Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbb963f7058e9d006a33a3a6b01d32b9313c1740759aeddc012ead2655b7853
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7ea2026d43a5ea62248c30b6d0a451d7075855b74d29e935f98bc113c58633
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88943e18e673ffb22df6ebf0bf03fae2c2f4be0412660ba047596b2c7472a03
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61749655a035d30004ad5fae4ebdbbca6c540a67d05ef95ab88a3baa8654b2dc
+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 +1,314 @@
+{"current_steps": 1, "total_steps": 900, "loss": 1.2731, "lr": 8.88888888888889e-07, "epoch": 0.0055286800276434, "percentage": 0.11, "elapsed_time": "0:01:57", "remaining_time": "1 day, 5:19:24"}
+{"current_steps": 2, "total_steps": 900, "loss": 1.2615, "lr": 1.777777777777778e-06, "epoch": 0.0110573600552868, "percentage": 0.22, "elapsed_time": "0:03:43", "remaining_time": "1 day, 3:52:40"}
+{"current_steps": 3, "total_steps": 900, "loss": 1.2505, "lr": 2.666666666666667e-06, "epoch": 0.0165860400829302, "percentage": 0.33, "elapsed_time": "0:05:31", "remaining_time": "1 day, 3:31:51"}
+{"current_steps": 4, "total_steps": 900, "loss": 1.2581, "lr": 3.555555555555556e-06, "epoch": 0.0221147201105736, "percentage": 0.44, "elapsed_time": "0:07:19", "remaining_time": "1 day, 3:21:29"}
+{"current_steps": 5, "total_steps": 900, "loss": 1.2083, "lr": 4.444444444444444e-06, "epoch": 0.027643400138217002, "percentage": 0.56, "elapsed_time": "0:09:06", "remaining_time": "1 day, 3:11:10"}
+{"current_steps": 6, "total_steps": 900, "loss": 1.1506, "lr": 5.333333333333334e-06, "epoch": 0.0331720801658604, "percentage": 0.67, "elapsed_time": "0:10:54", "remaining_time": "1 day, 3:05:05"}
+{"current_steps": 7, "total_steps": 900, "loss": 1.1576, "lr": 6.222222222222223e-06, "epoch": 0.038700760193503804, "percentage": 0.78, "elapsed_time": "0:12:41", "remaining_time": "1 day, 2:59:33"}
+{"current_steps": 8, "total_steps": 900, "loss": 1.1651, "lr": 7.111111111111112e-06, "epoch": 0.0442294402211472, "percentage": 0.89, "elapsed_time": "0:14:29", "remaining_time": "1 day, 2:56:24"}
+{"current_steps": 9, "total_steps": 900, "loss": 1.1572, "lr": 8.000000000000001e-06, "epoch": 0.0497581202487906, "percentage": 1.0, "elapsed_time": "0:16:18", "remaining_time": "1 day, 2:53:47"}
+{"current_steps": 10, "total_steps": 900, "loss": 1.1352, "lr": 8.888888888888888e-06, "epoch": 0.055286800276434005, "percentage": 1.11, "elapsed_time": "0:18:05", "remaining_time": "1 day, 2:50:37"}
+{"current_steps": 11, "total_steps": 900, "loss": 1.1166, "lr": 9.777777777777779e-06, "epoch": 0.0608154803040774, "percentage": 1.22, "elapsed_time": "0:19:54", "remaining_time": "1 day, 2:49:17"}
+{"current_steps": 12, "total_steps": 900, "loss": 1.1148, "lr": 1.0666666666666667e-05, "epoch": 0.0663441603317208, "percentage": 1.33, "elapsed_time": "0:21:42", "remaining_time": "1 day, 2:45:49"}
+{"current_steps": 13, "total_steps": 900, "loss": 1.0741, "lr": 1.1555555555555556e-05, "epoch": 0.0718728403593642, "percentage": 1.44, "elapsed_time": "0:23:27", "remaining_time": "1 day, 2:41:05"}
+{"current_steps": 14, "total_steps": 900, "loss": 1.0653, "lr": 1.2444444444444446e-05, "epoch": 0.07740152038700761, "percentage": 1.56, "elapsed_time": "0:25:14", "remaining_time": "1 day, 2:37:56"}
+{"current_steps": 15, "total_steps": 900, "loss": 1.0556, "lr": 1.3333333333333333e-05, "epoch": 0.082930200414651, "percentage": 1.67, "elapsed_time": "0:27:01", "remaining_time": "1 day, 2:34:45"}
+{"current_steps": 16, "total_steps": 900, "loss": 1.0247, "lr": 1.4222222222222224e-05, "epoch": 0.0884588804422944, "percentage": 1.78, "elapsed_time": "0:28:50", "remaining_time": "1 day, 2:33:41"}
+{"current_steps": 17, "total_steps": 900, "loss": 1.0108, "lr": 1.5111111111111112e-05, "epoch": 0.09398756046993781, "percentage": 1.89, "elapsed_time": "0:30:38", "remaining_time": "1 day, 2:31:19"}
+{"current_steps": 18, "total_steps": 900, "loss": 0.9858, "lr": 1.6000000000000003e-05, "epoch": 0.0995162404975812, "percentage": 2.0, "elapsed_time": "0:32:23", "remaining_time": "1 day, 2:26:56"}
+{"current_steps": 19, "total_steps": 900, "loss": 0.9963, "lr": 1.688888888888889e-05, "epoch": 0.1050449205252246, "percentage": 2.11, "elapsed_time": "0:34:10", "remaining_time": "1 day, 2:24:26"}
+{"current_steps": 20, "total_steps": 900, "loss": 0.9705, "lr": 1.7777777777777777e-05, "epoch": 0.11057360055286801, "percentage": 2.22, "elapsed_time": "0:35:56", "remaining_time": "1 day, 2:21:33"}
+{"current_steps": 21, "total_steps": 900, "loss": 0.9861, "lr": 1.866666666666667e-05, "epoch": 0.1161022805805114, "percentage": 2.33, "elapsed_time": "0:37:43", "remaining_time": "1 day, 2:18:43"}
+{"current_steps": 22, "total_steps": 900, "loss": 0.9762, "lr": 1.9555555555555557e-05, "epoch": 0.1216309606081548, "percentage": 2.44, "elapsed_time": "0:39:29", "remaining_time": "1 day, 2:15:45"}
+{"current_steps": 23, "total_steps": 900, "loss": 0.953, "lr": 2.0444444444444446e-05, "epoch": 0.1271596406357982, "percentage": 2.56, "elapsed_time": "0:41:16", "remaining_time": "1 day, 2:13:54"}
+{"current_steps": 24, "total_steps": 900, "loss": 0.957, "lr": 2.1333333333333335e-05, "epoch": 0.1326883206634416, "percentage": 2.67, "elapsed_time": "0:43:04", "remaining_time": "1 day, 2:12:18"}
+{"current_steps": 25, "total_steps": 900, "loss": 0.9305, "lr": 2.2222222222222227e-05, "epoch": 0.138217000691085, "percentage": 2.78, "elapsed_time": "0:44:52", "remaining_time": "1 day, 2:10:29"}
+{"current_steps": 26, "total_steps": 900, "loss": 0.9251, "lr": 2.3111111111111112e-05, "epoch": 0.1437456807187284, "percentage": 2.89, "elapsed_time": "0:46:39", "remaining_time": "1 day, 2:08:14"}
+{"current_steps": 27, "total_steps": 900, "loss": 0.9367, "lr": 2.4e-05, "epoch": 0.1492743607463718, "percentage": 3.0, "elapsed_time": "0:48:25", "remaining_time": "1 day, 2:05:43"}
+{"current_steps": 28, "total_steps": 900, "loss": 0.9232, "lr": 2.4888888888888893e-05, "epoch": 0.15480304077401522, "percentage": 3.11, "elapsed_time": "0:50:14", "remaining_time": "1 day, 2:04:26"}
+{"current_steps": 29, "total_steps": 900, "loss": 0.9387, "lr": 2.577777777777778e-05, "epoch": 0.1603317208016586, "percentage": 3.22, "elapsed_time": "0:52:01", "remaining_time": "1 day, 2:02:20"}
+{"current_steps": 30, "total_steps": 900, "loss": 0.9125, "lr": 2.6666666666666667e-05, "epoch": 0.165860400829302, "percentage": 3.33, "elapsed_time": "0:53:49", "remaining_time": "1 day, 2:00:41"}
+{"current_steps": 31, "total_steps": 900, "loss": 0.9119, "lr": 2.755555555555556e-05, "epoch": 0.1713890808569454, "percentage": 3.44, "elapsed_time": "0:55:35", "remaining_time": "1 day, 1:58:30"}
+{"current_steps": 32, "total_steps": 900, "loss": 0.8996, "lr": 2.8444444444444447e-05, "epoch": 0.1769177608845888, "percentage": 3.56, "elapsed_time": "0:57:23", "remaining_time": "1 day, 1:56:32"}
+{"current_steps": 33, "total_steps": 900, "loss": 0.8985, "lr": 2.9333333333333333e-05, "epoch": 0.1824464409122322, "percentage": 3.67, "elapsed_time": "0:59:10", "remaining_time": "1 day, 1:54:47"}
+{"current_steps": 34, "total_steps": 900, "loss": 0.9139, "lr": 3.0222222222222225e-05, "epoch": 0.18797512093987562, "percentage": 3.78, "elapsed_time": "1:00:57", "remaining_time": "1 day, 1:52:31"}
+{"current_steps": 35, "total_steps": 900, "loss": 0.8807, "lr": 3.111111111111112e-05, "epoch": 0.193503800967519, "percentage": 3.89, "elapsed_time": "1:02:44", "remaining_time": "1 day, 1:50:33"}
+{"current_steps": 36, "total_steps": 900, "loss": 0.8864, "lr": 3.2000000000000005e-05, "epoch": 0.1990324809951624, "percentage": 4.0, "elapsed_time": "1:04:31", "remaining_time": "1 day, 1:48:30"}
+{"current_steps": 37, "total_steps": 900, "loss": 0.8923, "lr": 3.288888888888889e-05, "epoch": 0.2045611610228058, "percentage": 4.11, "elapsed_time": "1:06:17", "remaining_time": "1 day, 1:46:23"}
+{"current_steps": 38, "total_steps": 900, "loss": 0.8946, "lr": 3.377777777777778e-05, "epoch": 0.2100898410504492, "percentage": 4.22, "elapsed_time": "1:08:04", "remaining_time": "1 day, 1:44:17"}
+{"current_steps": 39, "total_steps": 900, "loss": 0.8882, "lr": 3.466666666666667e-05, "epoch": 0.2156185210780926, "percentage": 4.33, "elapsed_time": "1:09:52", "remaining_time": "1 day, 1:42:27"}
+{"current_steps": 40, "total_steps": 900, "loss": 0.8896, "lr": 3.555555555555555e-05, "epoch": 0.22114720110573602, "percentage": 4.44, "elapsed_time": "1:11:39", "remaining_time": "1 day, 1:40:30"}
+{"current_steps": 41, "total_steps": 900, "loss": 0.8778, "lr": 3.644444444444445e-05, "epoch": 0.22667588113337941, "percentage": 4.56, "elapsed_time": "1:13:26", "remaining_time": "1 day, 1:38:47"}
+{"current_steps": 42, "total_steps": 900, "loss": 0.8941, "lr": 3.733333333333334e-05, "epoch": 0.2322045611610228, "percentage": 4.67, "elapsed_time": "1:15:14", "remaining_time": "1 day, 1:36:59"}
+{"current_steps": 43, "total_steps": 900, "loss": 0.8806, "lr": 3.8222222222222226e-05, "epoch": 0.2377332411886662, "percentage": 4.78, "elapsed_time": "1:17:00", "remaining_time": "1 day, 1:34:53"}
+{"current_steps": 44, "total_steps": 900, "loss": 0.8906, "lr": 3.9111111111111115e-05, "epoch": 0.2432619212163096, "percentage": 4.89, "elapsed_time": "1:18:48", "remaining_time": "1 day, 1:33:09"}
+{"current_steps": 45, "total_steps": 900, "loss": 0.8751, "lr": 4e-05, "epoch": 0.248790601243953, "percentage": 5.0, "elapsed_time": "1:20:35", "remaining_time": "1 day, 1:31:15"}
+{"current_steps": 46, "total_steps": 900, "loss": 0.8788, "lr": 4.088888888888889e-05, "epoch": 0.2543192812715964, "percentage": 5.11, "elapsed_time": "1:22:22", "remaining_time": "1 day, 1:29:20"}
+{"current_steps": 47, "total_steps": 900, "loss": 0.876, "lr": 4.177777777777778e-05, "epoch": 0.2598479612992398, "percentage": 5.22, "elapsed_time": "1:24:10", "remaining_time": "1 day, 1:27:33"}
+{"current_steps": 48, "total_steps": 900, "loss": 0.8701, "lr": 4.266666666666667e-05, "epoch": 0.2653766413268832, "percentage": 5.33, "elapsed_time": "1:25:58", "remaining_time": "1 day, 1:26:00"}
+{"current_steps": 49, "total_steps": 900, "loss": 0.8781, "lr": 4.355555555555556e-05, "epoch": 0.2709053213545266, "percentage": 5.44, "elapsed_time": "1:27:46", "remaining_time": "1 day, 1:24:26"}
+{"current_steps": 50, "total_steps": 900, "loss": 0.8657, "lr": 4.444444444444445e-05, "epoch": 0.27643400138217, "percentage": 5.56, "elapsed_time": "1:29:34", "remaining_time": "1 day, 1:22:47"}
+{"current_steps": 51, "total_steps": 900, "loss": 0.8794, "lr": 4.5333333333333335e-05, "epoch": 0.2819626814098134, "percentage": 5.67, "elapsed_time": "1:31:21", "remaining_time": "1 day, 1:20:49"}
+{"current_steps": 52, "total_steps": 900, "loss": 0.8735, "lr": 4.6222222222222224e-05, "epoch": 0.2874913614374568, "percentage": 5.78, "elapsed_time": "1:33:08", "remaining_time": "1 day, 1:18:54"}
+{"current_steps": 53, "total_steps": 900, "loss": 0.87, "lr": 4.711111111111112e-05, "epoch": 0.2930200414651002, "percentage": 5.89, "elapsed_time": "1:34:55", "remaining_time": "1 day, 1:17:02"}
+{"current_steps": 54, "total_steps": 900, "loss": 0.8806, "lr": 4.8e-05, "epoch": 0.2985487214927436, "percentage": 6.0, "elapsed_time": "1:36:43", "remaining_time": "1 day, 1:15:15"}
+{"current_steps": 55, "total_steps": 900, "loss": 0.8638, "lr": 4.88888888888889e-05, "epoch": 0.304077401520387, "percentage": 6.11, "elapsed_time": "1:38:30", "remaining_time": "1 day, 1:13:27"}
+{"current_steps": 56, "total_steps": 900, "loss": 0.8777, "lr": 4.9777777777777785e-05, "epoch": 0.30960608154803043, "percentage": 6.22, "elapsed_time": "1:40:18", "remaining_time": "1 day, 1:11:39"}
+{"current_steps": 57, "total_steps": 900, "loss": 0.8615, "lr": 5.066666666666667e-05, "epoch": 0.3151347615756738, "percentage": 6.33, "elapsed_time": "1:42:04", "remaining_time": "1 day, 1:09:43"}
+{"current_steps": 58, "total_steps": 900, "loss": 0.8568, "lr": 5.155555555555556e-05, "epoch": 0.3206634416033172, "percentage": 6.44, "elapsed_time": "1:43:52", "remaining_time": "1 day, 1:08:04"}
+{"current_steps": 59, "total_steps": 900, "loss": 0.8624, "lr": 5.244444444444445e-05, "epoch": 0.3261921216309606, "percentage": 6.56, "elapsed_time": "1:45:40", "remaining_time": "1 day, 1:06:14"}
+{"current_steps": 60, "total_steps": 900, "loss": 0.8862, "lr": 5.333333333333333e-05, "epoch": 0.331720801658604, "percentage": 6.67, "elapsed_time": "1:47:27", "remaining_time": "1 day, 1:04:21"}
+{"current_steps": 61, "total_steps": 900, "loss": 0.8569, "lr": 5.422222222222223e-05, "epoch": 0.3372494816862474, "percentage": 6.78, "elapsed_time": "1:49:12", "remaining_time": "1 day, 1:02:10"}
+{"current_steps": 62, "total_steps": 900, "loss": 0.8691, "lr": 5.511111111111112e-05, "epoch": 0.3427781617138908, "percentage": 6.89, "elapsed_time": "1:50:58", "remaining_time": "1 day, 1:00:02"}
+{"current_steps": 63, "total_steps": 900, "loss": 0.8686, "lr": 5.6e-05, "epoch": 0.3483068417415342, "percentage": 7.0, "elapsed_time": "1:52:44", "remaining_time": "1 day, 0:57:57"}
+{"current_steps": 64, "total_steps": 900, "loss": 0.8615, "lr": 5.6888888888888895e-05, "epoch": 0.3538355217691776, "percentage": 7.11, "elapsed_time": "1:54:32", "remaining_time": "1 day, 0:56:09"}
+{"current_steps": 65, "total_steps": 900, "loss": 0.8593, "lr": 5.777777777777778e-05, "epoch": 0.359364201796821, "percentage": 7.22, "elapsed_time": "1:56:18", "remaining_time": "1 day, 0:54:04"}
+{"current_steps": 66, "total_steps": 900, "loss": 0.8421, "lr": 5.8666666666666665e-05, "epoch": 0.3648928818244644, "percentage": 7.33, "elapsed_time": "1:58:05", "remaining_time": "1 day, 0:52:18"}
+{"current_steps": 67, "total_steps": 900, "loss": 0.8551, "lr": 5.955555555555556e-05, "epoch": 0.3704215618521078, "percentage": 7.44, "elapsed_time": "1:59:52", "remaining_time": "1 day, 0:50:26"}
+{"current_steps": 68, "total_steps": 900, "loss": 0.8575, "lr": 6.044444444444445e-05, "epoch": 0.37595024187975123, "percentage": 7.56, "elapsed_time": "2:01:41", "remaining_time": "1 day, 0:48:55"}
+{"current_steps": 69, "total_steps": 900, "loss": 0.8603, "lr": 6.133333333333334e-05, "epoch": 0.38147892190739463, "percentage": 7.67, "elapsed_time": "2:03:28", "remaining_time": "1 day, 0:46:59"}
+{"current_steps": 70, "total_steps": 900, "loss": 0.8652, "lr": 6.222222222222223e-05, "epoch": 0.387007601935038, "percentage": 7.78, "elapsed_time": "2:05:15", "remaining_time": "1 day, 0:45:10"}
+{"current_steps": 71, "total_steps": 900, "loss": 0.8538, "lr": 6.311111111111112e-05, "epoch": 0.3925362819626814, "percentage": 7.89, "elapsed_time": "2:07:02", "remaining_time": "1 day, 0:43:22"}
+{"current_steps": 72, "total_steps": 900, "loss": 0.8626, "lr": 6.400000000000001e-05, "epoch": 0.3980649619903248, "percentage": 8.0, "elapsed_time": "2:08:49", "remaining_time": "1 day, 0:41:34"}
+{"current_steps": 73, "total_steps": 900, "loss": 0.8706, "lr": 6.488888888888889e-05, "epoch": 0.4035936420179682, "percentage": 8.11, "elapsed_time": "2:10:37", "remaining_time": "1 day, 0:39:49"}
+{"current_steps": 74, "total_steps": 900, "loss": 0.8514, "lr": 6.577777777777777e-05, "epoch": 0.4091223220456116, "percentage": 8.22, "elapsed_time": "2:12:24", "remaining_time": "1 day, 0:37:58"}
+{"current_steps": 75, "total_steps": 900, "loss": 0.8478, "lr": 6.666666666666667e-05, "epoch": 0.414651002073255, "percentage": 8.33, "elapsed_time": "2:14:11", "remaining_time": "1 day, 0:36:05"}
+{"current_steps": 76, "total_steps": 900, "loss": 0.8511, "lr": 6.755555555555557e-05, "epoch": 0.4201796821008984, "percentage": 8.44, "elapsed_time": "2:15:58", "remaining_time": "1 day, 0:34:11"}
+{"current_steps": 77, "total_steps": 900, "loss": 0.8563, "lr": 6.844444444444445e-05, "epoch": 0.4257083621285418, "percentage": 8.56, "elapsed_time": "2:17:44", "remaining_time": "1 day, 0:32:13"}
+{"current_steps": 78, "total_steps": 900, "loss": 0.8497, "lr": 6.933333333333334e-05, "epoch": 0.4312370421561852, "percentage": 8.67, "elapsed_time": "2:19:31", "remaining_time": "1 day, 0:30:23"}
+{"current_steps": 79, "total_steps": 900, "loss": 0.8414, "lr": 7.022222222222222e-05, "epoch": 0.4367657221838286, "percentage": 8.78, "elapsed_time": "2:21:17", "remaining_time": "1 day, 0:28:24"}
+{"current_steps": 80, "total_steps": 900, "loss": 0.857, "lr": 7.11111111111111e-05, "epoch": 0.44229440221147204, "percentage": 8.89, "elapsed_time": "2:23:04", "remaining_time": "1 day, 0:26:32"}
+{"current_steps": 81, "total_steps": 900, "loss": 0.8563, "lr": 7.2e-05, "epoch": 0.44782308223911543, "percentage": 9.0, "elapsed_time": "2:24:51", "remaining_time": "1 day, 0:24:39"}
+{"current_steps": 82, "total_steps": 900, "loss": 0.8562, "lr": 7.28888888888889e-05, "epoch": 0.45335176226675883, "percentage": 9.11, "elapsed_time": "2:26:37", "remaining_time": "1 day, 0:22:43"}
+{"current_steps": 83, "total_steps": 900, "loss": 0.8666, "lr": 7.377777777777779e-05, "epoch": 0.4588804422944022, "percentage": 9.22, "elapsed_time": "2:28:24", "remaining_time": "1 day, 0:20:52"}
+{"current_steps": 84, "total_steps": 900, "loss": 0.8732, "lr": 7.466666666666667e-05, "epoch": 0.4644091223220456, "percentage": 9.33, "elapsed_time": "2:30:11", "remaining_time": "1 day, 0:19:00"}
+{"current_steps": 85, "total_steps": 900, "loss": 0.8614, "lr": 7.555555555555556e-05, "epoch": 0.469937802349689, "percentage": 9.44, "elapsed_time": "2:31:58", "remaining_time": "1 day, 0:17:11"}
+{"current_steps": 86, "total_steps": 900, "loss": 0.8497, "lr": 7.644444444444445e-05, "epoch": 0.4754664823773324, "percentage": 9.56, "elapsed_time": "2:33:45", "remaining_time": "1 day, 0:15:22"}
+{"current_steps": 87, "total_steps": 900, "loss": 0.8902, "lr": 7.733333333333333e-05, "epoch": 0.4809951624049758, "percentage": 9.67, "elapsed_time": "2:35:32", "remaining_time": "1 day, 0:13:35"}
+{"current_steps": 88, "total_steps": 900, "loss": 0.8652, "lr": 7.822222222222223e-05, "epoch": 0.4865238424326192, "percentage": 9.78, "elapsed_time": "2:37:19", "remaining_time": "1 day, 0:11:44"}
+{"current_steps": 89, "total_steps": 900, "loss": 0.8705, "lr": 7.911111111111112e-05, "epoch": 0.4920525224602626, "percentage": 9.89, "elapsed_time": "2:39:05", "remaining_time": "1 day, 0:09:40"}
+{"current_steps": 90, "total_steps": 900, "loss": 0.8703, "lr": 8e-05, "epoch": 0.497581202487906, "percentage": 10.0, "elapsed_time": "2:40:52", "remaining_time": "1 day, 0:07:51"}
+{"current_steps": 91, "total_steps": 900, "loss": 0.8452, "lr": 7.999969914366625e-05, "epoch": 0.5031098825155494, "percentage": 10.11, "elapsed_time": "2:42:38", "remaining_time": "1 day, 0:05:56"}
+{"current_steps": 92, "total_steps": 900, "loss": 0.8518, "lr": 7.999879657919071e-05, "epoch": 0.5086385625431928, "percentage": 10.22, "elapsed_time": "2:44:25", "remaining_time": "1 day, 0:04:01"}
+{"current_steps": 93, "total_steps": 900, "loss": 0.8493, "lr": 7.99972923201505e-05, "epoch": 0.5141672425708362, "percentage": 10.33, "elapsed_time": "2:46:10", "remaining_time": "1 day, 0:02:00"}
+{"current_steps": 94, "total_steps": 900, "loss": 0.8582, "lr": 7.999518638917391e-05, "epoch": 0.5196959225984796, "percentage": 10.44, "elapsed_time": "2:47:57", "remaining_time": "1 day, 0:00:12"}
+{"current_steps": 95, "total_steps": 900, "loss": 0.8508, "lr": 7.999247881794007e-05, "epoch": 0.525224602626123, "percentage": 10.56, "elapsed_time": "2:49:46", "remaining_time": "23:58:34"}
+{"current_steps": 96, "total_steps": 900, "loss": 0.8531, "lr": 7.998916964717848e-05, "epoch": 0.5307532826537664, "percentage": 10.67, "elapsed_time": "2:51:33", "remaining_time": "23:56:43"}
+{"current_steps": 97, "total_steps": 900, "loss": 0.8504, "lr": 7.998525892666838e-05, "epoch": 0.5362819626814098, "percentage": 10.78, "elapsed_time": "2:53:20", "remaining_time": "23:54:56"}
+{"current_steps": 98, "total_steps": 900, "loss": 0.8356, "lr": 7.998074671523805e-05, "epoch": 0.5418106427090532, "percentage": 10.89, "elapsed_time": "2:55:07", "remaining_time": "23:53:09"}
+{"current_steps": 99, "total_steps": 900, "loss": 0.8494, "lr": 7.997563308076384e-05, "epoch": 0.5473393227366966, "percentage": 11.0, "elapsed_time": "2:56:55", "remaining_time": "23:51:26"}
+{"current_steps": 100, "total_steps": 900, "loss": 0.8411, "lr": 7.996991810016922e-05, "epoch": 0.55286800276434, "percentage": 11.11, "elapsed_time": "2:58:42", "remaining_time": "23:49:38"}
+{"current_steps": 101, "total_steps": 900, "loss": 0.8332, "lr": 7.996360185942358e-05, "epoch": 0.5583966827919834, "percentage": 11.22, "elapsed_time": "3:00:28", "remaining_time": "23:47:45"}
+{"current_steps": 102, "total_steps": 900, "loss": 0.8464, "lr": 7.9956684453541e-05, "epoch": 0.5639253628196268, "percentage": 11.33, "elapsed_time": "3:02:15", "remaining_time": "23:45:57"}
+{"current_steps": 103, "total_steps": 900, "loss": 0.8501, "lr": 7.994916598657872e-05, "epoch": 0.5694540428472702, "percentage": 11.44, "elapsed_time": "3:04:01", "remaining_time": "23:44:00"}
+{"current_steps": 104, "total_steps": 900, "loss": 0.8421, "lr": 7.994104657163567e-05, "epoch": 0.5749827228749136, "percentage": 11.56, "elapsed_time": "3:05:47", "remaining_time": "23:42:04"}
+{"current_steps": 105, "total_steps": 900, "loss": 0.8274, "lr": 7.993232633085074e-05, "epoch": 0.580511402902557, "percentage": 11.67, "elapsed_time": "3:07:34", "remaining_time": "23:40:15"}
+{"current_steps": 106, "total_steps": 900, "loss": 0.8241, "lr": 7.992300539540088e-05, "epoch": 0.5860400829302004, "percentage": 11.78, "elapsed_time": "3:09:21", "remaining_time": "23:38:26"}
+{"current_steps": 107, "total_steps": 900, "loss": 0.8378, "lr": 7.991308390549925e-05, "epoch": 0.5915687629578438, "percentage": 11.89, "elapsed_time": "3:11:09", "remaining_time": "23:36:43"}
+{"current_steps": 108, "total_steps": 900, "loss": 0.838, "lr": 7.990256201039297e-05, "epoch": 0.5970974429854872, "percentage": 12.0, "elapsed_time": "3:12:56", "remaining_time": "23:34:52"}
+{"current_steps": 109, "total_steps": 900, "loss": 0.8365, "lr": 7.989143986836101e-05, "epoch": 0.6026261230131306, "percentage": 12.11, "elapsed_time": "3:14:42", "remaining_time": "23:33:00"}
+{"current_steps": 110, "total_steps": 900, "loss": 0.8412, "lr": 7.987971764671168e-05, "epoch": 0.608154803040774, "percentage": 12.22, "elapsed_time": "3:16:30", "remaining_time": "23:31:15"}
+{"current_steps": 111, "total_steps": 900, "loss": 0.8432, "lr": 7.986739552178024e-05, "epoch": 0.6136834830684175, "percentage": 12.33, "elapsed_time": "3:18:16", "remaining_time": "23:29:23"}
+{"current_steps": 112, "total_steps": 900, "loss": 0.8367, "lr": 7.985447367892616e-05, "epoch": 0.6192121630960609, "percentage": 12.44, "elapsed_time": "3:20:03", "remaining_time": "23:27:35"}
+{"current_steps": 113, "total_steps": 900, "loss": 0.8301, "lr": 7.984095231253031e-05, "epoch": 0.6247408431237043, "percentage": 12.56, "elapsed_time": "3:21:51", "remaining_time": "23:25:48"}
+{"current_steps": 114, "total_steps": 900, "loss": 0.8391, "lr": 7.982683162599218e-05, "epoch": 0.6302695231513477, "percentage": 12.67, "elapsed_time": "3:23:37", "remaining_time": "23:23:59"}
+{"current_steps": 115, "total_steps": 900, "loss": 0.8312, "lr": 7.981211183172663e-05, "epoch": 0.635798203178991, "percentage": 12.78, "elapsed_time": "3:25:24", "remaining_time": "23:22:10"}
+{"current_steps": 116, "total_steps": 900, "loss": 0.8323, "lr": 7.979679315116086e-05, "epoch": 0.6413268832066344, "percentage": 12.89, "elapsed_time": "3:27:12", "remaining_time": "23:20:23"}
+{"current_steps": 117, "total_steps": 900, "loss": 0.8388, "lr": 7.978087581473094e-05, "epoch": 0.6468555632342778, "percentage": 13.0, "elapsed_time": "3:28:58", "remaining_time": "23:18:30"}
+{"current_steps": 118, "total_steps": 900, "loss": 0.8357, "lr": 7.976436006187846e-05, "epoch": 0.6523842432619212, "percentage": 13.11, "elapsed_time": "3:30:45", "remaining_time": "23:16:40"}
+{"current_steps": 119, "total_steps": 900, "loss": 0.8253, "lr": 7.974724614104686e-05, "epoch": 0.6579129232895646, "percentage": 13.22, "elapsed_time": "3:32:32", "remaining_time": "23:14:55"}
+{"current_steps": 120, "total_steps": 900, "loss": 0.8392, "lr": 7.972953430967773e-05, "epoch": 0.663441603317208, "percentage": 13.33, "elapsed_time": "3:34:20", "remaining_time": "23:13:11"}
+{"current_steps": 121, "total_steps": 900, "loss": 0.8407, "lr": 7.971122483420687e-05, "epoch": 0.6689702833448514, "percentage": 13.44, "elapsed_time": "3:36:07", "remaining_time": "23:11:27"}
+{"current_steps": 122, "total_steps": 900, "loss": 0.8414, "lr": 7.96923179900604e-05, "epoch": 0.6744989633724948, "percentage": 13.56, "elapsed_time": "3:37:56", "remaining_time": "23:09:48"}
+{"current_steps": 123, "total_steps": 900, "loss": 0.8395, "lr": 7.967281406165047e-05, "epoch": 0.6800276434001382, "percentage": 13.67, "elapsed_time": "3:39:44", "remaining_time": "23:08:05"}
+{"current_steps": 124, "total_steps": 900, "loss": 0.8246, "lr": 7.965271334237114e-05, "epoch": 0.6855563234277816, "percentage": 13.78, "elapsed_time": "3:41:31", "remaining_time": "23:06:17"}
+{"current_steps": 125, "total_steps": 900, "loss": 0.8317, "lr": 7.963201613459381e-05, "epoch": 0.691085003455425, "percentage": 13.89, "elapsed_time": "3:43:18", "remaining_time": "23:04:31"}
+{"current_steps": 126, "total_steps": 900, "loss": 0.8349, "lr": 7.961072274966282e-05, "epoch": 0.6966136834830684, "percentage": 14.0, "elapsed_time": "3:45:05", "remaining_time": "23:02:42"}
+{"current_steps": 127, "total_steps": 900, "loss": 0.8345, "lr": 7.958883350789062e-05, "epoch": 0.7021423635107118, "percentage": 14.11, "elapsed_time": "3:46:53", "remaining_time": "23:00:57"}
+{"current_steps": 128, "total_steps": 900, "loss": 0.8221, "lr": 7.95663487385531e-05, "epoch": 0.7076710435383552, "percentage": 14.22, "elapsed_time": "3:48:39", "remaining_time": "22:59:05"}
+{"current_steps": 129, "total_steps": 900, "loss": 0.826, "lr": 7.954326877988446e-05, "epoch": 0.7131997235659986, "percentage": 14.33, "elapsed_time": "3:50:27", "remaining_time": "22:57:20"}
+{"current_steps": 130, "total_steps": 900, "loss": 0.8454, "lr": 7.951959397907237e-05, "epoch": 0.718728403593642, "percentage": 14.44, "elapsed_time": "3:52:14", "remaining_time": "22:55:32"}
+{"current_steps": 131, "total_steps": 900, "loss": 0.8355, "lr": 7.949532469225245e-05, "epoch": 0.7242570836212854, "percentage": 14.56, "elapsed_time": "3:54:00", "remaining_time": "22:53:43"}
+{"current_steps": 132, "total_steps": 900, "loss": 0.8369, "lr": 7.947046128450319e-05, "epoch": 0.7297857636489288, "percentage": 14.67, "elapsed_time": "3:55:49", "remaining_time": "22:52:01"}
+{"current_steps": 133, "total_steps": 900, "loss": 0.8347, "lr": 7.944500412984021e-05, "epoch": 0.7353144436765722, "percentage": 14.78, "elapsed_time": "3:57:34", "remaining_time": "22:50:05"}
+{"current_steps": 1, "total_steps": 900, "loss": 1.2731, "lr": 8.88888888888889e-07, "epoch": 0.0055286800276434, "percentage": 0.11, "elapsed_time": "0:02:06", "remaining_time": "1 day, 7:31:43"}
+{"current_steps": 2, "total_steps": 900, "loss": 1.2615, "lr": 1.777777777777778e-06, "epoch": 0.0110573600552868, "percentage": 0.22, "elapsed_time": "0:03:45", "remaining_time": "1 day, 4:08:12"}
+{"current_steps": 3, "total_steps": 900, "loss": 1.25, "lr": 2.666666666666667e-06, "epoch": 0.0165860400829302, "percentage": 0.33, "elapsed_time": "0:05:25", "remaining_time": "1 day, 3:00:46"}
+{"current_steps": 4, "total_steps": 900, "loss": 1.2586, "lr": 3.555555555555556e-06, "epoch": 0.0221147201105736, "percentage": 0.44, "elapsed_time": "0:07:04", "remaining_time": "1 day, 2:26:14"}
+{"current_steps": 5, "total_steps": 900, "loss": 1.2084, "lr": 4.444444444444444e-06, "epoch": 0.027643400138217002, "percentage": 0.56, "elapsed_time": "0:08:44", "remaining_time": "1 day, 2:04:21"}
+{"current_steps": 6, "total_steps": 900, "loss": 1.1507, "lr": 5.333333333333334e-06, "epoch": 0.0331720801658604, "percentage": 0.67, "elapsed_time": "0:10:23", "remaining_time": "1 day, 1:48:55"}
+{"current_steps": 7, "total_steps": 900, "loss": 1.1576, "lr": 6.222222222222223e-06, "epoch": 0.038700760193503804, "percentage": 0.78, "elapsed_time": "0:12:04", "remaining_time": "1 day, 1:39:52"}
+{"current_steps": 8, "total_steps": 900, "loss": 1.165, "lr": 7.111111111111112e-06, "epoch": 0.0442294402211472, "percentage": 0.89, "elapsed_time": "0:13:43", "remaining_time": "1 day, 1:30:49"}
+{"current_steps": 9, "total_steps": 900, "loss": 1.1571, "lr": 8.000000000000001e-06, "epoch": 0.0497581202487906, "percentage": 1.0, "elapsed_time": "0:15:23", "remaining_time": "1 day, 1:24:26"}
+{"current_steps": 10, "total_steps": 900, "loss": 1.1349, "lr": 8.888888888888888e-06, "epoch": 0.055286800276434005, "percentage": 1.11, "elapsed_time": "0:17:03", "remaining_time": "1 day, 1:18:06"}
+{"current_steps": 11, "total_steps": 900, "loss": 1.1165, "lr": 9.777777777777779e-06, "epoch": 0.0608154803040774, "percentage": 1.22, "elapsed_time": "0:18:42", "remaining_time": "1 day, 1:12:26"}
+{"current_steps": 12, "total_steps": 900, "loss": 1.1148, "lr": 1.0666666666666667e-05, "epoch": 0.0663441603317208, "percentage": 1.33, "elapsed_time": "0:20:23", "remaining_time": "1 day, 1:08:22"}
+{"current_steps": 13, "total_steps": 900, "loss": 1.0741, "lr": 1.1555555555555556e-05, "epoch": 0.0718728403593642, "percentage": 1.44, "elapsed_time": "0:22:03", "remaining_time": "1 day, 1:04:39"}
+{"current_steps": 14, "total_steps": 900, "loss": 1.0654, "lr": 1.2444444444444446e-05, "epoch": 0.07740152038700761, "percentage": 1.56, "elapsed_time": "0:23:42", "remaining_time": "1 day, 1:00:23"}
+{"current_steps": 15, "total_steps": 900, "loss": 1.0557, "lr": 1.3333333333333333e-05, "epoch": 0.082930200414651, "percentage": 1.67, "elapsed_time": "0:25:21", "remaining_time": "1 day, 0:56:34"}
+{"current_steps": 16, "total_steps": 900, "loss": 1.0246, "lr": 1.4222222222222224e-05, "epoch": 0.0884588804422944, "percentage": 1.78, "elapsed_time": "0:27:02", "remaining_time": "1 day, 0:53:46"}
+{"current_steps": 17, "total_steps": 900, "loss": 1.0104, "lr": 1.5111111111111112e-05, "epoch": 0.09398756046993781, "percentage": 1.89, "elapsed_time": "0:28:41", "remaining_time": "1 day, 0:50:25"}
+{"current_steps": 18, "total_steps": 900, "loss": 0.9855, "lr": 1.6000000000000003e-05, "epoch": 0.0995162404975812, "percentage": 2.0, "elapsed_time": "0:30:21", "remaining_time": "1 day, 0:47:20"}
+{"current_steps": 19, "total_steps": 900, "loss": 0.996, "lr": 1.688888888888889e-05, "epoch": 0.1050449205252246, "percentage": 2.11, "elapsed_time": "0:32:00", "remaining_time": "1 day, 0:44:07"}
+{"current_steps": 20, "total_steps": 900, "loss": 0.9701, "lr": 1.7777777777777777e-05, "epoch": 0.11057360055286801, "percentage": 2.22, "elapsed_time": "0:33:39", "remaining_time": "1 day, 0:41:05"}
+{"current_steps": 21, "total_steps": 900, "loss": 0.9855, "lr": 1.866666666666667e-05, "epoch": 0.1161022805805114, "percentage": 2.33, "elapsed_time": "0:35:19", "remaining_time": "1 day, 0:38:27"}
+{"current_steps": 22, "total_steps": 900, "loss": 0.9759, "lr": 1.9555555555555557e-05, "epoch": 0.1216309606081548, "percentage": 2.44, "elapsed_time": "0:36:58", "remaining_time": "1 day, 0:35:47"}
+{"current_steps": 23, "total_steps": 900, "loss": 0.9525, "lr": 2.0444444444444446e-05, "epoch": 0.1271596406357982, "percentage": 2.56, "elapsed_time": "0:38:38", "remaining_time": "1 day, 0:33:13"}
+{"current_steps": 24, "total_steps": 900, "loss": 0.9566, "lr": 2.1333333333333335e-05, "epoch": 0.1326883206634416, "percentage": 2.67, "elapsed_time": "0:40:17", "remaining_time": "1 day, 0:30:42"}
+{"current_steps": 25, "total_steps": 900, "loss": 0.9301, "lr": 2.2222222222222227e-05, "epoch": 0.138217000691085, "percentage": 2.78, "elapsed_time": "0:41:58", "remaining_time": "1 day, 0:29:07"}
+{"current_steps": 26, "total_steps": 900, "loss": 0.9247, "lr": 2.3111111111111112e-05, "epoch": 0.1437456807187284, "percentage": 2.89, "elapsed_time": "0:43:38", "remaining_time": "1 day, 0:27:11"}
+{"current_steps": 27, "total_steps": 900, "loss": 0.9368, "lr": 2.4e-05, "epoch": 0.1492743607463718, "percentage": 3.0, "elapsed_time": "0:45:17", "remaining_time": "1 day, 0:24:41"}
+{"current_steps": 28, "total_steps": 900, "loss": 0.9233, "lr": 2.4888888888888893e-05, "epoch": 0.15480304077401522, "percentage": 3.11, "elapsed_time": "0:46:57", "remaining_time": "1 day, 0:22:13"}
+{"current_steps": 29, "total_steps": 900, "loss": 0.9376, "lr": 2.577777777777778e-05, "epoch": 0.1603317208016586, "percentage": 3.22, "elapsed_time": "0:48:36", "remaining_time": "1 day, 0:20:02"}
+{"current_steps": 30, "total_steps": 900, "loss": 0.9115, "lr": 2.6666666666666667e-05, "epoch": 0.165860400829302, "percentage": 3.33, "elapsed_time": "0:50:16", "remaining_time": "1 day, 0:17:45"}
+{"current_steps": 31, "total_steps": 900, "loss": 0.9116, "lr": 2.755555555555556e-05, "epoch": 0.1713890808569454, "percentage": 3.44, "elapsed_time": "0:51:55", "remaining_time": "1 day, 0:15:35"}
+{"current_steps": 32, "total_steps": 900, "loss": 0.9001, "lr": 2.8444444444444447e-05, "epoch": 0.1769177608845888, "percentage": 3.56, "elapsed_time": "0:53:35", "remaining_time": "1 day, 0:13:45"}
+{"current_steps": 33, "total_steps": 900, "loss": 0.9001, "lr": 2.9333333333333333e-05, "epoch": 0.1824464409122322, "percentage": 3.67, "elapsed_time": "0:55:15", "remaining_time": "1 day, 0:11:37"}
+{"current_steps": 34, "total_steps": 900, "loss": 0.9145, "lr": 3.0222222222222225e-05, "epoch": 0.18797512093987562, "percentage": 3.78, "elapsed_time": "0:56:54", "remaining_time": "1 day, 0:09:24"}
+{"current_steps": 35, "total_steps": 900, "loss": 0.882, "lr": 3.111111111111112e-05, "epoch": 0.193503800967519, "percentage": 3.89, "elapsed_time": "0:58:34", "remaining_time": "1 day, 0:07:40"}
+{"current_steps": 36, "total_steps": 900, "loss": 0.8892, "lr": 3.2000000000000005e-05, "epoch": 0.1990324809951624, "percentage": 4.0, "elapsed_time": "1:00:13", "remaining_time": "1 day, 0:05:34"}
+{"current_steps": 37, "total_steps": 900, "loss": 0.89, "lr": 3.288888888888889e-05, "epoch": 0.2045611610228058, "percentage": 4.11, "elapsed_time": "1:01:53", "remaining_time": "1 day, 0:03:30"}
+{"current_steps": 38, "total_steps": 900, "loss": 0.8954, "lr": 3.377777777777778e-05, "epoch": 0.2100898410504492, "percentage": 4.22, "elapsed_time": "1:03:32", "remaining_time": "1 day, 0:01:26"}
+{"current_steps": 39, "total_steps": 900, "loss": 0.8839, "lr": 3.466666666666667e-05, "epoch": 0.2156185210780926, "percentage": 4.33, "elapsed_time": "1:05:12", "remaining_time": "23:59:36"}
+{"current_steps": 40, "total_steps": 900, "loss": 0.891, "lr": 3.555555555555555e-05, "epoch": 0.22114720110573602, "percentage": 4.44, "elapsed_time": "1:06:52", "remaining_time": "23:57:38"}
+{"current_steps": 41, "total_steps": 900, "loss": 0.8724, "lr": 3.644444444444445e-05, "epoch": 0.22667588113337941, "percentage": 4.56, "elapsed_time": "1:08:32", "remaining_time": "23:55:56"}
+{"current_steps": 42, "total_steps": 900, "loss": 0.8988, "lr": 3.733333333333334e-05, "epoch": 0.2322045611610228, "percentage": 4.67, "elapsed_time": "1:10:12", "remaining_time": "23:54:13"}
+{"current_steps": 43, "total_steps": 900, "loss": 0.8863, "lr": 3.8222222222222226e-05, "epoch": 0.2377332411886662, "percentage": 4.78, "elapsed_time": "1:11:51", "remaining_time": "23:52:13"}
+{"current_steps": 44, "total_steps": 900, "loss": 0.8936, "lr": 3.9111111111111115e-05, "epoch": 0.2432619212163096, "percentage": 4.89, "elapsed_time": "1:13:31", "remaining_time": "23:50:32"}
+{"current_steps": 45, "total_steps": 900, "loss": 0.8911, "lr": 4e-05, "epoch": 0.248790601243953, "percentage": 5.0, "elapsed_time": "1:15:11", "remaining_time": "23:48:33"}
+{"current_steps": 46, "total_steps": 900, "loss": 0.8839, "lr": 4.088888888888889e-05, "epoch": 0.2543192812715964, "percentage": 5.11, "elapsed_time": "1:16:50", "remaining_time": "23:46:36"}
+{"current_steps": 47, "total_steps": 900, "loss": 0.8894, "lr": 4.177777777777778e-05, "epoch": 0.2598479612992398, "percentage": 5.22, "elapsed_time": "1:18:29", "remaining_time": "23:44:38"}
+{"current_steps": 48, "total_steps": 900, "loss": 0.8721, "lr": 4.266666666666667e-05, "epoch": 0.2653766413268832, "percentage": 5.33, "elapsed_time": "1:20:09", "remaining_time": "23:42:42"}
+{"current_steps": 49, "total_steps": 900, "loss": 0.8884, "lr": 4.355555555555556e-05, "epoch": 0.2709053213545266, "percentage": 5.44, "elapsed_time": "1:21:48", "remaining_time": "23:40:46"}
+{"current_steps": 50, "total_steps": 900, "loss": 0.8732, "lr": 4.444444444444445e-05, "epoch": 0.27643400138217, "percentage": 5.56, "elapsed_time": "1:23:28", "remaining_time": "23:39:11"}
+{"current_steps": 51, "total_steps": 900, "loss": 0.8796, "lr": 4.5333333333333335e-05, "epoch": 0.2819626814098134, "percentage": 5.67, "elapsed_time": "1:25:08", "remaining_time": "23:37:16"}
+{"current_steps": 52, "total_steps": 900, "loss": 0.876, "lr": 4.6222222222222224e-05, "epoch": 0.2874913614374568, "percentage": 5.78, "elapsed_time": "1:26:48", "remaining_time": "23:35:32"}
+{"current_steps": 53, "total_steps": 900, "loss": 0.8663, "lr": 4.711111111111112e-05, "epoch": 0.2930200414651002, "percentage": 5.89, "elapsed_time": "1:28:27", "remaining_time": "23:33:37"}
+{"current_steps": 54, "total_steps": 900, "loss": 0.8771, "lr": 4.8e-05, "epoch": 0.2985487214927436, "percentage": 6.0, "elapsed_time": "1:30:06", "remaining_time": "23:31:43"}
+{"current_steps": 55, "total_steps": 900, "loss": 0.8556, "lr": 4.88888888888889e-05, "epoch": 0.304077401520387, "percentage": 6.11, "elapsed_time": "1:31:45", "remaining_time": "23:29:49"}
+{"current_steps": 56, "total_steps": 900, "loss": 0.8737, "lr": 4.9777777777777785e-05, "epoch": 0.30960608154803043, "percentage": 6.22, "elapsed_time": "1:33:25", "remaining_time": "23:27:59"}
+{"current_steps": 57, "total_steps": 900, "loss": 0.8554, "lr": 5.066666666666667e-05, "epoch": 0.3151347615756738, "percentage": 6.33, "elapsed_time": "1:35:04", "remaining_time": "23:26:09"}
+{"current_steps": 58, "total_steps": 900, "loss": 0.8509, "lr": 5.155555555555556e-05, "epoch": 0.3206634416033172, "percentage": 6.44, "elapsed_time": "1:36:43", "remaining_time": "23:24:16"}
+{"current_steps": 59, "total_steps": 900, "loss": 0.8629, "lr": 5.244444444444445e-05, "epoch": 0.3261921216309606, "percentage": 6.56, "elapsed_time": "1:38:23", "remaining_time": "23:22:26"}
+{"current_steps": 60, "total_steps": 900, "loss": 0.8862, "lr": 5.333333333333333e-05, "epoch": 0.331720801658604, "percentage": 6.67, "elapsed_time": "1:40:02", "remaining_time": "23:20:36"}
+{"current_steps": 61, "total_steps": 900, "loss": 0.8552, "lr": 5.422222222222223e-05, "epoch": 0.3372494816862474, "percentage": 6.78, "elapsed_time": "1:41:41", "remaining_time": "23:18:45"}
+{"current_steps": 62, "total_steps": 900, "loss": 0.8686, "lr": 5.511111111111112e-05, "epoch": 0.3427781617138908, "percentage": 6.89, "elapsed_time": "1:43:21", "remaining_time": "23:16:54"}
+{"current_steps": 63, "total_steps": 900, "loss": 0.8682, "lr": 5.6e-05, "epoch": 0.3483068417415342, "percentage": 7.0, "elapsed_time": "1:45:00", "remaining_time": "23:15:05"}
+{"current_steps": 64, "total_steps": 900, "loss": 0.861, "lr": 5.6888888888888895e-05, "epoch": 0.3538355217691776, "percentage": 7.11, "elapsed_time": "1:46:39", "remaining_time": "23:13:17"}
+{"current_steps": 65, "total_steps": 900, "loss": 0.8561, "lr": 5.777777777777778e-05, "epoch": 0.359364201796821, "percentage": 7.22, "elapsed_time": "1:48:19", "remaining_time": "23:11:27"}
+{"current_steps": 66, "total_steps": 900, "loss": 0.8429, "lr": 5.8666666666666665e-05, "epoch": 0.3648928818244644, "percentage": 7.33, "elapsed_time": "1:49:58", "remaining_time": "23:09:37"}
+{"current_steps": 67, "total_steps": 900, "loss": 0.8595, "lr": 5.955555555555556e-05, "epoch": 0.3704215618521078, "percentage": 7.44, "elapsed_time": "1:51:37", "remaining_time": "23:07:48"}
+{"current_steps": 68, "total_steps": 900, "loss": 0.8555, "lr": 6.044444444444445e-05, "epoch": 0.37595024187975123, "percentage": 7.56, "elapsed_time": "1:53:18", "remaining_time": "23:06:23"}
+{"current_steps": 69, "total_steps": 900, "loss": 0.8574, "lr": 6.133333333333334e-05, "epoch": 0.38147892190739463, "percentage": 7.67, "elapsed_time": "1:54:58", "remaining_time": "23:04:35"}
+{"current_steps": 70, "total_steps": 900, "loss": 0.861, "lr": 6.222222222222223e-05, "epoch": 0.387007601935038, "percentage": 7.78, "elapsed_time": "1:56:37", "remaining_time": "23:02:48"}
+{"current_steps": 71, "total_steps": 900, "loss": 0.8506, "lr": 6.311111111111112e-05, "epoch": 0.3925362819626814, "percentage": 7.89, "elapsed_time": "1:58:16", "remaining_time": "23:01:00"}
+{"current_steps": 72, "total_steps": 900, "loss": 0.8558, "lr": 6.400000000000001e-05, "epoch": 0.3980649619903248, "percentage": 8.0, "elapsed_time": "1:59:55", "remaining_time": "22:59:13"}
+{"current_steps": 73, "total_steps": 900, "loss": 0.8735, "lr": 6.488888888888889e-05, "epoch": 0.4035936420179682, "percentage": 8.11, "elapsed_time": "2:01:35", "remaining_time": "22:57:27"}
+{"current_steps": 74, "total_steps": 900, "loss": 0.8492, "lr": 6.577777777777777e-05, "epoch": 0.4091223220456116, "percentage": 8.22, "elapsed_time": "2:03:14", "remaining_time": "22:55:41"}
+{"current_steps": 75, "total_steps": 900, "loss": 0.8391, "lr": 6.666666666666667e-05, "epoch": 0.414651002073255, "percentage": 8.33, "elapsed_time": "2:04:54", "remaining_time": "22:54:04"}
+{"current_steps": 76, "total_steps": 900, "loss": 0.8805, "lr": 6.755555555555557e-05, "epoch": 0.4201796821008984, "percentage": 8.44, "elapsed_time": "2:06:35", "remaining_time": "22:52:27"}
+{"current_steps": 77, "total_steps": 900, "loss": 0.8714, "lr": 6.844444444444445e-05, "epoch": 0.4257083621285418, "percentage": 8.56, "elapsed_time": "2:08:14", "remaining_time": "22:50:41"}
+{"current_steps": 78, "total_steps": 900, "loss": 0.8682, "lr": 6.933333333333334e-05, "epoch": 0.4312370421561852, "percentage": 8.67, "elapsed_time": "2:09:53", "remaining_time": "22:48:54"}
+{"current_steps": 79, "total_steps": 900, "loss": 0.8515, "lr": 7.022222222222222e-05, "epoch": 0.4367657221838286, "percentage": 8.78, "elapsed_time": "2:11:33", "remaining_time": "22:47:08"}
+{"current_steps": 80, "total_steps": 900, "loss": 0.8586, "lr": 7.11111111111111e-05, "epoch": 0.44229440221147204, "percentage": 8.89, "elapsed_time": "2:13:12", "remaining_time": "22:45:22"}
+{"current_steps": 81, "total_steps": 900, "loss": 0.8593, "lr": 7.2e-05, "epoch": 0.44782308223911543, "percentage": 9.0, "elapsed_time": "2:14:51", "remaining_time": "22:43:35"}
+{"current_steps": 82, "total_steps": 900, "loss": 0.8618, "lr": 7.28888888888889e-05, "epoch": 0.45335176226675883, "percentage": 9.11, "elapsed_time": "2:16:30", "remaining_time": "22:41:50"}
+{"current_steps": 83, "total_steps": 900, "loss": 0.8471, "lr": 7.377777777777779e-05, "epoch": 0.4588804422944022, "percentage": 9.22, "elapsed_time": "2:18:10", "remaining_time": "22:40:03"}
+{"current_steps": 84, "total_steps": 900, "loss": 0.8638, "lr": 7.466666666666667e-05, "epoch": 0.4644091223220456, "percentage": 9.33, "elapsed_time": "2:19:49", "remaining_time": "22:38:18"}
+{"current_steps": 85, "total_steps": 900, "loss": 0.8471, "lr": 7.555555555555556e-05, "epoch": 0.469937802349689, "percentage": 9.44, "elapsed_time": "2:21:28", "remaining_time": "22:36:33"}
+{"current_steps": 86, "total_steps": 900, "loss": 0.8523, "lr": 7.644444444444445e-05, "epoch": 0.4754664823773324, "percentage": 9.56, "elapsed_time": "2:23:09", "remaining_time": "22:34:59"}
+{"current_steps": 87, "total_steps": 900, "loss": 0.87, "lr": 7.733333333333333e-05, "epoch": 0.4809951624049758, "percentage": 9.67, "elapsed_time": "2:24:49", "remaining_time": "22:33:23"}
+{"current_steps": 88, "total_steps": 900, "loss": 0.8438, "lr": 7.822222222222223e-05, "epoch": 0.4865238424326192, "percentage": 9.78, "elapsed_time": "2:26:29", "remaining_time": "22:31:38"}
+{"current_steps": 89, "total_steps": 900, "loss": 0.8583, "lr": 7.911111111111112e-05, "epoch": 0.4920525224602626, "percentage": 9.89, "elapsed_time": "2:28:08", "remaining_time": "22:29:54"}
+{"current_steps": 90, "total_steps": 900, "loss": 0.8593, "lr": 8e-05, "epoch": 0.497581202487906, "percentage": 10.0, "elapsed_time": "2:29:47", "remaining_time": "22:28:08"}
+{"current_steps": 91, "total_steps": 900, "loss": 0.8381, "lr": 7.999969914366625e-05, "epoch": 0.5031098825155494, "percentage": 10.11, "elapsed_time": "2:31:26", "remaining_time": "22:26:23"}
+{"current_steps": 92, "total_steps": 900, "loss": 0.8511, "lr": 7.999879657919071e-05, "epoch": 0.5086385625431928, "percentage": 10.22, "elapsed_time": "2:33:06", "remaining_time": "22:24:38"}
+{"current_steps": 93, "total_steps": 900, "loss": 0.8477, "lr": 7.99972923201505e-05, "epoch": 0.5141672425708362, "percentage": 10.33, "elapsed_time": "2:34:45", "remaining_time": "22:22:53"}
+{"current_steps": 94, "total_steps": 900, "loss": 0.8615, "lr": 7.999518638917391e-05, "epoch": 0.5196959225984796, "percentage": 10.44, "elapsed_time": "2:36:24", "remaining_time": "22:21:10"}
+{"current_steps": 95, "total_steps": 900, "loss": 0.8484, "lr": 7.999247881794007e-05, "epoch": 0.525224602626123, "percentage": 10.56, "elapsed_time": "2:38:04", "remaining_time": "22:19:27"}
+{"current_steps": 96, "total_steps": 900, "loss": 0.8462, "lr": 7.998916964717848e-05, "epoch": 0.5307532826537664, "percentage": 10.67, "elapsed_time": "2:39:43", "remaining_time": "22:17:42"}
+{"current_steps": 97, "total_steps": 900, "loss": 0.8412, "lr": 7.998525892666838e-05, "epoch": 0.5362819626814098, "percentage": 10.78, "elapsed_time": "2:41:22", "remaining_time": "22:15:58"}
+{"current_steps": 98, "total_steps": 900, "loss": 0.835, "lr": 7.998074671523805e-05, "epoch": 0.5418106427090532, "percentage": 10.89, "elapsed_time": "2:43:02", "remaining_time": "22:14:15"}
+{"current_steps": 99, "total_steps": 900, "loss": 0.8453, "lr": 7.997563308076384e-05, "epoch": 0.5473393227366966, "percentage": 11.0, "elapsed_time": "2:44:41", "remaining_time": "22:12:31"}
+{"current_steps": 100, "total_steps": 900, "loss": 0.8425, "lr": 7.996991810016922e-05, "epoch": 0.55286800276434, "percentage": 11.11, "elapsed_time": "2:46:20", "remaining_time": "22:10:46"}
+{"current_steps": 101, "total_steps": 900, "loss": 0.8355, "lr": 7.996360185942358e-05, "epoch": 0.5583966827919834, "percentage": 11.22, "elapsed_time": "2:48:00", "remaining_time": "22:09:03"}
+{"current_steps": 102, "total_steps": 900, "loss": 0.8509, "lr": 7.9956684453541e-05, "epoch": 0.5639253628196268, "percentage": 11.33, "elapsed_time": "2:49:39", "remaining_time": "22:07:21"}
+{"current_steps": 103, "total_steps": 900, "loss": 0.8437, "lr": 7.994916598657872e-05, "epoch": 0.5694540428472702, "percentage": 11.44, "elapsed_time": "2:51:19", "remaining_time": "22:05:37"}
+{"current_steps": 104, "total_steps": 900, "loss": 0.8434, "lr": 7.994104657163567e-05, "epoch": 0.5749827228749136, "percentage": 11.56, "elapsed_time": "2:52:58", "remaining_time": "22:03:54"}
+{"current_steps": 105, "total_steps": 900, "loss": 0.8283, "lr": 7.993232633085074e-05, "epoch": 0.580511402902557, "percentage": 11.67, "elapsed_time": "2:54:37", "remaining_time": "22:02:10"}
+{"current_steps": 106, "total_steps": 900, "loss": 0.8224, "lr": 7.992300539540088e-05, "epoch": 0.5860400829302004, "percentage": 11.78, "elapsed_time": "2:56:17", "remaining_time": "22:00:27"}
+{"current_steps": 107, "total_steps": 900, "loss": 0.8381, "lr": 7.991308390549925e-05, "epoch": 0.5915687629578438, "percentage": 11.89, "elapsed_time": "2:57:56", "remaining_time": "21:58:43"}
+{"current_steps": 108, "total_steps": 900, "loss": 0.8371, "lr": 7.990256201039297e-05, "epoch": 0.5970974429854872, "percentage": 12.0, "elapsed_time": "2:59:35", "remaining_time": "21:57:00"}
+{"current_steps": 109, "total_steps": 900, "loss": 0.8378, "lr": 7.989143986836101e-05, "epoch": 0.6026261230131306, "percentage": 12.11, "elapsed_time": "3:01:14", "remaining_time": "21:55:17"}
+{"current_steps": 110, "total_steps": 900, "loss": 0.8377, "lr": 7.987971764671168e-05, "epoch": 0.608154803040774, "percentage": 12.22, "elapsed_time": "3:02:54", "remaining_time": "21:53:33"}
+{"current_steps": 111, "total_steps": 900, "loss": 0.8401, "lr": 7.986739552178024e-05, "epoch": 0.6136834830684175, "percentage": 12.33, "elapsed_time": "3:04:33", "remaining_time": "21:51:52"}
+{"current_steps": 112, "total_steps": 900, "loss": 0.8358, "lr": 7.985447367892616e-05, "epoch": 0.6192121630960609, "percentage": 12.44, "elapsed_time": "3:06:13", "remaining_time": "21:50:10"}
+{"current_steps": 113, "total_steps": 900, "loss": 0.8274, "lr": 7.984095231253031e-05, "epoch": 0.6247408431237043, "percentage": 12.56, "elapsed_time": "3:07:52", "remaining_time": "21:48:27"}
+{"current_steps": 114, "total_steps": 900, "loss": 0.8356, "lr": 7.982683162599218e-05, "epoch": 0.6302695231513477, "percentage": 12.67, "elapsed_time": "3:09:31", "remaining_time": "21:46:45"}
+{"current_steps": 115, "total_steps": 900, "loss": 0.8279, "lr": 7.981211183172663e-05, "epoch": 0.635798203178991, "percentage": 12.78, "elapsed_time": "3:11:11", "remaining_time": "21:45:04"}
+{"current_steps": 116, "total_steps": 900, "loss": 0.8332, "lr": 7.979679315116086e-05, "epoch": 0.6413268832066344, "percentage": 12.89, "elapsed_time": "3:12:51", "remaining_time": "21:43:25"}
+{"current_steps": 117, "total_steps": 900, "loss": 0.8384, "lr": 7.978087581473094e-05, "epoch": 0.6468555632342778, "percentage": 13.0, "elapsed_time": "3:14:30", "remaining_time": "21:41:42"}
+{"current_steps": 118, "total_steps": 900, "loss": 0.8336, "lr": 7.976436006187846e-05, "epoch": 0.6523842432619212, "percentage": 13.11, "elapsed_time": "3:16:09", "remaining_time": "21:39:59"}
+{"current_steps": 119, "total_steps": 900, "loss": 0.8359, "lr": 7.974724614104686e-05, "epoch": 0.6579129232895646, "percentage": 13.22, "elapsed_time": "3:17:49", "remaining_time": "21:38:17"}
+{"current_steps": 120, "total_steps": 900, "loss": 0.8294, "lr": 7.972953430967773e-05, "epoch": 0.663441603317208, "percentage": 13.33, "elapsed_time": "3:19:29", "remaining_time": "21:36:43"}
+{"current_steps": 121, "total_steps": 900, "loss": 0.8462, "lr": 7.971122483420687e-05, "epoch": 0.6689702833448514, "percentage": 13.44, "elapsed_time": "3:21:09", "remaining_time": "21:35:04"}
+{"current_steps": 122, "total_steps": 900, "loss": 0.8406, "lr": 7.96923179900604e-05, "epoch": 0.6744989633724948, "percentage": 13.56, "elapsed_time": "3:22:50", "remaining_time": "21:33:32"}
+{"current_steps": 123, "total_steps": 900, "loss": 0.8428, "lr": 7.967281406165047e-05, "epoch": 0.6800276434001382, "percentage": 13.67, "elapsed_time": "3:24:30", "remaining_time": "21:31:54"}
+{"current_steps": 124, "total_steps": 900, "loss": 0.8254, "lr": 7.965271334237114e-05, "epoch": 0.6855563234277816, "percentage": 13.78, "elapsed_time": "3:26:10", "remaining_time": "21:30:12"}
+{"current_steps": 125, "total_steps": 900, "loss": 0.8352, "lr": 7.963201613459381e-05, "epoch": 0.691085003455425, "percentage": 13.89, "elapsed_time": "3:27:49", "remaining_time": "21:28:30"}
+{"current_steps": 126, "total_steps": 900, "loss": 0.8279, "lr": 7.961072274966282e-05, "epoch": 0.6966136834830684, "percentage": 14.0, "elapsed_time": "3:29:28", "remaining_time": "21:26:47"}
+{"current_steps": 127, "total_steps": 900, "loss": 0.8321, "lr": 7.958883350789062e-05, "epoch": 0.7021423635107118, "percentage": 14.11, "elapsed_time": "3:31:07", "remaining_time": "21:25:05"}
+{"current_steps": 128, "total_steps": 900, "loss": 0.8186, "lr": 7.95663487385531e-05, "epoch": 0.7076710435383552, "percentage": 14.22, "elapsed_time": "3:32:47", "remaining_time": "21:23:22"}
+{"current_steps": 129, "total_steps": 900, "loss": 0.8284, "lr": 7.954326877988446e-05, "epoch": 0.7131997235659986, "percentage": 14.33, "elapsed_time": "3:34:26", "remaining_time": "21:21:41"}
+{"current_steps": 130, "total_steps": 900, "loss": 0.8426, "lr": 7.951959397907237e-05, "epoch": 0.718728403593642, "percentage": 14.44, "elapsed_time": "3:36:06", "remaining_time": "21:19:59"}
+{"current_steps": 131, "total_steps": 900, "loss": 0.8272, "lr": 7.949532469225245e-05, "epoch": 0.7242570836212854, "percentage": 14.56, "elapsed_time": "3:37:45", "remaining_time": "21:18:16"}
+{"current_steps": 132, "total_steps": 900, "loss": 0.8284, "lr": 7.947046128450319e-05, "epoch": 0.7297857636489288, "percentage": 14.67, "elapsed_time": "3:39:24", "remaining_time": "21:16:36"}
+{"current_steps": 133, "total_steps": 900, "loss": 0.8325, "lr": 7.944500412984021e-05, "epoch": 0.7353144436765722, "percentage": 14.78, "elapsed_time": "3:41:04", "remaining_time": "21:14:53"}
+{"current_steps": 134, "total_steps": 900, "loss": 0.8283, "lr": 7.941895361121086e-05, "epoch": 0.7408431237042156, "percentage": 14.89, "elapsed_time": "3:42:43", "remaining_time": "21:13:12"}
+{"current_steps": 135, "total_steps": 900, "loss": 0.8346, "lr": 7.939231012048833e-05, "epoch": 0.7463718037318591, "percentage": 15.0, "elapsed_time": "3:44:22", "remaining_time": "21:11:29"}
+{"current_steps": 136, "total_steps": 900, "loss": 0.8234, "lr": 7.936507405846574e-05, "epoch": 0.7519004837595025, "percentage": 15.11, "elapsed_time": "3:46:02", "remaining_time": "21:09:47"}
+{"current_steps": 137, "total_steps": 900, "loss": 0.8217, "lr": 7.933724583485019e-05, "epoch": 0.7574291637871459, "percentage": 15.22, "elapsed_time": "3:47:41", "remaining_time": "21:08:05"}
+{"current_steps": 138, "total_steps": 900, "loss": 0.8239, "lr": 7.930882586825653e-05, "epoch": 0.7629578438147893, "percentage": 15.33, "elapsed_time": "3:49:20", "remaining_time": "21:06:24"}
+{"current_steps": 139, "total_steps": 900, "loss": 0.8292, "lr": 7.927981458620114e-05, "epoch": 0.7684865238424327, "percentage": 15.44, "elapsed_time": "3:51:00", "remaining_time": "21:04:42"}
+{"current_steps": 140, "total_steps": 900, "loss": 0.8295, "lr": 7.925021242509539e-05, "epoch": 0.774015203870076, "percentage": 15.56, "elapsed_time": "3:52:39", "remaining_time": "21:03:00"}
+{"current_steps": 141, "total_steps": 900, "loss": 0.8199, "lr": 7.922001983023918e-05, "epoch": 0.7795438838977194, "percentage": 15.67, "elapsed_time": "3:54:18", "remaining_time": "21:01:18"}
+{"current_steps": 142, "total_steps": 900, "loss": 0.8416, "lr": 7.918923725581416e-05, "epoch": 0.7850725639253628, "percentage": 15.78, "elapsed_time": "3:55:58", "remaining_time": "20:59:37"}
+{"current_steps": 143, "total_steps": 900, "loss": 0.8326, "lr": 7.915786516487698e-05, "epoch": 0.7906012439530062, "percentage": 15.89, "elapsed_time": "3:57:37", "remaining_time": "20:57:56"}
+{"current_steps": 144, "total_steps": 900, "loss": 0.8329, "lr": 7.912590402935223e-05, "epoch": 0.7961299239806496, "percentage": 16.0, "elapsed_time": "3:59:17", "remaining_time": "20:56:14"}
+{"current_steps": 145, "total_steps": 900, "loss": 0.8137, "lr": 7.909335433002543e-05, "epoch": 0.801658604008293, "percentage": 16.11, "elapsed_time": "4:00:56", "remaining_time": "20:54:32"}
+{"current_steps": 146, "total_steps": 900, "loss": 0.8203, "lr": 7.906021655653572e-05, "epoch": 0.8071872840359364, "percentage": 16.22, "elapsed_time": "4:02:35", "remaining_time": "20:52:51"}
+{"current_steps": 147, "total_steps": 900, "loss": 0.8272, "lr": 7.902649120736858e-05, "epoch": 0.8127159640635798, "percentage": 16.33, "elapsed_time": "4:04:14", "remaining_time": "20:51:09"}
+{"current_steps": 148, "total_steps": 900, "loss": 0.8294, "lr": 7.899217878984823e-05, "epoch": 0.8182446440912232, "percentage": 16.44, "elapsed_time": "4:05:54", "remaining_time": "20:49:27"}
+{"current_steps": 149, "total_steps": 900, "loss": 0.8242, "lr": 7.895727982013009e-05, "epoch": 0.8237733241188666, "percentage": 16.56, "elapsed_time": "4:07:33", "remaining_time": "20:47:45"}
+{"current_steps": 150, "total_steps": 900, "loss": 0.8078, "lr": 7.892179482319297e-05, "epoch": 0.82930200414651, "percentage": 16.67, "elapsed_time": "4:09:12", "remaining_time": "20:46:03"}
+{"current_steps": 151, "total_steps": 900, "loss": 0.8204, "lr": 7.888572433283114e-05, "epoch": 0.8348306841741534, "percentage": 16.78, "elapsed_time": "4:10:52", "remaining_time": "20:44:22"}
+{"current_steps": 152, "total_steps": 900, "loss": 0.8247, "lr": 7.884906889164642e-05, "epoch": 0.8403593642017968, "percentage": 16.89, "elapsed_time": "4:12:31", "remaining_time": "20:42:40"}
+{"current_steps": 153, "total_steps": 900, "loss": 0.8306, "lr": 7.881182905103986e-05, "epoch": 0.8458880442294402, "percentage": 17.0, "elapsed_time": "4:14:10", "remaining_time": "20:40:59"}
+{"current_steps": 154, "total_steps": 900, "loss": 0.816, "lr": 7.877400537120358e-05, "epoch": 0.8514167242570836, "percentage": 17.11, "elapsed_time": "4:15:49", "remaining_time": "20:39:17"}
+{"current_steps": 155, "total_steps": 900, "loss": 0.8635, "lr": 7.873559842111225e-05, "epoch": 0.856945404284727, "percentage": 17.22, "elapsed_time": "4:17:29", "remaining_time": "20:37:36"}
+{"current_steps": 156, "total_steps": 900, "loss": 0.8475, "lr": 7.869660877851456e-05, "epoch": 0.8624740843123704, "percentage": 17.33, "elapsed_time": "4:19:08", "remaining_time": "20:35:54"}
+{"current_steps": 157, "total_steps": 900, "loss": 0.8427, "lr": 7.86570370299246e-05, "epoch": 0.8680027643400138, "percentage": 17.44, "elapsed_time": "4:20:47", "remaining_time": "20:34:13"}
+{"current_steps": 158, "total_steps": 900, "loss": 0.8532, "lr": 7.861688377061289e-05, "epoch": 0.8735314443676572, "percentage": 17.56, "elapsed_time": "4:22:27", "remaining_time": "20:32:31"}
+{"current_steps": 159, "total_steps": 900, "loss": 0.8116, "lr": 7.857614960459756e-05, "epoch": 0.8790601243953006, "percentage": 17.67, "elapsed_time": "4:24:06", "remaining_time": "20:30:49"}
+{"current_steps": 160, "total_steps": 900, "loss": 0.8464, "lr": 7.853483514463521e-05, "epoch": 0.8845888044229441, "percentage": 17.78, "elapsed_time": "4:25:45", "remaining_time": "20:29:07"}
+{"current_steps": 161, "total_steps": 900, "loss": 0.8309, "lr": 7.84929410122117e-05, "epoch": 0.8901174844505875, "percentage": 17.89, "elapsed_time": "4:27:24", "remaining_time": "20:27:26"}
+{"current_steps": 162, "total_steps": 900, "loss": 0.8383, "lr": 7.845046783753276e-05, "epoch": 0.8956461644782309, "percentage": 18.0, "elapsed_time": "4:29:04", "remaining_time": "20:25:45"}
+{"current_steps": 163, "total_steps": 900, "loss": 0.833, "lr": 7.840741625951458e-05, "epoch": 0.9011748445058743, "percentage": 18.11, "elapsed_time": "4:30:43", "remaining_time": "20:24:04"}
+{"current_steps": 164, "total_steps": 900, "loss": 0.821, "lr": 7.836378692577416e-05, "epoch": 0.9067035245335177, "percentage": 18.22, "elapsed_time": "4:32:22", "remaining_time": "20:22:22"}
+{"current_steps": 165, "total_steps": 900, "loss": 0.8174, "lr": 7.831958049261956e-05, "epoch": 0.912232204561161, "percentage": 18.33, "elapsed_time": "4:34:02", "remaining_time": "20:20:41"}
+{"current_steps": 166, "total_steps": 900, "loss": 0.8229, "lr": 7.827479762504006e-05, "epoch": 0.9177608845888044, "percentage": 18.44, "elapsed_time": "4:35:41", "remaining_time": "20:19:00"}
+{"current_steps": 167, "total_steps": 900, "loss": 0.8325, "lr": 7.822943899669613e-05, "epoch": 0.9232895646164478, "percentage": 18.56, "elapsed_time": "4:37:20", "remaining_time": "20:17:19"}
+{"current_steps": 168, "total_steps": 900, "loss": 0.8043, "lr": 7.818350528990929e-05, "epoch": 0.9288182446440912, "percentage": 18.67, "elapsed_time": "4:38:59", "remaining_time": "20:15:38"}
+{"current_steps": 169, "total_steps": 900, "loss": 0.8159, "lr": 7.813699719565187e-05, "epoch": 0.9343469246717346, "percentage": 18.78, "elapsed_time": "4:40:39", "remaining_time": "20:13:56"}
+{"current_steps": 170, "total_steps": 900, "loss": 0.8103, "lr": 7.808991541353662e-05, "epoch": 0.939875604699378, "percentage": 18.89, "elapsed_time": "4:42:18", "remaining_time": "20:12:15"}
+{"current_steps": 171, "total_steps": 900, "loss": 0.8188, "lr": 7.804226065180615e-05, "epoch": 0.9454042847270214, "percentage": 19.0, "elapsed_time": "4:43:57", "remaining_time": "20:10:34"}
+{"current_steps": 172, "total_steps": 900, "loss": 0.8151, "lr": 7.799403362732231e-05, "epoch": 0.9509329647546648, "percentage": 19.11, "elapsed_time": "4:45:36", "remaining_time": "20:08:53"}
+{"current_steps": 173, "total_steps": 900, "loss": 0.8215, "lr": 7.794523506555537e-05, "epoch": 0.9564616447823082, "percentage": 19.22, "elapsed_time": "4:47:16", "remaining_time": "20:07:12"}
+{"current_steps": 174, "total_steps": 900, "loss": 0.8134, "lr": 7.789586570057317e-05, "epoch": 0.9619903248099516, "percentage": 19.33, "elapsed_time": "4:48:55", "remaining_time": "20:05:30"}
+{"current_steps": 175, "total_steps": 900, "loss": 0.8161, "lr": 7.784592627503004e-05, "epoch": 0.967519004837595, "percentage": 19.44, "elapsed_time": "4:50:34", "remaining_time": "20:03:49"}
+{"current_steps": 176, "total_steps": 900, "loss": 0.8164, "lr": 7.779541754015552e-05, "epoch": 0.9730476848652384, "percentage": 19.56, "elapsed_time": "4:52:14", "remaining_time": "20:02:11"}
+{"current_steps": 177, "total_steps": 900, "loss": 0.8159, "lr": 7.774434025574335e-05, "epoch": 0.9785763648928818, "percentage": 19.67, "elapsed_time": "4:53:53", "remaining_time": "20:00:30"}
+{"current_steps": 178, "total_steps": 900, "loss": 0.8097, "lr": 7.76926951901397e-05, "epoch": 0.9841050449205252, "percentage": 19.78, "elapsed_time": "4:55:33", "remaining_time": "19:58:49"}
+{"current_steps": 179, "total_steps": 900, "loss": 0.806, "lr": 7.764048312023183e-05, "epoch": 0.9896337249481686, "percentage": 19.89, "elapsed_time": "4:57:12", "remaining_time": "19:57:07"}
+{"current_steps": 180, "total_steps": 900, "loss": 0.8201, "lr": 7.758770483143634e-05, "epoch": 0.995162404975812, "percentage": 20.0, "elapsed_time": "4:58:52", "remaining_time": "19:55:28"}
+{"current_steps": 181, "total_steps": 900, "loss": 0.8063, "lr": 7.753436111768735e-05, "epoch": 1.0020732550103664, "percentage": 20.11, "elapsed_time": "5:02:21", "remaining_time": "20:01:03"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e889eb50c8481b741b8f5c3f509376577dfdec30a0bdacabe2e06649ab7c6a13
+size 7352