 142, "total_steps": 939, "loss": 0.5209, "lr": 1.9841187048001774e-05, "epoch": 0.4536741214057508, "percentage": 15.12, "elapsed_time": "0:25:21", "remaining_time": "2:22:21"}
+{"current_steps": 143, "total_steps": 939, "loss": 0.5318, "lr": 1.9834519412942938e-05, "epoch": 0.45686900958466453, "percentage": 15.23, "elapsed_time": "0:25:32", "remaining_time": "2:22:10"}
+{"current_steps": 144, "total_steps": 939, "loss": 0.5166, "lr": 1.9827715840480962e-05, "epoch": 0.46006389776357826, "percentage": 15.34, "elapsed_time": "0:25:42", "remaining_time": "2:21:56"}
+{"current_steps": 145, "total_steps": 939, "loss": 0.5423, "lr": 1.982077642465806e-05, "epoch": 0.46325878594249204, "percentage": 15.44, "elapsed_time": "0:25:54", "remaining_time": "2:21:52"}
+{"current_steps": 146, "total_steps": 939, "loss": 0.525, "lr": 1.9813701261394136e-05, "epoch": 0.46645367412140576, "percentage": 15.55, "elapsed_time": "0:26:05", "remaining_time": "2:21:45"}
+{"current_steps": 147, "total_steps": 939, "loss": 0.5217, "lr": 1.9806490448485463e-05, "epoch": 0.4696485623003195, "percentage": 15.65, "elapsed_time": "0:26:16", "remaining_time": "2:21:35"}
+{"current_steps": 148, "total_steps": 939, "loss": 0.5613, "lr": 1.9799144085603323e-05, "epoch": 0.4728434504792332, "percentage": 15.76, "elapsed_time": "0:26:27", "remaining_time": "2:21:23"}
+{"current_steps": 149, "total_steps": 939, "loss": 0.5696, "lr": 1.9791662274292638e-05, "epoch": 0.476038338658147, "percentage": 15.87, "elapsed_time": "0:26:38", "remaining_time": "2:21:15"}
+{"current_steps": 150, "total_steps": 939, "loss": 0.4712, "lr": 1.978404511797056e-05, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:26:48", "remaining_time": "2:21:01"}
+{"current_steps": 151, "total_steps": 939, "loss": 0.5456, "lr": 1.9776292721925046e-05, "epoch": 0.48242811501597443, "percentage": 16.08, "elapsed_time": "0:26:59", "remaining_time": "2:20:49"}
+{"current_steps": 152, "total_steps": 939, "loss": 0.5093, "lr": 1.97684051933134e-05, "epoch": 0.48562300319488816, "percentage": 16.19, "elapsed_time": "0:27:08", "remaining_time": "2:20:33"}
+{"current_steps": 153, "total_steps": 939, "loss": 0.523, "lr": 1.9760382641160792e-05, "epoch": 0.48881789137380194, "percentage": 16.29, "elapsed_time": "0:27:21", "remaining_time": "2:20:31"}
+{"current_steps": 154, "total_steps": 939, "loss": 0.5154, "lr": 1.9752225176358757e-05, "epoch": 0.49201277955271566, "percentage": 16.4, "elapsed_time": "0:27:33", "remaining_time": "2:20:29"}
+{"current_steps": 155, "total_steps": 939, "loss": 0.5242, "lr": 1.974393291166364e-05, "epoch": 0.4952076677316294, "percentage": 16.51, "elapsed_time": "0:27:45", "remaining_time": "2:20:23"}
+{"current_steps": 156, "total_steps": 939, "loss": 0.5526, "lr": 1.973550596169508e-05, "epoch": 0.4984025559105431, "percentage": 16.61, "elapsed_time": "0:27:54", "remaining_time": "2:20:04"}
+{"current_steps": 157, "total_steps": 939, "loss": 0.4775, "lr": 1.9726944442934378e-05, "epoch": 0.5015974440894568, "percentage": 16.72, "elapsed_time": "0:28:06", "remaining_time": "2:20:01"}
+{"current_steps": 158, "total_steps": 939, "loss": 0.4946, "lr": 1.971824847372292e-05, "epoch": 0.5047923322683706, "percentage": 16.83, "elapsed_time": "0:28:18", "remaining_time": "2:19:56"}
+{"current_steps": 159, "total_steps": 939, "loss": 0.5213, "lr": 1.9709418174260523e-05, "epoch": 0.5079872204472844, "percentage": 16.93, "elapsed_time": "0:28:29", "remaining_time": "2:19:47"}
+{"current_steps": 160, "total_steps": 939, "loss": 0.504, "lr": 1.9700453666603786e-05, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:28:38", "remaining_time": "2:19:29"}
+{"current_steps": 161, "total_steps": 939, "loss": 0.5285, "lr": 1.96913550746644e-05, "epoch": 0.5143769968051118, "percentage": 17.15, "elapsed_time": "0:28:50", "remaining_time": "2:19:22"}
+{"current_steps": 162, "total_steps": 939, "loss": 0.5258, "lr": 1.9682122524207426e-05, "epoch": 0.5175718849840255, "percentage": 17.25, "elapsed_time": "0:28:59", "remaining_time": "2:19:02"}
+{"current_steps": 163, "total_steps": 939, "loss": 0.5622, "lr": 1.9672756142849564e-05, "epoch": 0.5207667731629393, "percentage": 17.36, "elapsed_time": "0:29:08", "remaining_time": "2:18:42"}
+{"current_steps": 164, "total_steps": 939, "loss": 0.5459, "lr": 1.9663256060057395e-05, "epoch": 0.5239616613418531, "percentage": 17.47, "elapsed_time": "0:29:18", "remaining_time": "2:18:28"}
+{"current_steps": 165, "total_steps": 939, "loss": 0.535, "lr": 1.965362240714557e-05, "epoch": 0.5271565495207667, "percentage": 17.57, "elapsed_time": "0:29:30", "remaining_time": "2:18:25"}
+{"current_steps": 166, "total_steps": 939, "loss": 0.5187, "lr": 1.9643855317275036e-05, "epoch": 0.5303514376996805, "percentage": 17.68, "elapsed_time": "0:29:43", "remaining_time": "2:18:26"}
+{"current_steps": 167, "total_steps": 939, "loss": 0.4926, "lr": 1.963395492545114e-05, "epoch": 0.5335463258785943, "percentage": 17.78, "elapsed_time": "0:29:50", "remaining_time": "2:17:59"}
+{"current_steps": 168, "total_steps": 939, "loss": 0.4925, "lr": 1.9623921368521814e-05, "epoch": 0.536741214057508, "percentage": 17.89, "elapsed_time": "0:30:03", "remaining_time": "2:17:54"}
+{"current_steps": 169, "total_steps": 939, "loss": 0.554, "lr": 1.961375478517564e-05, "epoch": 0.5399361022364217, "percentage": 18.0, "elapsed_time": "0:30:14", "remaining_time": "2:17:47"}
+{"current_steps": 170, "total_steps": 939, "loss": 0.5381, "lr": 1.9603455315939976e-05, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:30:26", "remaining_time": "2:17:44"}
+{"current_steps": 171, "total_steps": 939, "loss": 0.5398, "lr": 1.9593023103178984e-05, "epoch": 0.5463258785942492, "percentage": 18.21, "elapsed_time": "0:30:38", "remaining_time": "2:17:35"}
+{"current_steps": 172, "total_steps": 939, "loss": 0.5363, "lr": 1.9582458291091664e-05, "epoch": 0.549520766773163, "percentage": 18.32, "elapsed_time": "0:30:49", "remaining_time": "2:17:26"}
+{"current_steps": 173, "total_steps": 939, "loss": 0.5441, "lr": 1.9571761025709874e-05, "epoch": 0.5527156549520766, "percentage": 18.42, "elapsed_time": "0:30:59", "remaining_time": "2:17:15"}
+{"current_steps": 174, "total_steps": 939, "loss": 0.5771, "lr": 1.95609314548963e-05, "epoch": 0.5559105431309904, "percentage": 18.53, "elapsed_time": "0:31:08", "remaining_time": "2:16:53"}
+{"current_steps": 175, "total_steps": 939, "loss": 0.5208, "lr": 1.954996972834242e-05, "epoch": 0.5591054313099042, "percentage": 18.64, "elapsed_time": "0:31:19", "remaining_time": "2:16:44"}
+{"current_steps": 176, "total_steps": 939, "loss": 0.5107, "lr": 1.953887599756643e-05, "epoch": 0.5623003194888179, "percentage": 18.74, "elapsed_time": "0:31:30", "remaining_time": "2:16:37"}
+{"current_steps": 177, "total_steps": 939, "loss": 0.5377, "lr": 1.9527650415911154e-05, "epoch": 0.5654952076677316, "percentage": 18.85, "elapsed_time": "0:31:39", "remaining_time": "2:16:18"}
+{"current_steps": 178, "total_steps": 939, "loss": 0.5111, "lr": 1.9516293138541914e-05, "epoch": 0.5686900958466453, "percentage": 18.96, "elapsed_time": "0:31:50", "remaining_time": "2:16:08"}
+{"current_steps": 179, "total_steps": 939, "loss": 0.5088, "lr": 1.95048043224444e-05, "epoch": 0.5718849840255591, "percentage": 19.06, "elapsed_time": "0:31:58", "remaining_time": "2:15:44"}
+{"current_steps": 180, "total_steps": 939, "loss": 0.5453, "lr": 1.9493184126422494e-05, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:32:09", "remaining_time": "2:15:35"}
+{"current_steps": 181, "total_steps": 939, "loss": 0.5425, "lr": 1.948143271109606e-05, "epoch": 0.5782747603833865, "percentage": 19.28, "elapsed_time": "0:32:21", "remaining_time": "2:15:31"}
+{"current_steps": 182, "total_steps": 939, "loss": 0.527, "lr": 1.946955023889876e-05, "epoch": 0.5814696485623003, "percentage": 19.38, "elapsed_time": "0:32:32", "remaining_time": "2:15:19"}
+{"current_steps": 183, "total_steps": 939, "loss": 0.5247, "lr": 1.9457536874075765e-05, "epoch": 0.5846645367412141, "percentage": 19.49, "elapsed_time": "0:32:43", "remaining_time": "2:15:13"}
+{"current_steps": 184, "total_steps": 939, "loss": 0.5075, "lr": 1.9445392782681523e-05, "epoch": 0.5878594249201278, "percentage": 19.6, "elapsed_time": "0:32:50", "remaining_time": "2:14:46"}
+{"current_steps": 185, "total_steps": 939, "loss": 0.5242, "lr": 1.9433118132577432e-05, "epoch": 0.5910543130990416, "percentage": 19.7, "elapsed_time": "0:33:04", "remaining_time": "2:14:46"}
+{"current_steps": 186, "total_steps": 939, "loss": 0.4878, "lr": 1.9420713093429548e-05, "epoch": 0.5942492012779552, "percentage": 19.81, "elapsed_time": "0:33:15", "remaining_time": "2:14:40"}
+{"current_steps": 187, "total_steps": 939, "loss": 0.5006, "lr": 1.9408177836706215e-05, "epoch": 0.597444089456869, "percentage": 19.91, "elapsed_time": "0:33:26", "remaining_time": "2:14:27"}
+{"current_steps": 188, "total_steps": 939, "loss": 0.508, "lr": 1.939551253567571e-05, "epoch": 0.6006389776357828, "percentage": 20.02, "elapsed_time": "0:33:39", "remaining_time": "2:14:25"}
+{"current_steps": 189, "total_steps": 939, "loss": 0.4921, "lr": 1.9382717365403854e-05, "epoch": 0.6038338658146964, "percentage": 20.13, "elapsed_time": "0:33:52", "remaining_time": "2:14:23"}
+{"current_steps": 190, "total_steps": 939, "loss": 0.5269, "lr": 1.9369792502751568e-05, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:33:59", "remaining_time": "2:13:59"}
+{"current_steps": 191, "total_steps": 939, "loss": 0.4818, "lr": 1.9356738126372448e-05, "epoch": 0.610223642172524, "percentage": 20.34, "elapsed_time": "0:34:10", "remaining_time": "2:13:48"}
+{"current_steps": 192, "total_steps": 939, "loss": 0.5222, "lr": 1.9343554416710293e-05, "epoch": 0.6134185303514377, "percentage": 20.45, "elapsed_time": "0:34:22", "remaining_time": "2:13:45"}
+{"current_steps": 193, "total_steps": 939, "loss": 0.5458, "lr": 1.9330241555996606e-05, "epoch": 0.6166134185303515, "percentage": 20.55, "elapsed_time": "0:34:32", "remaining_time": "2:13:29"}
+{"current_steps": 194, "total_steps": 939, "loss": 0.5328, "lr": 1.9316799728248074e-05, "epoch": 0.6198083067092651, "percentage": 20.66, "elapsed_time": "0:34:43", "remaining_time": "2:13:20"}
+{"current_steps": 195, "total_steps": 939, "loss": 0.5213, "lr": 1.930322911926404e-05, "epoch": 0.6230031948881789, "percentage": 20.77, "elapsed_time": "0:34:55", "remaining_time": "2:13:15"}
+{"current_steps": 196, "total_steps": 939, "loss": 0.5231, "lr": 1.92895299166239e-05, "epoch": 0.6261980830670927, "percentage": 20.87, "elapsed_time": "0:35:07", "remaining_time": "2:13:09"}
+{"current_steps": 197, "total_steps": 939, "loss": 0.5229, "lr": 1.9275702309684557e-05, "epoch": 0.6293929712460063, "percentage": 20.98, "elapsed_time": "0:35:17", "remaining_time": "2:12:57"}
+{"current_steps": 198, "total_steps": 939, "loss": 0.4838, "lr": 1.9261746489577767e-05, "epoch": 0.6325878594249201, "percentage": 21.09, "elapsed_time": "0:35:27", "remaining_time": "2:12:40"}
+{"current_steps": 199, "total_steps": 939, "loss": 0.4933, "lr": 1.924766264920751e-05, "epoch": 0.6357827476038339, "percentage": 21.19, "elapsed_time": "0:35:39", "remaining_time": "2:12:35"}
+{"current_steps": 200, "total_steps": 939, "loss": 0.4876, "lr": 1.923345098324732e-05, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:35:50", "remaining_time": "2:12:24"}
+{"current_steps": 201, "total_steps": 939, "loss": 0.527, "lr": 1.92191116881376e-05, "epoch": 0.6421725239616614, "percentage": 21.41, "elapsed_time": "0:36:02", "remaining_time": "2:12:18"}
+{"current_steps": 202, "total_steps": 939, "loss": 0.54, "lr": 1.9204644962082915e-05, "epoch": 0.645367412140575, "percentage": 21.51, "elapsed_time": "0:36:13", "remaining_time": "2:12:11"}
+{"current_steps": 203, "total_steps": 939, "loss": 0.4843, "lr": 1.9190051005049218e-05, "epoch": 0.6485623003194888, "percentage": 21.62, "elapsed_time": "0:36:25", "remaining_time": "2:12:05"}
+{"current_steps": 204, "total_steps": 939, "loss": 0.5369, "lr": 1.917533001876113e-05, "epoch": 0.6517571884984026, "percentage": 21.73, "elapsed_time": "0:36:36", "remaining_time": "2:11:54"}
+{"current_steps": 205, "total_steps": 939, "loss": 0.4931, "lr": 1.9160482206699124e-05, "epoch": 0.6549520766773163, "percentage": 21.83, "elapsed_time": "0:36:46", "remaining_time": "2:11:41"}
+{"current_steps": 206, "total_steps": 939, "loss": 0.5258, "lr": 1.9145507774096706e-05, "epoch": 0.65814696485623, "percentage": 21.94, "elapsed_time": "0:36:59", "remaining_time": "2:11:35"}
+{"current_steps": 207, "total_steps": 939, "loss": 0.4991, "lr": 1.9130406927937616e-05, "epoch": 0.6613418530351438, "percentage": 22.04, "elapsed_time": "0:37:09", "remaining_time": "2:11:24"}
+{"current_steps": 208, "total_steps": 939, "loss": 0.5631, "lr": 1.9115179876952925e-05, "epoch": 0.6645367412140575, "percentage": 22.15, "elapsed_time": "0:37:17", "remaining_time": "2:11:02"}
+{"current_steps": 209, "total_steps": 939, "loss": 0.5526, "lr": 1.9099826831618168e-05, "epoch": 0.6677316293929713, "percentage": 22.26, "elapsed_time": "0:37:24", "remaining_time": "2:10:40"}
+{"current_steps": 210, "total_steps": 939, "loss": 0.4992, "lr": 1.9084348004150442e-05, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:37:33", "remaining_time": "2:10:22"}
+{"current_steps": 211, "total_steps": 939, "loss": 0.521, "lr": 1.9068743608505454e-05, "epoch": 0.6741214057507987, "percentage": 22.47, "elapsed_time": "0:37:43", "remaining_time": "2:10:09"}
+{"current_steps": 212, "total_steps": 939, "loss": 0.5414, "lr": 1.9053013860374588e-05, "epoch": 0.6773162939297125, "percentage": 22.58, "elapsed_time": "0:37:52", "remaining_time": "2:09:52"}
+{"current_steps": 213, "total_steps": 939, "loss": 0.5494, "lr": 1.9037158977181894e-05, "epoch": 0.6805111821086262, "percentage": 22.68, "elapsed_time": "0:38:04", "remaining_time": "2:09:45"}
+{"current_steps": 214, "total_steps": 939, "loss": 0.5621, "lr": 1.9021179178081107e-05, "epoch": 0.6837060702875399, "percentage": 22.79, "elapsed_time": "0:38:14", "remaining_time": "2:09:33"}
+{"current_steps": 215, "total_steps": 939, "loss": 0.4696, "lr": 1.900507468395261e-05, "epoch": 0.6869009584664537, "percentage": 22.9, "elapsed_time": "0:38:25", "remaining_time": "2:09:25"}
+{"current_steps": 216, "total_steps": 939, "loss": 0.5201, "lr": 1.8988845717400375e-05, "epoch": 0.6900958466453674, "percentage": 23.0, "elapsed_time": "0:38:34", "remaining_time": "2:09:06"}
+{"current_steps": 217, "total_steps": 939, "loss": 0.5601, "lr": 1.89724925027489e-05, "epoch": 0.6932907348242812, "percentage": 23.11, "elapsed_time": "0:38:43", "remaining_time": "2:08:52"}
+{"current_steps": 218, "total_steps": 939, "loss": 0.5517, "lr": 1.8956015266040086e-05, "epoch": 0.6964856230031949, "percentage": 23.22, "elapsed_time": "0:38:53", "remaining_time": "2:08:38"}
+{"current_steps": 219, "total_steps": 939, "loss": 0.5498, "lr": 1.8939414235030137e-05, "epoch": 0.6996805111821086, "percentage": 23.32, "elapsed_time": "0:39:04", "remaining_time": "2:08:27"}
+{"current_steps": 220, "total_steps": 939, "loss": 0.5442, "lr": 1.8922689639186387e-05, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:39:13", "remaining_time": "2:08:11"}
+{"current_steps": 221, "total_steps": 939, "loss": 0.516, "lr": 1.890584170968417e-05, "epoch": 0.7060702875399361, "percentage": 23.54, "elapsed_time": "0:39:25", "remaining_time": "2:08:04"}
+{"current_steps": 222, "total_steps": 939, "loss": 0.5438, "lr": 1.888887067940356e-05, "epoch": 0.7092651757188498, "percentage": 23.64, "elapsed_time": "0:39:35", "remaining_time": "2:07:53"}
+{"current_steps": 223, "total_steps": 939, "loss": 0.487, "lr": 1.8871776782926216e-05, "epoch": 0.7124600638977636, "percentage": 23.75, "elapsed_time": "0:39:43", "remaining_time": "2:07:32"}
+{"current_steps": 224, "total_steps": 939, "loss": 0.4993, "lr": 1.8854560256532098e-05, "epoch": 0.7156549520766773, "percentage": 23.86, "elapsed_time": "0:39:52", "remaining_time": "2:07:16"}
+{"current_steps": 225, "total_steps": 939, "loss": 0.5049, "lr": 1.8837221338196228e-05, "epoch": 0.7188498402555911, "percentage": 23.96, "elapsed_time": "0:40:00", "remaining_time": "2:06:57"}
+{"current_steps": 226, "total_steps": 939, "loss": 0.5522, "lr": 1.8819760267585368e-05, "epoch": 0.7220447284345048, "percentage": 24.07, "elapsed_time": "0:40:11", "remaining_time": "2:06:47"}
+{"current_steps": 227, "total_steps": 939, "loss": 0.5468, "lr": 1.880217728605474e-05, "epoch": 0.7252396166134185, "percentage": 24.17, "elapsed_time": "0:40:22", "remaining_time": "2:06:39"}
+{"current_steps": 228, "total_steps": 939, "loss": 0.5146, "lr": 1.8784472636644677e-05, "epoch": 0.7284345047923323, "percentage": 24.28, "elapsed_time": "0:40:34", "remaining_time": "2:06:30"}
+{"current_steps": 229, "total_steps": 939, "loss": 0.52, "lr": 1.8766646564077265e-05, "epoch": 0.731629392971246, "percentage": 24.39, "elapsed_time": "0:40:45", "remaining_time": "2:06:23"}
+{"current_steps": 230, "total_steps": 939, "loss": 0.5076, "lr": 1.8748699314752947e-05, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:40:55", "remaining_time": "2:06:08"}
+{"current_steps": 231, "total_steps": 939, "loss": 0.5162, "lr": 1.8730631136747138e-05, "epoch": 0.7380191693290735, "percentage": 24.6, "elapsed_time": "0:41:06", "remaining_time": "2:05:58"}
+{"current_steps": 232, "total_steps": 939, "loss": 0.5258, "lr": 1.871244227980679e-05, "epoch": 0.7412140575079872, "percentage": 24.71, "elapsed_time": "0:41:19", "remaining_time": "2:05:56"}
+{"current_steps": 233, "total_steps": 939, "loss": 0.5008, "lr": 1.8694132995346924e-05, "epoch": 0.744408945686901, "percentage": 24.81, "elapsed_time": "0:41:26", "remaining_time": "2:05:34"}
+{"current_steps": 234, "total_steps": 939, "loss": 0.4979, "lr": 1.8675703536447178e-05, "epoch": 0.7476038338658147, "percentage": 24.92, "elapsed_time": "0:41:35", "remaining_time": "2:05:17"}
+{"current_steps": 235, "total_steps": 939, "loss": 0.5145, "lr": 1.8657154157848302e-05, "epoch": 0.7507987220447284, "percentage": 25.03, "elapsed_time": "0:41:45", "remaining_time": "2:05:07"}
+{"current_steps": 236, "total_steps": 939, "loss": 0.4847, "lr": 1.8638485115948612e-05, "epoch": 0.7539936102236422, "percentage": 25.13, "elapsed_time": "0:41:57", "remaining_time": "2:04:59"}
+{"current_steps": 237, "total_steps": 939, "loss": 0.5308, "lr": 1.8619696668800494e-05, "epoch": 0.7571884984025559, "percentage": 25.24, "elapsed_time": "0:42:09", "remaining_time": "2:04:53"}
+{"current_steps": 238, "total_steps": 939, "loss": 0.5046, "lr": 1.860078907610679e-05, "epoch": 0.7603833865814696, "percentage": 25.35, "elapsed_time": "0:42:19", "remaining_time": "2:04:39"}
+{"current_steps": 239, "total_steps": 939, "loss": 0.5171, "lr": 1.858176259921724e-05, "epoch": 0.7635782747603834, "percentage": 25.45, "elapsed_time": "0:42:31", "remaining_time": "2:04:31"}
+{"current_steps": 240, "total_steps": 939, "loss": 0.4918, "lr": 1.856261750112485e-05, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:42:42", "remaining_time": "2:04:23"}
+{"current_steps": 241, "total_steps": 939, "loss": 0.5022, "lr": 1.8543354046462275e-05, "epoch": 0.7699680511182109, "percentage": 25.67, "elapsed_time": "0:42:53", "remaining_time": "2:04:14"}
+{"current_steps": 242, "total_steps": 939, "loss": 0.48, "lr": 1.8523972501498136e-05, "epoch": 0.7731629392971247, "percentage": 25.77, "elapsed_time": "0:43:05", "remaining_time": "2:04:07"}
+{"current_steps": 243, "total_steps": 939, "loss": 0.4905, "lr": 1.850447313413337e-05, "epoch": 0.7763578274760383, "percentage": 25.88, "elapsed_time": "0:43:17", "remaining_time": "2:03:58"}
+{"current_steps": 244, "total_steps": 939, "loss": 0.5968, "lr": 1.8484856213897496e-05, "epoch": 0.7795527156549521, "percentage": 25.99, "elapsed_time": "0:43:29", "remaining_time": "2:03:52"}
+{"current_steps": 245, "total_steps": 939, "loss": 0.5219, "lr": 1.846512201194492e-05, "epoch": 0.7827476038338658, "percentage": 26.09, "elapsed_time": "0:43:37", "remaining_time": "2:03:33"}
+{"current_steps": 246, "total_steps": 939, "loss": 0.5187, "lr": 1.844527080105116e-05, "epoch": 0.7859424920127795, "percentage": 26.2, "elapsed_time": "0:43:49", "remaining_time": "2:03:27"}
+{"current_steps": 247, "total_steps": 939, "loss": 0.5627, "lr": 1.8425302855609088e-05, "epoch": 0.7891373801916933, "percentage": 26.3, "elapsed_time": "0:44:01", "remaining_time": "2:03:21"}
+{"current_steps": 248, "total_steps": 939, "loss": 0.514, "lr": 1.8405218451625144e-05, "epoch": 0.792332268370607, "percentage": 26.41, "elapsed_time": "0:44:10", "remaining_time": "2:03:05"}
+{"current_steps": 249, "total_steps": 939, "loss": 0.4998, "lr": 1.8385017866715507e-05, "epoch": 0.7955271565495208, "percentage": 26.52, "elapsed_time": "0:44:23", "remaining_time": "2:03:01"}
+{"current_steps": 250, "total_steps": 939, "loss": 0.5127, "lr": 1.8364701380102267e-05, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:44:33", "remaining_time": "2:02:48"}
+{"current_steps": 251, "total_steps": 939, "loss": 0.4652, "lr": 1.8344269272609567e-05, "epoch": 0.8019169329073482, "percentage": 26.73, "elapsed_time": "0:44:41", "remaining_time": "2:02:29"}
+{"current_steps": 252, "total_steps": 939, "loss": 0.5054, "lr": 1.83237218266597e-05, "epoch": 0.805111821086262, "percentage": 26.84, "elapsed_time": "0:44:52", "remaining_time": "2:02:20"}
+{"current_steps": 253, "total_steps": 939, "loss": 0.4939, "lr": 1.830305932626924e-05, "epoch": 0.8083067092651757, "percentage": 26.94, "elapsed_time": "0:45:03", "remaining_time": "2:02:11"}
+{"current_steps": 254, "total_steps": 939, "loss": 0.4639, "lr": 1.8282282057045087e-05, "epoch": 0.8115015974440895, "percentage": 27.05, "elapsed_time": "0:45:13", "remaining_time": "2:01:56"}
+{"current_steps": 255, "total_steps": 939, "loss": 0.4844, "lr": 1.8261390306180544e-05, "epoch": 0.8146964856230032, "percentage": 27.16, "elapsed_time": "0:45:24", "remaining_time": "2:01:48"}
+{"current_steps": 256, "total_steps": 939, "loss": 0.5076, "lr": 1.8240384362451316e-05, "epoch": 0.8178913738019169, "percentage": 27.26, "elapsed_time": "0:45:34", "remaining_time": "2:01:36"}
+{"current_steps": 257, "total_steps": 939, "loss": 0.4893, "lr": 1.8219264516211543e-05, "epoch": 0.8210862619808307, "percentage": 27.37, "elapsed_time": "0:45:45", "remaining_time": "2:01:26"}
+{"current_steps": 258, "total_steps": 939, "loss": 0.4813, "lr": 1.819803105938979e-05, "epoch": 0.8242811501597445, "percentage": 27.48, "elapsed_time": "0:45:57", "remaining_time": "2:01:19"}
+{"current_steps": 259, "total_steps": 939, "loss": 0.4997, "lr": 1.8176684285484985e-05, "epoch": 0.8274760383386581, "percentage": 27.58, "elapsed_time": "0:46:09", "remaining_time": "2:01:10"}
+{"current_steps": 260, "total_steps": 939, "loss": 0.5245, "lr": 1.815522448956239e-05, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:46:18", "remaining_time": "2:00:56"}
+{"current_steps": 261, "total_steps": 939, "loss": 0.511, "lr": 1.8133651968249503e-05, "epoch": 0.8338658146964856, "percentage": 27.8, "elapsed_time": "0:46:29", "remaining_time": "2:00:45"}
+{"current_steps": 262, "total_steps": 939, "loss": 0.5461, "lr": 1.8111967019731977e-05, "epoch": 0.8370607028753994, "percentage": 27.9, "elapsed_time": "0:46:39", "remaining_time": "2:00:32"}
+{"current_steps": 263, "total_steps": 939, "loss": 0.533, "lr": 1.8090169943749477e-05, "epoch": 0.8402555910543131, "percentage": 28.01, "elapsed_time": "0:46:44", "remaining_time": "2:00:09"}
+{"current_steps": 264, "total_steps": 939, "loss": 0.5595, "lr": 1.8068261041591548e-05, "epoch": 0.8434504792332268, "percentage": 28.12, "elapsed_time": "0:46:54", "remaining_time": "1:59:56"}
+{"current_steps": 265, "total_steps": 939, "loss": 0.5091, "lr": 1.8046240616093452e-05, "epoch": 0.8466453674121406, "percentage": 28.22, "elapsed_time": "0:47:04", "remaining_time": "1:59:42"}
+{"current_steps": 266, "total_steps": 939, "loss": 0.4691, "lr": 1.802410897163199e-05, "epoch": 0.8498402555910544, "percentage": 28.33, "elapsed_time": "0:47:12", "remaining_time": "1:59:25"}
+{"current_steps": 267, "total_steps": 939, "loss": 0.495, "lr": 1.800186641412126e-05, "epoch": 0.853035143769968, "percentage": 28.43, "elapsed_time": "0:47:22", "remaining_time": "1:59:15"}
+{"current_steps": 268, "total_steps": 939, "loss": 0.4873, "lr": 1.7979513251008475e-05, "epoch": 0.8562300319488818, "percentage": 28.54, "elapsed_time": "0:47:32", "remaining_time": "1:59:01"}
+{"current_steps": 269, "total_steps": 939, "loss": 0.5081, "lr": 1.7957049791269684e-05, "epoch": 0.8594249201277955, "percentage": 28.65, "elapsed_time": "0:47:44", "remaining_time": "1:58:53"}
+{"current_steps": 270, "total_steps": 939, "loss": 0.5499, "lr": 1.7934476345405508e-05, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:47:55", "remaining_time": "1:58:44"}
+{"current_steps": 271, "total_steps": 939, "loss": 0.5376, "lr": 1.791179322543684e-05, "epoch": 0.865814696485623, "percentage": 28.86, "elapsed_time": "0:48:07", "remaining_time": "1:58:38"}
+{"current_steps": 272, "total_steps": 939, "loss": 0.5016, "lr": 1.788900074490056e-05, "epoch": 0.8690095846645367, "percentage": 28.97, "elapsed_time": "0:48:18", "remaining_time": "1:58:27"}
+{"current_steps": 273, "total_steps": 939, "loss": 0.4912, "lr": 1.7866099218845164e-05, "epoch": 0.8722044728434505, "percentage": 29.07, "elapsed_time": "0:48:29", "remaining_time": "1:58:17"}
+{"current_steps": 274, "total_steps": 939, "loss": 0.5407, "lr": 1.7843088963826437e-05, "epoch": 0.8753993610223643, "percentage": 29.18, "elapsed_time": "0:48:41", "remaining_time": "1:58:09"}
+{"current_steps": 275, "total_steps": 939, "loss": 0.5202, "lr": 1.7819970297903056e-05, "epoch": 0.8785942492012779, "percentage": 29.29, "elapsed_time": "0:48:53", "remaining_time": "1:58:02"}
+{"current_steps": 276, "total_steps": 939, "loss": 0.5356, "lr": 1.7796743540632226e-05, "epoch": 0.8817891373801917, "percentage": 29.39, "elapsed_time": "0:49:02", "remaining_time": "1:57:47"}
+{"current_steps": 277, "total_steps": 939, "loss": 0.5088, "lr": 1.7773409013065222e-05, "epoch": 0.8849840255591054, "percentage": 29.5, "elapsed_time": "0:49:14", "remaining_time": "1:57:41"}
+{"current_steps": 278, "total_steps": 939, "loss": 0.4674, "lr": 1.7749967037742976e-05, "epoch": 0.8881789137380192, "percentage": 29.61, "elapsed_time": "0:49:24", "remaining_time": "1:57:29"}
+{"current_steps": 279, "total_steps": 939, "loss": 0.5141, "lr": 1.772641793869162e-05, "epoch": 0.8913738019169329, "percentage": 29.71, "elapsed_time": "0:49:36", "remaining_time": "1:57:21"}
+{"current_steps": 280, "total_steps": 939, "loss": 0.5436, "lr": 1.7702762041418e-05, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:49:48", "remaining_time": "1:57:13"}
+{"current_steps": 281, "total_steps": 939, "loss": 0.5469, "lr": 1.7678999672905167e-05, "epoch": 0.8977635782747604, "percentage": 29.93, "elapsed_time": "0:49:58", "remaining_time": "1:57:01"}
+{"current_steps": 282, "total_steps": 939, "loss": 0.477, "lr": 1.7655131161607887e-05, "epoch": 0.9009584664536742, "percentage": 30.03, "elapsed_time": "0:50:11", "remaining_time": "1:56:56"}
+{"current_steps": 283, "total_steps": 939, "loss": 0.4949, "lr": 1.7631156837448063e-05, "epoch": 0.9041533546325878, "percentage": 30.14, "elapsed_time": "0:50:19", "remaining_time": "1:56:38"}
+{"current_steps": 284, "total_steps": 939, "loss": 0.4885, "lr": 1.7607077031810204e-05, "epoch": 0.9073482428115016, "percentage": 30.24, "elapsed_time": "0:50:28", "remaining_time": "1:56:24"}
+{"current_steps": 285, "total_steps": 939, "loss": 0.5402, "lr": 1.7582892077536832e-05, "epoch": 0.9105431309904153, "percentage": 30.35, "elapsed_time": "0:50:38", "remaining_time": "1:56:12"}
+{"current_steps": 286, "total_steps": 939, "loss": 0.5139, "lr": 1.755860230892389e-05, "epoch": 0.9137380191693291, "percentage": 30.46, "elapsed_time": "0:50:50", "remaining_time": "1:56:04"}
+{"current_steps": 287, "total_steps": 939, "loss": 0.5388, "lr": 1.75342080617161e-05, "epoch": 0.9169329073482428, "percentage": 30.56, "elapsed_time": "0:51:02", "remaining_time": "1:55:56"}
+{"current_steps": 288, "total_steps": 939, "loss": 0.5097, "lr": 1.750970967310235e-05, "epoch": 0.9201277955271565, "percentage": 30.67, "elapsed_time": "0:51:09", "remaining_time": "1:55:38"}
+{"current_steps": 289, "total_steps": 939, "loss": 0.4671, "lr": 1.7485107481711014e-05, "epoch": 0.9233226837060703, "percentage": 30.78, "elapsed_time": "0:51:21", "remaining_time": "1:55:29"}
+{"current_steps": 290, "total_steps": 939, "loss": 0.5505, "lr": 1.7460401827605277e-05, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:51:32", "remaining_time": "1:55:19"}
+{"current_steps": 291, "total_steps": 939, "loss": 0.4982, "lr": 1.7435593052278437e-05, "epoch": 0.9297124600638977, "percentage": 30.99, "elapsed_time": "0:51:44", "remaining_time": "1:55:12"}
+{"current_steps": 292, "total_steps": 939, "loss": 0.5131, "lr": 1.741068149864918e-05, "epoch": 0.9329073482428115, "percentage": 31.1, "elapsed_time": "0:51:53", "remaining_time": "1:54:58"}
+{"current_steps": 293, "total_steps": 939, "loss": 0.5345, "lr": 1.7385667511056853e-05, "epoch": 0.9361022364217252, "percentage": 31.2, "elapsed_time": "0:52:04", "remaining_time": "1:54:49"}
+{"current_steps": 294, "total_steps": 939, "loss": 0.508, "lr": 1.7360551435256673e-05, "epoch": 0.939297124600639, "percentage": 31.31, "elapsed_time": "0:52:12", "remaining_time": "1:54:33"}
+{"current_steps": 295, "total_steps": 939, "loss": 0.5033, "lr": 1.733533361841499e-05, "epoch": 0.9424920127795527, "percentage": 31.42, "elapsed_time": "0:52:21", "remaining_time": "1:54:18"}
+{"current_steps": 296, "total_steps": 939, "loss": 0.5782, "lr": 1.7310014409104456e-05, "epoch": 0.9456869009584664, "percentage": 31.52, "elapsed_time": "0:52:34", "remaining_time": "1:54:12"}
+{"current_steps": 297, "total_steps": 939, "loss": 0.4991, "lr": 1.728459415729922e-05, "epoch": 0.9488817891373802, "percentage": 31.63, "elapsed_time": "0:52:43", "remaining_time": "1:53:57"}
+{"current_steps": 298, "total_steps": 939, "loss": 0.5262, "lr": 1.7259073214370085e-05, "epoch": 0.952076677316294, "percentage": 31.74, "elapsed_time": "0:52:51", "remaining_time": "1:53:42"}
+{"current_steps": 299, "total_steps": 939, "loss": 0.5198, "lr": 1.7233451933079663e-05, "epoch": 0.9552715654952076, "percentage": 31.84, "elapsed_time": "0:53:04", "remaining_time": "1:53:36"}
+{"current_steps": 300, "total_steps": 939, "loss": 0.5044, "lr": 1.720773066757748e-05, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:53:16", "remaining_time": "1:53:28"}
+{"current_steps": 301, "total_steps": 939, "loss": 0.4913, "lr": 1.7181909773395108e-05, "epoch": 0.9616613418530351, "percentage": 32.06, "elapsed_time": "0:53:23", "remaining_time": "1:53:10"}
+{"current_steps": 302, "total_steps": 939, "loss": 0.5032, "lr": 1.715598960744121e-05, "epoch": 0.9648562300319489, "percentage": 32.16, "elapsed_time": "0:53:33", "remaining_time": "1:52:58"}
+{"current_steps": 303, "total_steps": 939, "loss": 0.4819, "lr": 1.7129970527996654e-05, "epoch": 0.9680511182108626, "percentage": 32.27, "elapsed_time": "0:53:45", "remaining_time": "1:52:51"}
+{"current_steps": 304, "total_steps": 939, "loss": 0.4706, "lr": 1.7103852894709517e-05, "epoch": 0.9712460063897763, "percentage": 32.37, "elapsed_time": "0:53:58", "remaining_time": "1:52:43"}
+{"current_steps": 305, "total_steps": 939, "loss": 0.4925, "lr": 1.707763706859015e-05, "epoch": 0.9744408945686901, "percentage": 32.48, "elapsed_time": "0:54:07", "remaining_time": "1:52:30"}
+{"current_steps": 306, "total_steps": 939, "loss": 0.4857, "lr": 1.7051323412006167e-05, "epoch": 0.9776357827476039, "percentage": 32.59, "elapsed_time": "0:54:17", "remaining_time": "1:52:18"}
+{"current_steps": 307, "total_steps": 939, "loss": 0.5001, "lr": 1.7024912288677434e-05, "epoch": 0.9808306709265175, "percentage": 32.69, "elapsed_time": "0:54:23", "remaining_time": "1:51:58"}
+{"current_steps": 308, "total_steps": 939, "loss": 0.5012, "lr": 1.6998404063671064e-05, "epoch": 0.9840255591054313, "percentage": 32.8, "elapsed_time": "0:54:34", "remaining_time": "1:51:48"}
+{"current_steps": 309, "total_steps": 939, "loss": 0.512, "lr": 1.6971799103396332e-05, "epoch": 0.987220447284345, "percentage": 32.91, "elapsed_time": "0:54:43", "remaining_time": "1:51:34"}
+{"current_steps": 310, "total_steps": 939, "loss": 0.4864, "lr": 1.6945097775599667e-05, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:54:54", "remaining_time": "1:51:24"}
+{"current_steps": 311, "total_steps": 939, "loss": 0.4719, "lr": 1.69183004493595e-05, "epoch": 0.9936102236421726, "percentage": 33.12, "elapsed_time": "0:55:04", "remaining_time": "1:51:12"}
+{"current_steps": 312, "total_steps": 939, "loss": 0.5792, "lr": 1.6891407495081228e-05, "epoch": 0.9968051118210862, "percentage": 33.23, "elapsed_time": "0:55:14", "remaining_time": "1:51:00"}
+{"current_steps": 313, "total_steps": 939, "loss": 0.5718, "lr": 1.686441928449204e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:55:25", "remaining_time": "1:50:51"}
+{"current_steps": 314, "total_steps": 939, "loss": 0.4178, "lr": 1.6837336190635824e-05, "epoch": 1.0031948881789137, "percentage": 33.44, "elapsed_time": "0:56:21", "remaining_time": "1:52:09"}
+{"current_steps": 315, "total_steps": 939, "loss": 0.423, "lr": 1.6810158587867973e-05, "epoch": 1.0063897763578276, "percentage": 33.55, "elapsed_time": "0:56:32", "remaining_time": "1:52:00"}
+{"current_steps": 316, "total_steps": 939, "loss": 0.3532, "lr": 1.6782886851850237e-05, "epoch": 1.0095846645367412, "percentage": 33.65, "elapsed_time": "0:56:40", "remaining_time": "1:51:43"}
+{"current_steps": 317, "total_steps": 939, "loss": 0.3665, "lr": 1.675552135954552e-05, "epoch": 1.012779552715655, "percentage": 33.76, "elapsed_time": "0:56:52", "remaining_time": "1:51:36"}
+{"current_steps": 318, "total_steps": 939, "loss": 0.3836, "lr": 1.672806248921266e-05, "epoch": 1.0159744408945688, "percentage": 33.87, "elapsed_time": "0:57:02", "remaining_time": "1:51:23"}
+{"current_steps": 319, "total_steps": 939, "loss": 0.3768, "lr": 1.6700510620401223e-05, "epoch": 1.0191693290734825, "percentage": 33.97, "elapsed_time": "0:57:12", "remaining_time": "1:51:10"}
+{"current_steps": 320, "total_steps": 939, "loss": 0.4059, "lr": 1.6672866133946244e-05, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:57:23", "remaining_time": "1:51:01"}
+{"current_steps": 321, "total_steps": 939, "loss": 0.4057, "lr": 1.664512941196295e-05, "epoch": 1.0255591054313098, "percentage": 34.19, "elapsed_time": "0:57:35", "remaining_time": "1:50:52"}
+{"current_steps": 322, "total_steps": 939, "loss": 0.4334, "lr": 1.6617300837841502e-05, "epoch": 1.0287539936102237, "percentage": 34.29, "elapsed_time": "0:57:44", "remaining_time": "1:50:38"}
+{"current_steps": 323, "total_steps": 939, "loss": 0.3821, "lr": 1.6589380796241687e-05, "epoch": 1.0319488817891374, "percentage": 34.4, "elapsed_time": "0:57:52", "remaining_time": "1:50:22"}
+{"current_steps": 324, "total_steps": 939, "loss": 0.3899, "lr": 1.6561369673087588e-05, "epoch": 1.035143769968051, "percentage": 34.5, "elapsed_time": "0:58:04", "remaining_time": "1:50:13"}
+{"current_steps": 325, "total_steps": 939, "loss": 0.3522, "lr": 1.653326785556227e-05, "epoch": 1.038338658146965, "percentage": 34.61, "elapsed_time": "0:58:12", "remaining_time": "1:49:57"}
+{"current_steps": 326, "total_steps": 939, "loss": 0.3838, "lr": 1.650507573210242e-05, "epoch": 1.0415335463258786, "percentage": 34.72, "elapsed_time": "0:58:24", "remaining_time": "1:49:49"}
+{"current_steps": 327, "total_steps": 939, "loss": 0.4566, "lr": 1.6476793692392966e-05, "epoch": 1.0447284345047922, "percentage": 34.82, "elapsed_time": "0:58:35", "remaining_time": "1:49:39"}
+{"current_steps": 328, "total_steps": 939, "loss": 0.3501, "lr": 1.6448422127361707e-05, "epoch": 1.0479233226837061, "percentage": 34.93, "elapsed_time": "0:58:46", "remaining_time": "1:49:29"}
+{"current_steps": 329, "total_steps": 939, "loss": 0.382, "lr": 1.641996142917391e-05, "epoch": 1.0511182108626198, "percentage": 35.04, "elapsed_time": "0:58:58", "remaining_time": "1:49:21"}
+{"current_steps": 330, "total_steps": 939, "loss": 0.4044, "lr": 1.6391411991226873e-05, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:59:10", "remaining_time": "1:49:11"}
+{"current_steps": 331, "total_steps": 939, "loss": 0.435, "lr": 1.6362774208144504e-05, "epoch": 1.0575079872204474, "percentage": 35.25, "elapsed_time": "0:59:22", "remaining_time": "1:49:03"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e48798705418901124a1b96255284ead524466490b91dee5e34b5d2bdf9611
+size 7224