Training in progress, epoch 0

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3883f3788c53d57461530cf3da07c2e95454f1696e6f35b795a61933a0943879
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2e7bf1557d482dd4d134215d600e051c68db8b8615fda699ec199f58ece8c7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0535f1ecd4c778f7a50b4f60968df01039fa563eb396123095ddba04db6ff14f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc55d41e1da2f26351efaf383bad2aa8c6967148f9f6c782c21afa56577a40d
+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 +1,354 @@
+{"current_steps": 1, "total_steps": 1026, "loss": 1.0797, "lr": 9.70873786407767e-08, "epoch": 0.0029211295034079843, "percentage": 0.1, "elapsed_time": "0:00:17", "remaining_time": "5:00:34"}
+{"current_steps": 2, "total_steps": 1026, "loss": 1.0936, "lr": 1.941747572815534e-07, "epoch": 0.005842259006815969, "percentage": 0.19, "elapsed_time": "0:00:35", "remaining_time": "5:02:42"}
+{"current_steps": 3, "total_steps": 1026, "loss": 1.0918, "lr": 2.9126213592233014e-07, "epoch": 0.008763388510223954, "percentage": 0.29, "elapsed_time": "0:00:47", "remaining_time": "4:30:05"}
+{"current_steps": 4, "total_steps": 1026, "loss": 1.1133, "lr": 3.883495145631068e-07, "epoch": 0.011684518013631937, "percentage": 0.39, "elapsed_time": "0:01:02", "remaining_time": "4:26:31"}
+{"current_steps": 5, "total_steps": 1026, "loss": 1.1201, "lr": 4.854368932038835e-07, "epoch": 0.014605647517039922, "percentage": 0.49, "elapsed_time": "0:01:16", "remaining_time": "4:20:15"}
+{"current_steps": 6, "total_steps": 1026, "loss": 1.059, "lr": 5.825242718446603e-07, "epoch": 0.017526777020447908, "percentage": 0.58, "elapsed_time": "0:01:32", "remaining_time": "4:21:57"}
+{"current_steps": 7, "total_steps": 1026, "loss": 1.0947, "lr": 6.79611650485437e-07, "epoch": 0.02044790652385589, "percentage": 0.68, "elapsed_time": "0:01:52", "remaining_time": "4:31:48"}
+{"current_steps": 8, "total_steps": 1026, "loss": 1.1033, "lr": 7.766990291262136e-07, "epoch": 0.023369036027263874, "percentage": 0.78, "elapsed_time": "0:02:10", "remaining_time": "4:36:32"}
+{"current_steps": 9, "total_steps": 1026, "loss": 1.1018, "lr": 8.737864077669904e-07, "epoch": 0.02629016553067186, "percentage": 0.88, "elapsed_time": "0:02:24", "remaining_time": "4:31:23"}
+{"current_steps": 10, "total_steps": 1026, "loss": 1.0596, "lr": 9.70873786407767e-07, "epoch": 0.029211295034079845, "percentage": 0.97, "elapsed_time": "0:02:41", "remaining_time": "4:33:52"}
+{"current_steps": 11, "total_steps": 1026, "loss": 1.0513, "lr": 1.0679611650485437e-06, "epoch": 0.03213242453748783, "percentage": 1.07, "elapsed_time": "0:02:57", "remaining_time": "4:33:14"}
+{"current_steps": 12, "total_steps": 1026, "loss": 1.0649, "lr": 1.1650485436893206e-06, "epoch": 0.035053554040895815, "percentage": 1.17, "elapsed_time": "0:03:12", "remaining_time": "4:30:32"}
+{"current_steps": 13, "total_steps": 1026, "loss": 1.0597, "lr": 1.2621359223300972e-06, "epoch": 0.0379746835443038, "percentage": 1.27, "elapsed_time": "0:03:29", "remaining_time": "4:31:32"}
+{"current_steps": 14, "total_steps": 1026, "loss": 1.0045, "lr": 1.359223300970874e-06, "epoch": 0.04089581304771178, "percentage": 1.36, "elapsed_time": "0:03:44", "remaining_time": "4:31:02"}
+{"current_steps": 15, "total_steps": 1026, "loss": 0.9864, "lr": 1.4563106796116506e-06, "epoch": 0.043816942551119765, "percentage": 1.46, "elapsed_time": "0:03:59", "remaining_time": "4:29:07"}
+{"current_steps": 16, "total_steps": 1026, "loss": 1.0039, "lr": 1.5533980582524272e-06, "epoch": 0.04673807205452775, "percentage": 1.56, "elapsed_time": "0:04:15", "remaining_time": "4:29:02"}
+{"current_steps": 17, "total_steps": 1026, "loss": 0.9687, "lr": 1.650485436893204e-06, "epoch": 0.04965920155793573, "percentage": 1.66, "elapsed_time": "0:04:32", "remaining_time": "4:29:29"}
+{"current_steps": 18, "total_steps": 1026, "loss": 0.9776, "lr": 1.7475728155339808e-06, "epoch": 0.05258033106134372, "percentage": 1.75, "elapsed_time": "0:04:46", "remaining_time": "4:27:35"}
+{"current_steps": 19, "total_steps": 1026, "loss": 0.9802, "lr": 1.8446601941747574e-06, "epoch": 0.055501460564751706, "percentage": 1.85, "elapsed_time": "0:05:01", "remaining_time": "4:25:57"}
+{"current_steps": 20, "total_steps": 1026, "loss": 0.9512, "lr": 1.941747572815534e-06, "epoch": 0.05842259006815969, "percentage": 1.95, "elapsed_time": "0:05:15", "remaining_time": "4:24:38"}
+{"current_steps": 21, "total_steps": 1026, "loss": 0.9299, "lr": 2.0388349514563107e-06, "epoch": 0.06134371957156767, "percentage": 2.05, "elapsed_time": "0:05:28", "remaining_time": "4:22:14"}
+{"current_steps": 22, "total_steps": 1026, "loss": 0.917, "lr": 2.1359223300970874e-06, "epoch": 0.06426484907497566, "percentage": 2.14, "elapsed_time": "0:05:46", "remaining_time": "4:23:11"}
+{"current_steps": 23, "total_steps": 1026, "loss": 0.92, "lr": 2.2330097087378645e-06, "epoch": 0.06718597857838364, "percentage": 2.24, "elapsed_time": "0:06:00", "remaining_time": "4:21:44"}
+{"current_steps": 24, "total_steps": 1026, "loss": 0.9156, "lr": 2.330097087378641e-06, "epoch": 0.07010710808179163, "percentage": 2.34, "elapsed_time": "0:06:16", "remaining_time": "4:22:03"}
+{"current_steps": 25, "total_steps": 1026, "loss": 0.9162, "lr": 2.427184466019418e-06, "epoch": 0.0730282375851996, "percentage": 2.44, "elapsed_time": "0:06:31", "remaining_time": "4:21:07"}
+{"current_steps": 26, "total_steps": 1026, "loss": 0.8907, "lr": 2.5242718446601945e-06, "epoch": 0.0759493670886076, "percentage": 2.53, "elapsed_time": "0:06:46", "remaining_time": "4:20:36"}
+{"current_steps": 27, "total_steps": 1026, "loss": 0.863, "lr": 2.621359223300971e-06, "epoch": 0.07887049659201557, "percentage": 2.63, "elapsed_time": "0:07:01", "remaining_time": "4:19:48"}
+{"current_steps": 28, "total_steps": 1026, "loss": 0.8383, "lr": 2.718446601941748e-06, "epoch": 0.08179162609542356, "percentage": 2.73, "elapsed_time": "0:07:17", "remaining_time": "4:19:50"}
+{"current_steps": 29, "total_steps": 1026, "loss": 0.8643, "lr": 2.8155339805825245e-06, "epoch": 0.08471275559883155, "percentage": 2.83, "elapsed_time": "0:07:32", "remaining_time": "4:19:13"}
+{"current_steps": 30, "total_steps": 1026, "loss": 0.84, "lr": 2.912621359223301e-06, "epoch": 0.08763388510223953, "percentage": 2.92, "elapsed_time": "0:07:44", "remaining_time": "4:17:04"}
+{"current_steps": 31, "total_steps": 1026, "loss": 0.8424, "lr": 3.0097087378640778e-06, "epoch": 0.09055501460564752, "percentage": 3.02, "elapsed_time": "0:08:00", "remaining_time": "4:17:12"}
+{"current_steps": 32, "total_steps": 1026, "loss": 0.8369, "lr": 3.1067961165048544e-06, "epoch": 0.0934761441090555, "percentage": 3.12, "elapsed_time": "0:08:15", "remaining_time": "4:16:41"}
+{"current_steps": 33, "total_steps": 1026, "loss": 0.8202, "lr": 3.2038834951456315e-06, "epoch": 0.09639727361246349, "percentage": 3.22, "elapsed_time": "0:08:32", "remaining_time": "4:17:08"}
+{"current_steps": 34, "total_steps": 1026, "loss": 0.799, "lr": 3.300970873786408e-06, "epoch": 0.09931840311587146, "percentage": 3.31, "elapsed_time": "0:08:44", "remaining_time": "4:15:10"}
+{"current_steps": 35, "total_steps": 1026, "loss": 0.8302, "lr": 3.398058252427185e-06, "epoch": 0.10223953261927946, "percentage": 3.41, "elapsed_time": "0:08:56", "remaining_time": "4:13:09"}
+{"current_steps": 36, "total_steps": 1026, "loss": 0.8051, "lr": 3.4951456310679615e-06, "epoch": 0.10516066212268745, "percentage": 3.51, "elapsed_time": "0:09:10", "remaining_time": "4:12:31"}
+{"current_steps": 37, "total_steps": 1026, "loss": 0.8067, "lr": 3.592233009708738e-06, "epoch": 0.10808179162609542, "percentage": 3.61, "elapsed_time": "0:09:24", "remaining_time": "4:11:20"}
+{"current_steps": 38, "total_steps": 1026, "loss": 0.7811, "lr": 3.689320388349515e-06, "epoch": 0.11100292112950341, "percentage": 3.7, "elapsed_time": "0:09:40", "remaining_time": "4:11:39"}
+{"current_steps": 39, "total_steps": 1026, "loss": 0.7788, "lr": 3.7864077669902915e-06, "epoch": 0.11392405063291139, "percentage": 3.8, "elapsed_time": "0:09:55", "remaining_time": "4:11:06"}
+{"current_steps": 40, "total_steps": 1026, "loss": 0.7935, "lr": 3.883495145631068e-06, "epoch": 0.11684518013631938, "percentage": 3.9, "elapsed_time": "0:10:09", "remaining_time": "4:10:13"}
+{"current_steps": 41, "total_steps": 1026, "loss": 0.7752, "lr": 3.980582524271845e-06, "epoch": 0.11976630963972736, "percentage": 4.0, "elapsed_time": "0:10:24", "remaining_time": "4:10:07"}
+{"current_steps": 42, "total_steps": 1026, "loss": 0.7544, "lr": 4.0776699029126215e-06, "epoch": 0.12268743914313535, "percentage": 4.09, "elapsed_time": "0:10:38", "remaining_time": "4:09:19"}
+{"current_steps": 43, "total_steps": 1026, "loss": 0.787, "lr": 4.1747572815533986e-06, "epoch": 0.12560856864654332, "percentage": 4.19, "elapsed_time": "0:10:52", "remaining_time": "4:08:36"}
+{"current_steps": 44, "total_steps": 1026, "loss": 0.7617, "lr": 4.271844660194175e-06, "epoch": 0.12852969814995133, "percentage": 4.29, "elapsed_time": "0:11:08", "remaining_time": "4:08:36"}
+{"current_steps": 45, "total_steps": 1026, "loss": 0.7662, "lr": 4.368932038834952e-06, "epoch": 0.1314508276533593, "percentage": 4.39, "elapsed_time": "0:11:21", "remaining_time": "4:07:47"}
+{"current_steps": 46, "total_steps": 1026, "loss": 0.7578, "lr": 4.466019417475729e-06, "epoch": 0.13437195715676728, "percentage": 4.48, "elapsed_time": "0:11:37", "remaining_time": "4:07:34"}
+{"current_steps": 47, "total_steps": 1026, "loss": 0.7465, "lr": 4.563106796116505e-06, "epoch": 0.13729308666017526, "percentage": 4.58, "elapsed_time": "0:11:53", "remaining_time": "4:07:52"}
+{"current_steps": 48, "total_steps": 1026, "loss": 0.7537, "lr": 4.660194174757282e-06, "epoch": 0.14021421616358326, "percentage": 4.68, "elapsed_time": "0:12:10", "remaining_time": "4:08:06"}
+{"current_steps": 49, "total_steps": 1026, "loss": 0.7386, "lr": 4.7572815533980585e-06, "epoch": 0.14313534566699124, "percentage": 4.78, "elapsed_time": "0:12:24", "remaining_time": "4:07:18"}
+{"current_steps": 50, "total_steps": 1026, "loss": 0.777, "lr": 4.854368932038836e-06, "epoch": 0.1460564751703992, "percentage": 4.87, "elapsed_time": "0:12:38", "remaining_time": "4:06:41"}
+{"current_steps": 51, "total_steps": 1026, "loss": 0.7391, "lr": 4.951456310679612e-06, "epoch": 0.14897760467380722, "percentage": 4.97, "elapsed_time": "0:12:52", "remaining_time": "4:06:03"}
+{"current_steps": 52, "total_steps": 1026, "loss": 0.7439, "lr": 5.048543689320389e-06, "epoch": 0.1518987341772152, "percentage": 5.07, "elapsed_time": "0:13:06", "remaining_time": "4:05:28"}
+{"current_steps": 53, "total_steps": 1026, "loss": 0.7641, "lr": 5.145631067961165e-06, "epoch": 0.15481986368062317, "percentage": 5.17, "elapsed_time": "0:13:23", "remaining_time": "4:05:44"}
+{"current_steps": 54, "total_steps": 1026, "loss": 0.734, "lr": 5.242718446601942e-06, "epoch": 0.15774099318403115, "percentage": 5.26, "elapsed_time": "0:13:36", "remaining_time": "4:04:54"}
+{"current_steps": 55, "total_steps": 1026, "loss": 0.7814, "lr": 5.3398058252427185e-06, "epoch": 0.16066212268743915, "percentage": 5.36, "elapsed_time": "0:13:49", "remaining_time": "4:04:09"}
+{"current_steps": 56, "total_steps": 1026, "loss": 0.7351, "lr": 5.436893203883496e-06, "epoch": 0.16358325219084713, "percentage": 5.46, "elapsed_time": "0:14:04", "remaining_time": "4:03:55"}
+{"current_steps": 57, "total_steps": 1026, "loss": 0.7213, "lr": 5.533980582524272e-06, "epoch": 0.1665043816942551, "percentage": 5.56, "elapsed_time": "0:14:15", "remaining_time": "4:02:30"}
+{"current_steps": 58, "total_steps": 1026, "loss": 0.7577, "lr": 5.631067961165049e-06, "epoch": 0.1694255111976631, "percentage": 5.65, "elapsed_time": "0:14:31", "remaining_time": "4:02:31"}
+{"current_steps": 59, "total_steps": 1026, "loss": 0.7431, "lr": 5.728155339805825e-06, "epoch": 0.17234664070107109, "percentage": 5.75, "elapsed_time": "0:14:46", "remaining_time": "4:02:13"}
+{"current_steps": 60, "total_steps": 1026, "loss": 0.7369, "lr": 5.825242718446602e-06, "epoch": 0.17526777020447906, "percentage": 5.85, "elapsed_time": "0:15:01", "remaining_time": "4:01:57"}
+{"current_steps": 61, "total_steps": 1026, "loss": 0.7126, "lr": 5.9223300970873785e-06, "epoch": 0.17818889970788704, "percentage": 5.95, "elapsed_time": "0:15:17", "remaining_time": "4:01:57"}
+{"current_steps": 62, "total_steps": 1026, "loss": 0.7367, "lr": 6.0194174757281556e-06, "epoch": 0.18111002921129504, "percentage": 6.04, "elapsed_time": "0:15:32", "remaining_time": "4:01:36"}
+{"current_steps": 63, "total_steps": 1026, "loss": 0.7228, "lr": 6.116504854368932e-06, "epoch": 0.18403115871470302, "percentage": 6.14, "elapsed_time": "0:15:48", "remaining_time": "4:01:33"}
+{"current_steps": 64, "total_steps": 1026, "loss": 0.7244, "lr": 6.213592233009709e-06, "epoch": 0.186952288218111, "percentage": 6.24, "elapsed_time": "0:15:59", "remaining_time": "4:00:27"}
+{"current_steps": 65, "total_steps": 1026, "loss": 0.7375, "lr": 6.310679611650487e-06, "epoch": 0.189873417721519, "percentage": 6.34, "elapsed_time": "0:16:14", "remaining_time": "4:00:08"}
+{"current_steps": 66, "total_steps": 1026, "loss": 0.7287, "lr": 6.407766990291263e-06, "epoch": 0.19279454722492698, "percentage": 6.43, "elapsed_time": "0:16:28", "remaining_time": "3:59:43"}
+{"current_steps": 67, "total_steps": 1026, "loss": 0.7123, "lr": 6.50485436893204e-06, "epoch": 0.19571567672833495, "percentage": 6.53, "elapsed_time": "0:16:43", "remaining_time": "3:59:25"}
+{"current_steps": 68, "total_steps": 1026, "loss": 0.7117, "lr": 6.601941747572816e-06, "epoch": 0.19863680623174293, "percentage": 6.63, "elapsed_time": "0:17:00", "remaining_time": "3:59:31"}
+{"current_steps": 69, "total_steps": 1026, "loss": 0.7141, "lr": 6.6990291262135935e-06, "epoch": 0.20155793573515093, "percentage": 6.73, "elapsed_time": "0:17:15", "remaining_time": "3:59:15"}
+{"current_steps": 70, "total_steps": 1026, "loss": 0.7183, "lr": 6.79611650485437e-06, "epoch": 0.2044790652385589, "percentage": 6.82, "elapsed_time": "0:17:29", "remaining_time": "3:58:46"}
+{"current_steps": 71, "total_steps": 1026, "loss": 0.7179, "lr": 6.893203883495147e-06, "epoch": 0.2074001947419669, "percentage": 6.92, "elapsed_time": "0:17:45", "remaining_time": "3:58:53"}
+{"current_steps": 72, "total_steps": 1026, "loss": 0.7147, "lr": 6.990291262135923e-06, "epoch": 0.2103213242453749, "percentage": 7.02, "elapsed_time": "0:17:59", "remaining_time": "3:58:29"}
+{"current_steps": 73, "total_steps": 1026, "loss": 0.7077, "lr": 7.0873786407767e-06, "epoch": 0.21324245374878287, "percentage": 7.12, "elapsed_time": "0:18:16", "remaining_time": "3:58:40"}
+{"current_steps": 74, "total_steps": 1026, "loss": 0.7027, "lr": 7.184466019417476e-06, "epoch": 0.21616358325219084, "percentage": 7.21, "elapsed_time": "0:18:27", "remaining_time": "3:57:32"}
+{"current_steps": 75, "total_steps": 1026, "loss": 0.6995, "lr": 7.2815533980582534e-06, "epoch": 0.21908471275559882, "percentage": 7.31, "elapsed_time": "0:18:41", "remaining_time": "3:56:54"}
+{"current_steps": 76, "total_steps": 1026, "loss": 0.7098, "lr": 7.37864077669903e-06, "epoch": 0.22200584225900682, "percentage": 7.41, "elapsed_time": "0:18:57", "remaining_time": "3:56:59"}
+{"current_steps": 77, "total_steps": 1026, "loss": 0.7111, "lr": 7.475728155339807e-06, "epoch": 0.2249269717624148, "percentage": 7.5, "elapsed_time": "0:19:12", "remaining_time": "3:56:46"}
+{"current_steps": 78, "total_steps": 1026, "loss": 0.6907, "lr": 7.572815533980583e-06, "epoch": 0.22784810126582278, "percentage": 7.6, "elapsed_time": "0:19:24", "remaining_time": "3:55:50"}
+{"current_steps": 79, "total_steps": 1026, "loss": 0.6987, "lr": 7.66990291262136e-06, "epoch": 0.23076923076923078, "percentage": 7.7, "elapsed_time": "0:19:38", "remaining_time": "3:55:27"}
+{"current_steps": 80, "total_steps": 1026, "loss": 0.706, "lr": 7.766990291262136e-06, "epoch": 0.23369036027263876, "percentage": 7.8, "elapsed_time": "0:19:52", "remaining_time": "3:54:58"}
+{"current_steps": 81, "total_steps": 1026, "loss": 0.6993, "lr": 7.864077669902913e-06, "epoch": 0.23661148977604674, "percentage": 7.89, "elapsed_time": "0:20:06", "remaining_time": "3:54:30"}
+{"current_steps": 82, "total_steps": 1026, "loss": 0.6961, "lr": 7.96116504854369e-06, "epoch": 0.2395326192794547, "percentage": 7.99, "elapsed_time": "0:20:18", "remaining_time": "3:53:43"}
+{"current_steps": 83, "total_steps": 1026, "loss": 0.7115, "lr": 8.058252427184466e-06, "epoch": 0.24245374878286272, "percentage": 8.09, "elapsed_time": "0:20:29", "remaining_time": "3:52:51"}
+{"current_steps": 84, "total_steps": 1026, "loss": 0.7057, "lr": 8.155339805825243e-06, "epoch": 0.2453748782862707, "percentage": 8.19, "elapsed_time": "0:20:46", "remaining_time": "3:52:57"}
+{"current_steps": 85, "total_steps": 1026, "loss": 0.6971, "lr": 8.25242718446602e-06, "epoch": 0.24829600778967867, "percentage": 8.28, "elapsed_time": "0:21:02", "remaining_time": "3:53:01"}
+{"current_steps": 86, "total_steps": 1026, "loss": 0.6644, "lr": 8.349514563106797e-06, "epoch": 0.25121713729308665, "percentage": 8.38, "elapsed_time": "0:21:19", "remaining_time": "3:53:05"}
+{"current_steps": 87, "total_steps": 1026, "loss": 0.6822, "lr": 8.446601941747573e-06, "epoch": 0.25413826679649465, "percentage": 8.48, "elapsed_time": "0:21:36", "remaining_time": "3:53:11"}
+{"current_steps": 88, "total_steps": 1026, "loss": 0.6767, "lr": 8.54368932038835e-06, "epoch": 0.25705939629990265, "percentage": 8.58, "elapsed_time": "0:21:48", "remaining_time": "3:52:28"}
+{"current_steps": 89, "total_steps": 1026, "loss": 0.7152, "lr": 8.640776699029127e-06, "epoch": 0.2599805258033106, "percentage": 8.67, "elapsed_time": "0:22:01", "remaining_time": "3:51:56"}
+{"current_steps": 90, "total_steps": 1026, "loss": 0.7159, "lr": 8.737864077669904e-06, "epoch": 0.2629016553067186, "percentage": 8.77, "elapsed_time": "0:22:18", "remaining_time": "3:52:00"}
+{"current_steps": 91, "total_steps": 1026, "loss": 0.7132, "lr": 8.834951456310681e-06, "epoch": 0.26582278481012656, "percentage": 8.87, "elapsed_time": "0:22:31", "remaining_time": "3:51:24"}
+{"current_steps": 92, "total_steps": 1026, "loss": 0.6809, "lr": 8.932038834951458e-06, "epoch": 0.26874391431353456, "percentage": 8.97, "elapsed_time": "0:22:45", "remaining_time": "3:51:02"}
+{"current_steps": 93, "total_steps": 1026, "loss": 0.6823, "lr": 9.029126213592233e-06, "epoch": 0.27166504381694256, "percentage": 9.06, "elapsed_time": "0:23:01", "remaining_time": "3:51:03"}
+{"current_steps": 94, "total_steps": 1026, "loss": 0.6898, "lr": 9.12621359223301e-06, "epoch": 0.2745861733203505, "percentage": 9.16, "elapsed_time": "0:23:15", "remaining_time": "3:50:35"}
+{"current_steps": 95, "total_steps": 1026, "loss": 0.6923, "lr": 9.223300970873788e-06, "epoch": 0.2775073028237585, "percentage": 9.26, "elapsed_time": "0:23:28", "remaining_time": "3:49:58"}
+{"current_steps": 96, "total_steps": 1026, "loss": 0.6734, "lr": 9.320388349514565e-06, "epoch": 0.2804284323271665, "percentage": 9.36, "elapsed_time": "0:23:40", "remaining_time": "3:49:18"}
+{"current_steps": 97, "total_steps": 1026, "loss": 0.6815, "lr": 9.41747572815534e-06, "epoch": 0.28334956183057447, "percentage": 9.45, "elapsed_time": "0:23:54", "remaining_time": "3:49:00"}
+{"current_steps": 98, "total_steps": 1026, "loss": 0.6885, "lr": 9.514563106796117e-06, "epoch": 0.2862706913339825, "percentage": 9.55, "elapsed_time": "0:24:09", "remaining_time": "3:48:44"}
+{"current_steps": 99, "total_steps": 1026, "loss": 0.69, "lr": 9.611650485436894e-06, "epoch": 0.2891918208373905, "percentage": 9.65, "elapsed_time": "0:24:23", "remaining_time": "3:48:26"}
+{"current_steps": 100, "total_steps": 1026, "loss": 0.6912, "lr": 9.708737864077671e-06, "epoch": 0.2921129503407984, "percentage": 9.75, "elapsed_time": "0:24:40", "remaining_time": "3:48:28"}
+{"current_steps": 101, "total_steps": 1026, "loss": 0.6985, "lr": 9.805825242718447e-06, "epoch": 0.29503407984420643, "percentage": 9.84, "elapsed_time": "0:24:57", "remaining_time": "3:48:31"}
+{"current_steps": 102, "total_steps": 1026, "loss": 0.6926, "lr": 9.902912621359224e-06, "epoch": 0.29795520934761444, "percentage": 9.94, "elapsed_time": "0:25:15", "remaining_time": "3:48:44"}
+{"current_steps": 103, "total_steps": 1026, "loss": 0.6906, "lr": 1e-05, "epoch": 0.3008763388510224, "percentage": 10.04, "elapsed_time": "0:25:30", "remaining_time": "3:48:32"}
+{"current_steps": 104, "total_steps": 1026, "loss": 0.675, "lr": 9.999971037507608e-06, "epoch": 0.3037974683544304, "percentage": 10.14, "elapsed_time": "0:25:43", "remaining_time": "3:48:00"}
+{"current_steps": 105, "total_steps": 1026, "loss": 0.6802, "lr": 9.99988415036596e-06, "epoch": 0.30671859785783834, "percentage": 10.23, "elapsed_time": "0:25:59", "remaining_time": "3:47:58"}
+{"current_steps": 106, "total_steps": 1026, "loss": 0.704, "lr": 9.99973933958164e-06, "epoch": 0.30963972736124634, "percentage": 10.33, "elapsed_time": "0:26:15", "remaining_time": "3:47:57"}
+{"current_steps": 107, "total_steps": 1026, "loss": 0.6872, "lr": 9.999536606832288e-06, "epoch": 0.31256085686465435, "percentage": 10.43, "elapsed_time": "0:26:31", "remaining_time": "3:47:52"}
+{"current_steps": 108, "total_steps": 1026, "loss": 0.6875, "lr": 9.999275954466555e-06, "epoch": 0.3154819863680623, "percentage": 10.53, "elapsed_time": "0:26:46", "remaining_time": "3:47:36"}
+{"current_steps": 109, "total_steps": 1026, "loss": 0.6976, "lr": 9.998957385504103e-06, "epoch": 0.3184031158714703, "percentage": 10.62, "elapsed_time": "0:26:58", "remaining_time": "3:46:58"}
+{"current_steps": 110, "total_steps": 1026, "loss": 0.6721, "lr": 9.99858090363555e-06, "epoch": 0.3213242453748783, "percentage": 10.72, "elapsed_time": "0:27:12", "remaining_time": "3:46:32"}
+{"current_steps": 111, "total_steps": 1026, "loss": 0.6994, "lr": 9.998146513222436e-06, "epoch": 0.32424537487828625, "percentage": 10.82, "elapsed_time": "0:27:28", "remaining_time": "3:46:32"}
+{"current_steps": 112, "total_steps": 1026, "loss": 0.6902, "lr": 9.997654219297176e-06, "epoch": 0.32716650438169426, "percentage": 10.92, "elapsed_time": "0:27:45", "remaining_time": "3:46:30"}
+{"current_steps": 113, "total_steps": 1026, "loss": 0.695, "lr": 9.997104027562991e-06, "epoch": 0.33008763388510226, "percentage": 11.01, "elapsed_time": "0:28:01", "remaining_time": "3:46:27"}
+{"current_steps": 114, "total_steps": 1026, "loss": 0.683, "lr": 9.996495944393853e-06, "epoch": 0.3330087633885102, "percentage": 11.11, "elapsed_time": "0:28:15", "remaining_time": "3:46:07"}
+{"current_steps": 115, "total_steps": 1026, "loss": 0.6738, "lr": 9.995829976834402e-06, "epoch": 0.3359298928919182, "percentage": 11.21, "elapsed_time": "0:28:29", "remaining_time": "3:45:44"}
+{"current_steps": 116, "total_steps": 1026, "loss": 0.6875, "lr": 9.995106132599869e-06, "epoch": 0.3388510223953262, "percentage": 11.31, "elapsed_time": "0:28:43", "remaining_time": "3:45:18"}
+{"current_steps": 117, "total_steps": 1026, "loss": 0.6874, "lr": 9.99432442007599e-06, "epoch": 0.34177215189873417, "percentage": 11.4, "elapsed_time": "0:28:57", "remaining_time": "3:44:58"}
+{"current_steps": 118, "total_steps": 1026, "loss": 0.6836, "lr": 9.993484848318899e-06, "epoch": 0.34469328140214217, "percentage": 11.5, "elapsed_time": "0:29:11", "remaining_time": "3:44:34"}
+{"current_steps": 119, "total_steps": 1026, "loss": 0.6935, "lr": 9.992587427055036e-06, "epoch": 0.3476144109055501, "percentage": 11.6, "elapsed_time": "0:29:25", "remaining_time": "3:44:19"}
+{"current_steps": 120, "total_steps": 1026, "loss": 0.6636, "lr": 9.99163216668102e-06, "epoch": 0.3505355404089581, "percentage": 11.7, "elapsed_time": "0:29:36", "remaining_time": "3:43:31"}
+{"current_steps": 121, "total_steps": 1026, "loss": 0.6833, "lr": 9.990619078263543e-06, "epoch": 0.35345666991236613, "percentage": 11.79, "elapsed_time": "0:29:49", "remaining_time": "3:43:02"}
+{"current_steps": 122, "total_steps": 1026, "loss": 0.6905, "lr": 9.989548173539229e-06, "epoch": 0.3563777994157741, "percentage": 11.89, "elapsed_time": "0:30:01", "remaining_time": "3:42:26"}
+{"current_steps": 123, "total_steps": 1026, "loss": 0.6911, "lr": 9.988419464914505e-06, "epoch": 0.3592989289191821, "percentage": 11.99, "elapsed_time": "0:30:16", "remaining_time": "3:42:18"}
+{"current_steps": 124, "total_steps": 1026, "loss": 0.6817, "lr": 9.98723296546546e-06, "epoch": 0.3622200584225901, "percentage": 12.09, "elapsed_time": "0:30:32", "remaining_time": "3:42:09"}
+{"current_steps": 125, "total_steps": 1026, "loss": 0.6873, "lr": 9.985988688937684e-06, "epoch": 0.36514118792599803, "percentage": 12.18, "elapsed_time": "0:30:46", "remaining_time": "3:41:47"}
+{"current_steps": 126, "total_steps": 1026, "loss": 0.693, "lr": 9.984686649746119e-06, "epoch": 0.36806231742940604, "percentage": 12.28, "elapsed_time": "0:31:03", "remaining_time": "3:41:51"}
+{"current_steps": 127, "total_steps": 1026, "loss": 0.6578, "lr": 9.983326862974882e-06, "epoch": 0.37098344693281404, "percentage": 12.38, "elapsed_time": "0:31:18", "remaining_time": "3:41:40"}
+{"current_steps": 128, "total_steps": 1026, "loss": 0.693, "lr": 9.981909344377101e-06, "epoch": 0.373904576436222, "percentage": 12.48, "elapsed_time": "0:31:34", "remaining_time": "3:41:30"}
+{"current_steps": 129, "total_steps": 1026, "loss": 0.6556, "lr": 9.980434110374725e-06, "epoch": 0.37682570593963, "percentage": 12.57, "elapsed_time": "0:31:49", "remaining_time": "3:41:18"}
+{"current_steps": 130, "total_steps": 1026, "loss": 0.6943, "lr": 9.978901178058333e-06, "epoch": 0.379746835443038, "percentage": 12.67, "elapsed_time": "0:32:04", "remaining_time": "3:41:06"}
+{"current_steps": 131, "total_steps": 1026, "loss": 0.6781, "lr": 9.977310565186945e-06, "epoch": 0.38266796494644595, "percentage": 12.77, "elapsed_time": "0:32:20", "remaining_time": "3:40:54"}
+{"current_steps": 132, "total_steps": 1026, "loss": 0.6564, "lr": 9.975662290187802e-06, "epoch": 0.38558909444985395, "percentage": 12.87, "elapsed_time": "0:32:34", "remaining_time": "3:40:35"}
+{"current_steps": 133, "total_steps": 1026, "loss": 0.675, "lr": 9.973956372156166e-06, "epoch": 0.3885102239532619, "percentage": 12.96, "elapsed_time": "0:32:45", "remaining_time": "3:39:57"}
+{"current_steps": 134, "total_steps": 1026, "loss": 0.6763, "lr": 9.972192830855095e-06, "epoch": 0.3914313534566699, "percentage": 13.06, "elapsed_time": "0:33:00", "remaining_time": "3:39:40"}
+{"current_steps": 135, "total_steps": 1026, "loss": 0.7015, "lr": 9.970371686715205e-06, "epoch": 0.3943524829600779, "percentage": 13.16, "elapsed_time": "0:33:15", "remaining_time": "3:39:30"}
+{"current_steps": 136, "total_steps": 1026, "loss": 0.6903, "lr": 9.96849296083445e-06, "epoch": 0.39727361246348586, "percentage": 13.26, "elapsed_time": "0:33:28", "remaining_time": "3:39:05"}
+{"current_steps": 137, "total_steps": 1026, "loss": 0.6631, "lr": 9.966556674977864e-06, "epoch": 0.40019474196689386, "percentage": 13.35, "elapsed_time": "0:33:43", "remaining_time": "3:38:48"}
+{"current_steps": 138, "total_steps": 1026, "loss": 0.6459, "lr": 9.964562851577307e-06, "epoch": 0.40311587147030187, "percentage": 13.45, "elapsed_time": "0:33:55", "remaining_time": "3:38:19"}
+{"current_steps": 139, "total_steps": 1026, "loss": 0.6729, "lr": 9.962511513731219e-06, "epoch": 0.4060370009737098, "percentage": 13.55, "elapsed_time": "0:34:10", "remaining_time": "3:38:03"}
+{"current_steps": 140, "total_steps": 1026, "loss": 0.6586, "lr": 9.960402685204347e-06, "epoch": 0.4089581304771178, "percentage": 13.65, "elapsed_time": "0:34:26", "remaining_time": "3:37:57"}
+{"current_steps": 141, "total_steps": 1026, "loss": 0.6785, "lr": 9.958236390427458e-06, "epoch": 0.4118792599805258, "percentage": 13.74, "elapsed_time": "0:34:40", "remaining_time": "3:37:40"}
+{"current_steps": 142, "total_steps": 1026, "loss": 0.6489, "lr": 9.956012654497073e-06, "epoch": 0.4148003894839338, "percentage": 13.84, "elapsed_time": "0:34:54", "remaining_time": "3:37:16"}
+{"current_steps": 143, "total_steps": 1026, "loss": 0.6894, "lr": 9.953731503175166e-06, "epoch": 0.4177215189873418, "percentage": 13.94, "elapsed_time": "0:35:13", "remaining_time": "3:37:32"}
+{"current_steps": 144, "total_steps": 1026, "loss": 0.6533, "lr": 9.951392962888868e-06, "epoch": 0.4206426484907498, "percentage": 14.04, "elapsed_time": "0:35:25", "remaining_time": "3:36:59"}
+{"current_steps": 145, "total_steps": 1026, "loss": 0.6504, "lr": 9.948997060730161e-06, "epoch": 0.42356377799415773, "percentage": 14.13, "elapsed_time": "0:35:40", "remaining_time": "3:36:48"}
+{"current_steps": 146, "total_steps": 1026, "loss": 0.6508, "lr": 9.946543824455563e-06, "epoch": 0.42648490749756574, "percentage": 14.23, "elapsed_time": "0:35:54", "remaining_time": "3:36:25"}
+{"current_steps": 147, "total_steps": 1026, "loss": 0.6701, "lr": 9.94403328248581e-06, "epoch": 0.4294060370009737, "percentage": 14.33, "elapsed_time": "0:36:07", "remaining_time": "3:36:00"}
+{"current_steps": 148, "total_steps": 1026, "loss": 0.6746, "lr": 9.941465463905522e-06, "epoch": 0.4323271665043817, "percentage": 14.42, "elapsed_time": "0:36:22", "remaining_time": "3:35:45"}
+{"current_steps": 149, "total_steps": 1026, "loss": 0.6733, "lr": 9.938840398462872e-06, "epoch": 0.4352482960077897, "percentage": 14.52, "elapsed_time": "0:36:36", "remaining_time": "3:35:25"}
+{"current_steps": 150, "total_steps": 1026, "loss": 0.6703, "lr": 9.936158116569231e-06, "epoch": 0.43816942551119764, "percentage": 14.62, "elapsed_time": "0:36:47", "remaining_time": "3:34:51"}
+{"current_steps": 151, "total_steps": 1026, "loss": 0.6696, "lr": 9.933418649298831e-06, "epoch": 0.44109055501460565, "percentage": 14.72, "elapsed_time": "0:37:02", "remaining_time": "3:34:35"}
+{"current_steps": 152, "total_steps": 1026, "loss": 0.6534, "lr": 9.930622028388388e-06, "epoch": 0.44401168451801365, "percentage": 14.81, "elapsed_time": "0:37:17", "remaining_time": "3:34:27"}
+{"current_steps": 153, "total_steps": 1026, "loss": 0.6324, "lr": 9.92776828623675e-06, "epoch": 0.4469328140214216, "percentage": 14.91, "elapsed_time": "0:37:32", "remaining_time": "3:34:13"}
+{"current_steps": 154, "total_steps": 1026, "loss": 0.6572, "lr": 9.924857455904511e-06, "epoch": 0.4498539435248296, "percentage": 15.01, "elapsed_time": "0:37:48", "remaining_time": "3:34:06"}
+{"current_steps": 155, "total_steps": 1026, "loss": 0.6652, "lr": 9.921889571113629e-06, "epoch": 0.4527750730282376, "percentage": 15.11, "elapsed_time": "0:38:07", "remaining_time": "3:34:12"}
+{"current_steps": 156, "total_steps": 1026, "loss": 0.671, "lr": 9.918864666247042e-06, "epoch": 0.45569620253164556, "percentage": 15.2, "elapsed_time": "0:38:20", "remaining_time": "3:33:48"}
+{"current_steps": 157, "total_steps": 1026, "loss": 0.6557, "lr": 9.915782776348263e-06, "epoch": 0.45861733203505356, "percentage": 15.3, "elapsed_time": "0:38:35", "remaining_time": "3:33:38"}
+{"current_steps": 158, "total_steps": 1026, "loss": 0.6759, "lr": 9.912643937120978e-06, "epoch": 0.46153846153846156, "percentage": 15.4, "elapsed_time": "0:38:51", "remaining_time": "3:33:27"}
+{"current_steps": 159, "total_steps": 1026, "loss": 0.6417, "lr": 9.909448184928629e-06, "epoch": 0.4644595910418695, "percentage": 15.5, "elapsed_time": "0:39:08", "remaining_time": "3:33:26"}
+{"current_steps": 160, "total_steps": 1026, "loss": 0.6662, "lr": 9.906195556793996e-06, "epoch": 0.4673807205452775, "percentage": 15.59, "elapsed_time": "0:39:20", "remaining_time": "3:32:58"}
+{"current_steps": 161, "total_steps": 1026, "loss": 0.6774, "lr": 9.902886090398764e-06, "epoch": 0.47030185004868547, "percentage": 15.69, "elapsed_time": "0:39:32", "remaining_time": "3:32:28"}
+{"current_steps": 162, "total_steps": 1026, "loss": 0.6618, "lr": 9.899519824083095e-06, "epoch": 0.47322297955209347, "percentage": 15.79, "elapsed_time": "0:39:45", "remaining_time": "3:32:04"}
+{"current_steps": 163, "total_steps": 1026, "loss": 0.6737, "lr": 9.896096796845172e-06, "epoch": 0.4761441090555015, "percentage": 15.89, "elapsed_time": "0:40:02", "remaining_time": "3:32:01"}
+{"current_steps": 164, "total_steps": 1026, "loss": 0.6587, "lr": 9.892617048340754e-06, "epoch": 0.4790652385589094, "percentage": 15.98, "elapsed_time": "0:40:18", "remaining_time": "3:31:50"}
+{"current_steps": 165, "total_steps": 1026, "loss": 0.6825, "lr": 9.889080618882719e-06, "epoch": 0.4819863680623174, "percentage": 16.08, "elapsed_time": "0:40:33", "remaining_time": "3:31:39"}
+{"current_steps": 166, "total_steps": 1026, "loss": 0.6702, "lr": 9.88548754944059e-06, "epoch": 0.48490749756572543, "percentage": 16.18, "elapsed_time": "0:40:46", "remaining_time": "3:31:14"}
+{"current_steps": 167, "total_steps": 1026, "loss": 0.6735, "lr": 9.881837881640064e-06, "epoch": 0.4878286270691334, "percentage": 16.28, "elapsed_time": "0:41:02", "remaining_time": "3:31:05"}
+{"current_steps": 168, "total_steps": 1026, "loss": 0.6547, "lr": 9.878131657762535e-06, "epoch": 0.4907497565725414, "percentage": 16.37, "elapsed_time": "0:41:18", "remaining_time": "3:30:56"}
+{"current_steps": 169, "total_steps": 1026, "loss": 0.6812, "lr": 9.874368920744594e-06, "epoch": 0.4936708860759494, "percentage": 16.47, "elapsed_time": "0:41:30", "remaining_time": "3:30:27"}
+{"current_steps": 170, "total_steps": 1026, "loss": 0.6512, "lr": 9.870549714177538e-06, "epoch": 0.49659201557935734, "percentage": 16.57, "elapsed_time": "0:41:43", "remaining_time": "3:30:04"}
+{"current_steps": 171, "total_steps": 1026, "loss": 0.6437, "lr": 9.866674082306861e-06, "epoch": 0.49951314508276534, "percentage": 16.67, "elapsed_time": "0:41:56", "remaining_time": "3:29:42"}
+{"current_steps": 172, "total_steps": 1026, "loss": 0.6563, "lr": 9.86274207003175e-06, "epoch": 0.5024342745861733, "percentage": 16.76, "elapsed_time": "0:42:12", "remaining_time": "3:29:32"}
+{"current_steps": 173, "total_steps": 1026, "loss": 0.683, "lr": 9.858753722904552e-06, "epoch": 0.5053554040895814, "percentage": 16.86, "elapsed_time": "0:42:26", "remaining_time": "3:29:15"}
+{"current_steps": 174, "total_steps": 1026, "loss": 0.672, "lr": 9.854709087130261e-06, "epoch": 0.5082765335929893, "percentage": 16.96, "elapsed_time": "0:42:40", "remaining_time": "3:28:57"}
+{"current_steps": 175, "total_steps": 1026, "loss": 0.6388, "lr": 9.850608209565967e-06, "epoch": 0.5111976630963972, "percentage": 17.06, "elapsed_time": "0:42:54", "remaining_time": "3:28:39"}
+{"current_steps": 176, "total_steps": 1026, "loss": 0.6592, "lr": 9.84645113772032e-06, "epoch": 0.5141187925998053, "percentage": 17.15, "elapsed_time": "0:43:11", "remaining_time": "3:28:35"}
+{"current_steps": 177, "total_steps": 1026, "loss": 0.6543, "lr": 9.842237919752994e-06, "epoch": 0.5170399221032133, "percentage": 17.25, "elapsed_time": "0:43:26", "remaining_time": "3:28:21"}
+{"current_steps": 178, "total_steps": 1026, "loss": 0.6566, "lr": 9.8379686044741e-06, "epoch": 0.5199610516066212, "percentage": 17.35, "elapsed_time": "0:43:44", "remaining_time": "3:28:22"}
+{"current_steps": 179, "total_steps": 1026, "loss": 0.6647, "lr": 9.833643241343642e-06, "epoch": 0.5228821811100293, "percentage": 17.45, "elapsed_time": "0:44:02", "remaining_time": "3:28:24"}
+{"current_steps": 180, "total_steps": 1026, "loss": 0.6391, "lr": 9.829261880470941e-06, "epoch": 0.5258033106134372, "percentage": 17.54, "elapsed_time": "0:44:15", "remaining_time": "3:27:58"}
+{"current_steps": 181, "total_steps": 1026, "loss": 0.6398, "lr": 9.82482457261405e-06, "epoch": 0.5287244401168452, "percentage": 17.64, "elapsed_time": "0:44:31", "remaining_time": "3:27:50"}
+{"current_steps": 182, "total_steps": 1026, "loss": 0.661, "lr": 9.820331369179166e-06, "epoch": 0.5316455696202531, "percentage": 17.74, "elapsed_time": "0:44:44", "remaining_time": "3:27:28"}
+{"current_steps": 183, "total_steps": 1026, "loss": 0.6547, "lr": 9.815782322220036e-06, "epoch": 0.5345666991236612, "percentage": 17.84, "elapsed_time": "0:44:59", "remaining_time": "3:27:15"}
+{"current_steps": 184, "total_steps": 1026, "loss": 0.6665, "lr": 9.811177484437357e-06, "epoch": 0.5374878286270691, "percentage": 17.93, "elapsed_time": "0:45:12", "remaining_time": "3:26:50"}
+{"current_steps": 185, "total_steps": 1026, "loss": 0.6652, "lr": 9.806516909178161e-06, "epoch": 0.5404089581304771, "percentage": 18.03, "elapsed_time": "0:45:25", "remaining_time": "3:26:32"}
+{"current_steps": 186, "total_steps": 1026, "loss": 0.6346, "lr": 9.801800650435194e-06, "epoch": 0.5433300876338851, "percentage": 18.13, "elapsed_time": "0:45:43", "remaining_time": "3:26:28"}
+{"current_steps": 187, "total_steps": 1026, "loss": 0.6689, "lr": 9.797028762846305e-06, "epoch": 0.5462512171372931, "percentage": 18.23, "elapsed_time": "0:45:54", "remaining_time": "3:25:56"}
+{"current_steps": 188, "total_steps": 1026, "loss": 0.6623, "lr": 9.792201301693793e-06, "epoch": 0.549172346640701, "percentage": 18.32, "elapsed_time": "0:46:08", "remaining_time": "3:25:38"}
+{"current_steps": 189, "total_steps": 1026, "loss": 0.6421, "lr": 9.787318322903784e-06, "epoch": 0.5520934761441091, "percentage": 18.42, "elapsed_time": "0:46:19", "remaining_time": "3:25:09"}
+{"current_steps": 190, "total_steps": 1026, "loss": 0.6829, "lr": 9.78237988304557e-06, "epoch": 0.555014605647517, "percentage": 18.52, "elapsed_time": "0:46:31", "remaining_time": "3:24:41"}
+{"current_steps": 191, "total_steps": 1026, "loss": 0.6639, "lr": 9.77738603933096e-06, "epoch": 0.557935735150925, "percentage": 18.62, "elapsed_time": "0:46:47", "remaining_time": "3:24:35"}
+{"current_steps": 192, "total_steps": 1026, "loss": 0.6488, "lr": 9.772336849613624e-06, "epoch": 0.560856864654333, "percentage": 18.71, "elapsed_time": "0:47:03", "remaining_time": "3:24:23"}
+{"current_steps": 193, "total_steps": 1026, "loss": 0.6195, "lr": 9.767232372388406e-06, "epoch": 0.563777994157741, "percentage": 18.81, "elapsed_time": "0:47:18", "remaining_time": "3:24:10"}
+{"current_steps": 194, "total_steps": 1026, "loss": 0.6602, "lr": 9.762072666790658e-06, "epoch": 0.5666991236611489, "percentage": 18.91, "elapsed_time": "0:47:34", "remaining_time": "3:24:00"}
+{"current_steps": 195, "total_steps": 1026, "loss": 0.6541, "lr": 9.756857792595555e-06, "epoch": 0.569620253164557, "percentage": 19.01, "elapsed_time": "0:47:47", "remaining_time": "3:23:40"}
+{"current_steps": 196, "total_steps": 1026, "loss": 0.6569, "lr": 9.751587810217398e-06, "epoch": 0.572541382667965, "percentage": 19.1, "elapsed_time": "0:48:02", "remaining_time": "3:23:27"}
+{"current_steps": 197, "total_steps": 1026, "loss": 0.6572, "lr": 9.746262780708919e-06, "epoch": 0.5754625121713729, "percentage": 19.2, "elapsed_time": "0:48:19", "remaining_time": "3:23:21"}
+{"current_steps": 198, "total_steps": 1026, "loss": 0.6594, "lr": 9.740882765760567e-06, "epoch": 0.578383641674781, "percentage": 19.3, "elapsed_time": "0:48:36", "remaining_time": "3:23:14"}
+{"current_steps": 199, "total_steps": 1026, "loss": 0.6571, "lr": 9.735447827699798e-06, "epoch": 0.5813047711781889, "percentage": 19.4, "elapsed_time": "0:48:52", "remaining_time": "3:23:06"}
+{"current_steps": 200, "total_steps": 1026, "loss": 0.6494, "lr": 9.729958029490353e-06, "epoch": 0.5842259006815969, "percentage": 19.49, "elapsed_time": "0:49:07", "remaining_time": "3:22:54"}
+{"current_steps": 201, "total_steps": 1026, "loss": 0.6385, "lr": 9.72441343473153e-06, "epoch": 0.5871470301850049, "percentage": 19.59, "elapsed_time": "0:49:23", "remaining_time": "3:22:42"}
+{"current_steps": 202, "total_steps": 1026, "loss": 0.6584, "lr": 9.718814107657441e-06, "epoch": 0.5900681596884129, "percentage": 19.69, "elapsed_time": "0:49:35", "remaining_time": "3:22:19"}
+{"current_steps": 203, "total_steps": 1026, "loss": 0.6554, "lr": 9.713160113136272e-06, "epoch": 0.5929892891918208, "percentage": 19.79, "elapsed_time": "0:49:51", "remaining_time": "3:22:06"}
+{"current_steps": 204, "total_steps": 1026, "loss": 0.6584, "lr": 9.707451516669533e-06, "epoch": 0.5959104186952289, "percentage": 19.88, "elapsed_time": "0:50:05", "remaining_time": "3:21:50"}
+{"current_steps": 205, "total_steps": 1026, "loss": 0.6471, "lr": 9.701688384391296e-06, "epoch": 0.5988315481986368, "percentage": 19.98, "elapsed_time": "0:50:16", "remaining_time": "3:21:19"}
+{"current_steps": 206, "total_steps": 1026, "loss": 0.6351, "lr": 9.695870783067434e-06, "epoch": 0.6017526777020448, "percentage": 20.08, "elapsed_time": "0:50:33", "remaining_time": "3:21:15"}
+{"current_steps": 207, "total_steps": 1026, "loss": 0.6466, "lr": 9.689998780094839e-06, "epoch": 0.6046738072054528, "percentage": 20.18, "elapsed_time": "0:50:46", "remaining_time": "3:20:52"}
+{"current_steps": 208, "total_steps": 1026, "loss": 0.6342, "lr": 9.684072443500645e-06, "epoch": 0.6075949367088608, "percentage": 20.27, "elapsed_time": "0:50:58", "remaining_time": "3:20:29"}
+{"current_steps": 209, "total_steps": 1026, "loss": 0.6532, "lr": 9.678091841941446e-06, "epoch": 0.6105160662122687, "percentage": 20.37, "elapsed_time": "0:51:13", "remaining_time": "3:20:13"}
+{"current_steps": 210, "total_steps": 1026, "loss": 0.6378, "lr": 9.672057044702492e-06, "epoch": 0.6134371957156767, "percentage": 20.47, "elapsed_time": "0:51:29", "remaining_time": "3:20:06"}
+{"current_steps": 211, "total_steps": 1026, "loss": 0.6603, "lr": 9.665968121696892e-06, "epoch": 0.6163583252190847, "percentage": 20.57, "elapsed_time": "0:51:40", "remaining_time": "3:19:36"}
+{"current_steps": 212, "total_steps": 1026, "loss": 0.6459, "lr": 9.659825143464798e-06, "epoch": 0.6192794547224927, "percentage": 20.66, "elapsed_time": "0:51:58", "remaining_time": "3:19:33"}
+{"current_steps": 213, "total_steps": 1026, "loss": 0.6508, "lr": 9.653628181172596e-06, "epoch": 0.6222005842259006, "percentage": 20.76, "elapsed_time": "0:52:15", "remaining_time": "3:19:28"}
+{"current_steps": 214, "total_steps": 1026, "loss": 0.63, "lr": 9.647377306612075e-06, "epoch": 0.6251217137293087, "percentage": 20.86, "elapsed_time": "0:52:24", "remaining_time": "3:18:50"}
+{"current_steps": 215, "total_steps": 1026, "loss": 0.6633, "lr": 9.641072592199599e-06, "epoch": 0.6280428432327166, "percentage": 20.96, "elapsed_time": "0:52:40", "remaining_time": "3:18:41"}
+{"current_steps": 216, "total_steps": 1026, "loss": 0.6704, "lr": 9.634714110975263e-06, "epoch": 0.6309639727361246, "percentage": 21.05, "elapsed_time": "0:52:58", "remaining_time": "3:18:38"}
+{"current_steps": 217, "total_steps": 1026, "loss": 0.654, "lr": 9.628301936602053e-06, "epoch": 0.6338851022395326, "percentage": 21.15, "elapsed_time": "0:53:15", "remaining_time": "3:18:33"}
+{"current_steps": 218, "total_steps": 1026, "loss": 0.6597, "lr": 9.62183614336499e-06, "epoch": 0.6368062317429406, "percentage": 21.25, "elapsed_time": "0:53:28", "remaining_time": "3:18:10"}
+{"current_steps": 219, "total_steps": 1026, "loss": 0.6658, "lr": 9.61531680617027e-06, "epoch": 0.6397273612463485, "percentage": 21.35, "elapsed_time": "0:53:42", "remaining_time": "3:17:55"}
+{"current_steps": 220, "total_steps": 1026, "loss": 0.6644, "lr": 9.608744000544392e-06, "epoch": 0.6426484907497566, "percentage": 21.44, "elapsed_time": "0:53:57", "remaining_time": "3:17:41"}
+{"current_steps": 221, "total_steps": 1026, "loss": 0.6294, "lr": 9.602117802633293e-06, "epoch": 0.6455696202531646, "percentage": 21.54, "elapsed_time": "0:54:09", "remaining_time": "3:17:14"}
+{"current_steps": 222, "total_steps": 1026, "loss": 0.6473, "lr": 9.595438289201453e-06, "epoch": 0.6484907497565725, "percentage": 21.64, "elapsed_time": "0:54:20", "remaining_time": "3:16:48"}
+{"current_steps": 223, "total_steps": 1026, "loss": 0.6563, "lr": 9.588705537631014e-06, "epoch": 0.6514118792599806, "percentage": 21.73, "elapsed_time": "0:54:34", "remaining_time": "3:16:32"}
+{"current_steps": 224, "total_steps": 1026, "loss": 0.6527, "lr": 9.581919625920886e-06, "epoch": 0.6543330087633885, "percentage": 21.83, "elapsed_time": "0:54:49", "remaining_time": "3:16:17"}
+{"current_steps": 225, "total_steps": 1026, "loss": 0.6435, "lr": 9.575080632685832e-06, "epoch": 0.6572541382667965, "percentage": 21.93, "elapsed_time": "0:55:03", "remaining_time": "3:16:01"}
+{"current_steps": 226, "total_steps": 1026, "loss": 0.6258, "lr": 9.568188637155569e-06, "epoch": 0.6601752677702045, "percentage": 22.03, "elapsed_time": "0:55:21", "remaining_time": "3:15:56"}
+{"current_steps": 227, "total_steps": 1026, "loss": 0.628, "lr": 9.561243719173844e-06, "epoch": 0.6630963972736125, "percentage": 22.12, "elapsed_time": "0:55:38", "remaining_time": "3:15:49"}
+{"current_steps": 228, "total_steps": 1026, "loss": 0.6631, "lr": 9.554245959197511e-06, "epoch": 0.6660175267770204, "percentage": 22.22, "elapsed_time": "0:55:51", "remaining_time": "3:15:29"}
+{"current_steps": 229, "total_steps": 1026, "loss": 0.6453, "lr": 9.5471954382956e-06, "epoch": 0.6689386562804285, "percentage": 22.32, "elapsed_time": "0:56:04", "remaining_time": "3:15:11"}
+{"current_steps": 230, "total_steps": 1026, "loss": 0.648, "lr": 9.54009223814837e-06, "epoch": 0.6718597857838364, "percentage": 22.42, "elapsed_time": "0:56:21", "remaining_time": "3:15:03"}
+{"current_steps": 231, "total_steps": 1026, "loss": 0.6679, "lr": 9.532936441046376e-06, "epoch": 0.6747809152872444, "percentage": 22.51, "elapsed_time": "0:56:39", "remaining_time": "3:14:59"}
+{"current_steps": 232, "total_steps": 1026, "loss": 0.6707, "lr": 9.525728129889505e-06, "epoch": 0.6777020447906524, "percentage": 22.61, "elapsed_time": "0:56:55", "remaining_time": "3:14:50"}
+{"current_steps": 233, "total_steps": 1026, "loss": 0.6533, "lr": 9.51846738818602e-06, "epoch": 0.6806231742940604, "percentage": 22.71, "elapsed_time": "0:57:11", "remaining_time": "3:14:38"}
+{"current_steps": 234, "total_steps": 1026, "loss": 0.6392, "lr": 9.511154300051591e-06, "epoch": 0.6835443037974683, "percentage": 22.81, "elapsed_time": "0:57:23", "remaining_time": "3:14:16"}
+{"current_steps": 235, "total_steps": 1026, "loss": 0.6327, "lr": 9.503788950208324e-06, "epoch": 0.6864654333008764, "percentage": 22.9, "elapsed_time": "0:57:39", "remaining_time": "3:14:03"}
+{"current_steps": 236, "total_steps": 1026, "loss": 0.6422, "lr": 9.49637142398377e-06, "epoch": 0.6893865628042843, "percentage": 23.0, "elapsed_time": "0:57:54", "remaining_time": "3:13:49"}
+{"current_steps": 237, "total_steps": 1026, "loss": 0.6367, "lr": 9.48890180730995e-06, "epoch": 0.6923076923076923, "percentage": 23.1, "elapsed_time": "0:58:07", "remaining_time": "3:13:30"}
+{"current_steps": 238, "total_steps": 1026, "loss": 0.6472, "lr": 9.481380186722354e-06, "epoch": 0.6952288218111002, "percentage": 23.2, "elapsed_time": "0:58:20", "remaining_time": "3:13:11"}
+{"current_steps": 239, "total_steps": 1026, "loss": 0.6663, "lr": 9.473806649358929e-06, "epoch": 0.6981499513145083, "percentage": 23.29, "elapsed_time": "0:58:36", "remaining_time": "3:12:58"}
+{"current_steps": 240, "total_steps": 1026, "loss": 0.6294, "lr": 9.466181282959083e-06, "epoch": 0.7010710808179162, "percentage": 23.39, "elapsed_time": "0:58:52", "remaining_time": "3:12:49"}
+{"current_steps": 241, "total_steps": 1026, "loss": 0.6543, "lr": 9.458504175862665e-06, "epoch": 0.7039922103213242, "percentage": 23.49, "elapsed_time": "0:59:10", "remaining_time": "3:12:45"}
+{"current_steps": 242, "total_steps": 1026, "loss": 0.653, "lr": 9.450775417008936e-06, "epoch": 0.7069133398247323, "percentage": 23.59, "elapsed_time": "0:59:25", "remaining_time": "3:12:31"}
+{"current_steps": 243, "total_steps": 1026, "loss": 0.6486, "lr": 9.442995095935542e-06, "epoch": 0.7098344693281402, "percentage": 23.68, "elapsed_time": "0:59:40", "remaining_time": "3:12:16"}
+{"current_steps": 244, "total_steps": 1026, "loss": 0.6356, "lr": 9.43516330277748e-06, "epoch": 0.7127555988315482, "percentage": 23.78, "elapsed_time": "0:59:55", "remaining_time": "3:12:03"}
+{"current_steps": 245, "total_steps": 1026, "loss": 0.6341, "lr": 9.427280128266049e-06, "epoch": 0.7156767283349562, "percentage": 23.88, "elapsed_time": "1:00:08", "remaining_time": "3:11:43"}
+{"current_steps": 246, "total_steps": 1026, "loss": 0.6541, "lr": 9.419345663727805e-06, "epoch": 0.7185978578383642, "percentage": 23.98, "elapsed_time": "1:00:26", "remaining_time": "3:11:37"}
+{"current_steps": 247, "total_steps": 1026, "loss": 0.665, "lr": 9.411360001083496e-06, "epoch": 0.7215189873417721, "percentage": 24.07, "elapsed_time": "1:00:41", "remaining_time": "3:11:25"}
+{"current_steps": 248, "total_steps": 1026, "loss": 0.6303, "lr": 9.403323232846994e-06, "epoch": 0.7244401168451802, "percentage": 24.17, "elapsed_time": "1:00:56", "remaining_time": "3:11:10"}
+{"current_steps": 249, "total_steps": 1026, "loss": 0.6316, "lr": 9.395235452124239e-06, "epoch": 0.7273612463485881, "percentage": 24.27, "elapsed_time": "1:01:10", "remaining_time": "3:10:54"}
+{"current_steps": 250, "total_steps": 1026, "loss": 0.6564, "lr": 9.387096752612144e-06, "epoch": 0.7302823758519961, "percentage": 24.37, "elapsed_time": "1:01:26", "remaining_time": "3:10:42"}
+{"current_steps": 251, "total_steps": 1026, "loss": 0.6542, "lr": 9.378907228597518e-06, "epoch": 0.7332035053554041, "percentage": 24.46, "elapsed_time": "1:01:37", "remaining_time": "3:10:16"}
+{"current_steps": 252, "total_steps": 1026, "loss": 0.6475, "lr": 9.370666974955973e-06, "epoch": 0.7361246348588121, "percentage": 24.56, "elapsed_time": "1:01:54", "remaining_time": "3:10:09"}
+{"current_steps": 253, "total_steps": 1026, "loss": 0.65, "lr": 9.362376087150822e-06, "epoch": 0.73904576436222, "percentage": 24.66, "elapsed_time": "1:02:09", "remaining_time": "3:09:55"}
+{"current_steps": 254, "total_steps": 1026, "loss": 0.6291, "lr": 9.354034661231976e-06, "epoch": 0.7419668938656281, "percentage": 24.76, "elapsed_time": "1:02:24", "remaining_time": "3:09:42"}
+{"current_steps": 255, "total_steps": 1026, "loss": 0.6478, "lr": 9.345642793834825e-06, "epoch": 0.744888023369036, "percentage": 24.85, "elapsed_time": "1:02:41", "remaining_time": "3:09:31"}
+{"current_steps": 256, "total_steps": 1026, "loss": 0.6338, "lr": 9.337200582179134e-06, "epoch": 0.747809152872444, "percentage": 24.95, "elapsed_time": "1:02:54", "remaining_time": "3:09:13"}
+{"current_steps": 257, "total_steps": 1026, "loss": 0.6426, "lr": 9.328708124067893e-06, "epoch": 0.750730282375852, "percentage": 25.05, "elapsed_time": "1:03:10", "remaining_time": "3:09:03"}
+{"current_steps": 258, "total_steps": 1026, "loss": 0.649, "lr": 9.320165517886207e-06, "epoch": 0.75365141187926, "percentage": 25.15, "elapsed_time": "1:03:24", "remaining_time": "3:08:45"}
+{"current_steps": 259, "total_steps": 1026, "loss": 0.6495, "lr": 9.31157286260014e-06, "epoch": 0.7565725413826679, "percentage": 25.24, "elapsed_time": "1:03:35", "remaining_time": "3:08:18"}
+{"current_steps": 260, "total_steps": 1026, "loss": 0.6582, "lr": 9.302930257755579e-06, "epoch": 0.759493670886076, "percentage": 25.34, "elapsed_time": "1:03:50", "remaining_time": "3:08:05"}
+{"current_steps": 261, "total_steps": 1026, "loss": 0.6482, "lr": 9.294237803477076e-06, "epoch": 0.762414800389484, "percentage": 25.44, "elapsed_time": "1:04:05", "remaining_time": "3:07:51"}
+{"current_steps": 262, "total_steps": 1026, "loss": 0.6491, "lr": 9.285495600466683e-06, "epoch": 0.7653359298928919, "percentage": 25.54, "elapsed_time": "1:04:20", "remaining_time": "3:07:36"}
+{"current_steps": 263, "total_steps": 1026, "loss": 0.6257, "lr": 9.276703750002801e-06, "epoch": 0.7682570593963, "percentage": 25.63, "elapsed_time": "1:04:35", "remaining_time": "3:07:23"}
+{"current_steps": 264, "total_steps": 1026, "loss": 0.6535, "lr": 9.267862353938988e-06, "epoch": 0.7711781888997079, "percentage": 25.73, "elapsed_time": "1:04:47", "remaining_time": "3:07:02"}
+{"current_steps": 265, "total_steps": 1026, "loss": 0.6441, "lr": 9.258971514702789e-06, "epoch": 0.7740993184031159, "percentage": 25.83, "elapsed_time": "1:05:00", "remaining_time": "3:06:42"}
+{"current_steps": 266, "total_steps": 1026, "loss": 0.6265, "lr": 9.250031335294551e-06, "epoch": 0.7770204479065238, "percentage": 25.93, "elapsed_time": "1:05:17", "remaining_time": "3:06:33"}
+{"current_steps": 267, "total_steps": 1026, "loss": 0.6328, "lr": 9.241041919286227e-06, "epoch": 0.7799415774099319, "percentage": 26.02, "elapsed_time": "1:05:30", "remaining_time": "3:06:12"}
+{"current_steps": 268, "total_steps": 1026, "loss": 0.6354, "lr": 9.232003370820171e-06, "epoch": 0.7828627069133398, "percentage": 26.12, "elapsed_time": "1:05:47", "remaining_time": "3:06:05"}
+{"current_steps": 269, "total_steps": 1026, "loss": 0.6432, "lr": 9.222915794607942e-06, "epoch": 0.7857838364167478, "percentage": 26.22, "elapsed_time": "1:06:02", "remaining_time": "3:05:51"}
+{"current_steps": 270, "total_steps": 1026, "loss": 0.6301, "lr": 9.213779295929082e-06, "epoch": 0.7887049659201558, "percentage": 26.32, "elapsed_time": "1:06:15", "remaining_time": "3:05:32"}
+{"current_steps": 271, "total_steps": 1026, "loss": 0.6308, "lr": 9.204593980629898e-06, "epoch": 0.7916260954235638, "percentage": 26.41, "elapsed_time": "1:06:29", "remaining_time": "3:05:15"}
+{"current_steps": 272, "total_steps": 1026, "loss": 0.6317, "lr": 9.195359955122244e-06, "epoch": 0.7945472249269717, "percentage": 26.51, "elapsed_time": "1:06:46", "remaining_time": "3:05:07"}
+{"current_steps": 273, "total_steps": 1026, "loss": 0.6322, "lr": 9.186077326382275e-06, "epoch": 0.7974683544303798, "percentage": 26.61, "elapsed_time": "1:07:05", "remaining_time": "3:05:03"}
+{"current_steps": 274, "total_steps": 1026, "loss": 0.6586, "lr": 9.176746201949216e-06, "epoch": 0.8003894839337877, "percentage": 26.71, "elapsed_time": "1:07:23", "remaining_time": "3:04:56"}
+{"current_steps": 275, "total_steps": 1026, "loss": 0.6517, "lr": 9.167366689924116e-06, "epoch": 0.8033106134371957, "percentage": 26.8, "elapsed_time": "1:07:39", "remaining_time": "3:04:45"}
+{"current_steps": 276, "total_steps": 1026, "loss": 0.6432, "lr": 9.157938898968594e-06, "epoch": 0.8062317429406037, "percentage": 26.9, "elapsed_time": "1:07:54", "remaining_time": "3:04:31"}
+{"current_steps": 277, "total_steps": 1026, "loss": 0.6387, "lr": 9.14846293830358e-06, "epoch": 0.8091528724440117, "percentage": 27.0, "elapsed_time": "1:08:09", "remaining_time": "3:04:17"}
+{"current_steps": 278, "total_steps": 1026, "loss": 0.6367, "lr": 9.138938917708047e-06, "epoch": 0.8120740019474196, "percentage": 27.1, "elapsed_time": "1:08:26", "remaining_time": "3:04:08"}
+{"current_steps": 279, "total_steps": 1026, "loss": 0.6313, "lr": 9.129366947517746e-06, "epoch": 0.8149951314508277, "percentage": 27.19, "elapsed_time": "1:08:37", "remaining_time": "3:03:45"}
+{"current_steps": 280, "total_steps": 1026, "loss": 0.6365, "lr": 9.119747138623925e-06, "epoch": 0.8179162609542356, "percentage": 27.29, "elapsed_time": "1:08:54", "remaining_time": "3:03:34"}
+{"current_steps": 281, "total_steps": 1026, "loss": 0.6549, "lr": 9.110079602472035e-06, "epoch": 0.8208373904576436, "percentage": 27.39, "elapsed_time": "1:09:07", "remaining_time": "3:03:15"}
+{"current_steps": 282, "total_steps": 1026, "loss": 0.6476, "lr": 9.100364451060457e-06, "epoch": 0.8237585199610516, "percentage": 27.49, "elapsed_time": "1:09:21", "remaining_time": "3:03:00"}
+{"current_steps": 283, "total_steps": 1026, "loss": 0.6317, "lr": 9.090601796939192e-06, "epoch": 0.8266796494644596, "percentage": 27.58, "elapsed_time": "1:09:35", "remaining_time": "3:02:42"}
+{"current_steps": 284, "total_steps": 1026, "loss": 0.6305, "lr": 9.080791753208553e-06, "epoch": 0.8296007789678675, "percentage": 27.68, "elapsed_time": "1:09:49", "remaining_time": "3:02:24"}
+{"current_steps": 285, "total_steps": 1026, "loss": 0.6373, "lr": 9.070934433517872e-06, "epoch": 0.8325219084712756, "percentage": 27.78, "elapsed_time": "1:10:03", "remaining_time": "3:02:09"}
+{"current_steps": 286, "total_steps": 1026, "loss": 0.6395, "lr": 9.061029952064165e-06, "epoch": 0.8354430379746836, "percentage": 27.88, "elapsed_time": "1:10:19", "remaining_time": "3:01:56"}
+{"current_steps": 287, "total_steps": 1026, "loss": 0.6354, "lr": 9.05107842359082e-06, "epoch": 0.8383641674780915, "percentage": 27.97, "elapsed_time": "1:10:34", "remaining_time": "3:01:44"}
+{"current_steps": 288, "total_steps": 1026, "loss": 0.6365, "lr": 9.041079963386263e-06, "epoch": 0.8412852969814996, "percentage": 28.07, "elapsed_time": "1:10:51", "remaining_time": "3:01:34"}
+{"current_steps": 289, "total_steps": 1026, "loss": 0.6513, "lr": 9.031034687282627e-06, "epoch": 0.8442064264849075, "percentage": 28.17, "elapsed_time": "1:11:06", "remaining_time": "3:01:19"}
+{"current_steps": 290, "total_steps": 1026, "loss": 0.6253, "lr": 9.020942711654404e-06, "epoch": 0.8471275559883155, "percentage": 28.27, "elapsed_time": "1:11:22", "remaining_time": "3:01:08"}
+{"current_steps": 291, "total_steps": 1026, "loss": 0.6347, "lr": 9.0108041534171e-06, "epoch": 0.8500486854917235, "percentage": 28.36, "elapsed_time": "1:11:37", "remaining_time": "3:00:54"}
+{"current_steps": 292, "total_steps": 1026, "loss": 0.632, "lr": 9.000619130025885e-06, "epoch": 0.8529698149951315, "percentage": 28.46, "elapsed_time": "1:11:47", "remaining_time": "3:00:28"}
+{"current_steps": 293, "total_steps": 1026, "loss": 0.6447, "lr": 8.99038775947422e-06, "epoch": 0.8558909444985394, "percentage": 28.56, "elapsed_time": "1:11:59", "remaining_time": "3:00:05"}
+{"current_steps": 294, "total_steps": 1026, "loss": 0.6546, "lr": 8.980110160292503e-06, "epoch": 0.8588120740019474, "percentage": 28.65, "elapsed_time": "1:12:15", "remaining_time": "2:59:54"}
+{"current_steps": 295, "total_steps": 1026, "loss": 0.6353, "lr": 8.969786451546691e-06, "epoch": 0.8617332035053554, "percentage": 28.75, "elapsed_time": "1:12:32", "remaining_time": "2:59:45"}
+{"current_steps": 296, "total_steps": 1026, "loss": 0.6316, "lr": 8.959416752836915e-06, "epoch": 0.8646543330087634, "percentage": 28.85, "elapsed_time": "1:12:44", "remaining_time": "2:59:23"}
+{"current_steps": 297, "total_steps": 1026, "loss": 0.6281, "lr": 8.949001184296107e-06, "epoch": 0.8675754625121713, "percentage": 28.95, "elapsed_time": "1:12:54", "remaining_time": "2:58:57"}
+{"current_steps": 298, "total_steps": 1026, "loss": 0.63, "lr": 8.938539866588593e-06, "epoch": 0.8704965920155794, "percentage": 29.04, "elapsed_time": "1:13:09", "remaining_time": "2:58:43"}
+{"current_steps": 299, "total_steps": 1026, "loss": 0.6462, "lr": 8.928032920908709e-06, "epoch": 0.8734177215189873, "percentage": 29.14, "elapsed_time": "1:13:21", "remaining_time": "2:58:22"}
+{"current_steps": 300, "total_steps": 1026, "loss": 0.6405, "lr": 8.917480468979387e-06, "epoch": 0.8763388510223953, "percentage": 29.24, "elapsed_time": "1:13:35", "remaining_time": "2:58:05"}
+{"current_steps": 301, "total_steps": 1026, "loss": 0.6428, "lr": 8.906882633050753e-06, "epoch": 0.8792599805258033, "percentage": 29.34, "elapsed_time": "1:13:48", "remaining_time": "2:57:46"}
+{"current_steps": 302, "total_steps": 1026, "loss": 0.65, "lr": 8.896239535898702e-06, "epoch": 0.8821811100292113, "percentage": 29.43, "elapsed_time": "1:14:01", "remaining_time": "2:57:29"}
+{"current_steps": 303, "total_steps": 1026, "loss": 0.6397, "lr": 8.885551300823483e-06, "epoch": 0.8851022395326192, "percentage": 29.53, "elapsed_time": "1:14:16", "remaining_time": "2:57:14"}
+{"current_steps": 304, "total_steps": 1026, "loss": 0.6235, "lr": 8.874818051648267e-06, "epoch": 0.8880233690360273, "percentage": 29.63, "elapsed_time": "1:14:30", "remaining_time": "2:56:58"}
+{"current_steps": 305, "total_steps": 1026, "loss": 0.6428, "lr": 8.864039912717713e-06, "epoch": 0.8909444985394352, "percentage": 29.73, "elapsed_time": "1:14:46", "remaining_time": "2:56:44"}
+{"current_steps": 306, "total_steps": 1026, "loss": 0.6477, "lr": 8.853217008896526e-06, "epoch": 0.8938656280428432, "percentage": 29.82, "elapsed_time": "1:14:58", "remaining_time": "2:56:24"}
+{"current_steps": 307, "total_steps": 1026, "loss": 0.6356, "lr": 8.842349465568018e-06, "epoch": 0.8967867575462513, "percentage": 29.92, "elapsed_time": "1:15:13", "remaining_time": "2:56:11"}
+{"current_steps": 308, "total_steps": 1026, "loss": 0.6177, "lr": 8.831437408632639e-06, "epoch": 0.8997078870496592, "percentage": 30.02, "elapsed_time": "1:15:30", "remaining_time": "2:56:01"}
+{"current_steps": 309, "total_steps": 1026, "loss": 0.6328, "lr": 8.820480964506542e-06, "epoch": 0.9026290165530672, "percentage": 30.12, "elapsed_time": "1:15:45", "remaining_time": "2:55:48"}
+{"current_steps": 310, "total_steps": 1026, "loss": 0.6302, "lr": 8.809480260120096e-06, "epoch": 0.9055501460564752, "percentage": 30.21, "elapsed_time": "1:16:03", "remaining_time": "2:55:40"}
+{"current_steps": 311, "total_steps": 1026, "loss": 0.6249, "lr": 8.798435422916425e-06, "epoch": 0.9084712755598832, "percentage": 30.31, "elapsed_time": "1:16:18", "remaining_time": "2:55:27"}
+{"current_steps": 312, "total_steps": 1026, "loss": 0.6276, "lr": 8.787346580849939e-06, "epoch": 0.9113924050632911, "percentage": 30.41, "elapsed_time": "1:16:31", "remaining_time": "2:55:07"}
+{"current_steps": 313, "total_steps": 1026, "loss": 0.6365, "lr": 8.776213862384838e-06, "epoch": 0.9143135345666992, "percentage": 30.51, "elapsed_time": "1:16:47", "remaining_time": "2:54:55"}
+{"current_steps": 314, "total_steps": 1026, "loss": 0.6585, "lr": 8.76503739649363e-06, "epoch": 0.9172346640701071, "percentage": 30.6, "elapsed_time": "1:17:01", "remaining_time": "2:54:39"}
+{"current_steps": 315, "total_steps": 1026, "loss": 0.6381, "lr": 8.753817312655642e-06, "epoch": 0.9201557935735151, "percentage": 30.7, "elapsed_time": "1:17:16", "remaining_time": "2:54:26"}
+{"current_steps": 316, "total_steps": 1026, "loss": 0.6391, "lr": 8.742553740855507e-06, "epoch": 0.9230769230769231, "percentage": 30.8, "elapsed_time": "1:17:30", "remaining_time": "2:54:08"}
+{"current_steps": 317, "total_steps": 1026, "loss": 0.6426, "lr": 8.73124681158167e-06, "epoch": 0.9259980525803311, "percentage": 30.9, "elapsed_time": "1:17:44", "remaining_time": "2:53:51"}
+{"current_steps": 318, "total_steps": 1026, "loss": 0.6327, "lr": 8.719896655824878e-06, "epoch": 0.928919182083739, "percentage": 30.99, "elapsed_time": "1:17:58", "remaining_time": "2:53:36"}
+{"current_steps": 319, "total_steps": 1026, "loss": 0.6339, "lr": 8.708503405076646e-06, "epoch": 0.9318403115871471, "percentage": 31.09, "elapsed_time": "1:18:15", "remaining_time": "2:53:27"}
+{"current_steps": 320, "total_steps": 1026, "loss": 0.6329, "lr": 8.697067191327748e-06, "epoch": 0.934761441090555, "percentage": 31.19, "elapsed_time": "1:18:29", "remaining_time": "2:53:09"}
+{"current_steps": 321, "total_steps": 1026, "loss": 0.6304, "lr": 8.685588147066688e-06, "epoch": 0.937682570593963, "percentage": 31.29, "elapsed_time": "1:18:43", "remaining_time": "2:52:53"}
+{"current_steps": 322, "total_steps": 1026, "loss": 0.6494, "lr": 8.67406640527816e-06, "epoch": 0.9406037000973709, "percentage": 31.38, "elapsed_time": "1:18:57", "remaining_time": "2:52:37"}
+{"current_steps": 323, "total_steps": 1026, "loss": 0.6333, "lr": 8.662502099441505e-06, "epoch": 0.943524829600779, "percentage": 31.48, "elapsed_time": "1:19:12", "remaining_time": "2:52:24"}
+{"current_steps": 324, "total_steps": 1026, "loss": 0.6278, "lr": 8.650895363529172e-06, "epoch": 0.9464459591041869, "percentage": 31.58, "elapsed_time": "1:19:26", "remaining_time": "2:52:06"}
+{"current_steps": 325, "total_steps": 1026, "loss": 0.6389, "lr": 8.639246332005163e-06, "epoch": 0.9493670886075949, "percentage": 31.68, "elapsed_time": "1:19:37", "remaining_time": "2:51:45"}
+{"current_steps": 326, "total_steps": 1026, "loss": 0.6139, "lr": 8.627555139823468e-06, "epoch": 0.952288218111003, "percentage": 31.77, "elapsed_time": "1:19:52", "remaining_time": "2:51:31"}
+{"current_steps": 327, "total_steps": 1026, "loss": 0.6214, "lr": 8.615821922426517e-06, "epoch": 0.9552093476144109, "percentage": 31.87, "elapsed_time": "1:20:07", "remaining_time": "2:51:16"}
+{"current_steps": 328, "total_steps": 1026, "loss": 0.6424, "lr": 8.604046815743598e-06, "epoch": 0.9581304771178188, "percentage": 31.97, "elapsed_time": "1:20:22", "remaining_time": "2:51:02"}
+{"current_steps": 329, "total_steps": 1026, "loss": 0.6382, "lr": 8.592229956189283e-06, "epoch": 0.9610516066212269, "percentage": 32.07, "elapsed_time": "1:20:35", "remaining_time": "2:50:43"}
+{"current_steps": 330, "total_steps": 1026, "loss": 0.6239, "lr": 8.580371480661857e-06, "epoch": 0.9639727361246349, "percentage": 32.16, "elapsed_time": "1:20:49", "remaining_time": "2:50:28"}
+{"current_steps": 331, "total_steps": 1026, "loss": 0.6518, "lr": 8.568471526541721e-06, "epoch": 0.9668938656280428, "percentage": 32.26, "elapsed_time": "1:21:05", "remaining_time": "2:50:15"}
+{"current_steps": 332, "total_steps": 1026, "loss": 0.6587, "lr": 8.556530231689809e-06, "epoch": 0.9698149951314509, "percentage": 32.36, "elapsed_time": "1:21:22", "remaining_time": "2:50:07"}
+{"current_steps": 333, "total_steps": 1026, "loss": 0.6443, "lr": 8.544547734445983e-06, "epoch": 0.9727361246348588, "percentage": 32.46, "elapsed_time": "1:21:34", "remaining_time": "2:49:46"}
+{"current_steps": 334, "total_steps": 1026, "loss": 0.6558, "lr": 8.532524173627438e-06, "epoch": 0.9756572541382668, "percentage": 32.55, "elapsed_time": "1:21:49", "remaining_time": "2:49:32"}
+{"current_steps": 335, "total_steps": 1026, "loss": 0.624, "lr": 8.520459688527091e-06, "epoch": 0.9785783836416748, "percentage": 32.65, "elapsed_time": "1:22:06", "remaining_time": "2:49:20"}
+{"current_steps": 336, "total_steps": 1026, "loss": 0.6393, "lr": 8.508354418911966e-06, "epoch": 0.9814995131450828, "percentage": 32.75, "elapsed_time": "1:22:20", "remaining_time": "2:49:05"}
+{"current_steps": 337, "total_steps": 1026, "loss": 0.6332, "lr": 8.496208505021572e-06, "epoch": 0.9844206426484907, "percentage": 32.85, "elapsed_time": "1:22:35", "remaining_time": "2:48:52"}
+{"current_steps": 338, "total_steps": 1026, "loss": 0.6215, "lr": 8.484022087566284e-06, "epoch": 0.9873417721518988, "percentage": 32.94, "elapsed_time": "1:22:54", "remaining_time": "2:48:44"}
+{"current_steps": 339, "total_steps": 1026, "loss": 0.6314, "lr": 8.471795307725713e-06, "epoch": 0.9902629016553067, "percentage": 33.04, "elapsed_time": "1:23:09", "remaining_time": "2:48:31"}
+{"current_steps": 340, "total_steps": 1026, "loss": 0.6222, "lr": 8.459528307147066e-06, "epoch": 0.9931840311587147, "percentage": 33.14, "elapsed_time": "1:23:25", "remaining_time": "2:48:18"}
+{"current_steps": 341, "total_steps": 1026, "loss": 0.6374, "lr": 8.447221227943507e-06, "epoch": 0.9961051606621227, "percentage": 33.24, "elapsed_time": "1:23:39", "remaining_time": "2:48:04"}
+{"current_steps": 342, "total_steps": 1026, "loss": 0.6311, "lr": 8.434874212692513e-06, "epoch": 0.9990262901655307, "percentage": 33.33, "elapsed_time": "1:23:56", "remaining_time": "2:47:53"}
+{"current_steps": 343, "total_steps": 1026, "loss": 1.0196, "lr": 8.422487404434214e-06, "epoch": 1.0019474196689386, "percentage": 33.43, "elapsed_time": "1:25:13", "remaining_time": "2:49:41"}
+{"current_steps": 344, "total_steps": 1026, "loss": 0.5889, "lr": 8.41006094666975e-06, "epoch": 1.0048685491723466, "percentage": 33.53, "elapsed_time": "1:25:24", "remaining_time": "2:49:19"}
+{"current_steps": 345, "total_steps": 1026, "loss": 0.5552, "lr": 8.397594983359591e-06, "epoch": 1.0077896786757545, "percentage": 33.63, "elapsed_time": "1:25:36", "remaining_time": "2:48:58"}
+{"current_steps": 346, "total_steps": 1026, "loss": 0.494, "lr": 8.385089658921892e-06, "epoch": 1.0107108081791627, "percentage": 33.72, "elapsed_time": "1:25:47", "remaining_time": "2:48:36"}
+{"current_steps": 347, "total_steps": 1026, "loss": 0.5878, "lr": 8.372545118230793e-06, "epoch": 1.0136319376825706, "percentage": 33.82, "elapsed_time": "1:26:00", "remaining_time": "2:48:18"}
+{"current_steps": 348, "total_steps": 1026, "loss": 0.6464, "lr": 8.35996150661476e-06, "epoch": 1.0165530671859786, "percentage": 33.92, "elapsed_time": "1:26:14", "remaining_time": "2:48:00"}
+{"current_steps": 349, "total_steps": 1026, "loss": 0.5632, "lr": 8.347338969854898e-06, "epoch": 1.0194741966893865, "percentage": 34.02, "elapsed_time": "1:26:30", "remaining_time": "2:47:48"}
+{"current_steps": 350, "total_steps": 1026, "loss": 0.6121, "lr": 8.334677654183254e-06, "epoch": 1.0223953261927945, "percentage": 34.11, "elapsed_time": "1:26:44", "remaining_time": "2:47:31"}
+{"current_steps": 351, "total_steps": 1026, "loss": 0.5922, "lr": 8.321977706281135e-06, "epoch": 1.0253164556962024, "percentage": 34.21, "elapsed_time": "1:26:59", "remaining_time": "2:47:17"}
+{"current_steps": 352, "total_steps": 1026, "loss": 0.5375, "lr": 8.309239273277394e-06, "epoch": 1.0282375851996106, "percentage": 34.31, "elapsed_time": "1:27:13", "remaining_time": "2:47:00"}
+{"current_steps": 353, "total_steps": 1026, "loss": 0.5973, "lr": 8.296462502746743e-06, "epoch": 1.0311587147030186, "percentage": 34.41, "elapsed_time": "1:27:28", "remaining_time": "2:46:46"}
+{"current_steps": 354, "total_steps": 1026, "loss": 0.6017, "lr": 8.283647542708026e-06, "epoch": 1.0340798442064265, "percentage": 34.5, "elapsed_time": "1:27:42", "remaining_time": "2:46:30"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc8ba7d4010f1373a087a89199c6502e58c0222143a47272204bda39b4c7004
+size 7352