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:e9b3c1dae2805a43271930ab78e0f2a20a8b9d25f3e0db3bfb2e03f14109332d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1290714bdfc4c7e8b730cfc1a165e9ae111e840f5474211e571f323bcea72034
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d905b923e37743aeb0b04f91e2cfaa84c844ade4222623be10c3cb99b93a18
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcff29d1109b43c4471b9d00f9d08beb44543a33a1340045b3d4593a780de56
+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 +1,324 @@
+{"current_steps": 1, "total_steps": 1620, "loss": 1.0575, "lr": 4.938271604938272e-07, "epoch": 0.0030828516377649326, "percentage": 0.06, "elapsed_time": "0:04:31", "remaining_time": "5 days, 2:18:09"}
+{"current_steps": 2, "total_steps": 1620, "loss": 1.0587, "lr": 9.876543209876544e-07, "epoch": 0.006165703275529865, "percentage": 0.12, "elapsed_time": "0:08:10", "remaining_time": "4 days, 14:18:59"}
+{"current_steps": 3, "total_steps": 1620, "loss": 1.0534, "lr": 1.4814814814814815e-06, "epoch": 0.009248554913294798, "percentage": 0.19, "elapsed_time": "0:11:50", "remaining_time": "4 days, 10:19:09"}
+{"current_steps": 4, "total_steps": 1620, "loss": 1.0505, "lr": 1.9753086419753087e-06, "epoch": 0.01233140655105973, "percentage": 0.25, "elapsed_time": "0:15:28", "remaining_time": "4 days, 8:13:51"}
+{"current_steps": 5, "total_steps": 1620, "loss": 1.0419, "lr": 2.469135802469136e-06, "epoch": 0.015414258188824663, "percentage": 0.31, "elapsed_time": "0:19:07", "remaining_time": "4 days, 7:00:01"}
+{"current_steps": 6, "total_steps": 1620, "loss": 1.0026, "lr": 2.962962962962963e-06, "epoch": 0.018497109826589597, "percentage": 0.37, "elapsed_time": "0:22:47", "remaining_time": "4 days, 6:10:13"}
+{"current_steps": 7, "total_steps": 1620, "loss": 0.9988, "lr": 3.4567901234567904e-06, "epoch": 0.02157996146435453, "percentage": 0.43, "elapsed_time": "0:26:27", "remaining_time": "4 days, 5:35:49"}
+{"current_steps": 8, "total_steps": 1620, "loss": 0.967, "lr": 3.9506172839506175e-06, "epoch": 0.02466281310211946, "percentage": 0.49, "elapsed_time": "0:30:06", "remaining_time": "4 days, 5:07:24"}
+{"current_steps": 9, "total_steps": 1620, "loss": 0.9602, "lr": 4.444444444444444e-06, "epoch": 0.027745664739884393, "percentage": 0.56, "elapsed_time": "0:33:45", "remaining_time": "4 days, 4:43:59"}
+{"current_steps": 10, "total_steps": 1620, "loss": 0.9497, "lr": 4.938271604938272e-06, "epoch": 0.030828516377649325, "percentage": 0.62, "elapsed_time": "0:37:25", "remaining_time": "4 days, 4:24:07"}
+{"current_steps": 11, "total_steps": 1620, "loss": 0.9548, "lr": 5.432098765432099e-06, "epoch": 0.03391136801541426, "percentage": 0.68, "elapsed_time": "0:41:04", "remaining_time": "4 days, 4:07:32"}
+{"current_steps": 12, "total_steps": 1620, "loss": 0.9431, "lr": 5.925925925925926e-06, "epoch": 0.03699421965317919, "percentage": 0.74, "elapsed_time": "0:44:43", "remaining_time": "4 days, 3:52:32"}
+{"current_steps": 13, "total_steps": 1620, "loss": 0.9022, "lr": 6.419753086419753e-06, "epoch": 0.04007707129094412, "percentage": 0.8, "elapsed_time": "0:48:22", "remaining_time": "4 days, 3:39:34"}
+{"current_steps": 14, "total_steps": 1620, "loss": 0.8804, "lr": 6.913580246913581e-06, "epoch": 0.04315992292870906, "percentage": 0.86, "elapsed_time": "0:52:01", "remaining_time": "4 days, 3:27:34"}
+{"current_steps": 15, "total_steps": 1620, "loss": 0.8637, "lr": 7.4074074074074075e-06, "epoch": 0.046242774566473986, "percentage": 0.93, "elapsed_time": "0:55:40", "remaining_time": "4 days, 3:17:16"}
+{"current_steps": 16, "total_steps": 1620, "loss": 0.8406, "lr": 7.901234567901235e-06, "epoch": 0.04932562620423892, "percentage": 0.99, "elapsed_time": "0:59:19", "remaining_time": "4 days, 3:07:16"}
+{"current_steps": 17, "total_steps": 1620, "loss": 0.828, "lr": 8.395061728395062e-06, "epoch": 0.05240847784200385, "percentage": 1.05, "elapsed_time": "1:02:58", "remaining_time": "4 days, 2:58:28"}
+{"current_steps": 18, "total_steps": 1620, "loss": 0.8077, "lr": 8.888888888888888e-06, "epoch": 0.055491329479768786, "percentage": 1.11, "elapsed_time": "1:06:37", "remaining_time": "4 days, 2:49:32"}
+{"current_steps": 19, "total_steps": 1620, "loss": 0.8, "lr": 9.382716049382717e-06, "epoch": 0.05857418111753372, "percentage": 1.17, "elapsed_time": "1:10:16", "remaining_time": "4 days, 2:41:21"}
+{"current_steps": 20, "total_steps": 1620, "loss": 0.787, "lr": 9.876543209876543e-06, "epoch": 0.06165703275529865, "percentage": 1.23, "elapsed_time": "1:13:55", "remaining_time": "4 days, 2:33:57"}
+{"current_steps": 21, "total_steps": 1620, "loss": 0.7734, "lr": 1.037037037037037e-05, "epoch": 0.06473988439306358, "percentage": 1.3, "elapsed_time": "1:17:34", "remaining_time": "4 days, 2:26:45"}
+{"current_steps": 22, "total_steps": 1620, "loss": 0.7634, "lr": 1.0864197530864198e-05, "epoch": 0.06782273603082851, "percentage": 1.36, "elapsed_time": "1:21:13", "remaining_time": "4 days, 2:19:40"}
+{"current_steps": 23, "total_steps": 1620, "loss": 0.7532, "lr": 1.1358024691358025e-05, "epoch": 0.07090558766859345, "percentage": 1.42, "elapsed_time": "1:24:52", "remaining_time": "4 days, 2:12:45"}
+{"current_steps": 24, "total_steps": 1620, "loss": 0.7551, "lr": 1.1851851851851852e-05, "epoch": 0.07398843930635839, "percentage": 1.48, "elapsed_time": "1:28:30", "remaining_time": "4 days, 2:06:14"}
+{"current_steps": 25, "total_steps": 1620, "loss": 0.7444, "lr": 1.234567901234568e-05, "epoch": 0.07707129094412331, "percentage": 1.54, "elapsed_time": "1:32:09", "remaining_time": "4 days, 1:59:52"}
+{"current_steps": 26, "total_steps": 1620, "loss": 0.7352, "lr": 1.2839506172839507e-05, "epoch": 0.08015414258188824, "percentage": 1.6, "elapsed_time": "1:35:48", "remaining_time": "4 days, 1:53:59"}
+{"current_steps": 27, "total_steps": 1620, "loss": 0.7333, "lr": 1.3333333333333333e-05, "epoch": 0.08323699421965318, "percentage": 1.67, "elapsed_time": "1:39:27", "remaining_time": "4 days, 1:48:08"}
+{"current_steps": 28, "total_steps": 1620, "loss": 0.729, "lr": 1.3827160493827162e-05, "epoch": 0.08631984585741811, "percentage": 1.73, "elapsed_time": "1:43:06", "remaining_time": "4 days, 1:42:21"}
+{"current_steps": 29, "total_steps": 1620, "loss": 0.7201, "lr": 1.4320987654320988e-05, "epoch": 0.08940269749518305, "percentage": 1.79, "elapsed_time": "1:46:45", "remaining_time": "4 days, 1:36:38"}
+{"current_steps": 30, "total_steps": 1620, "loss": 0.7175, "lr": 1.4814814814814815e-05, "epoch": 0.09248554913294797, "percentage": 1.85, "elapsed_time": "1:50:24", "remaining_time": "4 days, 1:31:21"}
+{"current_steps": 31, "total_steps": 1620, "loss": 0.7153, "lr": 1.5308641975308643e-05, "epoch": 0.09556840077071291, "percentage": 1.91, "elapsed_time": "1:54:03", "remaining_time": "4 days, 1:26:17"}
+{"current_steps": 32, "total_steps": 1620, "loss": 0.7043, "lr": 1.580246913580247e-05, "epoch": 0.09865125240847784, "percentage": 1.98, "elapsed_time": "1:57:42", "remaining_time": "4 days, 1:21:14"}
+{"current_steps": 33, "total_steps": 1620, "loss": 0.7016, "lr": 1.6296296296296297e-05, "epoch": 0.10173410404624278, "percentage": 2.04, "elapsed_time": "2:01:21", "remaining_time": "4 days, 1:15:58"}
+{"current_steps": 34, "total_steps": 1620, "loss": 0.7019, "lr": 1.6790123456790123e-05, "epoch": 0.1048169556840077, "percentage": 2.1, "elapsed_time": "2:05:00", "remaining_time": "4 days, 1:10:56"}
+{"current_steps": 35, "total_steps": 1620, "loss": 0.6924, "lr": 1.728395061728395e-05, "epoch": 0.10789980732177264, "percentage": 2.16, "elapsed_time": "2:08:39", "remaining_time": "4 days, 1:06:07"}
+{"current_steps": 36, "total_steps": 1620, "loss": 0.6954, "lr": 1.7777777777777777e-05, "epoch": 0.11098265895953757, "percentage": 2.22, "elapsed_time": "2:12:17", "remaining_time": "4 days, 1:01:06"}
+{"current_steps": 37, "total_steps": 1620, "loss": 0.6926, "lr": 1.8271604938271607e-05, "epoch": 0.11406551059730251, "percentage": 2.28, "elapsed_time": "2:15:56", "remaining_time": "4 days, 0:56:08"}
+{"current_steps": 38, "total_steps": 1620, "loss": 0.6884, "lr": 1.8765432098765433e-05, "epoch": 0.11714836223506744, "percentage": 2.35, "elapsed_time": "2:19:35", "remaining_time": "4 days, 0:51:32"}
+{"current_steps": 39, "total_steps": 1620, "loss": 0.6848, "lr": 1.925925925925926e-05, "epoch": 0.12023121387283237, "percentage": 2.41, "elapsed_time": "2:23:14", "remaining_time": "4 days, 0:46:48"}
+{"current_steps": 40, "total_steps": 1620, "loss": 0.6773, "lr": 1.9753086419753087e-05, "epoch": 0.1233140655105973, "percentage": 2.47, "elapsed_time": "2:26:53", "remaining_time": "4 days, 0:42:25"}
+{"current_steps": 41, "total_steps": 1620, "loss": 0.6727, "lr": 2.0246913580246917e-05, "epoch": 0.12639691714836224, "percentage": 2.53, "elapsed_time": "2:30:33", "remaining_time": "4 days, 0:38:06"}
+{"current_steps": 42, "total_steps": 1620, "loss": 0.6757, "lr": 2.074074074074074e-05, "epoch": 0.12947976878612716, "percentage": 2.59, "elapsed_time": "2:34:12", "remaining_time": "4 days, 0:33:33"}
+{"current_steps": 43, "total_steps": 1620, "loss": 0.6731, "lr": 2.123456790123457e-05, "epoch": 0.1325626204238921, "percentage": 2.65, "elapsed_time": "2:37:51", "remaining_time": "4 days, 0:29:29"}
+{"current_steps": 44, "total_steps": 1620, "loss": 0.6699, "lr": 2.1728395061728397e-05, "epoch": 0.13564547206165703, "percentage": 2.72, "elapsed_time": "2:41:30", "remaining_time": "4 days, 0:25:02"}
+{"current_steps": 45, "total_steps": 1620, "loss": 0.6698, "lr": 2.2222222222222227e-05, "epoch": 0.13872832369942195, "percentage": 2.78, "elapsed_time": "2:45:09", "remaining_time": "4 days, 0:20:28"}
+{"current_steps": 46, "total_steps": 1620, "loss": 0.6651, "lr": 2.271604938271605e-05, "epoch": 0.1418111753371869, "percentage": 2.84, "elapsed_time": "2:48:48", "remaining_time": "4 days, 0:16:13"}
+{"current_steps": 47, "total_steps": 1620, "loss": 0.6702, "lr": 2.320987654320988e-05, "epoch": 0.14489402697495182, "percentage": 2.9, "elapsed_time": "2:52:27", "remaining_time": "4 days, 0:11:45"}
+{"current_steps": 48, "total_steps": 1620, "loss": 0.6663, "lr": 2.3703703703703703e-05, "epoch": 0.14797687861271677, "percentage": 2.96, "elapsed_time": "2:56:06", "remaining_time": "4 days, 0:07:21"}
+{"current_steps": 49, "total_steps": 1620, "loss": 0.6599, "lr": 2.4197530864197533e-05, "epoch": 0.1510597302504817, "percentage": 3.02, "elapsed_time": "2:59:45", "remaining_time": "4 days, 0:03:11"}
+{"current_steps": 50, "total_steps": 1620, "loss": 0.6674, "lr": 2.469135802469136e-05, "epoch": 0.15414258188824662, "percentage": 3.09, "elapsed_time": "3:03:24", "remaining_time": "3 days, 23:58:58"}
+{"current_steps": 51, "total_steps": 1620, "loss": 0.6596, "lr": 2.5185185185185187e-05, "epoch": 0.15722543352601157, "percentage": 3.15, "elapsed_time": "3:07:03", "remaining_time": "3 days, 23:54:42"}
+{"current_steps": 52, "total_steps": 1620, "loss": 0.662, "lr": 2.5679012345679013e-05, "epoch": 0.1603082851637765, "percentage": 3.21, "elapsed_time": "3:10:42", "remaining_time": "3 days, 23:50:34"}
+{"current_steps": 53, "total_steps": 1620, "loss": 0.6596, "lr": 2.6172839506172843e-05, "epoch": 0.16339113680154144, "percentage": 3.27, "elapsed_time": "3:14:21", "remaining_time": "3 days, 23:46:25"}
+{"current_steps": 54, "total_steps": 1620, "loss": 0.6578, "lr": 2.6666666666666667e-05, "epoch": 0.16647398843930636, "percentage": 3.33, "elapsed_time": "3:18:00", "remaining_time": "3 days, 23:42:09"}
+{"current_steps": 55, "total_steps": 1620, "loss": 0.6498, "lr": 2.7160493827160497e-05, "epoch": 0.16955684007707128, "percentage": 3.4, "elapsed_time": "3:21:39", "remaining_time": "3 days, 23:37:54"}
+{"current_steps": 56, "total_steps": 1620, "loss": 0.6483, "lr": 2.7654320987654323e-05, "epoch": 0.17263969171483623, "percentage": 3.46, "elapsed_time": "3:25:17", "remaining_time": "3 days, 23:33:41"}
+{"current_steps": 57, "total_steps": 1620, "loss": 0.648, "lr": 2.814814814814815e-05, "epoch": 0.17572254335260115, "percentage": 3.52, "elapsed_time": "3:28:56", "remaining_time": "3 days, 23:29:35"}
+{"current_steps": 58, "total_steps": 1620, "loss": 0.6471, "lr": 2.8641975308641977e-05, "epoch": 0.1788053949903661, "percentage": 3.58, "elapsed_time": "3:32:36", "remaining_time": "3 days, 23:25:34"}
+{"current_steps": 59, "total_steps": 1620, "loss": 0.6445, "lr": 2.9135802469135807e-05, "epoch": 0.18188824662813102, "percentage": 3.64, "elapsed_time": "3:36:14", "remaining_time": "3 days, 23:21:26"}
+{"current_steps": 60, "total_steps": 1620, "loss": 0.6502, "lr": 2.962962962962963e-05, "epoch": 0.18497109826589594, "percentage": 3.7, "elapsed_time": "3:39:53", "remaining_time": "3 days, 23:17:14"}
+{"current_steps": 61, "total_steps": 1620, "loss": 0.6484, "lr": 3.012345679012346e-05, "epoch": 0.1880539499036609, "percentage": 3.77, "elapsed_time": "3:43:32", "remaining_time": "3 days, 23:13:08"}
+{"current_steps": 62, "total_steps": 1620, "loss": 0.6413, "lr": 3.061728395061729e-05, "epoch": 0.19113680154142582, "percentage": 3.83, "elapsed_time": "3:47:11", "remaining_time": "3 days, 23:09:12"}
+{"current_steps": 63, "total_steps": 1620, "loss": 0.6376, "lr": 3.111111111111112e-05, "epoch": 0.19421965317919074, "percentage": 3.89, "elapsed_time": "3:50:51", "remaining_time": "3 days, 23:05:30"}
+{"current_steps": 64, "total_steps": 1620, "loss": 0.6398, "lr": 3.160493827160494e-05, "epoch": 0.1973025048169557, "percentage": 3.95, "elapsed_time": "3:54:30", "remaining_time": "3 days, 23:01:25"}
+{"current_steps": 65, "total_steps": 1620, "loss": 0.64, "lr": 3.209876543209877e-05, "epoch": 0.2003853564547206, "percentage": 4.01, "elapsed_time": "3:58:09", "remaining_time": "3 days, 22:57:32"}
+{"current_steps": 66, "total_steps": 1620, "loss": 0.6404, "lr": 3.259259259259259e-05, "epoch": 0.20346820809248556, "percentage": 4.07, "elapsed_time": "4:01:48", "remaining_time": "3 days, 22:53:21"}
+{"current_steps": 67, "total_steps": 1620, "loss": 0.6391, "lr": 3.308641975308642e-05, "epoch": 0.20655105973025048, "percentage": 4.14, "elapsed_time": "4:05:27", "remaining_time": "3 days, 22:49:27"}
+{"current_steps": 68, "total_steps": 1620, "loss": 0.6417, "lr": 3.3580246913580247e-05, "epoch": 0.2096339113680154, "percentage": 4.2, "elapsed_time": "4:09:06", "remaining_time": "3 days, 22:45:21"}
+{"current_steps": 69, "total_steps": 1620, "loss": 0.6328, "lr": 3.4074074074074077e-05, "epoch": 0.21271676300578035, "percentage": 4.26, "elapsed_time": "4:12:45", "remaining_time": "3 days, 22:41:23"}
+{"current_steps": 70, "total_steps": 1620, "loss": 0.6382, "lr": 3.45679012345679e-05, "epoch": 0.21579961464354527, "percentage": 4.32, "elapsed_time": "4:16:24", "remaining_time": "3 days, 22:37:30"}
+{"current_steps": 71, "total_steps": 1620, "loss": 0.6327, "lr": 3.506172839506173e-05, "epoch": 0.21888246628131022, "percentage": 4.38, "elapsed_time": "4:20:03", "remaining_time": "3 days, 22:33:43"}
+{"current_steps": 72, "total_steps": 1620, "loss": 0.6369, "lr": 3.555555555555555e-05, "epoch": 0.22196531791907514, "percentage": 4.44, "elapsed_time": "4:23:42", "remaining_time": "3 days, 22:29:50"}
+{"current_steps": 73, "total_steps": 1620, "loss": 0.6353, "lr": 3.604938271604938e-05, "epoch": 0.22504816955684007, "percentage": 4.51, "elapsed_time": "4:27:21", "remaining_time": "3 days, 22:25:47"}
+{"current_steps": 74, "total_steps": 1620, "loss": 0.6329, "lr": 3.654320987654321e-05, "epoch": 0.22813102119460502, "percentage": 4.57, "elapsed_time": "4:31:00", "remaining_time": "3 days, 22:21:50"}
+{"current_steps": 75, "total_steps": 1620, "loss": 0.6337, "lr": 3.703703703703704e-05, "epoch": 0.23121387283236994, "percentage": 4.63, "elapsed_time": "4:34:39", "remaining_time": "3 days, 22:17:50"}
+{"current_steps": 76, "total_steps": 1620, "loss": 0.6341, "lr": 3.7530864197530867e-05, "epoch": 0.2342967244701349, "percentage": 4.69, "elapsed_time": "4:38:18", "remaining_time": "3 days, 22:14:00"}
+{"current_steps": 77, "total_steps": 1620, "loss": 0.6278, "lr": 3.80246913580247e-05, "epoch": 0.2373795761078998, "percentage": 4.75, "elapsed_time": "4:41:57", "remaining_time": "3 days, 22:10:09"}
+{"current_steps": 78, "total_steps": 1620, "loss": 0.6249, "lr": 3.851851851851852e-05, "epoch": 0.24046242774566473, "percentage": 4.81, "elapsed_time": "4:45:36", "remaining_time": "3 days, 22:06:10"}
+{"current_steps": 79, "total_steps": 1620, "loss": 0.633, "lr": 3.901234567901235e-05, "epoch": 0.24354527938342968, "percentage": 4.88, "elapsed_time": "4:49:15", "remaining_time": "3 days, 22:02:14"}
+{"current_steps": 80, "total_steps": 1620, "loss": 0.6415, "lr": 3.950617283950617e-05, "epoch": 0.2466281310211946, "percentage": 4.94, "elapsed_time": "4:52:54", "remaining_time": "3 days, 21:58:24"}
+{"current_steps": 81, "total_steps": 1620, "loss": 0.6339, "lr": 4e-05, "epoch": 0.24971098265895952, "percentage": 5.0, "elapsed_time": "4:56:33", "remaining_time": "3 days, 21:54:36"}
+{"current_steps": 82, "total_steps": 1620, "loss": 0.631, "lr": 4.049382716049383e-05, "epoch": 0.2527938342967245, "percentage": 5.06, "elapsed_time": "5:00:12", "remaining_time": "3 days, 21:50:40"}
+{"current_steps": 83, "total_steps": 1620, "loss": 0.6349, "lr": 4.098765432098766e-05, "epoch": 0.2558766859344894, "percentage": 5.12, "elapsed_time": "5:03:51", "remaining_time": "3 days, 21:46:44"}
+{"current_steps": 84, "total_steps": 1620, "loss": 0.6325, "lr": 4.148148148148148e-05, "epoch": 0.2589595375722543, "percentage": 5.19, "elapsed_time": "5:07:30", "remaining_time": "3 days, 21:42:56"}
+{"current_steps": 85, "total_steps": 1620, "loss": 0.6249, "lr": 4.197530864197531e-05, "epoch": 0.26204238921001927, "percentage": 5.25, "elapsed_time": "5:11:08", "remaining_time": "3 days, 21:38:59"}
+{"current_steps": 86, "total_steps": 1620, "loss": 0.6257, "lr": 4.246913580246914e-05, "epoch": 0.2651252408477842, "percentage": 5.31, "elapsed_time": "5:14:47", "remaining_time": "3 days, 21:35:03"}
+{"current_steps": 87, "total_steps": 1620, "loss": 0.6276, "lr": 4.296296296296297e-05, "epoch": 0.2682080924855491, "percentage": 5.37, "elapsed_time": "5:18:26", "remaining_time": "3 days, 21:31:10"}
+{"current_steps": 88, "total_steps": 1620, "loss": 0.6379, "lr": 4.345679012345679e-05, "epoch": 0.27129094412331406, "percentage": 5.43, "elapsed_time": "5:22:05", "remaining_time": "3 days, 21:27:20"}
+{"current_steps": 89, "total_steps": 1620, "loss": 0.6287, "lr": 4.395061728395062e-05, "epoch": 0.274373795761079, "percentage": 5.49, "elapsed_time": "5:25:44", "remaining_time": "3 days, 21:23:30"}
+{"current_steps": 90, "total_steps": 1620, "loss": 0.661, "lr": 4.444444444444445e-05, "epoch": 0.2774566473988439, "percentage": 5.56, "elapsed_time": "5:29:23", "remaining_time": "3 days, 21:19:43"}
+{"current_steps": 91, "total_steps": 1620, "loss": 0.6783, "lr": 4.493827160493828e-05, "epoch": 0.28053949903660885, "percentage": 5.62, "elapsed_time": "5:33:02", "remaining_time": "3 days, 21:15:56"}
+{"current_steps": 92, "total_steps": 1620, "loss": 0.6423, "lr": 4.54320987654321e-05, "epoch": 0.2836223506743738, "percentage": 5.68, "elapsed_time": "5:36:42", "remaining_time": "3 days, 21:12:11"}
+{"current_steps": 93, "total_steps": 1620, "loss": 0.637, "lr": 4.592592592592593e-05, "epoch": 0.28670520231213875, "percentage": 5.74, "elapsed_time": "5:40:21", "remaining_time": "3 days, 21:08:21"}
+{"current_steps": 94, "total_steps": 1620, "loss": 0.6467, "lr": 4.641975308641976e-05, "epoch": 0.28978805394990365, "percentage": 5.8, "elapsed_time": "5:43:59", "remaining_time": "3 days, 21:04:26"}
+{"current_steps": 95, "total_steps": 1620, "loss": 0.6374, "lr": 4.691358024691359e-05, "epoch": 0.2928709055876686, "percentage": 5.86, "elapsed_time": "5:47:38", "remaining_time": "3 days, 21:00:38"}
+{"current_steps": 96, "total_steps": 1620, "loss": 0.6303, "lr": 4.7407407407407407e-05, "epoch": 0.29595375722543354, "percentage": 5.93, "elapsed_time": "5:51:18", "remaining_time": "3 days, 20:56:57"}
+{"current_steps": 97, "total_steps": 1620, "loss": 0.6337, "lr": 4.7901234567901237e-05, "epoch": 0.29903660886319844, "percentage": 5.99, "elapsed_time": "5:54:57", "remaining_time": "3 days, 20:53:08"}
+{"current_steps": 98, "total_steps": 1620, "loss": 0.6291, "lr": 4.8395061728395067e-05, "epoch": 0.3021194605009634, "percentage": 6.05, "elapsed_time": "5:58:36", "remaining_time": "3 days, 20:49:19"}
+{"current_steps": 99, "total_steps": 1620, "loss": 0.6316, "lr": 4.88888888888889e-05, "epoch": 0.30520231213872834, "percentage": 6.11, "elapsed_time": "6:02:14", "remaining_time": "3 days, 20:45:28"}
+{"current_steps": 100, "total_steps": 1620, "loss": 0.6292, "lr": 4.938271604938272e-05, "epoch": 0.30828516377649323, "percentage": 6.17, "elapsed_time": "6:05:53", "remaining_time": "3 days, 20:41:34"}
+{"current_steps": 101, "total_steps": 1620, "loss": 0.6277, "lr": 4.987654320987655e-05, "epoch": 0.3113680154142582, "percentage": 6.23, "elapsed_time": "6:09:32", "remaining_time": "3 days, 20:37:44"}
+{"current_steps": 102, "total_steps": 1620, "loss": 0.6273, "lr": 5.037037037037037e-05, "epoch": 0.31445086705202313, "percentage": 6.3, "elapsed_time": "6:13:11", "remaining_time": "3 days, 20:33:50"}
+{"current_steps": 103, "total_steps": 1620, "loss": 0.6235, "lr": 5.08641975308642e-05, "epoch": 0.3175337186897881, "percentage": 6.36, "elapsed_time": "6:16:50", "remaining_time": "3 days, 20:30:07"}
+{"current_steps": 104, "total_steps": 1620, "loss": 0.6296, "lr": 5.1358024691358027e-05, "epoch": 0.320616570327553, "percentage": 6.42, "elapsed_time": "6:20:28", "remaining_time": "3 days, 20:26:15"}
+{"current_steps": 105, "total_steps": 1620, "loss": 0.6245, "lr": 5.1851851851851857e-05, "epoch": 0.3236994219653179, "percentage": 6.48, "elapsed_time": "6:24:08", "remaining_time": "3 days, 20:22:32"}
+{"current_steps": 106, "total_steps": 1620, "loss": 0.6251, "lr": 5.234567901234569e-05, "epoch": 0.3267822736030829, "percentage": 6.54, "elapsed_time": "6:27:47", "remaining_time": "3 days, 20:18:46"}
+{"current_steps": 107, "total_steps": 1620, "loss": 0.6282, "lr": 5.283950617283952e-05, "epoch": 0.32986512524084777, "percentage": 6.6, "elapsed_time": "6:31:26", "remaining_time": "3 days, 20:14:58"}
+{"current_steps": 108, "total_steps": 1620, "loss": 0.6245, "lr": 5.333333333333333e-05, "epoch": 0.3329479768786127, "percentage": 6.67, "elapsed_time": "6:35:05", "remaining_time": "3 days, 20:11:10"}
+{"current_steps": 109, "total_steps": 1620, "loss": 0.6178, "lr": 5.382716049382716e-05, "epoch": 0.33603082851637767, "percentage": 6.73, "elapsed_time": "6:38:43", "remaining_time": "3 days, 20:07:23"}
+{"current_steps": 110, "total_steps": 1620, "loss": 0.6166, "lr": 5.432098765432099e-05, "epoch": 0.33911368015414256, "percentage": 6.79, "elapsed_time": "6:42:22", "remaining_time": "3 days, 20:03:35"}
+{"current_steps": 111, "total_steps": 1620, "loss": 0.6274, "lr": 5.481481481481482e-05, "epoch": 0.3421965317919075, "percentage": 6.85, "elapsed_time": "6:46:01", "remaining_time": "3 days, 19:59:43"}
+{"current_steps": 112, "total_steps": 1620, "loss": 0.6239, "lr": 5.5308641975308647e-05, "epoch": 0.34527938342967246, "percentage": 6.91, "elapsed_time": "6:49:40", "remaining_time": "3 days, 19:55:55"}
+{"current_steps": 113, "total_steps": 1620, "loss": 0.6335, "lr": 5.580246913580247e-05, "epoch": 0.34836223506743735, "percentage": 6.98, "elapsed_time": "6:53:19", "remaining_time": "3 days, 19:52:08"}
+{"current_steps": 114, "total_steps": 1620, "loss": 0.6243, "lr": 5.62962962962963e-05, "epoch": 0.3514450867052023, "percentage": 7.04, "elapsed_time": "6:56:57", "remaining_time": "3 days, 19:48:19"}
+{"current_steps": 115, "total_steps": 1620, "loss": 0.6291, "lr": 5.679012345679013e-05, "epoch": 0.35452793834296725, "percentage": 7.1, "elapsed_time": "7:00:37", "remaining_time": "3 days, 19:44:35"}
+{"current_steps": 116, "total_steps": 1620, "loss": 0.6285, "lr": 5.728395061728395e-05, "epoch": 0.3576107899807322, "percentage": 7.16, "elapsed_time": "7:04:15", "remaining_time": "3 days, 19:40:50"}
+{"current_steps": 117, "total_steps": 1620, "loss": 0.6137, "lr": 5.777777777777778e-05, "epoch": 0.3606936416184971, "percentage": 7.22, "elapsed_time": "7:07:55", "remaining_time": "3 days, 19:37:09"}
+{"current_steps": 118, "total_steps": 1620, "loss": 0.6248, "lr": 5.827160493827161e-05, "epoch": 0.36377649325626205, "percentage": 7.28, "elapsed_time": "7:11:34", "remaining_time": "3 days, 19:33:25"}
+{"current_steps": 119, "total_steps": 1620, "loss": 0.6201, "lr": 5.876543209876544e-05, "epoch": 0.366859344894027, "percentage": 7.35, "elapsed_time": "7:15:13", "remaining_time": "3 days, 19:29:38"}
+{"current_steps": 120, "total_steps": 1620, "loss": 0.6265, "lr": 5.925925925925926e-05, "epoch": 0.3699421965317919, "percentage": 7.41, "elapsed_time": "7:18:52", "remaining_time": "3 days, 19:25:52"}
+{"current_steps": 121, "total_steps": 1620, "loss": 0.6324, "lr": 5.975308641975309e-05, "epoch": 0.37302504816955684, "percentage": 7.47, "elapsed_time": "7:22:31", "remaining_time": "3 days, 19:22:07"}
+{"current_steps": 122, "total_steps": 1620, "loss": 0.6199, "lr": 6.024691358024692e-05, "epoch": 0.3761078998073218, "percentage": 7.53, "elapsed_time": "7:26:10", "remaining_time": "3 days, 19:18:29"}
+{"current_steps": 123, "total_steps": 1620, "loss": 0.6243, "lr": 6.074074074074075e-05, "epoch": 0.3791907514450867, "percentage": 7.59, "elapsed_time": "7:29:52", "remaining_time": "3 days, 19:15:23"}
+{"current_steps": 124, "total_steps": 1620, "loss": 0.621, "lr": 6.123456790123457e-05, "epoch": 0.38227360308285163, "percentage": 7.65, "elapsed_time": "7:33:34", "remaining_time": "3 days, 19:12:11"}
+{"current_steps": 125, "total_steps": 1620, "loss": 0.616, "lr": 6.17283950617284e-05, "epoch": 0.3853564547206166, "percentage": 7.72, "elapsed_time": "7:37:13", "remaining_time": "3 days, 19:08:26"}
+{"current_steps": 126, "total_steps": 1620, "loss": 0.6227, "lr": 6.222222222222223e-05, "epoch": 0.3884393063583815, "percentage": 7.78, "elapsed_time": "7:40:52", "remaining_time": "3 days, 19:04:39"}
+{"current_steps": 127, "total_steps": 1620, "loss": 0.6208, "lr": 6.271604938271606e-05, "epoch": 0.3915221579961464, "percentage": 7.84, "elapsed_time": "7:44:31", "remaining_time": "3 days, 19:00:53"}
+{"current_steps": 128, "total_steps": 1620, "loss": 0.613, "lr": 6.320987654320988e-05, "epoch": 0.3946050096339114, "percentage": 7.9, "elapsed_time": "7:48:10", "remaining_time": "3 days, 18:57:09"}
+{"current_steps": 129, "total_steps": 1620, "loss": 0.617, "lr": 6.37037037037037e-05, "epoch": 0.3976878612716763, "percentage": 7.96, "elapsed_time": "7:51:49", "remaining_time": "3 days, 18:53:19"}
+{"current_steps": 130, "total_steps": 1620, "loss": 0.6161, "lr": 6.419753086419754e-05, "epoch": 0.4007707129094412, "percentage": 8.02, "elapsed_time": "7:55:27", "remaining_time": "3 days, 18:49:31"}
+{"current_steps": 131, "total_steps": 1620, "loss": 0.6136, "lr": 6.469135802469136e-05, "epoch": 0.40385356454720617, "percentage": 8.09, "elapsed_time": "7:59:06", "remaining_time": "3 days, 18:45:44"}
+{"current_steps": 132, "total_steps": 1620, "loss": 0.6175, "lr": 6.518518518518519e-05, "epoch": 0.4069364161849711, "percentage": 8.15, "elapsed_time": "8:02:45", "remaining_time": "3 days, 18:42:02"}
+{"current_steps": 133, "total_steps": 1620, "loss": 0.6193, "lr": 6.567901234567901e-05, "epoch": 0.410019267822736, "percentage": 8.21, "elapsed_time": "8:06:24", "remaining_time": "3 days, 18:38:17"}
+{"current_steps": 134, "total_steps": 1620, "loss": 0.6139, "lr": 6.617283950617285e-05, "epoch": 0.41310211946050096, "percentage": 8.27, "elapsed_time": "8:10:03", "remaining_time": "3 days, 18:34:31"}
+{"current_steps": 135, "total_steps": 1620, "loss": 0.6432, "lr": 6.666666666666667e-05, "epoch": 0.4161849710982659, "percentage": 8.33, "elapsed_time": "8:13:41", "remaining_time": "3 days, 18:30:41"}
+{"current_steps": 136, "total_steps": 1620, "loss": 0.622, "lr": 6.716049382716049e-05, "epoch": 0.4192678227360308, "percentage": 8.4, "elapsed_time": "8:17:20", "remaining_time": "3 days, 18:26:54"}
+{"current_steps": 137, "total_steps": 1620, "loss": 0.6314, "lr": 6.765432098765433e-05, "epoch": 0.42235067437379575, "percentage": 8.46, "elapsed_time": "8:20:59", "remaining_time": "3 days, 18:23:11"}
+{"current_steps": 138, "total_steps": 1620, "loss": 0.6196, "lr": 6.814814814814815e-05, "epoch": 0.4254335260115607, "percentage": 8.52, "elapsed_time": "8:24:38", "remaining_time": "3 days, 18:19:29"}
+{"current_steps": 139, "total_steps": 1620, "loss": 0.6252, "lr": 6.864197530864199e-05, "epoch": 0.42851637764932565, "percentage": 8.58, "elapsed_time": "8:28:17", "remaining_time": "3 days, 18:15:42"}
+{"current_steps": 140, "total_steps": 1620, "loss": 0.619, "lr": 6.91358024691358e-05, "epoch": 0.43159922928709055, "percentage": 8.64, "elapsed_time": "8:31:56", "remaining_time": "3 days, 18:11:59"}
+{"current_steps": 141, "total_steps": 1620, "loss": 0.6156, "lr": 6.962962962962964e-05, "epoch": 0.4346820809248555, "percentage": 8.7, "elapsed_time": "8:35:36", "remaining_time": "3 days, 18:08:21"}
+{"current_steps": 142, "total_steps": 1620, "loss": 0.6167, "lr": 7.012345679012346e-05, "epoch": 0.43776493256262045, "percentage": 8.77, "elapsed_time": "8:39:15", "remaining_time": "3 days, 18:04:38"}
+{"current_steps": 143, "total_steps": 1620, "loss": 0.6142, "lr": 7.06172839506173e-05, "epoch": 0.44084778420038534, "percentage": 8.83, "elapsed_time": "8:42:54", "remaining_time": "3 days, 18:00:55"}
+{"current_steps": 144, "total_steps": 1620, "loss": 0.6197, "lr": 7.11111111111111e-05, "epoch": 0.4439306358381503, "percentage": 8.89, "elapsed_time": "8:46:33", "remaining_time": "3 days, 17:57:08"}
+{"current_steps": 145, "total_steps": 1620, "loss": 0.6167, "lr": 7.160493827160494e-05, "epoch": 0.44701348747591524, "percentage": 8.95, "elapsed_time": "8:50:12", "remaining_time": "3 days, 17:53:25"}
+{"current_steps": 146, "total_steps": 1620, "loss": 0.6189, "lr": 7.209876543209877e-05, "epoch": 0.45009633911368013, "percentage": 9.01, "elapsed_time": "8:53:51", "remaining_time": "3 days, 17:49:42"}
+{"current_steps": 147, "total_steps": 1620, "loss": 0.6155, "lr": 7.25925925925926e-05, "epoch": 0.4531791907514451, "percentage": 9.07, "elapsed_time": "8:57:29", "remaining_time": "3 days, 17:45:54"}
+{"current_steps": 148, "total_steps": 1620, "loss": 0.609, "lr": 7.308641975308643e-05, "epoch": 0.45626204238921003, "percentage": 9.14, "elapsed_time": "9:01:08", "remaining_time": "3 days, 17:42:14"}
+{"current_steps": 149, "total_steps": 1620, "loss": 0.61, "lr": 7.358024691358025e-05, "epoch": 0.4593448940269749, "percentage": 9.2, "elapsed_time": "9:04:47", "remaining_time": "3 days, 17:38:29"}
+{"current_steps": 150, "total_steps": 1620, "loss": 0.605, "lr": 7.407407407407409e-05, "epoch": 0.4624277456647399, "percentage": 9.26, "elapsed_time": "9:08:26", "remaining_time": "3 days, 17:34:47"}
+{"current_steps": 151, "total_steps": 1620, "loss": 0.6078, "lr": 7.456790123456791e-05, "epoch": 0.4655105973025048, "percentage": 9.32, "elapsed_time": "9:12:06", "remaining_time": "3 days, 17:31:06"}
+{"current_steps": 152, "total_steps": 1620, "loss": 0.6058, "lr": 7.506172839506173e-05, "epoch": 0.4685934489402698, "percentage": 9.38, "elapsed_time": "9:15:44", "remaining_time": "3 days, 17:27:21"}
+{"current_steps": 153, "total_steps": 1620, "loss": 0.6159, "lr": 7.555555555555556e-05, "epoch": 0.47167630057803467, "percentage": 9.44, "elapsed_time": "9:19:23", "remaining_time": "3 days, 17:23:36"}
+{"current_steps": 154, "total_steps": 1620, "loss": 0.6079, "lr": 7.60493827160494e-05, "epoch": 0.4747591522157996, "percentage": 9.51, "elapsed_time": "9:23:02", "remaining_time": "3 days, 17:19:49"}
+{"current_steps": 155, "total_steps": 1620, "loss": 0.6347, "lr": 7.654320987654322e-05, "epoch": 0.47784200385356457, "percentage": 9.57, "elapsed_time": "9:26:41", "remaining_time": "3 days, 17:16:08"}
+{"current_steps": 156, "total_steps": 1620, "loss": 0.639, "lr": 7.703703703703704e-05, "epoch": 0.48092485549132946, "percentage": 9.63, "elapsed_time": "9:30:20", "remaining_time": "3 days, 17:12:27"}
+{"current_steps": 157, "total_steps": 1620, "loss": 0.6235, "lr": 7.753086419753086e-05, "epoch": 0.4840077071290944, "percentage": 9.69, "elapsed_time": "9:33:59", "remaining_time": "3 days, 17:08:43"}
+{"current_steps": 158, "total_steps": 1620, "loss": 0.6216, "lr": 7.80246913580247e-05, "epoch": 0.48709055876685936, "percentage": 9.75, "elapsed_time": "9:37:38", "remaining_time": "3 days, 17:04:59"}
+{"current_steps": 159, "total_steps": 1620, "loss": 0.6251, "lr": 7.851851851851852e-05, "epoch": 0.49017341040462425, "percentage": 9.81, "elapsed_time": "9:41:17", "remaining_time": "3 days, 17:01:16"}
+{"current_steps": 160, "total_steps": 1620, "loss": 0.614, "lr": 7.901234567901235e-05, "epoch": 0.4932562620423892, "percentage": 9.88, "elapsed_time": "9:44:56", "remaining_time": "3 days, 16:57:32"}
+{"current_steps": 161, "total_steps": 1620, "loss": 0.6198, "lr": 7.950617283950618e-05, "epoch": 0.49633911368015415, "percentage": 9.94, "elapsed_time": "9:48:35", "remaining_time": "3 days, 16:53:49"}
+{"current_steps": 162, "total_steps": 1620, "loss": 0.6197, "lr": 8e-05, "epoch": 0.49942196531791905, "percentage": 10.0, "elapsed_time": "9:52:14", "remaining_time": "3 days, 16:50:07"}
+{"current_steps": 163, "total_steps": 1620, "loss": 0.6158, "lr": 7.999990714302639e-05, "epoch": 0.502504816955684, "percentage": 10.06, "elapsed_time": "9:55:53", "remaining_time": "3 days, 16:46:24"}
+{"current_steps": 164, "total_steps": 1620, "loss": 0.6174, "lr": 7.999962857253669e-05, "epoch": 0.505587668593449, "percentage": 10.12, "elapsed_time": "9:59:31", "remaining_time": "3 days, 16:42:41"}
+{"current_steps": 165, "total_steps": 1620, "loss": 0.6132, "lr": 7.999916428982425e-05, "epoch": 0.5086705202312138, "percentage": 10.19, "elapsed_time": "10:03:10", "remaining_time": "3 days, 16:38:57"}
+{"current_steps": 166, "total_steps": 1620, "loss": 0.608, "lr": 7.999851429704464e-05, "epoch": 0.5117533718689788, "percentage": 10.25, "elapsed_time": "10:06:49", "remaining_time": "3 days, 16:35:13"}
+{"current_steps": 167, "total_steps": 1620, "loss": 0.6093, "lr": 7.999767859721572e-05, "epoch": 0.5148362235067437, "percentage": 10.31, "elapsed_time": "10:10:28", "remaining_time": "3 days, 16:31:30"}
+{"current_steps": 168, "total_steps": 1620, "loss": 0.6142, "lr": 7.99966571942175e-05, "epoch": 0.5179190751445086, "percentage": 10.37, "elapsed_time": "10:14:07", "remaining_time": "3 days, 16:27:49"}
+{"current_steps": 169, "total_steps": 1620, "loss": 0.6069, "lr": 7.99954500927922e-05, "epoch": 0.5210019267822736, "percentage": 10.43, "elapsed_time": "10:17:46", "remaining_time": "3 days, 16:24:08"}
+{"current_steps": 170, "total_steps": 1620, "loss": 0.6016, "lr": 7.999405729854421e-05, "epoch": 0.5240847784200385, "percentage": 10.49, "elapsed_time": "10:21:25", "remaining_time": "3 days, 16:20:26"}
+{"current_steps": 171, "total_steps": 1620, "loss": 0.6007, "lr": 7.999247881794007e-05, "epoch": 0.5271676300578034, "percentage": 10.56, "elapsed_time": "10:25:05", "remaining_time": "3 days, 16:16:46"}
+{"current_steps": 172, "total_steps": 1620, "loss": 0.605, "lr": 7.99907146583084e-05, "epoch": 0.5302504816955684, "percentage": 10.62, "elapsed_time": "10:28:44", "remaining_time": "3 days, 16:13:04"}
+{"current_steps": 173, "total_steps": 1620, "loss": 0.6045, "lr": 7.998876482783996e-05, "epoch": 0.5333333333333333, "percentage": 10.68, "elapsed_time": "10:32:23", "remaining_time": "3 days, 16:09:22"}
+{"current_steps": 174, "total_steps": 1620, "loss": 0.5999, "lr": 7.99866293355875e-05, "epoch": 0.5364161849710982, "percentage": 10.74, "elapsed_time": "10:36:02", "remaining_time": "3 days, 16:05:42"}
+{"current_steps": 175, "total_steps": 1620, "loss": 0.6001, "lr": 7.99843081914658e-05, "epoch": 0.5394990366088632, "percentage": 10.8, "elapsed_time": "10:39:41", "remaining_time": "3 days, 16:02:05"}
+{"current_steps": 176, "total_steps": 1620, "loss": 0.5973, "lr": 7.998180140625156e-05, "epoch": 0.5425818882466281, "percentage": 10.86, "elapsed_time": "10:43:20", "remaining_time": "3 days, 15:58:22"}
+{"current_steps": 177, "total_steps": 1620, "loss": 0.6045, "lr": 7.997910899158342e-05, "epoch": 0.545664739884393, "percentage": 10.93, "elapsed_time": "10:46:59", "remaining_time": "3 days, 15:54:40"}
+{"current_steps": 178, "total_steps": 1620, "loss": 0.5974, "lr": 7.997623095996184e-05, "epoch": 0.548747591522158, "percentage": 10.99, "elapsed_time": "10:50:38", "remaining_time": "3 days, 15:50:58"}
+{"current_steps": 179, "total_steps": 1620, "loss": 0.5912, "lr": 7.997316732474911e-05, "epoch": 0.5518304431599229, "percentage": 11.05, "elapsed_time": "10:54:18", "remaining_time": "3 days, 15:47:18"}
+{"current_steps": 180, "total_steps": 1620, "loss": 0.5974, "lr": 7.996991810016922e-05, "epoch": 0.5549132947976878, "percentage": 11.11, "elapsed_time": "10:57:57", "remaining_time": "3 days, 15:43:37"}
+{"current_steps": 181, "total_steps": 1620, "loss": 0.5951, "lr": 7.996648330130779e-05, "epoch": 0.5579961464354528, "percentage": 11.17, "elapsed_time": "11:01:36", "remaining_time": "3 days, 15:39:55"}
+{"current_steps": 182, "total_steps": 1620, "loss": 0.6022, "lr": 7.996286294411211e-05, "epoch": 0.5610789980732177, "percentage": 11.23, "elapsed_time": "11:05:15", "remaining_time": "3 days, 15:36:14"}
+{"current_steps": 183, "total_steps": 1620, "loss": 0.6044, "lr": 7.995905704539095e-05, "epoch": 0.5641618497109827, "percentage": 11.3, "elapsed_time": "11:08:54", "remaining_time": "3 days, 15:32:34"}
+{"current_steps": 184, "total_steps": 1620, "loss": 0.6017, "lr": 7.99550656228145e-05, "epoch": 0.5672447013487476, "percentage": 11.36, "elapsed_time": "11:12:33", "remaining_time": "3 days, 15:28:52"}
+{"current_steps": 185, "total_steps": 1620, "loss": 0.5976, "lr": 7.995088869491435e-05, "epoch": 0.5703275529865125, "percentage": 11.42, "elapsed_time": "11:16:13", "remaining_time": "3 days, 15:25:19"}
+{"current_steps": 186, "total_steps": 1620, "loss": 0.5962, "lr": 7.994652628108334e-05, "epoch": 0.5734104046242775, "percentage": 11.48, "elapsed_time": "11:19:52", "remaining_time": "3 days, 15:21:38"}
+{"current_steps": 187, "total_steps": 1620, "loss": 0.6042, "lr": 7.994197840157548e-05, "epoch": 0.5764932562620424, "percentage": 11.54, "elapsed_time": "11:23:31", "remaining_time": "3 days, 15:17:53"}
+{"current_steps": 188, "total_steps": 1620, "loss": 0.5965, "lr": 7.993724507750591e-05, "epoch": 0.5795761078998073, "percentage": 11.6, "elapsed_time": "11:27:10", "remaining_time": "3 days, 15:14:10"}
+{"current_steps": 189, "total_steps": 1620, "loss": 0.6167, "lr": 7.993232633085074e-05, "epoch": 0.5826589595375723, "percentage": 11.67, "elapsed_time": "11:30:49", "remaining_time": "3 days, 15:10:28"}
+{"current_steps": 190, "total_steps": 1620, "loss": 0.6013, "lr": 7.992722218444694e-05, "epoch": 0.5857418111753372, "percentage": 11.73, "elapsed_time": "11:34:28", "remaining_time": "3 days, 15:06:48"}
+{"current_steps": 191, "total_steps": 1620, "loss": 0.6004, "lr": 7.992193266199231e-05, "epoch": 0.5888246628131021, "percentage": 11.79, "elapsed_time": "11:38:07", "remaining_time": "3 days, 15:03:08"}
+{"current_steps": 192, "total_steps": 1620, "loss": 0.6132, "lr": 7.991645778804529e-05, "epoch": 0.5919075144508671, "percentage": 11.85, "elapsed_time": "11:41:46", "remaining_time": "3 days, 14:59:25"}
+{"current_steps": 193, "total_steps": 1620, "loss": 0.6026, "lr": 7.99107975880249e-05, "epoch": 0.594990366088632, "percentage": 11.91, "elapsed_time": "11:45:25", "remaining_time": "3 days, 14:55:44"}
+{"current_steps": 194, "total_steps": 1620, "loss": 0.603, "lr": 7.99049520882106e-05, "epoch": 0.5980732177263969, "percentage": 11.98, "elapsed_time": "11:49:04", "remaining_time": "3 days, 14:52:06"}
+{"current_steps": 195, "total_steps": 1620, "loss": 0.6045, "lr": 7.989892131574214e-05, "epoch": 0.6011560693641619, "percentage": 12.04, "elapsed_time": "11:52:43", "remaining_time": "3 days, 14:48:24"}
+{"current_steps": 196, "total_steps": 1620, "loss": 0.5993, "lr": 7.989270529861949e-05, "epoch": 0.6042389210019268, "percentage": 12.1, "elapsed_time": "11:56:23", "remaining_time": "3 days, 14:44:44"}
+{"current_steps": 197, "total_steps": 1620, "loss": 0.5979, "lr": 7.98863040657027e-05, "epoch": 0.6073217726396917, "percentage": 12.16, "elapsed_time": "12:00:01", "remaining_time": "3 days, 14:41:02"}
+{"current_steps": 198, "total_steps": 1620, "loss": 0.6005, "lr": 7.987971764671168e-05, "epoch": 0.6104046242774567, "percentage": 12.22, "elapsed_time": "12:03:40", "remaining_time": "3 days, 14:37:21"}
+{"current_steps": 199, "total_steps": 1620, "loss": 0.5967, "lr": 7.987294607222624e-05, "epoch": 0.6134874759152216, "percentage": 12.28, "elapsed_time": "12:07:19", "remaining_time": "3 days, 14:33:39"}
+{"current_steps": 200, "total_steps": 1620, "loss": 0.6054, "lr": 7.986598937368572e-05, "epoch": 0.6165703275529865, "percentage": 12.35, "elapsed_time": "12:10:58", "remaining_time": "3 days, 14:29:56"}
+{"current_steps": 201, "total_steps": 1620, "loss": 0.5972, "lr": 7.985884758338903e-05, "epoch": 0.6196531791907515, "percentage": 12.41, "elapsed_time": "12:14:37", "remaining_time": "3 days, 14:26:17"}
+{"current_steps": 202, "total_steps": 1620, "loss": 0.5943, "lr": 7.985152073449444e-05, "epoch": 0.6227360308285164, "percentage": 12.47, "elapsed_time": "12:18:17", "remaining_time": "3 days, 14:22:36"}
+{"current_steps": 203, "total_steps": 1620, "loss": 0.5994, "lr": 7.98440088610194e-05, "epoch": 0.6258188824662813, "percentage": 12.53, "elapsed_time": "12:21:55", "remaining_time": "3 days, 14:18:54"}
+{"current_steps": 204, "total_steps": 1620, "loss": 0.5945, "lr": 7.983631199784038e-05, "epoch": 0.6289017341040463, "percentage": 12.59, "elapsed_time": "12:25:34", "remaining_time": "3 days, 14:15:12"}
+{"current_steps": 205, "total_steps": 1620, "loss": 0.5901, "lr": 7.982843018069277e-05, "epoch": 0.6319845857418112, "percentage": 12.65, "elapsed_time": "12:29:14", "remaining_time": "3 days, 14:11:33"}
+{"current_steps": 206, "total_steps": 1620, "loss": 0.5909, "lr": 7.982036344617065e-05, "epoch": 0.6350674373795762, "percentage": 12.72, "elapsed_time": "12:32:53", "remaining_time": "3 days, 14:07:53"}
+{"current_steps": 207, "total_steps": 1620, "loss": 0.589, "lr": 7.981211183172663e-05, "epoch": 0.638150289017341, "percentage": 12.78, "elapsed_time": "12:36:32", "remaining_time": "3 days, 14:04:15"}
+{"current_steps": 208, "total_steps": 1620, "loss": 0.588, "lr": 7.980367537567175e-05, "epoch": 0.641233140655106, "percentage": 12.84, "elapsed_time": "12:40:11", "remaining_time": "3 days, 14:00:35"}
+{"current_steps": 209, "total_steps": 1620, "loss": 0.5895, "lr": 7.979505411717516e-05, "epoch": 0.644315992292871, "percentage": 12.9, "elapsed_time": "12:43:51", "remaining_time": "3 days, 13:56:55"}
+{"current_steps": 210, "total_steps": 1620, "loss": 0.5906, "lr": 7.978624809626407e-05, "epoch": 0.6473988439306358, "percentage": 12.96, "elapsed_time": "12:47:30", "remaining_time": "3 days, 13:53:14"}
+{"current_steps": 211, "total_steps": 1620, "loss": 0.5866, "lr": 7.977725735382349e-05, "epoch": 0.6504816955684007, "percentage": 13.02, "elapsed_time": "12:51:09", "remaining_time": "3 days, 13:49:37"}
+{"current_steps": 212, "total_steps": 1620, "loss": 0.5868, "lr": 7.976808193159611e-05, "epoch": 0.6535645472061657, "percentage": 13.09, "elapsed_time": "12:54:49", "remaining_time": "3 days, 13:45:57"}
+{"current_steps": 213, "total_steps": 1620, "loss": 0.5818, "lr": 7.9758721872182e-05, "epoch": 0.6566473988439306, "percentage": 13.15, "elapsed_time": "12:58:28", "remaining_time": "3 days, 13:42:18"}
+{"current_steps": 214, "total_steps": 1620, "loss": 0.5868, "lr": 7.97491772190385e-05, "epoch": 0.6597302504816955, "percentage": 13.21, "elapsed_time": "13:02:07", "remaining_time": "3 days, 13:38:36"}
+{"current_steps": 215, "total_steps": 1620, "loss": 0.5816, "lr": 7.973944801648001e-05, "epoch": 0.6628131021194605, "percentage": 13.27, "elapsed_time": "13:05:46", "remaining_time": "3 days, 13:34:57"}
+{"current_steps": 216, "total_steps": 1620, "loss": 0.5855, "lr": 7.972953430967773e-05, "epoch": 0.6658959537572254, "percentage": 13.33, "elapsed_time": "13:09:25", "remaining_time": "3 days, 13:31:15"}
+{"current_steps": 217, "total_steps": 1620, "loss": 0.5956, "lr": 7.971943614465949e-05, "epoch": 0.6689788053949903, "percentage": 13.4, "elapsed_time": "13:13:04", "remaining_time": "3 days, 13:27:35"}
+{"current_steps": 218, "total_steps": 1620, "loss": 0.582, "lr": 7.970915356830956e-05, "epoch": 0.6720616570327553, "percentage": 13.46, "elapsed_time": "13:16:43", "remaining_time": "3 days, 13:23:55"}
+{"current_steps": 219, "total_steps": 1620, "loss": 0.5825, "lr": 7.969868662836839e-05, "epoch": 0.6751445086705202, "percentage": 13.52, "elapsed_time": "13:20:23", "remaining_time": "3 days, 13:20:16"}
+{"current_steps": 220, "total_steps": 1620, "loss": 0.5843, "lr": 7.968803537343239e-05, "epoch": 0.6782273603082851, "percentage": 13.58, "elapsed_time": "13:24:02", "remaining_time": "3 days, 13:16:38"}
+{"current_steps": 221, "total_steps": 1620, "loss": 0.5999, "lr": 7.967719985295372e-05, "epoch": 0.6813102119460501, "percentage": 13.64, "elapsed_time": "13:27:41", "remaining_time": "3 days, 13:12:56"}
+{"current_steps": 222, "total_steps": 1620, "loss": 0.5968, "lr": 7.966618011724004e-05, "epoch": 0.684393063583815, "percentage": 13.7, "elapsed_time": "13:31:20", "remaining_time": "3 days, 13:09:16"}
+{"current_steps": 223, "total_steps": 1620, "loss": 0.5916, "lr": 7.965497621745437e-05, "epoch": 0.6874759152215799, "percentage": 13.77, "elapsed_time": "13:35:00", "remaining_time": "3 days, 13:05:38"}
+{"current_steps": 224, "total_steps": 1620, "loss": 0.5996, "lr": 7.964358820561469e-05, "epoch": 0.6905587668593449, "percentage": 13.83, "elapsed_time": "13:38:39", "remaining_time": "3 days, 13:02:00"}
+{"current_steps": 225, "total_steps": 1620, "loss": 0.5916, "lr": 7.963201613459381e-05, "epoch": 0.6936416184971098, "percentage": 13.89, "elapsed_time": "13:42:18", "remaining_time": "3 days, 12:58:19"}
+{"current_steps": 226, "total_steps": 1620, "loss": 0.5854, "lr": 7.962026005811914e-05, "epoch": 0.6967244701348747, "percentage": 13.95, "elapsed_time": "13:45:57", "remaining_time": "3 days, 12:54:40"}
+{"current_steps": 227, "total_steps": 1620, "loss": 0.5921, "lr": 7.96083200307723e-05, "epoch": 0.6998073217726397, "percentage": 14.01, "elapsed_time": "13:49:37", "remaining_time": "3 days, 12:51:02"}
+{"current_steps": 228, "total_steps": 1620, "loss": 0.5874, "lr": 7.959619610798909e-05, "epoch": 0.7028901734104046, "percentage": 14.07, "elapsed_time": "13:53:16", "remaining_time": "3 days, 12:47:21"}
+{"current_steps": 229, "total_steps": 1620, "loss": 0.5826, "lr": 7.958388834605901e-05, "epoch": 0.7059730250481696, "percentage": 14.14, "elapsed_time": "13:56:55", "remaining_time": "3 days, 12:43:43"}
+{"current_steps": 230, "total_steps": 1620, "loss": 0.5865, "lr": 7.957139680212518e-05, "epoch": 0.7090558766859345, "percentage": 14.2, "elapsed_time": "14:00:35", "remaining_time": "3 days, 12:40:04"}
+{"current_steps": 231, "total_steps": 1620, "loss": 0.5779, "lr": 7.95587215341839e-05, "epoch": 0.7121387283236994, "percentage": 14.26, "elapsed_time": "14:04:14", "remaining_time": "3 days, 12:36:24"}
+{"current_steps": 232, "total_steps": 1620, "loss": 0.5852, "lr": 7.954586260108454e-05, "epoch": 0.7152215799614644, "percentage": 14.32, "elapsed_time": "14:07:53", "remaining_time": "3 days, 12:32:42"}
+{"current_steps": 233, "total_steps": 1620, "loss": 0.5825, "lr": 7.953282006252919e-05, "epoch": 0.7183044315992293, "percentage": 14.38, "elapsed_time": "14:11:32", "remaining_time": "3 days, 12:29:02"}
+{"current_steps": 234, "total_steps": 1620, "loss": 0.5812, "lr": 7.951959397907237e-05, "epoch": 0.7213872832369942, "percentage": 14.44, "elapsed_time": "14:15:11", "remaining_time": "3 days, 12:25:21"}
+{"current_steps": 235, "total_steps": 1620, "loss": 0.5838, "lr": 7.950618441212078e-05, "epoch": 0.7244701348747592, "percentage": 14.51, "elapsed_time": "14:18:50", "remaining_time": "3 days, 12:21:42"}
+{"current_steps": 236, "total_steps": 1620, "loss": 0.583, "lr": 7.949259142393305e-05, "epoch": 0.7275529865125241, "percentage": 14.57, "elapsed_time": "14:22:30", "remaining_time": "3 days, 12:18:03"}
+{"current_steps": 237, "total_steps": 1620, "loss": 0.5817, "lr": 7.947881507761932e-05, "epoch": 0.730635838150289, "percentage": 14.63, "elapsed_time": "14:26:08", "remaining_time": "3 days, 12:14:22"}
+{"current_steps": 238, "total_steps": 1620, "loss": 0.5801, "lr": 7.946485543714108e-05, "epoch": 0.733718689788054, "percentage": 14.69, "elapsed_time": "14:29:48", "remaining_time": "3 days, 12:10:43"}
+{"current_steps": 239, "total_steps": 1620, "loss": 0.5796, "lr": 7.945071256731087e-05, "epoch": 0.7368015414258189, "percentage": 14.75, "elapsed_time": "14:33:27", "remaining_time": "3 days, 12:07:05"}
+{"current_steps": 240, "total_steps": 1620, "loss": 0.5747, "lr": 7.943638653379186e-05, "epoch": 0.7398843930635838, "percentage": 14.81, "elapsed_time": "14:37:07", "remaining_time": "3 days, 12:03:27"}
+{"current_steps": 241, "total_steps": 1620, "loss": 0.5795, "lr": 7.942187740309768e-05, "epoch": 0.7429672447013488, "percentage": 14.88, "elapsed_time": "14:40:46", "remaining_time": "3 days, 11:59:48"}
+{"current_steps": 242, "total_steps": 1620, "loss": 0.5773, "lr": 7.940718524259201e-05, "epoch": 0.7460500963391137, "percentage": 14.94, "elapsed_time": "14:44:26", "remaining_time": "3 days, 11:56:10"}
+{"current_steps": 243, "total_steps": 1620, "loss": 0.5736, "lr": 7.939231012048833e-05, "epoch": 0.7491329479768786, "percentage": 15.0, "elapsed_time": "14:48:05", "remaining_time": "3 days, 11:52:28"}
+{"current_steps": 244, "total_steps": 1620, "loss": 0.5845, "lr": 7.937725210584958e-05, "epoch": 0.7522157996146436, "percentage": 15.06, "elapsed_time": "14:51:44", "remaining_time": "3 days, 11:48:47"}
+{"current_steps": 245, "total_steps": 1620, "loss": 0.5776, "lr": 7.936201126858786e-05, "epoch": 0.7552986512524085, "percentage": 15.12, "elapsed_time": "14:55:23", "remaining_time": "3 days, 11:45:07"}
+{"current_steps": 246, "total_steps": 1620, "loss": 0.5803, "lr": 7.934658767946405e-05, "epoch": 0.7583815028901734, "percentage": 15.19, "elapsed_time": "14:59:02", "remaining_time": "3 days, 11:41:28"}
+{"current_steps": 247, "total_steps": 1620, "loss": 0.5784, "lr": 7.933098141008754e-05, "epoch": 0.7614643545279384, "percentage": 15.25, "elapsed_time": "15:02:42", "remaining_time": "3 days, 11:37:52"}
+{"current_steps": 248, "total_steps": 1620, "loss": 0.5837, "lr": 7.93151925329159e-05, "epoch": 0.7645472061657033, "percentage": 15.31, "elapsed_time": "15:06:21", "remaining_time": "3 days, 11:34:14"}
+{"current_steps": 249, "total_steps": 1620, "loss": 0.5825, "lr": 7.92992211212545e-05, "epoch": 0.7676300578034682, "percentage": 15.37, "elapsed_time": "15:10:01", "remaining_time": "3 days, 11:30:35"}
+{"current_steps": 250, "total_steps": 1620, "loss": 0.5872, "lr": 7.928306724925615e-05, "epoch": 0.7707129094412332, "percentage": 15.43, "elapsed_time": "15:13:40", "remaining_time": "3 days, 11:26:56"}
+{"current_steps": 251, "total_steps": 1620, "loss": 0.5899, "lr": 7.926673099192085e-05, "epoch": 0.7737957610789981, "percentage": 15.49, "elapsed_time": "15:17:19", "remaining_time": "3 days, 11:23:16"}
+{"current_steps": 252, "total_steps": 1620, "loss": 0.5827, "lr": 7.925021242509539e-05, "epoch": 0.776878612716763, "percentage": 15.56, "elapsed_time": "15:20:58", "remaining_time": "3 days, 11:19:37"}
+{"current_steps": 253, "total_steps": 1620, "loss": 0.5861, "lr": 7.923351162547295e-05, "epoch": 0.779961464354528, "percentage": 15.62, "elapsed_time": "15:24:38", "remaining_time": "3 days, 11:15:58"}
+{"current_steps": 254, "total_steps": 1620, "loss": 0.5738, "lr": 7.921662867059285e-05, "epoch": 0.7830443159922928, "percentage": 15.68, "elapsed_time": "15:28:17", "remaining_time": "3 days, 11:12:18"}
+{"current_steps": 255, "total_steps": 1620, "loss": 0.5788, "lr": 7.919956363884005e-05, "epoch": 0.7861271676300579, "percentage": 15.74, "elapsed_time": "15:31:56", "remaining_time": "3 days, 11:08:38"}
+{"current_steps": 256, "total_steps": 1620, "loss": 0.5809, "lr": 7.918231660944493e-05, "epoch": 0.7892100192678227, "percentage": 15.8, "elapsed_time": "15:35:36", "remaining_time": "3 days, 11:05:02"}
+{"current_steps": 257, "total_steps": 1620, "loss": 0.5785, "lr": 7.916488766248285e-05, "epoch": 0.7922928709055876, "percentage": 15.86, "elapsed_time": "15:39:16", "remaining_time": "3 days, 11:01:24"}
+{"current_steps": 258, "total_steps": 1620, "loss": 0.5748, "lr": 7.914727687887377e-05, "epoch": 0.7953757225433526, "percentage": 15.93, "elapsed_time": "15:42:55", "remaining_time": "3 days, 10:57:44"}
+{"current_steps": 259, "total_steps": 1620, "loss": 0.5761, "lr": 7.912948434038188e-05, "epoch": 0.7984585741811175, "percentage": 15.99, "elapsed_time": "15:46:34", "remaining_time": "3 days, 10:54:05"}
+{"current_steps": 260, "total_steps": 1620, "loss": 0.577, "lr": 7.911151012961526e-05, "epoch": 0.8015414258188824, "percentage": 16.05, "elapsed_time": "15:50:13", "remaining_time": "3 days, 10:50:26"}
+{"current_steps": 261, "total_steps": 1620, "loss": 0.5751, "lr": 7.909335433002543e-05, "epoch": 0.8046242774566474, "percentage": 16.11, "elapsed_time": "15:53:53", "remaining_time": "3 days, 10:46:47"}
+{"current_steps": 262, "total_steps": 1620, "loss": 0.5775, "lr": 7.907501702590702e-05, "epoch": 0.8077071290944123, "percentage": 16.17, "elapsed_time": "15:57:32", "remaining_time": "3 days, 10:43:08"}
+{"current_steps": 263, "total_steps": 1620, "loss": 0.5715, "lr": 7.905649830239739e-05, "epoch": 0.8107899807321772, "percentage": 16.23, "elapsed_time": "16:01:11", "remaining_time": "3 days, 10:39:29"}
+{"current_steps": 264, "total_steps": 1620, "loss": 0.5735, "lr": 7.903779824547614e-05, "epoch": 0.8138728323699422, "percentage": 16.3, "elapsed_time": "16:04:51", "remaining_time": "3 days, 10:35:51"}
+{"current_steps": 265, "total_steps": 1620, "loss": 0.579, "lr": 7.901891694196483e-05, "epoch": 0.8169556840077071, "percentage": 16.36, "elapsed_time": "16:08:30", "remaining_time": "3 days, 10:32:11"}
+{"current_steps": 266, "total_steps": 1620, "loss": 0.5729, "lr": 7.899985447952648e-05, "epoch": 0.820038535645472, "percentage": 16.42, "elapsed_time": "16:12:09", "remaining_time": "3 days, 10:28:30"}
+{"current_steps": 267, "total_steps": 1620, "loss": 0.5753, "lr": 7.898061094666521e-05, "epoch": 0.823121387283237, "percentage": 16.48, "elapsed_time": "16:15:49", "remaining_time": "3 days, 10:24:52"}
+{"current_steps": 268, "total_steps": 1620, "loss": 0.5785, "lr": 7.896118643272584e-05, "epoch": 0.8262042389210019, "percentage": 16.54, "elapsed_time": "16:19:28", "remaining_time": "3 days, 10:21:12"}
+{"current_steps": 269, "total_steps": 1620, "loss": 0.5714, "lr": 7.894158102789344e-05, "epoch": 0.8292870905587668, "percentage": 16.6, "elapsed_time": "16:23:07", "remaining_time": "3 days, 10:17:32"}
+{"current_steps": 270, "total_steps": 1620, "loss": 0.5842, "lr": 7.892179482319297e-05, "epoch": 0.8323699421965318, "percentage": 16.67, "elapsed_time": "16:26:46", "remaining_time": "3 days, 10:13:52"}
+{"current_steps": 271, "total_steps": 1620, "loss": 0.5782, "lr": 7.890182791048875e-05, "epoch": 0.8354527938342967, "percentage": 16.73, "elapsed_time": "16:30:25", "remaining_time": "3 days, 10:10:12"}
+{"current_steps": 272, "total_steps": 1620, "loss": 0.5907, "lr": 7.888168038248414e-05, "epoch": 0.8385356454720616, "percentage": 16.79, "elapsed_time": "16:34:05", "remaining_time": "3 days, 10:06:33"}
+{"current_steps": 273, "total_steps": 1620, "loss": 0.5855, "lr": 7.886135233272108e-05, "epoch": 0.8416184971098266, "percentage": 16.85, "elapsed_time": "16:37:44", "remaining_time": "3 days, 10:02:55"}
+{"current_steps": 274, "total_steps": 1620, "loss": 0.5804, "lr": 7.88408438555796e-05, "epoch": 0.8447013487475915, "percentage": 16.91, "elapsed_time": "16:41:25", "remaining_time": "3 days, 9:59:25"}
+{"current_steps": 275, "total_steps": 1620, "loss": 0.5835, "lr": 7.882015504627749e-05, "epoch": 0.8477842003853564, "percentage": 16.98, "elapsed_time": "16:45:06", "remaining_time": "3 days, 9:55:55"}
+{"current_steps": 276, "total_steps": 1620, "loss": 0.5725, "lr": 7.879928600086974e-05, "epoch": 0.8508670520231214, "percentage": 17.04, "elapsed_time": "16:48:46", "remaining_time": "3 days, 9:52:15"}
+{"current_steps": 277, "total_steps": 1620, "loss": 0.5735, "lr": 7.87782368162482e-05, "epoch": 0.8539499036608863, "percentage": 17.1, "elapsed_time": "16:52:25", "remaining_time": "3 days, 9:48:35"}
+{"current_steps": 278, "total_steps": 1620, "loss": 0.5748, "lr": 7.875700759014099e-05, "epoch": 0.8570327552986513, "percentage": 17.16, "elapsed_time": "16:56:04", "remaining_time": "3 days, 9:44:56"}
+{"current_steps": 279, "total_steps": 1620, "loss": 0.5754, "lr": 7.873559842111225e-05, "epoch": 0.8601156069364162, "percentage": 17.22, "elapsed_time": "16:59:43", "remaining_time": "3 days, 9:41:15"}
+{"current_steps": 280, "total_steps": 1620, "loss": 0.5697, "lr": 7.871400940856147e-05, "epoch": 0.8631984585741811, "percentage": 17.28, "elapsed_time": "17:03:22", "remaining_time": "3 days, 9:37:36"}
+{"current_steps": 281, "total_steps": 1620, "loss": 0.5677, "lr": 7.869224065272321e-05, "epoch": 0.8662813102119461, "percentage": 17.35, "elapsed_time": "17:07:01", "remaining_time": "3 days, 9:33:55"}
+{"current_steps": 282, "total_steps": 1620, "loss": 0.5725, "lr": 7.867029225466649e-05, "epoch": 0.869364161849711, "percentage": 17.41, "elapsed_time": "17:10:40", "remaining_time": "3 days, 9:30:15"}
+{"current_steps": 283, "total_steps": 1620, "loss": 0.5664, "lr": 7.864816431629439e-05, "epoch": 0.8724470134874759, "percentage": 17.47, "elapsed_time": "17:14:19", "remaining_time": "3 days, 9:26:34"}
+{"current_steps": 284, "total_steps": 1620, "loss": 0.5693, "lr": 7.862585694034358e-05, "epoch": 0.8755298651252409, "percentage": 17.53, "elapsed_time": "17:17:59", "remaining_time": "3 days, 9:22:55"}
+{"current_steps": 285, "total_steps": 1620, "loss": 0.5681, "lr": 7.860337023038387e-05, "epoch": 0.8786127167630058, "percentage": 17.59, "elapsed_time": "17:21:38", "remaining_time": "3 days, 9:19:14"}
+{"current_steps": 286, "total_steps": 1620, "loss": 0.5701, "lr": 7.858070429081761e-05, "epoch": 0.8816955684007707, "percentage": 17.65, "elapsed_time": "17:25:17", "remaining_time": "3 days, 9:15:34"}
+{"current_steps": 287, "total_steps": 1620, "loss": 0.561, "lr": 7.855785922687933e-05, "epoch": 0.8847784200385357, "percentage": 17.72, "elapsed_time": "17:28:56", "remaining_time": "3 days, 9:11:54"}
+{"current_steps": 288, "total_steps": 1620, "loss": 0.5652, "lr": 7.853483514463521e-05, "epoch": 0.8878612716763006, "percentage": 17.78, "elapsed_time": "17:32:35", "remaining_time": "3 days, 9:08:14"}
+{"current_steps": 289, "total_steps": 1620, "loss": 0.564, "lr": 7.851163215098261e-05, "epoch": 0.8909441233140655, "percentage": 17.84, "elapsed_time": "17:36:14", "remaining_time": "3 days, 9:04:35"}
+{"current_steps": 290, "total_steps": 1620, "loss": 0.5733, "lr": 7.848825035364947e-05, "epoch": 0.8940269749518305, "percentage": 17.9, "elapsed_time": "17:39:54", "remaining_time": "3 days, 9:00:58"}
+{"current_steps": 291, "total_steps": 1620, "loss": 0.5647, "lr": 7.846468986119397e-05, "epoch": 0.8971098265895954, "percentage": 17.96, "elapsed_time": "17:43:33", "remaining_time": "3 days, 8:57:18"}
+{"current_steps": 292, "total_steps": 1620, "loss": 0.5667, "lr": 7.84409507830039e-05, "epoch": 0.9001926782273603, "percentage": 18.02, "elapsed_time": "17:47:13", "remaining_time": "3 days, 8:53:40"}
+{"current_steps": 293, "total_steps": 1620, "loss": 0.5704, "lr": 7.841703322929622e-05, "epoch": 0.9032755298651253, "percentage": 18.09, "elapsed_time": "17:50:52", "remaining_time": "3 days, 8:50:01"}
+{"current_steps": 294, "total_steps": 1620, "loss": 0.564, "lr": 7.839293731111648e-05, "epoch": 0.9063583815028902, "percentage": 18.15, "elapsed_time": "17:54:31", "remaining_time": "3 days, 8:46:21"}
+{"current_steps": 295, "total_steps": 1620, "loss": 0.5727, "lr": 7.836866314033842e-05, "epoch": 0.9094412331406551, "percentage": 18.21, "elapsed_time": "17:58:11", "remaining_time": "3 days, 8:42:42"}
+{"current_steps": 296, "total_steps": 1620, "loss": 0.5669, "lr": 7.834421082966332e-05, "epoch": 0.9125240847784201, "percentage": 18.27, "elapsed_time": "18:01:50", "remaining_time": "3 days, 8:39:01"}
+{"current_steps": 297, "total_steps": 1620, "loss": 0.5664, "lr": 7.831958049261956e-05, "epoch": 0.915606936416185, "percentage": 18.33, "elapsed_time": "18:05:29", "remaining_time": "3 days, 8:35:22"}
+{"current_steps": 298, "total_steps": 1620, "loss": 0.5692, "lr": 7.829477224356207e-05, "epoch": 0.9186897880539499, "percentage": 18.4, "elapsed_time": "18:09:08", "remaining_time": "3 days, 8:31:42"}
+{"current_steps": 299, "total_steps": 1620, "loss": 0.5617, "lr": 7.82697861976718e-05, "epoch": 0.9217726396917149, "percentage": 18.46, "elapsed_time": "18:12:47", "remaining_time": "3 days, 8:28:02"}
+{"current_steps": 300, "total_steps": 1620, "loss": 0.5665, "lr": 7.82446224709552e-05, "epoch": 0.9248554913294798, "percentage": 18.52, "elapsed_time": "18:16:26", "remaining_time": "3 days, 8:24:22"}
+{"current_steps": 301, "total_steps": 1620, "loss": 0.5637, "lr": 7.82192811802436e-05, "epoch": 0.9279383429672448, "percentage": 18.58, "elapsed_time": "18:20:06", "remaining_time": "3 days, 8:20:44"}
+{"current_steps": 302, "total_steps": 1620, "loss": 0.564, "lr": 7.81937624431928e-05, "epoch": 0.9310211946050096, "percentage": 18.64, "elapsed_time": "18:23:45", "remaining_time": "3 days, 8:17:05"}
+{"current_steps": 303, "total_steps": 1620, "loss": 0.5626, "lr": 7.816806637828246e-05, "epoch": 0.9341040462427745, "percentage": 18.7, "elapsed_time": "18:27:25", "remaining_time": "3 days, 8:13:26"}
+{"current_steps": 304, "total_steps": 1620, "loss": 0.5581, "lr": 7.814219310481547e-05, "epoch": 0.9371868978805395, "percentage": 18.77, "elapsed_time": "18:31:04", "remaining_time": "3 days, 8:09:47"}
+{"current_steps": 305, "total_steps": 1620, "loss": 0.5604, "lr": 7.811614274291757e-05, "epoch": 0.9402697495183044, "percentage": 18.83, "elapsed_time": "18:34:43", "remaining_time": "3 days, 8:06:07"}
+{"current_steps": 306, "total_steps": 1620, "loss": 0.5589, "lr": 7.808991541353662e-05, "epoch": 0.9433526011560693, "percentage": 18.89, "elapsed_time": "18:38:23", "remaining_time": "3 days, 8:02:29"}
+{"current_steps": 307, "total_steps": 1620, "loss": 0.5637, "lr": 7.806351123844215e-05, "epoch": 0.9464354527938343, "percentage": 18.95, "elapsed_time": "18:42:02", "remaining_time": "3 days, 7:58:51"}
+{"current_steps": 308, "total_steps": 1620, "loss": 0.5607, "lr": 7.803693034022475e-05, "epoch": 0.9495183044315992, "percentage": 19.01, "elapsed_time": "18:45:42", "remaining_time": "3 days, 7:55:12"}
+{"current_steps": 309, "total_steps": 1620, "loss": 0.559, "lr": 7.801017284229552e-05, "epoch": 0.9526011560693641, "percentage": 19.07, "elapsed_time": "18:49:21", "remaining_time": "3 days, 7:51:33"}
+{"current_steps": 310, "total_steps": 1620, "loss": 0.5559, "lr": 7.798323886888545e-05, "epoch": 0.9556840077071291, "percentage": 19.14, "elapsed_time": "18:53:00", "remaining_time": "3 days, 7:47:53"}
+{"current_steps": 311, "total_steps": 1620, "loss": 0.5569, "lr": 7.795612854504493e-05, "epoch": 0.958766859344894, "percentage": 19.2, "elapsed_time": "18:56:39", "remaining_time": "3 days, 7:44:12"}
+{"current_steps": 312, "total_steps": 1620, "loss": 0.5574, "lr": 7.792884199664307e-05, "epoch": 0.9618497109826589, "percentage": 19.26, "elapsed_time": "19:00:19", "remaining_time": "3 days, 7:40:33"}
+{"current_steps": 313, "total_steps": 1620, "loss": 0.5621, "lr": 7.790137935036718e-05, "epoch": 0.9649325626204239, "percentage": 19.32, "elapsed_time": "19:03:58", "remaining_time": "3 days, 7:36:55"}
+{"current_steps": 314, "total_steps": 1620, "loss": 0.5544, "lr": 7.787374073372221e-05, "epoch": 0.9680154142581888, "percentage": 19.38, "elapsed_time": "19:07:38", "remaining_time": "3 days, 7:33:17"}
+{"current_steps": 315, "total_steps": 1620, "loss": 0.5562, "lr": 7.784592627503004e-05, "epoch": 0.9710982658959537, "percentage": 19.44, "elapsed_time": "19:11:17", "remaining_time": "3 days, 7:29:38"}
+{"current_steps": 316, "total_steps": 1620, "loss": 0.5564, "lr": 7.781793610342897e-05, "epoch": 0.9741811175337187, "percentage": 19.51, "elapsed_time": "19:14:56", "remaining_time": "3 days, 7:25:58"}
+{"current_steps": 317, "total_steps": 1620, "loss": 0.5571, "lr": 7.77897703488732e-05, "epoch": 0.9772639691714836, "percentage": 19.57, "elapsed_time": "19:18:35", "remaining_time": "3 days, 7:22:17"}
+{"current_steps": 318, "total_steps": 1620, "loss": 0.5625, "lr": 7.7761429142132e-05, "epoch": 0.9803468208092485, "percentage": 19.63, "elapsed_time": "19:22:15", "remaining_time": "3 days, 7:18:38"}
+{"current_steps": 319, "total_steps": 1620, "loss": 0.5589, "lr": 7.773291261478936e-05, "epoch": 0.9834296724470135, "percentage": 19.69, "elapsed_time": "19:25:54", "remaining_time": "3 days, 7:15:00"}
+{"current_steps": 320, "total_steps": 1620, "loss": 0.5599, "lr": 7.770422089924315e-05, "epoch": 0.9865125240847784, "percentage": 19.75, "elapsed_time": "19:29:33", "remaining_time": "3 days, 7:11:21"}
+{"current_steps": 321, "total_steps": 1620, "loss": 0.5617, "lr": 7.767535412870469e-05, "epoch": 0.9895953757225433, "percentage": 19.81, "elapsed_time": "19:33:13", "remaining_time": "3 days, 7:07:42"}
+{"current_steps": 322, "total_steps": 1620, "loss": 0.5599, "lr": 7.764631243719804e-05, "epoch": 0.9926782273603083, "percentage": 19.88, "elapsed_time": "19:36:52", "remaining_time": "3 days, 7:04:02"}
+{"current_steps": 323, "total_steps": 1620, "loss": 0.5575, "lr": 7.761709595955936e-05, "epoch": 0.9957610789980732, "percentage": 19.94, "elapsed_time": "19:40:31", "remaining_time": "3 days, 7:00:23"}
+{"current_steps": 324, "total_steps": 1620, "loss": 0.5599, "lr": 7.758770483143634e-05, "epoch": 0.9988439306358381, "percentage": 20.0, "elapsed_time": "19:44:10", "remaining_time": "3 days, 6:56:43"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b85a45df49aa56489a83518068e562a3a16ba235fa92348f8359bd66e2e7f8c
+size 7160