Training in progress, epoch 1

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7993272bdf9c80eafb1e1378a995bac942f5dba802bfadac17adbc440bbdefce
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf14aca43c684dd26d4b472fe5276d7db869023ae419eacba68fceea89e7244
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc998e1aab1da48554cfe7e42e4559f72169e8b0a6ee62645492f6b2ccc5037
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b9251c40a7e2116e1bb612a193e20f4b368e87f793032924d922970cca21a9
+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 +1,329 @@
+{"current_steps": 1, "total_steps": 1565, "loss": 0.9383, "lr": 6.369426751592358e-08, "epoch": 0.003194888178913738, "percentage": 0.06, "elapsed_time": "0:00:19", "remaining_time": "8:16:14"}
+{"current_steps": 2, "total_steps": 1565, "loss": 0.8501, "lr": 1.2738853503184715e-07, "epoch": 0.006389776357827476, "percentage": 0.13, "elapsed_time": "0:00:29", "remaining_time": "6:25:03"}
+{"current_steps": 3, "total_steps": 1565, "loss": 0.8873, "lr": 1.9108280254777072e-07, "epoch": 0.009584664536741214, "percentage": 0.19, "elapsed_time": "0:00:40", "remaining_time": "5:50:39"}
+{"current_steps": 4, "total_steps": 1565, "loss": 0.8131, "lr": 2.547770700636943e-07, "epoch": 0.012779552715654952, "percentage": 0.26, "elapsed_time": "0:00:52", "remaining_time": "5:44:03"}
+{"current_steps": 5, "total_steps": 1565, "loss": 0.8905, "lr": 3.1847133757961787e-07, "epoch": 0.01597444089456869, "percentage": 0.32, "elapsed_time": "0:01:04", "remaining_time": "5:35:48"}
+{"current_steps": 6, "total_steps": 1565, "loss": 0.8607, "lr": 3.8216560509554143e-07, "epoch": 0.019169329073482427, "percentage": 0.38, "elapsed_time": "0:01:14", "remaining_time": "5:24:34"}
+{"current_steps": 7, "total_steps": 1565, "loss": 0.8923, "lr": 4.45859872611465e-07, "epoch": 0.022364217252396165, "percentage": 0.45, "elapsed_time": "0:01:26", "remaining_time": "5:20:36"}
+{"current_steps": 8, "total_steps": 1565, "loss": 0.8642, "lr": 5.095541401273886e-07, "epoch": 0.025559105431309903, "percentage": 0.51, "elapsed_time": "0:01:36", "remaining_time": "5:13:33"}
+{"current_steps": 9, "total_steps": 1565, "loss": 0.854, "lr": 5.732484076433121e-07, "epoch": 0.02875399361022364, "percentage": 0.58, "elapsed_time": "0:01:48", "remaining_time": "5:12:58"}
+{"current_steps": 10, "total_steps": 1565, "loss": 0.8144, "lr": 6.369426751592357e-07, "epoch": 0.03194888178913738, "percentage": 0.64, "elapsed_time": "0:01:59", "remaining_time": "5:10:42"}
+{"current_steps": 11, "total_steps": 1565, "loss": 0.8821, "lr": 7.006369426751592e-07, "epoch": 0.03514376996805112, "percentage": 0.7, "elapsed_time": "0:02:11", "remaining_time": "5:10:26"}
+{"current_steps": 12, "total_steps": 1565, "loss": 0.9157, "lr": 7.643312101910829e-07, "epoch": 0.038338658146964855, "percentage": 0.77, "elapsed_time": "0:02:23", "remaining_time": "5:09:33"}
+{"current_steps": 13, "total_steps": 1565, "loss": 0.8396, "lr": 8.280254777070064e-07, "epoch": 0.04153354632587859, "percentage": 0.83, "elapsed_time": "0:02:30", "remaining_time": "5:00:21"}
+{"current_steps": 14, "total_steps": 1565, "loss": 0.844, "lr": 8.9171974522293e-07, "epoch": 0.04472843450479233, "percentage": 0.89, "elapsed_time": "0:02:40", "remaining_time": "4:55:43"}
+{"current_steps": 15, "total_steps": 1565, "loss": 0.7945, "lr": 9.554140127388537e-07, "epoch": 0.04792332268370607, "percentage": 0.96, "elapsed_time": "0:02:51", "remaining_time": "4:54:36"}
+{"current_steps": 16, "total_steps": 1565, "loss": 0.8179, "lr": 1.0191082802547772e-06, "epoch": 0.051118210862619806, "percentage": 1.02, "elapsed_time": "0:03:00", "remaining_time": "4:51:03"}
+{"current_steps": 17, "total_steps": 1565, "loss": 0.7676, "lr": 1.0828025477707007e-06, "epoch": 0.054313099041533544, "percentage": 1.09, "elapsed_time": "0:03:11", "remaining_time": "4:50:45"}
+{"current_steps": 18, "total_steps": 1565, "loss": 0.796, "lr": 1.1464968152866242e-06, "epoch": 0.05750798722044728, "percentage": 1.15, "elapsed_time": "0:03:23", "remaining_time": "4:51:42"}
+{"current_steps": 19, "total_steps": 1565, "loss": 0.8002, "lr": 1.210191082802548e-06, "epoch": 0.06070287539936102, "percentage": 1.21, "elapsed_time": "0:03:35", "remaining_time": "4:52:44"}
+{"current_steps": 20, "total_steps": 1565, "loss": 0.7476, "lr": 1.2738853503184715e-06, "epoch": 0.06389776357827476, "percentage": 1.28, "elapsed_time": "0:03:45", "remaining_time": "4:50:17"}
+{"current_steps": 21, "total_steps": 1565, "loss": 0.7302, "lr": 1.337579617834395e-06, "epoch": 0.0670926517571885, "percentage": 1.34, "elapsed_time": "0:03:56", "remaining_time": "4:50:08"}
+{"current_steps": 22, "total_steps": 1565, "loss": 0.6852, "lr": 1.4012738853503185e-06, "epoch": 0.07028753993610223, "percentage": 1.41, "elapsed_time": "0:04:05", "remaining_time": "4:47:28"}
+{"current_steps": 23, "total_steps": 1565, "loss": 0.8135, "lr": 1.4649681528662422e-06, "epoch": 0.07348242811501597, "percentage": 1.47, "elapsed_time": "0:04:17", "remaining_time": "4:47:16"}
+{"current_steps": 24, "total_steps": 1565, "loss": 0.7842, "lr": 1.5286624203821657e-06, "epoch": 0.07667731629392971, "percentage": 1.53, "elapsed_time": "0:04:25", "remaining_time": "4:44:09"}
+{"current_steps": 25, "total_steps": 1565, "loss": 0.6966, "lr": 1.5923566878980892e-06, "epoch": 0.07987220447284345, "percentage": 1.6, "elapsed_time": "0:04:35", "remaining_time": "4:43:10"}
+{"current_steps": 26, "total_steps": 1565, "loss": 0.7827, "lr": 1.6560509554140127e-06, "epoch": 0.08306709265175719, "percentage": 1.66, "elapsed_time": "0:04:47", "remaining_time": "4:43:50"}
+{"current_steps": 27, "total_steps": 1565, "loss": 0.7193, "lr": 1.7197452229299363e-06, "epoch": 0.08626198083067092, "percentage": 1.73, "elapsed_time": "0:04:58", "remaining_time": "4:43:41"}
+{"current_steps": 28, "total_steps": 1565, "loss": 0.7437, "lr": 1.78343949044586e-06, "epoch": 0.08945686900958466, "percentage": 1.79, "elapsed_time": "0:05:11", "remaining_time": "4:44:46"}
+{"current_steps": 29, "total_steps": 1565, "loss": 0.7621, "lr": 1.8471337579617835e-06, "epoch": 0.0926517571884984, "percentage": 1.85, "elapsed_time": "0:05:19", "remaining_time": "4:42:21"}
+{"current_steps": 30, "total_steps": 1565, "loss": 0.7465, "lr": 1.9108280254777074e-06, "epoch": 0.09584664536741214, "percentage": 1.92, "elapsed_time": "0:05:29", "remaining_time": "4:41:18"}
+{"current_steps": 31, "total_steps": 1565, "loss": 0.7195, "lr": 1.974522292993631e-06, "epoch": 0.09904153354632587, "percentage": 1.98, "elapsed_time": "0:05:41", "remaining_time": "4:41:37"}
+{"current_steps": 32, "total_steps": 1565, "loss": 0.7457, "lr": 2.0382165605095544e-06, "epoch": 0.10223642172523961, "percentage": 2.04, "elapsed_time": "0:05:52", "remaining_time": "4:41:31"}
+{"current_steps": 33, "total_steps": 1565, "loss": 0.6829, "lr": 2.101910828025478e-06, "epoch": 0.10543130990415335, "percentage": 2.11, "elapsed_time": "0:06:01", "remaining_time": "4:39:48"}
+{"current_steps": 34, "total_steps": 1565, "loss": 0.6998, "lr": 2.1656050955414015e-06, "epoch": 0.10862619808306709, "percentage": 2.17, "elapsed_time": "0:06:13", "remaining_time": "4:40:00"}
+{"current_steps": 35, "total_steps": 1565, "loss": 0.6925, "lr": 2.229299363057325e-06, "epoch": 0.11182108626198083, "percentage": 2.24, "elapsed_time": "0:06:24", "remaining_time": "4:39:48"}
+{"current_steps": 36, "total_steps": 1565, "loss": 0.6228, "lr": 2.2929936305732485e-06, "epoch": 0.11501597444089456, "percentage": 2.3, "elapsed_time": "0:06:36", "remaining_time": "4:40:35"}
+{"current_steps": 37, "total_steps": 1565, "loss": 0.6801, "lr": 2.356687898089172e-06, "epoch": 0.1182108626198083, "percentage": 2.36, "elapsed_time": "0:06:48", "remaining_time": "4:41:17"}
+{"current_steps": 38, "total_steps": 1565, "loss": 0.6746, "lr": 2.420382165605096e-06, "epoch": 0.12140575079872204, "percentage": 2.43, "elapsed_time": "0:06:58", "remaining_time": "4:40:32"}
+{"current_steps": 39, "total_steps": 1565, "loss": 0.6404, "lr": 2.4840764331210194e-06, "epoch": 0.12460063897763578, "percentage": 2.49, "elapsed_time": "0:07:11", "remaining_time": "4:41:15"}
+{"current_steps": 40, "total_steps": 1565, "loss": 0.6114, "lr": 2.547770700636943e-06, "epoch": 0.12779552715654952, "percentage": 2.56, "elapsed_time": "0:07:22", "remaining_time": "4:40:54"}
+{"current_steps": 41, "total_steps": 1565, "loss": 0.6364, "lr": 2.6114649681528665e-06, "epoch": 0.13099041533546327, "percentage": 2.62, "elapsed_time": "0:07:34", "remaining_time": "4:41:24"}
+{"current_steps": 42, "total_steps": 1565, "loss": 0.6559, "lr": 2.67515923566879e-06, "epoch": 0.134185303514377, "percentage": 2.68, "elapsed_time": "0:07:43", "remaining_time": "4:40:08"}
+{"current_steps": 43, "total_steps": 1565, "loss": 0.6459, "lr": 2.7388535031847135e-06, "epoch": 0.13738019169329074, "percentage": 2.75, "elapsed_time": "0:07:53", "remaining_time": "4:39:08"}
+{"current_steps": 44, "total_steps": 1565, "loss": 0.6164, "lr": 2.802547770700637e-06, "epoch": 0.14057507987220447, "percentage": 2.81, "elapsed_time": "0:08:03", "remaining_time": "4:38:50"}
+{"current_steps": 45, "total_steps": 1565, "loss": 0.6618, "lr": 2.8662420382165605e-06, "epoch": 0.14376996805111822, "percentage": 2.88, "elapsed_time": "0:08:15", "remaining_time": "4:38:52"}
+{"current_steps": 46, "total_steps": 1565, "loss": 0.6287, "lr": 2.9299363057324844e-06, "epoch": 0.14696485623003194, "percentage": 2.94, "elapsed_time": "0:08:24", "remaining_time": "4:37:37"}
+{"current_steps": 47, "total_steps": 1565, "loss": 0.6632, "lr": 2.993630573248408e-06, "epoch": 0.1501597444089457, "percentage": 3.0, "elapsed_time": "0:08:32", "remaining_time": "4:35:39"}
+{"current_steps": 48, "total_steps": 1565, "loss": 0.6386, "lr": 3.0573248407643314e-06, "epoch": 0.15335463258785942, "percentage": 3.07, "elapsed_time": "0:08:43", "remaining_time": "4:35:46"}
+{"current_steps": 49, "total_steps": 1565, "loss": 0.6321, "lr": 3.121019108280255e-06, "epoch": 0.15654952076677317, "percentage": 3.13, "elapsed_time": "0:08:53", "remaining_time": "4:35:17"}
+{"current_steps": 50, "total_steps": 1565, "loss": 0.5984, "lr": 3.1847133757961785e-06, "epoch": 0.1597444089456869, "percentage": 3.19, "elapsed_time": "0:09:05", "remaining_time": "4:35:15"}
+{"current_steps": 51, "total_steps": 1565, "loss": 0.6401, "lr": 3.248407643312102e-06, "epoch": 0.16293929712460065, "percentage": 3.26, "elapsed_time": "0:09:16", "remaining_time": "4:35:10"}
+{"current_steps": 52, "total_steps": 1565, "loss": 0.6553, "lr": 3.3121019108280255e-06, "epoch": 0.16613418530351437, "percentage": 3.32, "elapsed_time": "0:09:26", "remaining_time": "4:34:49"}
+{"current_steps": 53, "total_steps": 1565, "loss": 0.6004, "lr": 3.375796178343949e-06, "epoch": 0.16932907348242812, "percentage": 3.39, "elapsed_time": "0:09:33", "remaining_time": "4:32:42"}
+{"current_steps": 54, "total_steps": 1565, "loss": 0.5908, "lr": 3.4394904458598725e-06, "epoch": 0.17252396166134185, "percentage": 3.45, "elapsed_time": "0:09:45", "remaining_time": "4:33:12"}
+{"current_steps": 55, "total_steps": 1565, "loss": 0.6105, "lr": 3.5031847133757964e-06, "epoch": 0.1757188498402556, "percentage": 3.51, "elapsed_time": "0:09:53", "remaining_time": "4:31:29"}
+{"current_steps": 56, "total_steps": 1565, "loss": 0.5707, "lr": 3.56687898089172e-06, "epoch": 0.17891373801916932, "percentage": 3.58, "elapsed_time": "0:10:03", "remaining_time": "4:31:09"}
+{"current_steps": 57, "total_steps": 1565, "loss": 0.6062, "lr": 3.6305732484076435e-06, "epoch": 0.18210862619808307, "percentage": 3.64, "elapsed_time": "0:10:14", "remaining_time": "4:30:55"}
+{"current_steps": 58, "total_steps": 1565, "loss": 0.583, "lr": 3.694267515923567e-06, "epoch": 0.1853035143769968, "percentage": 3.71, "elapsed_time": "0:10:24", "remaining_time": "4:30:27"}
+{"current_steps": 59, "total_steps": 1565, "loss": 0.6009, "lr": 3.757961783439491e-06, "epoch": 0.18849840255591055, "percentage": 3.77, "elapsed_time": "0:10:31", "remaining_time": "4:28:49"}
+{"current_steps": 60, "total_steps": 1565, "loss": 0.5959, "lr": 3.821656050955415e-06, "epoch": 0.19169329073482427, "percentage": 3.83, "elapsed_time": "0:10:43", "remaining_time": "4:29:07"}
+{"current_steps": 61, "total_steps": 1565, "loss": 0.5914, "lr": 3.885350318471338e-06, "epoch": 0.19488817891373802, "percentage": 3.9, "elapsed_time": "0:10:56", "remaining_time": "4:29:36"}
+{"current_steps": 62, "total_steps": 1565, "loss": 0.5472, "lr": 3.949044585987262e-06, "epoch": 0.19808306709265175, "percentage": 3.96, "elapsed_time": "0:11:03", "remaining_time": "4:27:55"}
+{"current_steps": 63, "total_steps": 1565, "loss": 0.5857, "lr": 4.012738853503185e-06, "epoch": 0.2012779552715655, "percentage": 4.03, "elapsed_time": "0:11:11", "remaining_time": "4:26:39"}
+{"current_steps": 64, "total_steps": 1565, "loss": 0.5802, "lr": 4.076433121019109e-06, "epoch": 0.20447284345047922, "percentage": 4.09, "elapsed_time": "0:11:21", "remaining_time": "4:26:12"}
+{"current_steps": 65, "total_steps": 1565, "loss": 0.6168, "lr": 4.140127388535032e-06, "epoch": 0.20766773162939298, "percentage": 4.15, "elapsed_time": "0:11:31", "remaining_time": "4:26:07"}
+{"current_steps": 66, "total_steps": 1565, "loss": 0.5501, "lr": 4.203821656050956e-06, "epoch": 0.2108626198083067, "percentage": 4.22, "elapsed_time": "0:11:40", "remaining_time": "4:25:07"}
+{"current_steps": 67, "total_steps": 1565, "loss": 0.5535, "lr": 4.26751592356688e-06, "epoch": 0.21405750798722045, "percentage": 4.28, "elapsed_time": "0:11:52", "remaining_time": "4:25:36"}
+{"current_steps": 68, "total_steps": 1565, "loss": 0.5462, "lr": 4.331210191082803e-06, "epoch": 0.21725239616613418, "percentage": 4.35, "elapsed_time": "0:11:58", "remaining_time": "4:23:38"}
+{"current_steps": 69, "total_steps": 1565, "loss": 0.6007, "lr": 4.394904458598727e-06, "epoch": 0.22044728434504793, "percentage": 4.41, "elapsed_time": "0:12:10", "remaining_time": "4:23:56"}
+{"current_steps": 70, "total_steps": 1565, "loss": 0.6178, "lr": 4.45859872611465e-06, "epoch": 0.22364217252396165, "percentage": 4.47, "elapsed_time": "0:12:22", "remaining_time": "4:24:23"}
+{"current_steps": 71, "total_steps": 1565, "loss": 0.5302, "lr": 4.522292993630574e-06, "epoch": 0.2268370607028754, "percentage": 4.54, "elapsed_time": "0:12:33", "remaining_time": "4:24:22"}
+{"current_steps": 72, "total_steps": 1565, "loss": 0.5561, "lr": 4.585987261146497e-06, "epoch": 0.23003194888178913, "percentage": 4.6, "elapsed_time": "0:12:42", "remaining_time": "4:23:40"}
+{"current_steps": 73, "total_steps": 1565, "loss": 0.5538, "lr": 4.649681528662421e-06, "epoch": 0.23322683706070288, "percentage": 4.66, "elapsed_time": "0:12:54", "remaining_time": "4:23:48"}
+{"current_steps": 74, "total_steps": 1565, "loss": 0.5356, "lr": 4.713375796178344e-06, "epoch": 0.2364217252396166, "percentage": 4.73, "elapsed_time": "0:13:05", "remaining_time": "4:23:40"}
+{"current_steps": 75, "total_steps": 1565, "loss": 0.5395, "lr": 4.777070063694268e-06, "epoch": 0.23961661341853036, "percentage": 4.79, "elapsed_time": "0:13:16", "remaining_time": "4:23:36"}
+{"current_steps": 76, "total_steps": 1565, "loss": 0.5611, "lr": 4.840764331210192e-06, "epoch": 0.24281150159744408, "percentage": 4.86, "elapsed_time": "0:13:27", "remaining_time": "4:23:34"}
+{"current_steps": 77, "total_steps": 1565, "loss": 0.5113, "lr": 4.904458598726115e-06, "epoch": 0.24600638977635783, "percentage": 4.92, "elapsed_time": "0:13:35", "remaining_time": "4:22:29"}
+{"current_steps": 78, "total_steps": 1565, "loss": 0.5518, "lr": 4.968152866242039e-06, "epoch": 0.24920127795527156, "percentage": 4.98, "elapsed_time": "0:13:47", "remaining_time": "4:22:55"}
+{"current_steps": 79, "total_steps": 1565, "loss": 0.5642, "lr": 5.031847133757962e-06, "epoch": 0.2523961661341853, "percentage": 5.05, "elapsed_time": "0:13:59", "remaining_time": "4:23:07"}
+{"current_steps": 80, "total_steps": 1565, "loss": 0.5218, "lr": 5.095541401273886e-06, "epoch": 0.25559105431309903, "percentage": 5.11, "elapsed_time": "0:14:07", "remaining_time": "4:22:15"}
+{"current_steps": 81, "total_steps": 1565, "loss": 0.5713, "lr": 5.159235668789809e-06, "epoch": 0.25878594249201275, "percentage": 5.18, "elapsed_time": "0:14:18", "remaining_time": "4:22:17"}
+{"current_steps": 82, "total_steps": 1565, "loss": 0.5852, "lr": 5.222929936305733e-06, "epoch": 0.26198083067092653, "percentage": 5.24, "elapsed_time": "0:14:25", "remaining_time": "4:20:56"}
+{"current_steps": 83, "total_steps": 1565, "loss": 0.535, "lr": 5.286624203821657e-06, "epoch": 0.26517571884984026, "percentage": 5.3, "elapsed_time": "0:14:36", "remaining_time": "4:20:44"}
+{"current_steps": 84, "total_steps": 1565, "loss": 0.492, "lr": 5.35031847133758e-06, "epoch": 0.268370607028754, "percentage": 5.37, "elapsed_time": "0:14:43", "remaining_time": "4:19:39"}
+{"current_steps": 85, "total_steps": 1565, "loss": 0.5889, "lr": 5.414012738853504e-06, "epoch": 0.2715654952076677, "percentage": 5.43, "elapsed_time": "0:14:51", "remaining_time": "4:18:48"}
+{"current_steps": 86, "total_steps": 1565, "loss": 0.5668, "lr": 5.477707006369427e-06, "epoch": 0.2747603833865815, "percentage": 5.5, "elapsed_time": "0:15:03", "remaining_time": "4:19:05"}
+{"current_steps": 87, "total_steps": 1565, "loss": 0.5657, "lr": 5.541401273885351e-06, "epoch": 0.2779552715654952, "percentage": 5.56, "elapsed_time": "0:15:15", "remaining_time": "4:19:16"}
+{"current_steps": 88, "total_steps": 1565, "loss": 0.5976, "lr": 5.605095541401274e-06, "epoch": 0.28115015974440893, "percentage": 5.62, "elapsed_time": "0:15:27", "remaining_time": "4:19:35"}
+{"current_steps": 89, "total_steps": 1565, "loss": 0.4985, "lr": 5.668789808917198e-06, "epoch": 0.28434504792332266, "percentage": 5.69, "elapsed_time": "0:15:40", "remaining_time": "4:19:53"}
+{"current_steps": 90, "total_steps": 1565, "loss": 0.5345, "lr": 5.732484076433121e-06, "epoch": 0.28753993610223644, "percentage": 5.75, "elapsed_time": "0:15:51", "remaining_time": "4:19:56"}
+{"current_steps": 91, "total_steps": 1565, "loss": 0.5467, "lr": 5.796178343949045e-06, "epoch": 0.29073482428115016, "percentage": 5.81, "elapsed_time": "0:16:02", "remaining_time": "4:19:46"}
+{"current_steps": 92, "total_steps": 1565, "loss": 0.5107, "lr": 5.859872611464969e-06, "epoch": 0.2939297124600639, "percentage": 5.88, "elapsed_time": "0:16:13", "remaining_time": "4:19:43"}
+{"current_steps": 93, "total_steps": 1565, "loss": 0.5486, "lr": 5.923566878980892e-06, "epoch": 0.2971246006389776, "percentage": 5.94, "elapsed_time": "0:16:25", "remaining_time": "4:19:53"}
+{"current_steps": 94, "total_steps": 1565, "loss": 0.5955, "lr": 5.987261146496816e-06, "epoch": 0.3003194888178914, "percentage": 6.01, "elapsed_time": "0:16:37", "remaining_time": "4:20:04"}
+{"current_steps": 95, "total_steps": 1565, "loss": 0.532, "lr": 6.050955414012739e-06, "epoch": 0.3035143769968051, "percentage": 6.07, "elapsed_time": "0:16:48", "remaining_time": "4:20:00"}
+{"current_steps": 96, "total_steps": 1565, "loss": 0.5624, "lr": 6.114649681528663e-06, "epoch": 0.30670926517571884, "percentage": 6.13, "elapsed_time": "0:17:00", "remaining_time": "4:20:13"}
+{"current_steps": 97, "total_steps": 1565, "loss": 0.5271, "lr": 6.178343949044586e-06, "epoch": 0.30990415335463256, "percentage": 6.2, "elapsed_time": "0:17:08", "remaining_time": "4:19:21"}
+{"current_steps": 98, "total_steps": 1565, "loss": 0.5524, "lr": 6.24203821656051e-06, "epoch": 0.31309904153354634, "percentage": 6.26, "elapsed_time": "0:17:16", "remaining_time": "4:18:37"}
+{"current_steps": 99, "total_steps": 1565, "loss": 0.532, "lr": 6.305732484076433e-06, "epoch": 0.31629392971246006, "percentage": 6.33, "elapsed_time": "0:17:25", "remaining_time": "4:17:59"}
+{"current_steps": 100, "total_steps": 1565, "loss": 0.5869, "lr": 6.369426751592357e-06, "epoch": 0.3194888178913738, "percentage": 6.39, "elapsed_time": "0:17:37", "remaining_time": "4:18:10"}
+{"current_steps": 101, "total_steps": 1565, "loss": 0.5493, "lr": 6.433121019108281e-06, "epoch": 0.3226837060702875, "percentage": 6.45, "elapsed_time": "0:17:47", "remaining_time": "4:17:54"}
+{"current_steps": 102, "total_steps": 1565, "loss": 0.5698, "lr": 6.496815286624204e-06, "epoch": 0.3258785942492013, "percentage": 6.52, "elapsed_time": "0:17:57", "remaining_time": "4:17:39"}
+{"current_steps": 103, "total_steps": 1565, "loss": 0.5142, "lr": 6.560509554140128e-06, "epoch": 0.329073482428115, "percentage": 6.58, "elapsed_time": "0:18:10", "remaining_time": "4:18:02"}
+{"current_steps": 104, "total_steps": 1565, "loss": 0.5554, "lr": 6.624203821656051e-06, "epoch": 0.33226837060702874, "percentage": 6.65, "elapsed_time": "0:18:23", "remaining_time": "4:18:17"}
+{"current_steps": 105, "total_steps": 1565, "loss": 0.5157, "lr": 6.687898089171975e-06, "epoch": 0.3354632587859425, "percentage": 6.71, "elapsed_time": "0:18:34", "remaining_time": "4:18:12"}
+{"current_steps": 106, "total_steps": 1565, "loss": 0.5098, "lr": 6.751592356687898e-06, "epoch": 0.33865814696485624, "percentage": 6.77, "elapsed_time": "0:18:42", "remaining_time": "4:17:33"}
+{"current_steps": 107, "total_steps": 1565, "loss": 0.5716, "lr": 6.815286624203822e-06, "epoch": 0.34185303514376997, "percentage": 6.84, "elapsed_time": "0:18:52", "remaining_time": "4:17:14"}
+{"current_steps": 108, "total_steps": 1565, "loss": 0.53, "lr": 6.878980891719745e-06, "epoch": 0.3450479233226837, "percentage": 6.9, "elapsed_time": "0:19:02", "remaining_time": "4:16:51"}
+{"current_steps": 109, "total_steps": 1565, "loss": 0.5407, "lr": 6.942675159235669e-06, "epoch": 0.34824281150159747, "percentage": 6.96, "elapsed_time": "0:19:14", "remaining_time": "4:16:55"}
+{"current_steps": 110, "total_steps": 1565, "loss": 0.5353, "lr": 7.006369426751593e-06, "epoch": 0.3514376996805112, "percentage": 7.03, "elapsed_time": "0:19:24", "remaining_time": "4:16:38"}
+{"current_steps": 111, "total_steps": 1565, "loss": 0.622, "lr": 7.070063694267516e-06, "epoch": 0.3546325878594249, "percentage": 7.09, "elapsed_time": "0:19:33", "remaining_time": "4:16:15"}
+{"current_steps": 112, "total_steps": 1565, "loss": 0.5838, "lr": 7.13375796178344e-06, "epoch": 0.35782747603833864, "percentage": 7.16, "elapsed_time": "0:19:42", "remaining_time": "4:15:41"}
+{"current_steps": 113, "total_steps": 1565, "loss": 0.5755, "lr": 7.197452229299363e-06, "epoch": 0.3610223642172524, "percentage": 7.22, "elapsed_time": "0:19:53", "remaining_time": "4:15:36"}
+{"current_steps": 114, "total_steps": 1565, "loss": 0.6179, "lr": 7.261146496815287e-06, "epoch": 0.36421725239616615, "percentage": 7.28, "elapsed_time": "0:20:05", "remaining_time": "4:15:48"}
+{"current_steps": 115, "total_steps": 1565, "loss": 0.4982, "lr": 7.32484076433121e-06, "epoch": 0.36741214057507987, "percentage": 7.35, "elapsed_time": "0:20:17", "remaining_time": "4:15:55"}
+{"current_steps": 116, "total_steps": 1565, "loss": 0.5276, "lr": 7.388535031847134e-06, "epoch": 0.3706070287539936, "percentage": 7.41, "elapsed_time": "0:20:29", "remaining_time": "4:15:55"}
+{"current_steps": 117, "total_steps": 1565, "loss": 0.5046, "lr": 7.452229299363057e-06, "epoch": 0.3738019169329074, "percentage": 7.48, "elapsed_time": "0:20:38", "remaining_time": "4:15:27"}
+{"current_steps": 118, "total_steps": 1565, "loss": 0.5254, "lr": 7.515923566878982e-06, "epoch": 0.3769968051118211, "percentage": 7.54, "elapsed_time": "0:20:49", "remaining_time": "4:15:21"}
+{"current_steps": 119, "total_steps": 1565, "loss": 0.5183, "lr": 7.579617834394906e-06, "epoch": 0.3801916932907348, "percentage": 7.6, "elapsed_time": "0:20:59", "remaining_time": "4:15:07"}
+{"current_steps": 120, "total_steps": 1565, "loss": 0.5284, "lr": 7.64331210191083e-06, "epoch": 0.38338658146964855, "percentage": 7.67, "elapsed_time": "0:21:11", "remaining_time": "4:15:10"}
+{"current_steps": 121, "total_steps": 1565, "loss": 0.5468, "lr": 7.707006369426753e-06, "epoch": 0.3865814696485623, "percentage": 7.73, "elapsed_time": "0:21:22", "remaining_time": "4:15:08"}
+{"current_steps": 122, "total_steps": 1565, "loss": 0.518, "lr": 7.770700636942676e-06, "epoch": 0.38977635782747605, "percentage": 7.8, "elapsed_time": "0:21:34", "remaining_time": "4:15:13"}
+{"current_steps": 123, "total_steps": 1565, "loss": 0.5598, "lr": 7.8343949044586e-06, "epoch": 0.3929712460063898, "percentage": 7.86, "elapsed_time": "0:21:45", "remaining_time": "4:15:02"}
+{"current_steps": 124, "total_steps": 1565, "loss": 0.5521, "lr": 7.898089171974524e-06, "epoch": 0.3961661341853035, "percentage": 7.92, "elapsed_time": "0:21:56", "remaining_time": "4:14:58"}
+{"current_steps": 125, "total_steps": 1565, "loss": 0.5488, "lr": 7.961783439490447e-06, "epoch": 0.3993610223642173, "percentage": 7.99, "elapsed_time": "0:22:08", "remaining_time": "4:15:06"}
+{"current_steps": 126, "total_steps": 1565, "loss": 0.6081, "lr": 8.02547770700637e-06, "epoch": 0.402555910543131, "percentage": 8.05, "elapsed_time": "0:22:21", "remaining_time": "4:15:15"}
+{"current_steps": 127, "total_steps": 1565, "loss": 0.5526, "lr": 8.089171974522295e-06, "epoch": 0.4057507987220447, "percentage": 8.12, "elapsed_time": "0:22:30", "remaining_time": "4:14:57"}
+{"current_steps": 128, "total_steps": 1565, "loss": 0.5061, "lr": 8.152866242038218e-06, "epoch": 0.40894568690095845, "percentage": 8.18, "elapsed_time": "0:22:43", "remaining_time": "4:15:01"}
+{"current_steps": 129, "total_steps": 1565, "loss": 0.5374, "lr": 8.21656050955414e-06, "epoch": 0.41214057507987223, "percentage": 8.24, "elapsed_time": "0:22:54", "remaining_time": "4:14:58"}
+{"current_steps": 130, "total_steps": 1565, "loss": 0.5733, "lr": 8.280254777070064e-06, "epoch": 0.41533546325878595, "percentage": 8.31, "elapsed_time": "0:23:04", "remaining_time": "4:14:46"}
+{"current_steps": 131, "total_steps": 1565, "loss": 0.556, "lr": 8.343949044585989e-06, "epoch": 0.4185303514376997, "percentage": 8.37, "elapsed_time": "0:23:17", "remaining_time": "4:15:02"}
+{"current_steps": 132, "total_steps": 1565, "loss": 0.5139, "lr": 8.407643312101912e-06, "epoch": 0.4217252396166134, "percentage": 8.43, "elapsed_time": "0:23:25", "remaining_time": "4:14:19"}
+{"current_steps": 133, "total_steps": 1565, "loss": 0.5317, "lr": 8.471337579617835e-06, "epoch": 0.4249201277955272, "percentage": 8.5, "elapsed_time": "0:23:36", "remaining_time": "4:14:10"}
+{"current_steps": 134, "total_steps": 1565, "loss": 0.596, "lr": 8.53503184713376e-06, "epoch": 0.4281150159744409, "percentage": 8.56, "elapsed_time": "0:23:46", "remaining_time": "4:13:52"}
+{"current_steps": 135, "total_steps": 1565, "loss": 0.5386, "lr": 8.598726114649683e-06, "epoch": 0.43130990415335463, "percentage": 8.63, "elapsed_time": "0:23:57", "remaining_time": "4:13:48"}
+{"current_steps": 136, "total_steps": 1565, "loss": 0.5288, "lr": 8.662420382165606e-06, "epoch": 0.43450479233226835, "percentage": 8.69, "elapsed_time": "0:24:08", "remaining_time": "4:13:41"}
+{"current_steps": 137, "total_steps": 1565, "loss": 0.5339, "lr": 8.726114649681529e-06, "epoch": 0.43769968051118213, "percentage": 8.75, "elapsed_time": "0:24:17", "remaining_time": "4:13:14"}
+{"current_steps": 138, "total_steps": 1565, "loss": 0.5455, "lr": 8.789808917197454e-06, "epoch": 0.44089456869009586, "percentage": 8.82, "elapsed_time": "0:24:27", "remaining_time": "4:12:57"}
+{"current_steps": 139, "total_steps": 1565, "loss": 0.5567, "lr": 8.853503184713377e-06, "epoch": 0.4440894568690096, "percentage": 8.88, "elapsed_time": "0:24:39", "remaining_time": "4:12:57"}
+{"current_steps": 140, "total_steps": 1565, "loss": 0.5209, "lr": 8.9171974522293e-06, "epoch": 0.4472843450479233, "percentage": 8.95, "elapsed_time": "0:24:49", "remaining_time": "4:12:35"}
+{"current_steps": 141, "total_steps": 1565, "loss": 0.5873, "lr": 8.980891719745225e-06, "epoch": 0.4504792332268371, "percentage": 9.01, "elapsed_time": "0:25:00", "remaining_time": "4:12:33"}
+{"current_steps": 142, "total_steps": 1565, "loss": 0.5259, "lr": 9.044585987261148e-06, "epoch": 0.4536741214057508, "percentage": 9.07, "elapsed_time": "0:25:12", "remaining_time": "4:12:34"}
+{"current_steps": 143, "total_steps": 1565, "loss": 0.5347, "lr": 9.10828025477707e-06, "epoch": 0.45686900958466453, "percentage": 9.14, "elapsed_time": "0:25:22", "remaining_time": "4:12:22"}
+{"current_steps": 144, "total_steps": 1565, "loss": 0.5212, "lr": 9.171974522292994e-06, "epoch": 0.46006389776357826, "percentage": 9.2, "elapsed_time": "0:25:32", "remaining_time": "4:12:05"}
+{"current_steps": 145, "total_steps": 1565, "loss": 0.5464, "lr": 9.235668789808919e-06, "epoch": 0.46325878594249204, "percentage": 9.27, "elapsed_time": "0:25:44", "remaining_time": "4:12:06"}
+{"current_steps": 146, "total_steps": 1565, "loss": 0.5296, "lr": 9.299363057324842e-06, "epoch": 0.46645367412140576, "percentage": 9.33, "elapsed_time": "0:25:55", "remaining_time": "4:12:02"}
+{"current_steps": 147, "total_steps": 1565, "loss": 0.5245, "lr": 9.363057324840765e-06, "epoch": 0.4696485623003195, "percentage": 9.39, "elapsed_time": "0:26:06", "remaining_time": "4:11:52"}
+{"current_steps": 148, "total_steps": 1565, "loss": 0.5633, "lr": 9.426751592356688e-06, "epoch": 0.4728434504792332, "percentage": 9.46, "elapsed_time": "0:26:17", "remaining_time": "4:11:39"}
+{"current_steps": 149, "total_steps": 1565, "loss": 0.5667, "lr": 9.490445859872613e-06, "epoch": 0.476038338658147, "percentage": 9.52, "elapsed_time": "0:26:28", "remaining_time": "4:11:34"}
+{"current_steps": 150, "total_steps": 1565, "loss": 0.4761, "lr": 9.554140127388536e-06, "epoch": 0.4792332268370607, "percentage": 9.58, "elapsed_time": "0:26:38", "remaining_time": "4:11:18"}
+{"current_steps": 151, "total_steps": 1565, "loss": 0.5482, "lr": 9.617834394904459e-06, "epoch": 0.48242811501597443, "percentage": 9.65, "elapsed_time": "0:26:48", "remaining_time": "4:11:05"}
+{"current_steps": 152, "total_steps": 1565, "loss": 0.5105, "lr": 9.681528662420384e-06, "epoch": 0.48562300319488816, "percentage": 9.71, "elapsed_time": "0:26:58", "remaining_time": "4:10:44"}
+{"current_steps": 153, "total_steps": 1565, "loss": 0.5265, "lr": 9.745222929936307e-06, "epoch": 0.48881789137380194, "percentage": 9.78, "elapsed_time": "0:27:10", "remaining_time": "4:10:50"}
+{"current_steps": 154, "total_steps": 1565, "loss": 0.5198, "lr": 9.80891719745223e-06, "epoch": 0.49201277955271566, "percentage": 9.84, "elapsed_time": "0:27:22", "remaining_time": "4:10:53"}
+{"current_steps": 155, "total_steps": 1565, "loss": 0.5267, "lr": 9.872611464968153e-06, "epoch": 0.4952076677316294, "percentage": 9.9, "elapsed_time": "0:27:34", "remaining_time": "4:10:51"}
+{"current_steps": 156, "total_steps": 1565, "loss": 0.5562, "lr": 9.936305732484078e-06, "epoch": 0.4984025559105431, "percentage": 9.97, "elapsed_time": "0:27:43", "remaining_time": "4:10:26"}
+{"current_steps": 157, "total_steps": 1565, "loss": 0.4791, "lr": 1e-05, "epoch": 0.5015974440894568, "percentage": 10.03, "elapsed_time": "0:27:55", "remaining_time": "4:10:30"}
+{"current_steps": 158, "total_steps": 1565, "loss": 0.4971, "lr": 9.999987553871966e-06, "epoch": 0.5047923322683706, "percentage": 10.1, "elapsed_time": "0:28:07", "remaining_time": "4:10:29"}
+{"current_steps": 159, "total_steps": 1565, "loss": 0.5263, "lr": 9.999950215549828e-06, "epoch": 0.5079872204472844, "percentage": 10.16, "elapsed_time": "0:28:18", "remaining_time": "4:10:20"}
+{"current_steps": 160, "total_steps": 1565, "loss": 0.509, "lr": 9.999887985219473e-06, "epoch": 0.5111821086261981, "percentage": 10.22, "elapsed_time": "0:28:27", "remaining_time": "4:09:55"}
+{"current_steps": 161, "total_steps": 1565, "loss": 0.5325, "lr": 9.999800863190708e-06, "epoch": 0.5143769968051118, "percentage": 10.29, "elapsed_time": "0:28:39", "remaining_time": "4:09:51"}
+{"current_steps": 162, "total_steps": 1565, "loss": 0.5259, "lr": 9.99968884989727e-06, "epoch": 0.5175718849840255, "percentage": 10.35, "elapsed_time": "0:28:48", "remaining_time": "4:09:25"}
+{"current_steps": 163, "total_steps": 1565, "loss": 0.559, "lr": 9.99955194589681e-06, "epoch": 0.5207667731629393, "percentage": 10.42, "elapsed_time": "0:28:56", "remaining_time": "4:08:57"}
+{"current_steps": 164, "total_steps": 1565, "loss": 0.5486, "lr": 9.999390151870899e-06, "epoch": 0.5239616613418531, "percentage": 10.48, "elapsed_time": "0:29:06", "remaining_time": "4:08:42"}
+{"current_steps": 165, "total_steps": 1565, "loss": 0.535, "lr": 9.999203468625017e-06, "epoch": 0.5271565495207667, "percentage": 10.54, "elapsed_time": "0:29:18", "remaining_time": "4:08:44"}
+{"current_steps": 166, "total_steps": 1565, "loss": 0.5217, "lr": 9.998991897088563e-06, "epoch": 0.5303514376996805, "percentage": 10.61, "elapsed_time": "0:29:32", "remaining_time": "4:08:54"}
+{"current_steps": 167, "total_steps": 1565, "loss": 0.496, "lr": 9.99875543831483e-06, "epoch": 0.5335463258785943, "percentage": 10.67, "elapsed_time": "0:29:39", "remaining_time": "4:08:14"}
+{"current_steps": 168, "total_steps": 1565, "loss": 0.4961, "lr": 9.998494093481022e-06, "epoch": 0.536741214057508, "percentage": 10.73, "elapsed_time": "0:29:51", "remaining_time": "4:08:15"}
+{"current_steps": 169, "total_steps": 1565, "loss": 0.5553, "lr": 9.998207863888228e-06, "epoch": 0.5399361022364217, "percentage": 10.8, "elapsed_time": "0:30:02", "remaining_time": "4:08:10"}
+{"current_steps": 170, "total_steps": 1565, "loss": 0.5398, "lr": 9.997896750961429e-06, "epoch": 0.5431309904153354, "percentage": 10.86, "elapsed_time": "0:30:14", "remaining_time": "4:08:13"}
+{"current_steps": 171, "total_steps": 1565, "loss": 0.5414, "lr": 9.997560756249485e-06, "epoch": 0.5463258785942492, "percentage": 10.93, "elapsed_time": "0:30:26", "remaining_time": "4:08:05"}
+{"current_steps": 172, "total_steps": 1565, "loss": 0.5376, "lr": 9.997199881425128e-06, "epoch": 0.549520766773163, "percentage": 10.99, "elapsed_time": "0:30:37", "remaining_time": "4:07:59"}
+{"current_steps": 173, "total_steps": 1565, "loss": 0.5478, "lr": 9.99681412828496e-06, "epoch": 0.5527156549520766, "percentage": 11.05, "elapsed_time": "0:30:47", "remaining_time": "4:07:47"}
+{"current_steps": 174, "total_steps": 1565, "loss": 0.5747, "lr": 9.99640349874943e-06, "epoch": 0.5559105431309904, "percentage": 11.12, "elapsed_time": "0:30:55", "remaining_time": "4:07:17"}
+{"current_steps": 175, "total_steps": 1565, "loss": 0.5228, "lr": 9.995967994862838e-06, "epoch": 0.5591054313099042, "percentage": 11.18, "elapsed_time": "0:31:07", "remaining_time": "4:07:11"}
+{"current_steps": 176, "total_steps": 1565, "loss": 0.5109, "lr": 9.995507618793321e-06, "epoch": 0.5623003194888179, "percentage": 11.25, "elapsed_time": "0:31:18", "remaining_time": "4:07:07"}
+{"current_steps": 177, "total_steps": 1565, "loss": 0.5408, "lr": 9.995022372832836e-06, "epoch": 0.5654952076677316, "percentage": 11.31, "elapsed_time": "0:31:27", "remaining_time": "4:06:39"}
+{"current_steps": 178, "total_steps": 1565, "loss": 0.5158, "lr": 9.994512259397159e-06, "epoch": 0.5686900958466453, "percentage": 11.37, "elapsed_time": "0:31:38", "remaining_time": "4:06:31"}
+{"current_steps": 179, "total_steps": 1565, "loss": 0.5093, "lr": 9.993977281025862e-06, "epoch": 0.5718849840255591, "percentage": 11.44, "elapsed_time": "0:31:45", "remaining_time": "4:05:56"}
+{"current_steps": 180, "total_steps": 1565, "loss": 0.5449, "lr": 9.993417440382312e-06, "epoch": 0.5750798722044729, "percentage": 11.5, "elapsed_time": "0:31:56", "remaining_time": "4:05:49"}
+{"current_steps": 181, "total_steps": 1565, "loss": 0.5456, "lr": 9.992832740253646e-06, "epoch": 0.5782747603833865, "percentage": 11.57, "elapsed_time": "0:32:09", "remaining_time": "4:05:50"}
+{"current_steps": 182, "total_steps": 1565, "loss": 0.5241, "lr": 9.992223183550764e-06, "epoch": 0.5814696485623003, "percentage": 11.63, "elapsed_time": "0:32:19", "remaining_time": "4:05:37"}
+{"current_steps": 183, "total_steps": 1565, "loss": 0.5249, "lr": 9.991588773308317e-06, "epoch": 0.5846645367412141, "percentage": 11.69, "elapsed_time": "0:32:31", "remaining_time": "4:05:35"}
+{"current_steps": 184, "total_steps": 1565, "loss": 0.5098, "lr": 9.990929512684685e-06, "epoch": 0.5878594249201278, "percentage": 11.76, "elapsed_time": "0:32:38", "remaining_time": "4:04:55"}
+{"current_steps": 185, "total_steps": 1565, "loss": 0.5254, "lr": 9.990245404961964e-06, "epoch": 0.5910543130990416, "percentage": 11.82, "elapsed_time": "0:32:51", "remaining_time": "4:05:05"}
+{"current_steps": 186, "total_steps": 1565, "loss": 0.4867, "lr": 9.98953645354595e-06, "epoch": 0.5942492012779552, "percentage": 11.88, "elapsed_time": "0:33:03", "remaining_time": "4:05:02"}
+{"current_steps": 187, "total_steps": 1565, "loss": 0.5028, "lr": 9.988802661966125e-06, "epoch": 0.597444089456869, "percentage": 11.95, "elapsed_time": "0:33:13", "remaining_time": "4:04:47"}
+{"current_steps": 188, "total_steps": 1565, "loss": 0.511, "lr": 9.988044033875633e-06, "epoch": 0.6006389776357828, "percentage": 12.01, "elapsed_time": "0:33:26", "remaining_time": "4:04:53"}
+{"current_steps": 189, "total_steps": 1565, "loss": 0.4933, "lr": 9.987260573051268e-06, "epoch": 0.6038338658146964, "percentage": 12.08, "elapsed_time": "0:33:39", "remaining_time": "4:04:59"}
+{"current_steps": 190, "total_steps": 1565, "loss": 0.5248, "lr": 9.986452283393452e-06, "epoch": 0.6070287539936102, "percentage": 12.14, "elapsed_time": "0:33:46", "remaining_time": "4:04:24"}
+{"current_steps": 191, "total_steps": 1565, "loss": 0.4816, "lr": 9.985619168926213e-06, "epoch": 0.610223642172524, "percentage": 12.2, "elapsed_time": "0:33:56", "remaining_time": "4:04:12"}
+{"current_steps": 192, "total_steps": 1565, "loss": 0.5229, "lr": 9.984761233797175e-06, "epoch": 0.6134185303514377, "percentage": 12.27, "elapsed_time": "0:34:09", "remaining_time": "4:04:15"}
+{"current_steps": 193, "total_steps": 1565, "loss": 0.5433, "lr": 9.983878482277522e-06, "epoch": 0.6166134185303515, "percentage": 12.33, "elapsed_time": "0:34:18", "remaining_time": "4:03:55"}
+{"current_steps": 194, "total_steps": 1565, "loss": 0.5315, "lr": 9.982970918761991e-06, "epoch": 0.6198083067092651, "percentage": 12.4, "elapsed_time": "0:34:29", "remaining_time": "4:03:47"}
+{"current_steps": 195, "total_steps": 1565, "loss": 0.5238, "lr": 9.982038547768844e-06, "epoch": 0.6230031948881789, "percentage": 12.46, "elapsed_time": "0:34:41", "remaining_time": "4:03:46"}
+{"current_steps": 196, "total_steps": 1565, "loss": 0.5266, "lr": 9.981081373939843e-06, "epoch": 0.6261980830670927, "percentage": 12.52, "elapsed_time": "0:34:54", "remaining_time": "4:03:46"}
+{"current_steps": 197, "total_steps": 1565, "loss": 0.5208, "lr": 9.980099402040231e-06, "epoch": 0.6293929712460063, "percentage": 12.59, "elapsed_time": "0:35:04", "remaining_time": "4:03:32"}
+{"current_steps": 198, "total_steps": 1565, "loss": 0.4867, "lr": 9.979092636958707e-06, "epoch": 0.6325878594249201, "percentage": 12.65, "elapsed_time": "0:35:13", "remaining_time": "4:03:09"}
+{"current_steps": 199, "total_steps": 1565, "loss": 0.4918, "lr": 9.978061083707403e-06, "epoch": 0.6357827476038339, "percentage": 12.72, "elapsed_time": "0:35:25", "remaining_time": "4:03:08"}
+{"current_steps": 200, "total_steps": 1565, "loss": 0.489, "lr": 9.977004747421856e-06, "epoch": 0.6389776357827476, "percentage": 12.78, "elapsed_time": "0:35:36", "remaining_time": "4:02:58"}
+{"current_steps": 201, "total_steps": 1565, "loss": 0.528, "lr": 9.975923633360985e-06, "epoch": 0.6421725239616614, "percentage": 12.84, "elapsed_time": "0:35:47", "remaining_time": "4:02:56"}
+{"current_steps": 202, "total_steps": 1565, "loss": 0.5402, "lr": 9.974817746907064e-06, "epoch": 0.645367412140575, "percentage": 12.91, "elapsed_time": "0:35:59", "remaining_time": "4:02:51"}
+{"current_steps": 203, "total_steps": 1565, "loss": 0.4801, "lr": 9.973687093565692e-06, "epoch": 0.6485623003194888, "percentage": 12.97, "elapsed_time": "0:36:11", "remaining_time": "4:02:49"}
+{"current_steps": 204, "total_steps": 1565, "loss": 0.5348, "lr": 9.972531678965776e-06, "epoch": 0.6517571884984026, "percentage": 13.04, "elapsed_time": "0:36:22", "remaining_time": "4:02:39"}
+{"current_steps": 205, "total_steps": 1565, "loss": 0.4932, "lr": 9.971351508859488e-06, "epoch": 0.6549520766773163, "percentage": 13.1, "elapsed_time": "0:36:32", "remaining_time": "4:02:23"}
+{"current_steps": 206, "total_steps": 1565, "loss": 0.5217, "lr": 9.970146589122247e-06, "epoch": 0.65814696485623, "percentage": 13.16, "elapsed_time": "0:36:44", "remaining_time": "4:02:22"}
+{"current_steps": 207, "total_steps": 1565, "loss": 0.5007, "lr": 9.96891692575269e-06, "epoch": 0.6613418530351438, "percentage": 13.23, "elapsed_time": "0:36:54", "remaining_time": "4:02:10"}
+{"current_steps": 208, "total_steps": 1565, "loss": 0.5632, "lr": 9.967662524872631e-06, "epoch": 0.6645367412140575, "percentage": 13.29, "elapsed_time": "0:37:02", "remaining_time": "4:01:39"}
+{"current_steps": 209, "total_steps": 1565, "loss": 0.5512, "lr": 9.96638339272705e-06, "epoch": 0.6677316293929713, "percentage": 13.35, "elapsed_time": "0:37:09", "remaining_time": "4:01:07"}
+{"current_steps": 210, "total_steps": 1565, "loss": 0.4998, "lr": 9.96507953568404e-06, "epoch": 0.670926517571885, "percentage": 13.42, "elapsed_time": "0:37:18", "remaining_time": "4:00:44"}
+{"current_steps": 211, "total_steps": 1565, "loss": 0.5203, "lr": 9.963750960234792e-06, "epoch": 0.6741214057507987, "percentage": 13.48, "elapsed_time": "0:37:28", "remaining_time": "4:00:28"}
+{"current_steps": 212, "total_steps": 1565, "loss": 0.5391, "lr": 9.962397672993552e-06, "epoch": 0.6773162939297125, "percentage": 13.55, "elapsed_time": "0:37:37", "remaining_time": "4:00:06"}
+{"current_steps": 213, "total_steps": 1565, "loss": 0.5474, "lr": 9.961019680697593e-06, "epoch": 0.6805111821086262, "percentage": 13.61, "elapsed_time": "0:37:49", "remaining_time": "4:00:02"}
+{"current_steps": 214, "total_steps": 1565, "loss": 0.5607, "lr": 9.959616990207186e-06, "epoch": 0.6837060702875399, "percentage": 13.67, "elapsed_time": "0:37:59", "remaining_time": "3:59:50"}
+{"current_steps": 215, "total_steps": 1565, "loss": 0.4683, "lr": 9.958189608505554e-06, "epoch": 0.6869009584664537, "percentage": 13.74, "elapsed_time": "0:38:10", "remaining_time": "3:59:44"}
+{"current_steps": 216, "total_steps": 1565, "loss": 0.5193, "lr": 9.956737542698853e-06, "epoch": 0.6900958466453674, "percentage": 13.8, "elapsed_time": "0:38:19", "remaining_time": "3:59:19"}
+{"current_steps": 217, "total_steps": 1565, "loss": 0.5602, "lr": 9.955260800016115e-06, "epoch": 0.6932907348242812, "percentage": 13.87, "elapsed_time": "0:38:28", "remaining_time": "3:59:01"}
+{"current_steps": 218, "total_steps": 1565, "loss": 0.5511, "lr": 9.953759387809235e-06, "epoch": 0.6964856230031949, "percentage": 13.93, "elapsed_time": "0:38:38", "remaining_time": "3:58:45"}
+{"current_steps": 219, "total_steps": 1565, "loss": 0.548, "lr": 9.952233313552916e-06, "epoch": 0.6996805111821086, "percentage": 13.99, "elapsed_time": "0:38:49", "remaining_time": "3:58:35"}
+{"current_steps": 220, "total_steps": 1565, "loss": 0.5441, "lr": 9.950682584844653e-06, "epoch": 0.7028753993610224, "percentage": 14.06, "elapsed_time": "0:38:58", "remaining_time": "3:58:13"}
+{"current_steps": 221, "total_steps": 1565, "loss": 0.5144, "lr": 9.949107209404664e-06, "epoch": 0.7060702875399361, "percentage": 14.12, "elapsed_time": "0:39:09", "remaining_time": "3:58:09"}
+{"current_steps": 222, "total_steps": 1565, "loss": 0.5422, "lr": 9.947507195075886e-06, "epoch": 0.7092651757188498, "percentage": 14.19, "elapsed_time": "0:39:20", "remaining_time": "3:57:59"}
+{"current_steps": 223, "total_steps": 1565, "loss": 0.4851, "lr": 9.945882549823906e-06, "epoch": 0.7124600638977636, "percentage": 14.25, "elapsed_time": "0:39:27", "remaining_time": "3:57:28"}
+{"current_steps": 224, "total_steps": 1565, "loss": 0.5009, "lr": 9.944233281736945e-06, "epoch": 0.7156549520766773, "percentage": 14.31, "elapsed_time": "0:39:36", "remaining_time": "3:57:08"}
+{"current_steps": 225, "total_steps": 1565, "loss": 0.5056, "lr": 9.942559399025803e-06, "epoch": 0.7188498402555911, "percentage": 14.38, "elapsed_time": "0:39:44", "remaining_time": "3:56:41"}
+{"current_steps": 226, "total_steps": 1565, "loss": 0.5518, "lr": 9.940860910023823e-06, "epoch": 0.7220447284345048, "percentage": 14.44, "elapsed_time": "0:39:55", "remaining_time": "3:56:33"}
+{"current_steps": 227, "total_steps": 1565, "loss": 0.5458, "lr": 9.939137823186851e-06, "epoch": 0.7252396166134185, "percentage": 14.5, "elapsed_time": "0:40:06", "remaining_time": "3:56:27"}
+{"current_steps": 228, "total_steps": 1565, "loss": 0.5168, "lr": 9.937390147093189e-06, "epoch": 0.7284345047923323, "percentage": 14.57, "elapsed_time": "0:40:17", "remaining_time": "3:56:18"}
+{"current_steps": 229, "total_steps": 1565, "loss": 0.5215, "lr": 9.935617890443557e-06, "epoch": 0.731629392971246, "percentage": 14.63, "elapsed_time": "0:40:29", "remaining_time": "3:56:14"}
+{"current_steps": 230, "total_steps": 1565, "loss": 0.5068, "lr": 9.933821062061049e-06, "epoch": 0.7348242811501597, "percentage": 14.7, "elapsed_time": "0:40:38", "remaining_time": "3:55:56"}
+{"current_steps": 231, "total_steps": 1565, "loss": 0.5156, "lr": 9.931999670891089e-06, "epoch": 0.7380191693290735, "percentage": 14.76, "elapsed_time": "0:40:49", "remaining_time": "3:55:47"}
+{"current_steps": 232, "total_steps": 1565, "loss": 0.526, "lr": 9.930153726001382e-06, "epoch": 0.7412140575079872, "percentage": 14.82, "elapsed_time": "0:41:03", "remaining_time": "3:55:52"}
+{"current_steps": 233, "total_steps": 1565, "loss": 0.4998, "lr": 9.928283236581874e-06, "epoch": 0.744408945686901, "percentage": 14.89, "elapsed_time": "0:41:10", "remaining_time": "3:55:21"}
+{"current_steps": 234, "total_steps": 1565, "loss": 0.4989, "lr": 9.926388211944707e-06, "epoch": 0.7476038338658147, "percentage": 14.95, "elapsed_time": "0:41:18", "remaining_time": "3:54:59"}
+{"current_steps": 235, "total_steps": 1565, "loss": 0.5155, "lr": 9.924468661524169e-06, "epoch": 0.7507987220447284, "percentage": 15.02, "elapsed_time": "0:41:29", "remaining_time": "3:54:49"}
+{"current_steps": 236, "total_steps": 1565, "loss": 0.4856, "lr": 9.922524594876646e-06, "epoch": 0.7539936102236422, "percentage": 15.08, "elapsed_time": "0:41:41", "remaining_time": "3:54:44"}
+{"current_steps": 237, "total_steps": 1565, "loss": 0.527, "lr": 9.92055602168058e-06, "epoch": 0.7571884984025559, "percentage": 15.14, "elapsed_time": "0:41:52", "remaining_time": "3:54:41"}
+{"current_steps": 238, "total_steps": 1565, "loss": 0.5049, "lr": 9.918562951736419e-06, "epoch": 0.7603833865814696, "percentage": 15.21, "elapsed_time": "0:42:02", "remaining_time": "3:54:25"}
+{"current_steps": 239, "total_steps": 1565, "loss": 0.5165, "lr": 9.916545394966561e-06, "epoch": 0.7635782747603834, "percentage": 15.27, "elapsed_time": "0:42:14", "remaining_time": "3:54:19"}
+{"current_steps": 240, "total_steps": 1565, "loss": 0.4928, "lr": 9.914503361415316e-06, "epoch": 0.7667731629392971, "percentage": 15.34, "elapsed_time": "0:42:25", "remaining_time": "3:54:14"}
+{"current_steps": 241, "total_steps": 1565, "loss": 0.5016, "lr": 9.912436861248847e-06, "epoch": 0.7699680511182109, "percentage": 15.4, "elapsed_time": "0:42:36", "remaining_time": "3:54:06"}
+{"current_steps": 242, "total_steps": 1565, "loss": 0.4804, "lr": 9.910345904755126e-06, "epoch": 0.7731629392971247, "percentage": 15.46, "elapsed_time": "0:42:48", "remaining_time": "3:54:01"}
+{"current_steps": 243, "total_steps": 1565, "loss": 0.4915, "lr": 9.908230502343877e-06, "epoch": 0.7763578274760383, "percentage": 15.53, "elapsed_time": "0:43:00", "remaining_time": "3:53:56"}
+{"current_steps": 244, "total_steps": 1565, "loss": 0.594, "lr": 9.906090664546527e-06, "epoch": 0.7795527156549521, "percentage": 15.59, "elapsed_time": "0:43:12", "remaining_time": "3:53:53"}
+{"current_steps": 245, "total_steps": 1565, "loss": 0.5227, "lr": 9.903926402016153e-06, "epoch": 0.7827476038338658, "percentage": 15.65, "elapsed_time": "0:43:19", "remaining_time": "3:53:26"}
+{"current_steps": 246, "total_steps": 1565, "loss": 0.5194, "lr": 9.901737725527435e-06, "epoch": 0.7859424920127795, "percentage": 15.72, "elapsed_time": "0:43:32", "remaining_time": "3:53:25"}
+{"current_steps": 247, "total_steps": 1565, "loss": 0.563, "lr": 9.899524645976585e-06, "epoch": 0.7891373801916933, "percentage": 15.78, "elapsed_time": "0:43:44", "remaining_time": "3:53:23"}
+{"current_steps": 248, "total_steps": 1565, "loss": 0.5143, "lr": 9.897287174381321e-06, "epoch": 0.792332268370607, "percentage": 15.85, "elapsed_time": "0:43:53", "remaining_time": "3:53:02"}
+{"current_steps": 249, "total_steps": 1565, "loss": 0.5012, "lr": 9.895025321880776e-06, "epoch": 0.7955271565495208, "percentage": 15.91, "elapsed_time": "0:44:05", "remaining_time": "3:53:04"}
+{"current_steps": 250, "total_steps": 1565, "loss": 0.5126, "lr": 9.89273909973548e-06, "epoch": 0.7987220447284346, "percentage": 15.97, "elapsed_time": "0:44:15", "remaining_time": "3:52:49"}
+{"current_steps": 251, "total_steps": 1565, "loss": 0.4657, "lr": 9.890428519327275e-06, "epoch": 0.8019169329073482, "percentage": 16.04, "elapsed_time": "0:44:23", "remaining_time": "3:52:24"}
+{"current_steps": 252, "total_steps": 1565, "loss": 0.5049, "lr": 9.888093592159275e-06, "epoch": 0.805111821086262, "percentage": 16.1, "elapsed_time": "0:44:34", "remaining_time": "3:52:17"}
+{"current_steps": 253, "total_steps": 1565, "loss": 0.4968, "lr": 9.885734329855798e-06, "epoch": 0.8083067092651757, "percentage": 16.17, "elapsed_time": "0:44:46", "remaining_time": "3:52:09"}
+{"current_steps": 254, "total_steps": 1565, "loss": 0.4646, "lr": 9.88335074416232e-06, "epoch": 0.8115015974440895, "percentage": 16.23, "elapsed_time": "0:44:55", "remaining_time": "3:51:51"}
+{"current_steps": 255, "total_steps": 1565, "loss": 0.4875, "lr": 9.8809428469454e-06, "epoch": 0.8146964856230032, "percentage": 16.29, "elapsed_time": "0:45:06", "remaining_time": "3:51:45"}
+{"current_steps": 256, "total_steps": 1565, "loss": 0.5077, "lr": 9.878510650192644e-06, "epoch": 0.8178913738019169, "percentage": 16.36, "elapsed_time": "0:45:16", "remaining_time": "3:51:31"}
+{"current_steps": 257, "total_steps": 1565, "loss": 0.4919, "lr": 9.87605416601262e-06, "epoch": 0.8210862619808307, "percentage": 16.42, "elapsed_time": "0:45:27", "remaining_time": "3:51:23"}
+{"current_steps": 258, "total_steps": 1565, "loss": 0.4813, "lr": 9.873573406634817e-06, "epoch": 0.8242811501597445, "percentage": 16.49, "elapsed_time": "0:45:39", "remaining_time": "3:51:18"}
+{"current_steps": 259, "total_steps": 1565, "loss": 0.4978, "lr": 9.871068384409573e-06, "epoch": 0.8274760383386581, "percentage": 16.55, "elapsed_time": "0:45:50", "remaining_time": "3:51:11"}
+{"current_steps": 260, "total_steps": 1565, "loss": 0.5225, "lr": 9.86853911180802e-06, "epoch": 0.8306709265175719, "percentage": 16.61, "elapsed_time": "0:46:00", "remaining_time": "3:50:54"}
+{"current_steps": 261, "total_steps": 1565, "loss": 0.5104, "lr": 9.865985601422018e-06, "epoch": 0.8338658146964856, "percentage": 16.68, "elapsed_time": "0:46:10", "remaining_time": "3:50:43"}
+{"current_steps": 262, "total_steps": 1565, "loss": 0.5466, "lr": 9.863407865964095e-06, "epoch": 0.8370607028753994, "percentage": 16.74, "elapsed_time": "0:46:20", "remaining_time": "3:50:28"}
+{"current_steps": 263, "total_steps": 1565, "loss": 0.5316, "lr": 9.860805918267377e-06, "epoch": 0.8402555910543131, "percentage": 16.81, "elapsed_time": "0:46:26", "remaining_time": "3:49:54"}
+{"current_steps": 264, "total_steps": 1565, "loss": 0.5596, "lr": 9.85817977128554e-06, "epoch": 0.8434504792332268, "percentage": 16.87, "elapsed_time": "0:46:35", "remaining_time": "3:49:38"}
+{"current_steps": 265, "total_steps": 1565, "loss": 0.5076, "lr": 9.855529438092723e-06, "epoch": 0.8466453674121406, "percentage": 16.93, "elapsed_time": "0:46:45", "remaining_time": "3:49:22"}
+{"current_steps": 266, "total_steps": 1565, "loss": 0.4682, "lr": 9.852854931883484e-06, "epoch": 0.8498402555910544, "percentage": 17.0, "elapsed_time": "0:46:53", "remaining_time": "3:49:00"}
+{"current_steps": 267, "total_steps": 1565, "loss": 0.4942, "lr": 9.850156265972722e-06, "epoch": 0.853035143769968, "percentage": 17.06, "elapsed_time": "0:47:04", "remaining_time": "3:48:49"}
+{"current_steps": 268, "total_steps": 1565, "loss": 0.4869, "lr": 9.84743345379561e-06, "epoch": 0.8562300319488818, "percentage": 17.12, "elapsed_time": "0:47:13", "remaining_time": "3:48:32"}
+{"current_steps": 269, "total_steps": 1565, "loss": 0.5055, "lr": 9.844686508907538e-06, "epoch": 0.8594249201277955, "percentage": 17.19, "elapsed_time": "0:47:25", "remaining_time": "3:48:29"}
+{"current_steps": 270, "total_steps": 1565, "loss": 0.5482, "lr": 9.841915444984037e-06, "epoch": 0.8626198083067093, "percentage": 17.25, "elapsed_time": "0:47:36", "remaining_time": "3:48:21"}
+{"current_steps": 271, "total_steps": 1565, "loss": 0.5376, "lr": 9.839120275820713e-06, "epoch": 0.865814696485623, "percentage": 17.32, "elapsed_time": "0:47:48", "remaining_time": "3:48:18"}
+{"current_steps": 272, "total_steps": 1565, "loss": 0.5005, "lr": 9.83630101533318e-06, "epoch": 0.8690095846645367, "percentage": 17.38, "elapsed_time": "0:47:59", "remaining_time": "3:48:09"}
+{"current_steps": 273, "total_steps": 1565, "loss": 0.4929, "lr": 9.833457677556988e-06, "epoch": 0.8722044728434505, "percentage": 17.44, "elapsed_time": "0:48:10", "remaining_time": "3:47:59"}
+{"current_steps": 274, "total_steps": 1565, "loss": 0.538, "lr": 9.830590276647557e-06, "epoch": 0.8753993610223643, "percentage": 17.51, "elapsed_time": "0:48:21", "remaining_time": "3:47:53"}
+{"current_steps": 275, "total_steps": 1565, "loss": 0.5195, "lr": 9.8276988268801e-06, "epoch": 0.8785942492012779, "percentage": 17.57, "elapsed_time": "0:48:34", "remaining_time": "3:47:50"}
+{"current_steps": 276, "total_steps": 1565, "loss": 0.5322, "lr": 9.824783342649562e-06, "epoch": 0.8817891373801917, "percentage": 17.64, "elapsed_time": "0:48:43", "remaining_time": "3:47:31"}
+{"current_steps": 277, "total_steps": 1565, "loss": 0.5103, "lr": 9.821843838470536e-06, "epoch": 0.8849840255591054, "percentage": 17.7, "elapsed_time": "0:48:55", "remaining_time": "3:47:29"}
+{"current_steps": 278, "total_steps": 1565, "loss": 0.467, "lr": 9.8188803289772e-06, "epoch": 0.8881789137380192, "percentage": 17.76, "elapsed_time": "0:49:05", "remaining_time": "3:47:16"}
+{"current_steps": 279, "total_steps": 1565, "loss": 0.514, "lr": 9.815892828923244e-06, "epoch": 0.8913738019169329, "percentage": 17.83, "elapsed_time": "0:49:17", "remaining_time": "3:47:10"}
+{"current_steps": 280, "total_steps": 1565, "loss": 0.5439, "lr": 9.812881353181789e-06, "epoch": 0.8945686900958466, "percentage": 17.89, "elapsed_time": "0:49:29", "remaining_time": "3:47:06"}
+{"current_steps": 281, "total_steps": 1565, "loss": 0.5474, "lr": 9.809845916745323e-06, "epoch": 0.8977635782747604, "percentage": 17.96, "elapsed_time": "0:49:39", "remaining_time": "3:46:53"}
+{"current_steps": 282, "total_steps": 1565, "loss": 0.4777, "lr": 9.806786534725614e-06, "epoch": 0.9009584664536742, "percentage": 18.02, "elapsed_time": "0:49:51", "remaining_time": "3:46:52"}
+{"current_steps": 283, "total_steps": 1565, "loss": 0.4952, "lr": 9.803703222353647e-06, "epoch": 0.9041533546325878, "percentage": 18.08, "elapsed_time": "0:49:59", "remaining_time": "3:46:28"}
+{"current_steps": 284, "total_steps": 1565, "loss": 0.4909, "lr": 9.800595994979546e-06, "epoch": 0.9073482428115016, "percentage": 18.15, "elapsed_time": "0:50:08", "remaining_time": "3:46:12"}
+{"current_steps": 285, "total_steps": 1565, "loss": 0.5408, "lr": 9.797464868072489e-06, "epoch": 0.9105431309904153, "percentage": 18.21, "elapsed_time": "0:50:18", "remaining_time": "3:45:56"}
+{"current_steps": 286, "total_steps": 1565, "loss": 0.5117, "lr": 9.794309857220636e-06, "epoch": 0.9137380191693291, "percentage": 18.27, "elapsed_time": "0:50:30", "remaining_time": "3:45:52"}
+{"current_steps": 287, "total_steps": 1565, "loss": 0.5387, "lr": 9.791130978131056e-06, "epoch": 0.9169329073482428, "percentage": 18.34, "elapsed_time": "0:50:42", "remaining_time": "3:45:46"}
+{"current_steps": 288, "total_steps": 1565, "loss": 0.5062, "lr": 9.787928246629646e-06, "epoch": 0.9201277955271565, "percentage": 18.4, "elapsed_time": "0:50:49", "remaining_time": "3:45:21"}
+{"current_steps": 289, "total_steps": 1565, "loss": 0.4684, "lr": 9.784701678661045e-06, "epoch": 0.9233226837060703, "percentage": 18.47, "elapsed_time": "0:51:00", "remaining_time": "3:45:14"}
+{"current_steps": 290, "total_steps": 1565, "loss": 0.5475, "lr": 9.781451290288566e-06, "epoch": 0.9265175718849841, "percentage": 18.53, "elapsed_time": "0:51:11", "remaining_time": "3:45:05"}
+{"current_steps": 291, "total_steps": 1565, "loss": 0.4979, "lr": 9.77817709769411e-06, "epoch": 0.9297124600638977, "percentage": 18.59, "elapsed_time": "0:51:23", "remaining_time": "3:45:00"}
+{"current_steps": 292, "total_steps": 1565, "loss": 0.5121, "lr": 9.774879117178082e-06, "epoch": 0.9329073482428115, "percentage": 18.66, "elapsed_time": "0:51:32", "remaining_time": "3:44:43"}
+{"current_steps": 293, "total_steps": 1565, "loss": 0.5313, "lr": 9.77155736515932e-06, "epoch": 0.9361022364217252, "percentage": 18.72, "elapsed_time": "0:51:44", "remaining_time": "3:44:35"}
+{"current_steps": 294, "total_steps": 1565, "loss": 0.5063, "lr": 9.768211858175002e-06, "epoch": 0.939297124600639, "percentage": 18.79, "elapsed_time": "0:51:52", "remaining_time": "3:44:15"}
+{"current_steps": 295, "total_steps": 1565, "loss": 0.5038, "lr": 9.764842612880574e-06, "epoch": 0.9424920127795527, "percentage": 18.85, "elapsed_time": "0:52:01", "remaining_time": "3:43:56"}
+{"current_steps": 296, "total_steps": 1565, "loss": 0.5743, "lr": 9.761449646049657e-06, "epoch": 0.9456869009584664, "percentage": 18.91, "elapsed_time": "0:52:13", "remaining_time": "3:43:54"}
+{"current_steps": 297, "total_steps": 1565, "loss": 0.4978, "lr": 9.758032974573972e-06, "epoch": 0.9488817891373802, "percentage": 18.98, "elapsed_time": "0:52:22", "remaining_time": "3:43:35"}
+{"current_steps": 298, "total_steps": 1565, "loss": 0.5228, "lr": 9.754592615463251e-06, "epoch": 0.952076677316294, "percentage": 19.04, "elapsed_time": "0:52:30", "remaining_time": "3:43:16"}
+{"current_steps": 299, "total_steps": 1565, "loss": 0.5183, "lr": 9.751128585845155e-06, "epoch": 0.9552715654952076, "percentage": 19.11, "elapsed_time": "0:52:43", "remaining_time": "3:43:14"}
+{"current_steps": 300, "total_steps": 1565, "loss": 0.504, "lr": 9.747640902965185e-06, "epoch": 0.9584664536741214, "percentage": 19.17, "elapsed_time": "0:52:55", "remaining_time": "3:43:10"}
+{"current_steps": 301, "total_steps": 1565, "loss": 0.4878, "lr": 9.744129584186599e-06, "epoch": 0.9616613418530351, "percentage": 19.23, "elapsed_time": "0:53:02", "remaining_time": "3:42:44"}
+{"current_steps": 302, "total_steps": 1565, "loss": 0.501, "lr": 9.74059464699033e-06, "epoch": 0.9648562300319489, "percentage": 19.3, "elapsed_time": "0:53:12", "remaining_time": "3:42:30"}
+{"current_steps": 303, "total_steps": 1565, "loss": 0.4838, "lr": 9.737036108974885e-06, "epoch": 0.9680511182108626, "percentage": 19.36, "elapsed_time": "0:53:24", "remaining_time": "3:42:27"}
+{"current_steps": 304, "total_steps": 1565, "loss": 0.4671, "lr": 9.733453987856277e-06, "epoch": 0.9712460063897763, "percentage": 19.42, "elapsed_time": "0:53:36", "remaining_time": "3:42:22"}
+{"current_steps": 305, "total_steps": 1565, "loss": 0.493, "lr": 9.729848301467919e-06, "epoch": 0.9744408945686901, "percentage": 19.49, "elapsed_time": "0:53:45", "remaining_time": "3:42:06"}
+{"current_steps": 306, "total_steps": 1565, "loss": 0.4878, "lr": 9.726219067760546e-06, "epoch": 0.9776357827476039, "percentage": 19.55, "elapsed_time": "0:53:56", "remaining_time": "3:41:54"}
+{"current_steps": 307, "total_steps": 1565, "loss": 0.4988, "lr": 9.722566304802117e-06, "epoch": 0.9808306709265175, "percentage": 19.62, "elapsed_time": "0:54:01", "remaining_time": "3:41:24"}
+{"current_steps": 308, "total_steps": 1565, "loss": 0.4999, "lr": 9.718890030777739e-06, "epoch": 0.9840255591054313, "percentage": 19.68, "elapsed_time": "0:54:12", "remaining_time": "3:41:14"}
+{"current_steps": 309, "total_steps": 1565, "loss": 0.5116, "lr": 9.715190263989562e-06, "epoch": 0.987220447284345, "percentage": 19.74, "elapsed_time": "0:54:21", "remaining_time": "3:40:57"}
+{"current_steps": 310, "total_steps": 1565, "loss": 0.487, "lr": 9.711467022856691e-06, "epoch": 0.9904153354632588, "percentage": 19.81, "elapsed_time": "0:54:32", "remaining_time": "3:40:47"}
+{"current_steps": 311, "total_steps": 1565, "loss": 0.4741, "lr": 9.707720325915105e-06, "epoch": 0.9936102236421726, "percentage": 19.87, "elapsed_time": "0:54:42", "remaining_time": "3:40:34"}
+{"current_steps": 312, "total_steps": 1565, "loss": 0.5758, "lr": 9.703950191817549e-06, "epoch": 0.9968051118210862, "percentage": 19.94, "elapsed_time": "0:54:52", "remaining_time": "3:40:21"}
+{"current_steps": 313, "total_steps": 1565, "loss": 0.5728, "lr": 9.70015663933345e-06, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "0:55:03", "remaining_time": "3:40:13"}
+{"current_steps": 314, "total_steps": 1565, "loss": 0.4466, "lr": 9.69633968734883e-06, "epoch": 1.0031948881789137, "percentage": 20.06, "elapsed_time": "0:55:57", "remaining_time": "3:42:56"}
+{"current_steps": 315, "total_steps": 1565, "loss": 0.4587, "lr": 9.692499354866194e-06, "epoch": 1.0063897763578276, "percentage": 20.13, "elapsed_time": "0:56:09", "remaining_time": "3:42:49"}
+{"current_steps": 316, "total_steps": 1565, "loss": 0.3889, "lr": 9.688635661004449e-06, "epoch": 1.0095846645367412, "percentage": 20.19, "elapsed_time": "0:56:16", "remaining_time": "3:42:25"}
+{"current_steps": 317, "total_steps": 1565, "loss": 0.4001, "lr": 9.68474862499881e-06, "epoch": 1.012779552715655, "percentage": 20.26, "elapsed_time": "0:56:29", "remaining_time": "3:42:22"}
+{"current_steps": 318, "total_steps": 1565, "loss": 0.416, "lr": 9.680838266200691e-06, "epoch": 1.0159744408945688, "percentage": 20.32, "elapsed_time": "0:56:38", "remaining_time": "3:42:08"}
+{"current_steps": 319, "total_steps": 1565, "loss": 0.4103, "lr": 9.676904604077628e-06, "epoch": 1.0191693290734825, "percentage": 20.38, "elapsed_time": "0:56:48", "remaining_time": "3:41:52"}
+{"current_steps": 320, "total_steps": 1565, "loss": 0.4375, "lr": 9.672947658213163e-06, "epoch": 1.0223642172523961, "percentage": 20.45, "elapsed_time": "0:56:59", "remaining_time": "3:41:45"}
+{"current_steps": 321, "total_steps": 1565, "loss": 0.4412, "lr": 9.668967448306758e-06, "epoch": 1.0255591054313098, "percentage": 20.51, "elapsed_time": "0:57:11", "remaining_time": "3:41:38"}
+{"current_steps": 322, "total_steps": 1565, "loss": 0.4684, "lr": 9.664963994173695e-06, "epoch": 1.0287539936102237, "percentage": 20.58, "elapsed_time": "0:57:20", "remaining_time": "3:41:20"}
+{"current_steps": 323, "total_steps": 1565, "loss": 0.4199, "lr": 9.660937315744974e-06, "epoch": 1.0319488817891374, "percentage": 20.64, "elapsed_time": "0:57:28", "remaining_time": "3:41:00"}
+{"current_steps": 324, "total_steps": 1565, "loss": 0.4302, "lr": 9.656887433067217e-06, "epoch": 1.035143769968051, "percentage": 20.7, "elapsed_time": "0:57:40", "remaining_time": "3:40:53"}
+{"current_steps": 325, "total_steps": 1565, "loss": 0.3838, "lr": 9.65281436630257e-06, "epoch": 1.038338658146965, "percentage": 20.77, "elapsed_time": "0:57:47", "remaining_time": "3:40:31"}
+{"current_steps": 326, "total_steps": 1565, "loss": 0.4223, "lr": 9.648718135728592e-06, "epoch": 1.0415335463258786, "percentage": 20.83, "elapsed_time": "0:57:59", "remaining_time": "3:40:25"}
+{"current_steps": 327, "total_steps": 1565, "loss": 0.4868, "lr": 9.644598761738171e-06, "epoch": 1.0447284345047922, "percentage": 20.89, "elapsed_time": "0:58:10", "remaining_time": "3:40:16"}
+{"current_steps": 328, "total_steps": 1565, "loss": 0.3837, "lr": 9.640456264839408e-06, "epoch": 1.0479233226837061, "percentage": 20.96, "elapsed_time": "0:58:22", "remaining_time": "3:40:07"}
+{"current_steps": 329, "total_steps": 1565, "loss": 0.4189, "lr": 9.636290665655525e-06, "epoch": 1.0511182108626198, "percentage": 21.02, "elapsed_time": "0:58:34", "remaining_time": "3:40:02"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63d56d20a7cb80f90cabc198067dd826aeba9f437b0dd463e2ecc99aede0bae
+size 7224