Training in progress, epoch 1

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94516ff897ea27a2af34c92f65a7c779e88bd382378b8f7da5093dd05bb1670
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2b80888850c88fa97f393e5d0643efcf5ebe6b5a319cb6d58ff7c2508c7223
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e1ce10019c53e34ff4551b461beb88f2e069526663fb096884c42fa53d29e6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939a7a8d22c9b1b1bb802282c9c14657bbc27936ebacc1db8e3854fbfee84f58
+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 +1,398 @@
+{"current_steps": 1, "total_steps": 1955, "loss": 0.8762, "lr": 2.0408163265306121e-07, "epoch": 0.0025575447570332483, "percentage": 0.05, "elapsed_time": "0:00:33", "remaining_time": "18:03:33"}
+{"current_steps": 2, "total_steps": 1955, "loss": 0.8699, "lr": 4.0816326530612243e-07, "epoch": 0.005115089514066497, "percentage": 0.1, "elapsed_time": "0:00:51", "remaining_time": "13:57:51"}
+{"current_steps": 3, "total_steps": 1955, "loss": 0.9018, "lr": 6.122448979591837e-07, "epoch": 0.0076726342710997444, "percentage": 0.15, "elapsed_time": "0:01:15", "remaining_time": "13:43:50"}
+{"current_steps": 4, "total_steps": 1955, "loss": 0.8466, "lr": 8.163265306122449e-07, "epoch": 0.010230179028132993, "percentage": 0.2, "elapsed_time": "0:01:38", "remaining_time": "13:17:16"}
+{"current_steps": 5, "total_steps": 1955, "loss": 0.8952, "lr": 1.0204081632653063e-06, "epoch": 0.01278772378516624, "percentage": 0.26, "elapsed_time": "0:02:01", "remaining_time": "13:08:49"}
+{"current_steps": 6, "total_steps": 1955, "loss": 0.8882, "lr": 1.2244897959183673e-06, "epoch": 0.015345268542199489, "percentage": 0.31, "elapsed_time": "0:02:21", "remaining_time": "12:43:51"}
+{"current_steps": 7, "total_steps": 1955, "loss": 0.8517, "lr": 1.4285714285714286e-06, "epoch": 0.017902813299232736, "percentage": 0.36, "elapsed_time": "0:02:44", "remaining_time": "12:41:31"}
+{"current_steps": 8, "total_steps": 1955, "loss": 0.8213, "lr": 1.6326530612244897e-06, "epoch": 0.020460358056265986, "percentage": 0.41, "elapsed_time": "0:03:05", "remaining_time": "12:33:12"}
+{"current_steps": 9, "total_steps": 1955, "loss": 0.8375, "lr": 1.8367346938775512e-06, "epoch": 0.023017902813299233, "percentage": 0.46, "elapsed_time": "0:03:25", "remaining_time": "12:22:15"}
+{"current_steps": 10, "total_steps": 1955, "loss": 0.8227, "lr": 2.0408163265306125e-06, "epoch": 0.02557544757033248, "percentage": 0.51, "elapsed_time": "0:03:46", "remaining_time": "12:14:46"}
+{"current_steps": 11, "total_steps": 1955, "loss": 0.7821, "lr": 2.244897959183674e-06, "epoch": 0.028132992327365727, "percentage": 0.56, "elapsed_time": "0:04:09", "remaining_time": "12:14:41"}
+{"current_steps": 12, "total_steps": 1955, "loss": 0.8069, "lr": 2.4489795918367347e-06, "epoch": 0.030690537084398978, "percentage": 0.61, "elapsed_time": "0:04:33", "remaining_time": "12:16:49"}
+{"current_steps": 13, "total_steps": 1955, "loss": 0.7687, "lr": 2.6530612244897964e-06, "epoch": 0.03324808184143223, "percentage": 0.66, "elapsed_time": "0:04:55", "remaining_time": "12:15:34"}
+{"current_steps": 14, "total_steps": 1955, "loss": 0.7481, "lr": 2.8571428571428573e-06, "epoch": 0.03580562659846547, "percentage": 0.72, "elapsed_time": "0:05:17", "remaining_time": "12:14:27"}
+{"current_steps": 15, "total_steps": 1955, "loss": 0.7843, "lr": 3.0612244897959185e-06, "epoch": 0.03836317135549872, "percentage": 0.77, "elapsed_time": "0:05:39", "remaining_time": "12:11:15"}
+{"current_steps": 16, "total_steps": 1955, "loss": 0.7432, "lr": 3.2653061224489794e-06, "epoch": 0.04092071611253197, "percentage": 0.82, "elapsed_time": "0:06:02", "remaining_time": "12:11:34"}
+{"current_steps": 17, "total_steps": 1955, "loss": 0.7054, "lr": 3.469387755102041e-06, "epoch": 0.043478260869565216, "percentage": 0.87, "elapsed_time": "0:06:24", "remaining_time": "12:10:08"}
+{"current_steps": 18, "total_steps": 1955, "loss": 0.7199, "lr": 3.6734693877551024e-06, "epoch": 0.04603580562659847, "percentage": 0.92, "elapsed_time": "0:06:45", "remaining_time": "12:07:53"}
+{"current_steps": 19, "total_steps": 1955, "loss": 0.7265, "lr": 3.877551020408164e-06, "epoch": 0.04859335038363171, "percentage": 0.97, "elapsed_time": "0:07:09", "remaining_time": "12:09:44"}
+{"current_steps": 20, "total_steps": 1955, "loss": 0.6897, "lr": 4.081632653061225e-06, "epoch": 0.05115089514066496, "percentage": 1.02, "elapsed_time": "0:07:30", "remaining_time": "12:05:47"}
+{"current_steps": 21, "total_steps": 1955, "loss": 0.6527, "lr": 4.2857142857142855e-06, "epoch": 0.05370843989769821, "percentage": 1.07, "elapsed_time": "0:07:51", "remaining_time": "12:03:12"}
+{"current_steps": 22, "total_steps": 1955, "loss": 0.6451, "lr": 4.489795918367348e-06, "epoch": 0.056265984654731455, "percentage": 1.13, "elapsed_time": "0:08:14", "remaining_time": "12:04:12"}
+{"current_steps": 23, "total_steps": 1955, "loss": 0.6535, "lr": 4.693877551020409e-06, "epoch": 0.058823529411764705, "percentage": 1.18, "elapsed_time": "0:08:38", "remaining_time": "12:06:30"}
+{"current_steps": 24, "total_steps": 1955, "loss": 0.6166, "lr": 4.897959183673469e-06, "epoch": 0.061381074168797956, "percentage": 1.23, "elapsed_time": "0:09:01", "remaining_time": "12:05:50"}
+{"current_steps": 25, "total_steps": 1955, "loss": 0.6304, "lr": 5.1020408163265315e-06, "epoch": 0.0639386189258312, "percentage": 1.28, "elapsed_time": "0:09:21", "remaining_time": "12:02:08"}
+{"current_steps": 26, "total_steps": 1955, "loss": 0.6238, "lr": 5.306122448979593e-06, "epoch": 0.06649616368286446, "percentage": 1.33, "elapsed_time": "0:09:41", "remaining_time": "11:58:29"}
+{"current_steps": 27, "total_steps": 1955, "loss": 0.6212, "lr": 5.510204081632653e-06, "epoch": 0.06905370843989769, "percentage": 1.38, "elapsed_time": "0:10:03", "remaining_time": "11:58:11"}
+{"current_steps": 28, "total_steps": 1955, "loss": 0.6129, "lr": 5.7142857142857145e-06, "epoch": 0.07161125319693094, "percentage": 1.43, "elapsed_time": "0:10:27", "remaining_time": "11:59:13"}
+{"current_steps": 29, "total_steps": 1955, "loss": 0.6006, "lr": 5.918367346938776e-06, "epoch": 0.0741687979539642, "percentage": 1.48, "elapsed_time": "0:10:48", "remaining_time": "11:57:32"}
+{"current_steps": 30, "total_steps": 1955, "loss": 0.5835, "lr": 6.122448979591837e-06, "epoch": 0.07672634271099744, "percentage": 1.53, "elapsed_time": "0:11:12", "remaining_time": "11:58:46"}
+{"current_steps": 31, "total_steps": 1955, "loss": 0.629, "lr": 6.326530612244899e-06, "epoch": 0.0792838874680307, "percentage": 1.59, "elapsed_time": "0:11:35", "remaining_time": "11:59:41"}
+{"current_steps": 32, "total_steps": 1955, "loss": 0.6188, "lr": 6.530612244897959e-06, "epoch": 0.08184143222506395, "percentage": 1.64, "elapsed_time": "0:11:56", "remaining_time": "11:57:42"}
+{"current_steps": 33, "total_steps": 1955, "loss": 0.585, "lr": 6.734693877551021e-06, "epoch": 0.08439897698209718, "percentage": 1.69, "elapsed_time": "0:12:18", "remaining_time": "11:56:26"}
+{"current_steps": 34, "total_steps": 1955, "loss": 0.6271, "lr": 6.938775510204082e-06, "epoch": 0.08695652173913043, "percentage": 1.74, "elapsed_time": "0:12:42", "remaining_time": "11:58:15"}
+{"current_steps": 35, "total_steps": 1955, "loss": 0.5862, "lr": 7.1428571428571436e-06, "epoch": 0.08951406649616368, "percentage": 1.79, "elapsed_time": "0:13:05", "remaining_time": "11:57:45"}
+{"current_steps": 36, "total_steps": 1955, "loss": 0.5928, "lr": 7.346938775510205e-06, "epoch": 0.09207161125319693, "percentage": 1.84, "elapsed_time": "0:13:20", "remaining_time": "11:51:22"}
+{"current_steps": 37, "total_steps": 1955, "loss": 0.5901, "lr": 7.551020408163265e-06, "epoch": 0.09462915601023018, "percentage": 1.89, "elapsed_time": "0:13:42", "remaining_time": "11:50:15"}
+{"current_steps": 38, "total_steps": 1955, "loss": 0.568, "lr": 7.755102040816327e-06, "epoch": 0.09718670076726342, "percentage": 1.94, "elapsed_time": "0:14:05", "remaining_time": "11:50:50"}
+{"current_steps": 39, "total_steps": 1955, "loss": 0.5572, "lr": 7.959183673469388e-06, "epoch": 0.09974424552429667, "percentage": 1.99, "elapsed_time": "0:14:28", "remaining_time": "11:50:49"}
+{"current_steps": 40, "total_steps": 1955, "loss": 0.5871, "lr": 8.16326530612245e-06, "epoch": 0.10230179028132992, "percentage": 2.05, "elapsed_time": "0:14:47", "remaining_time": "11:48:17"}
+{"current_steps": 41, "total_steps": 1955, "loss": 0.579, "lr": 8.36734693877551e-06, "epoch": 0.10485933503836317, "percentage": 2.1, "elapsed_time": "0:15:10", "remaining_time": "11:48:46"}
+{"current_steps": 42, "total_steps": 1955, "loss": 0.5415, "lr": 8.571428571428571e-06, "epoch": 0.10741687979539642, "percentage": 2.15, "elapsed_time": "0:15:32", "remaining_time": "11:47:56"}
+{"current_steps": 43, "total_steps": 1955, "loss": 0.5713, "lr": 8.775510204081633e-06, "epoch": 0.10997442455242967, "percentage": 2.2, "elapsed_time": "0:15:53", "remaining_time": "11:46:50"}
+{"current_steps": 44, "total_steps": 1955, "loss": 0.5769, "lr": 8.979591836734695e-06, "epoch": 0.11253196930946291, "percentage": 2.25, "elapsed_time": "0:16:16", "remaining_time": "11:46:44"}
+{"current_steps": 45, "total_steps": 1955, "loss": 0.549, "lr": 9.183673469387756e-06, "epoch": 0.11508951406649616, "percentage": 2.3, "elapsed_time": "0:16:38", "remaining_time": "11:46:36"}
+{"current_steps": 46, "total_steps": 1955, "loss": 0.5677, "lr": 9.387755102040818e-06, "epoch": 0.11764705882352941, "percentage": 2.35, "elapsed_time": "0:17:01", "remaining_time": "11:46:36"}
+{"current_steps": 47, "total_steps": 1955, "loss": 0.5592, "lr": 9.591836734693878e-06, "epoch": 0.12020460358056266, "percentage": 2.4, "elapsed_time": "0:17:25", "remaining_time": "11:47:39"}
+{"current_steps": 48, "total_steps": 1955, "loss": 0.5461, "lr": 9.795918367346939e-06, "epoch": 0.12276214833759591, "percentage": 2.46, "elapsed_time": "0:17:47", "remaining_time": "11:46:44"}
+{"current_steps": 49, "total_steps": 1955, "loss": 0.5753, "lr": 1e-05, "epoch": 0.12531969309462915, "percentage": 2.51, "elapsed_time": "0:18:09", "remaining_time": "11:46:36"}
+{"current_steps": 50, "total_steps": 1955, "loss": 0.5198, "lr": 1.0204081632653063e-05, "epoch": 0.1278772378516624, "percentage": 2.56, "elapsed_time": "0:18:29", "remaining_time": "11:44:27"}
+{"current_steps": 51, "total_steps": 1955, "loss": 0.5562, "lr": 1.0408163265306123e-05, "epoch": 0.13043478260869565, "percentage": 2.61, "elapsed_time": "0:18:48", "remaining_time": "11:41:57"}
+{"current_steps": 52, "total_steps": 1955, "loss": 0.5257, "lr": 1.0612244897959186e-05, "epoch": 0.1329923273657289, "percentage": 2.66, "elapsed_time": "0:19:09", "remaining_time": "11:41:13"}
+{"current_steps": 53, "total_steps": 1955, "loss": 0.5788, "lr": 1.0816326530612246e-05, "epoch": 0.13554987212276215, "percentage": 2.71, "elapsed_time": "0:19:30", "remaining_time": "11:40:13"}
+{"current_steps": 54, "total_steps": 1955, "loss": 0.5152, "lr": 1.1020408163265306e-05, "epoch": 0.13810741687979539, "percentage": 2.76, "elapsed_time": "0:19:51", "remaining_time": "11:39:12"}
+{"current_steps": 55, "total_steps": 1955, "loss": 0.5547, "lr": 1.1224489795918367e-05, "epoch": 0.14066496163682865, "percentage": 2.81, "elapsed_time": "0:20:11", "remaining_time": "11:37:39"}
+{"current_steps": 56, "total_steps": 1955, "loss": 0.542, "lr": 1.1428571428571429e-05, "epoch": 0.1432225063938619, "percentage": 2.86, "elapsed_time": "0:20:27", "remaining_time": "11:33:32"}
+{"current_steps": 57, "total_steps": 1955, "loss": 0.5385, "lr": 1.1632653061224491e-05, "epoch": 0.14578005115089515, "percentage": 2.92, "elapsed_time": "0:20:47", "remaining_time": "11:32:20"}
+{"current_steps": 58, "total_steps": 1955, "loss": 0.5319, "lr": 1.1836734693877552e-05, "epoch": 0.1483375959079284, "percentage": 2.97, "elapsed_time": "0:21:08", "remaining_time": "11:31:35"}
+{"current_steps": 59, "total_steps": 1955, "loss": 0.538, "lr": 1.2040816326530614e-05, "epoch": 0.15089514066496162, "percentage": 3.02, "elapsed_time": "0:21:30", "remaining_time": "11:31:24"}
+{"current_steps": 60, "total_steps": 1955, "loss": 0.5211, "lr": 1.2244897959183674e-05, "epoch": 0.1534526854219949, "percentage": 3.07, "elapsed_time": "0:21:54", "remaining_time": "11:32:04"}
+{"current_steps": 61, "total_steps": 1955, "loss": 0.554, "lr": 1.2448979591836736e-05, "epoch": 0.15601023017902813, "percentage": 3.12, "elapsed_time": "0:22:18", "remaining_time": "11:32:35"}
+{"current_steps": 62, "total_steps": 1955, "loss": 0.5117, "lr": 1.2653061224489798e-05, "epoch": 0.1585677749360614, "percentage": 3.17, "elapsed_time": "0:22:39", "remaining_time": "11:32:00"}
+{"current_steps": 63, "total_steps": 1955, "loss": 0.5454, "lr": 1.2857142857142859e-05, "epoch": 0.16112531969309463, "percentage": 3.22, "elapsed_time": "0:23:03", "remaining_time": "11:32:38"}
+{"current_steps": 64, "total_steps": 1955, "loss": 0.5365, "lr": 1.3061224489795918e-05, "epoch": 0.1636828644501279, "percentage": 3.27, "elapsed_time": "0:23:23", "remaining_time": "11:31:11"}
+{"current_steps": 65, "total_steps": 1955, "loss": 0.5237, "lr": 1.326530612244898e-05, "epoch": 0.16624040920716113, "percentage": 3.32, "elapsed_time": "0:23:46", "remaining_time": "11:31:26"}
+{"current_steps": 66, "total_steps": 1955, "loss": 0.5305, "lr": 1.3469387755102042e-05, "epoch": 0.16879795396419436, "percentage": 3.38, "elapsed_time": "0:24:07", "remaining_time": "11:30:21"}
+{"current_steps": 67, "total_steps": 1955, "loss": 0.5371, "lr": 1.3673469387755102e-05, "epoch": 0.17135549872122763, "percentage": 3.43, "elapsed_time": "0:24:27", "remaining_time": "11:29:20"}
+{"current_steps": 68, "total_steps": 1955, "loss": 0.5394, "lr": 1.3877551020408165e-05, "epoch": 0.17391304347826086, "percentage": 3.48, "elapsed_time": "0:24:49", "remaining_time": "11:28:58"}
+{"current_steps": 69, "total_steps": 1955, "loss": 0.5539, "lr": 1.4081632653061225e-05, "epoch": 0.17647058823529413, "percentage": 3.53, "elapsed_time": "0:25:07", "remaining_time": "11:26:47"}
+{"current_steps": 70, "total_steps": 1955, "loss": 0.5406, "lr": 1.4285714285714287e-05, "epoch": 0.17902813299232737, "percentage": 3.58, "elapsed_time": "0:25:30", "remaining_time": "11:27:00"}
+{"current_steps": 71, "total_steps": 1955, "loss": 0.5176, "lr": 1.448979591836735e-05, "epoch": 0.1815856777493606, "percentage": 3.63, "elapsed_time": "0:25:52", "remaining_time": "11:26:25"}
+{"current_steps": 72, "total_steps": 1955, "loss": 0.5301, "lr": 1.469387755102041e-05, "epoch": 0.18414322250639387, "percentage": 3.68, "elapsed_time": "0:26:16", "remaining_time": "11:27:02"}
+{"current_steps": 73, "total_steps": 1955, "loss": 0.5231, "lr": 1.4897959183673472e-05, "epoch": 0.1867007672634271, "percentage": 3.73, "elapsed_time": "0:26:37", "remaining_time": "11:26:36"}
+{"current_steps": 74, "total_steps": 1955, "loss": 0.5001, "lr": 1.510204081632653e-05, "epoch": 0.18925831202046037, "percentage": 3.79, "elapsed_time": "0:26:58", "remaining_time": "11:25:37"}
+{"current_steps": 75, "total_steps": 1955, "loss": 0.5223, "lr": 1.530612244897959e-05, "epoch": 0.1918158567774936, "percentage": 3.84, "elapsed_time": "0:27:15", "remaining_time": "11:23:21"}
+{"current_steps": 76, "total_steps": 1955, "loss": 0.4948, "lr": 1.5510204081632655e-05, "epoch": 0.19437340153452684, "percentage": 3.89, "elapsed_time": "0:27:38", "remaining_time": "11:23:27"}
+{"current_steps": 77, "total_steps": 1955, "loss": 0.5295, "lr": 1.5714285714285715e-05, "epoch": 0.1969309462915601, "percentage": 3.94, "elapsed_time": "0:28:00", "remaining_time": "11:23:16"}
+{"current_steps": 78, "total_steps": 1955, "loss": 0.5089, "lr": 1.5918367346938776e-05, "epoch": 0.19948849104859334, "percentage": 3.99, "elapsed_time": "0:28:23", "remaining_time": "11:23:22"}
+{"current_steps": 79, "total_steps": 1955, "loss": 0.5154, "lr": 1.612244897959184e-05, "epoch": 0.2020460358056266, "percentage": 4.04, "elapsed_time": "0:28:48", "remaining_time": "11:24:13"}
+{"current_steps": 80, "total_steps": 1955, "loss": 0.4973, "lr": 1.63265306122449e-05, "epoch": 0.20460358056265984, "percentage": 4.09, "elapsed_time": "0:29:08", "remaining_time": "11:22:53"}
+{"current_steps": 81, "total_steps": 1955, "loss": 0.5303, "lr": 1.653061224489796e-05, "epoch": 0.2071611253196931, "percentage": 4.14, "elapsed_time": "0:29:30", "remaining_time": "11:22:46"}
+{"current_steps": 82, "total_steps": 1955, "loss": 0.5098, "lr": 1.673469387755102e-05, "epoch": 0.20971867007672634, "percentage": 4.19, "elapsed_time": "0:29:55", "remaining_time": "11:23:35"}
+{"current_steps": 83, "total_steps": 1955, "loss": 0.519, "lr": 1.6938775510204085e-05, "epoch": 0.21227621483375958, "percentage": 4.25, "elapsed_time": "0:30:16", "remaining_time": "11:22:57"}
+{"current_steps": 84, "total_steps": 1955, "loss": 0.5275, "lr": 1.7142857142857142e-05, "epoch": 0.21483375959079284, "percentage": 4.3, "elapsed_time": "0:30:36", "remaining_time": "11:21:51"}
+{"current_steps": 85, "total_steps": 1955, "loss": 0.514, "lr": 1.7346938775510206e-05, "epoch": 0.21739130434782608, "percentage": 4.35, "elapsed_time": "0:31:00", "remaining_time": "11:22:19"}
+{"current_steps": 86, "total_steps": 1955, "loss": 0.4932, "lr": 1.7551020408163266e-05, "epoch": 0.21994884910485935, "percentage": 4.4, "elapsed_time": "0:31:22", "remaining_time": "11:21:42"}
+{"current_steps": 87, "total_steps": 1955, "loss": 0.5426, "lr": 1.7755102040816327e-05, "epoch": 0.22250639386189258, "percentage": 4.45, "elapsed_time": "0:31:45", "remaining_time": "11:21:52"}
+{"current_steps": 88, "total_steps": 1955, "loss": 0.548, "lr": 1.795918367346939e-05, "epoch": 0.22506393861892582, "percentage": 4.5, "elapsed_time": "0:32:06", "remaining_time": "11:21:05"}
+{"current_steps": 89, "total_steps": 1955, "loss": 0.5132, "lr": 1.816326530612245e-05, "epoch": 0.22762148337595908, "percentage": 4.55, "elapsed_time": "0:32:26", "remaining_time": "11:20:20"}
+{"current_steps": 90, "total_steps": 1955, "loss": 0.5156, "lr": 1.836734693877551e-05, "epoch": 0.23017902813299232, "percentage": 4.6, "elapsed_time": "0:32:46", "remaining_time": "11:19:12"}
+{"current_steps": 91, "total_steps": 1955, "loss": 0.5395, "lr": 1.8571428571428575e-05, "epoch": 0.23273657289002558, "percentage": 4.65, "elapsed_time": "0:33:11", "remaining_time": "11:19:57"}
+{"current_steps": 92, "total_steps": 1955, "loss": 0.5098, "lr": 1.8775510204081636e-05, "epoch": 0.23529411764705882, "percentage": 4.71, "elapsed_time": "0:33:34", "remaining_time": "11:19:49"}
+{"current_steps": 93, "total_steps": 1955, "loss": 0.5064, "lr": 1.8979591836734696e-05, "epoch": 0.23785166240409208, "percentage": 4.76, "elapsed_time": "0:33:59", "remaining_time": "11:20:28"}
+{"current_steps": 94, "total_steps": 1955, "loss": 0.5459, "lr": 1.9183673469387756e-05, "epoch": 0.24040920716112532, "percentage": 4.81, "elapsed_time": "0:34:21", "remaining_time": "11:20:11"}
+{"current_steps": 95, "total_steps": 1955, "loss": 0.5472, "lr": 1.9387755102040817e-05, "epoch": 0.24296675191815856, "percentage": 4.86, "elapsed_time": "0:34:45", "remaining_time": "11:20:33"}
+{"current_steps": 96, "total_steps": 1955, "loss": 0.5216, "lr": 1.9591836734693877e-05, "epoch": 0.24552429667519182, "percentage": 4.91, "elapsed_time": "0:35:06", "remaining_time": "11:19:57"}
+{"current_steps": 97, "total_steps": 1955, "loss": 0.4993, "lr": 1.979591836734694e-05, "epoch": 0.24808184143222506, "percentage": 4.96, "elapsed_time": "0:35:28", "remaining_time": "11:19:28"}
+{"current_steps": 98, "total_steps": 1955, "loss": 0.5296, "lr": 2e-05, "epoch": 0.2506393861892583, "percentage": 5.01, "elapsed_time": "0:35:49", "remaining_time": "11:18:46"}
+{"current_steps": 99, "total_steps": 1955, "loss": 0.5164, "lr": 2.0204081632653062e-05, "epoch": 0.2531969309462916, "percentage": 5.06, "elapsed_time": "0:36:10", "remaining_time": "11:18:14"}
+{"current_steps": 100, "total_steps": 1955, "loss": 0.5093, "lr": 2.0408163265306126e-05, "epoch": 0.2557544757033248, "percentage": 5.12, "elapsed_time": "0:36:30", "remaining_time": "11:17:20"}
+{"current_steps": 101, "total_steps": 1955, "loss": 0.5334, "lr": 2.0612244897959183e-05, "epoch": 0.25831202046035806, "percentage": 5.17, "elapsed_time": "0:36:52", "remaining_time": "11:16:55"}
+{"current_steps": 102, "total_steps": 1955, "loss": 0.4578, "lr": 2.0816326530612247e-05, "epoch": 0.2608695652173913, "percentage": 5.22, "elapsed_time": "0:37:15", "remaining_time": "11:16:50"}
+{"current_steps": 103, "total_steps": 1955, "loss": 0.4868, "lr": 2.1020408163265307e-05, "epoch": 0.26342710997442453, "percentage": 5.27, "elapsed_time": "0:37:37", "remaining_time": "11:16:38"}
+{"current_steps": 104, "total_steps": 1955, "loss": 0.5002, "lr": 2.122448979591837e-05, "epoch": 0.2659846547314578, "percentage": 5.32, "elapsed_time": "0:37:59", "remaining_time": "11:16:13"}
+{"current_steps": 105, "total_steps": 1955, "loss": 0.5185, "lr": 2.1428571428571428e-05, "epoch": 0.26854219948849106, "percentage": 5.37, "elapsed_time": "0:38:20", "remaining_time": "11:15:35"}
+{"current_steps": 106, "total_steps": 1955, "loss": 0.4988, "lr": 2.1632653061224492e-05, "epoch": 0.2710997442455243, "percentage": 5.42, "elapsed_time": "0:38:43", "remaining_time": "11:15:34"}
+{"current_steps": 107, "total_steps": 1955, "loss": 0.505, "lr": 2.1836734693877552e-05, "epoch": 0.27365728900255754, "percentage": 5.47, "elapsed_time": "0:39:05", "remaining_time": "11:15:17"}
+{"current_steps": 108, "total_steps": 1955, "loss": 0.4985, "lr": 2.2040816326530613e-05, "epoch": 0.27621483375959077, "percentage": 5.52, "elapsed_time": "0:39:27", "remaining_time": "11:14:54"}
+{"current_steps": 109, "total_steps": 1955, "loss": 0.4955, "lr": 2.2244897959183677e-05, "epoch": 0.27877237851662406, "percentage": 5.58, "elapsed_time": "0:39:51", "remaining_time": "11:14:58"}
+{"current_steps": 110, "total_steps": 1955, "loss": 0.468, "lr": 2.2448979591836734e-05, "epoch": 0.2813299232736573, "percentage": 5.63, "elapsed_time": "0:40:14", "remaining_time": "11:14:56"}
+{"current_steps": 111, "total_steps": 1955, "loss": 0.4973, "lr": 2.2653061224489798e-05, "epoch": 0.28388746803069054, "percentage": 5.68, "elapsed_time": "0:40:36", "remaining_time": "11:14:30"}
+{"current_steps": 112, "total_steps": 1955, "loss": 0.5118, "lr": 2.2857142857142858e-05, "epoch": 0.2864450127877238, "percentage": 5.73, "elapsed_time": "0:40:58", "remaining_time": "11:14:16"}
+{"current_steps": 113, "total_steps": 1955, "loss": 0.5015, "lr": 2.3061224489795922e-05, "epoch": 0.289002557544757, "percentage": 5.78, "elapsed_time": "0:41:22", "remaining_time": "11:14:34"}
+{"current_steps": 114, "total_steps": 1955, "loss": 0.5076, "lr": 2.3265306122448982e-05, "epoch": 0.2915601023017903, "percentage": 5.83, "elapsed_time": "0:41:46", "remaining_time": "11:14:31"}
+{"current_steps": 115, "total_steps": 1955, "loss": 0.5101, "lr": 2.3469387755102043e-05, "epoch": 0.29411764705882354, "percentage": 5.88, "elapsed_time": "0:42:11", "remaining_time": "11:15:06"}
+{"current_steps": 116, "total_steps": 1955, "loss": 0.5588, "lr": 2.3673469387755103e-05, "epoch": 0.2966751918158568, "percentage": 5.93, "elapsed_time": "0:42:33", "remaining_time": "11:14:44"}
+{"current_steps": 117, "total_steps": 1955, "loss": 0.5301, "lr": 2.3877551020408167e-05, "epoch": 0.29923273657289, "percentage": 5.98, "elapsed_time": "0:42:56", "remaining_time": "11:14:30"}
+{"current_steps": 118, "total_steps": 1955, "loss": 0.5213, "lr": 2.4081632653061227e-05, "epoch": 0.30179028132992325, "percentage": 6.04, "elapsed_time": "0:43:14", "remaining_time": "11:13:10"}
+{"current_steps": 119, "total_steps": 1955, "loss": 0.507, "lr": 2.4285714285714285e-05, "epoch": 0.30434782608695654, "percentage": 6.09, "elapsed_time": "0:43:37", "remaining_time": "11:13:02"}
+{"current_steps": 120, "total_steps": 1955, "loss": 0.5319, "lr": 2.448979591836735e-05, "epoch": 0.3069053708439898, "percentage": 6.14, "elapsed_time": "0:44:01", "remaining_time": "11:13:08"}
+{"current_steps": 121, "total_steps": 1955, "loss": 0.5082, "lr": 2.469387755102041e-05, "epoch": 0.309462915601023, "percentage": 6.19, "elapsed_time": "0:44:22", "remaining_time": "11:12:37"}
+{"current_steps": 122, "total_steps": 1955, "loss": 0.5134, "lr": 2.4897959183673473e-05, "epoch": 0.31202046035805625, "percentage": 6.24, "elapsed_time": "0:44:47", "remaining_time": "11:12:52"}
+{"current_steps": 123, "total_steps": 1955, "loss": 0.513, "lr": 2.5102040816326533e-05, "epoch": 0.3145780051150895, "percentage": 6.29, "elapsed_time": "0:45:11", "remaining_time": "11:13:08"}
+{"current_steps": 124, "total_steps": 1955, "loss": 0.5112, "lr": 2.5306122448979597e-05, "epoch": 0.3171355498721228, "percentage": 6.34, "elapsed_time": "0:45:29", "remaining_time": "11:11:45"}
+{"current_steps": 125, "total_steps": 1955, "loss": 0.534, "lr": 2.5510204081632654e-05, "epoch": 0.319693094629156, "percentage": 6.39, "elapsed_time": "0:45:50", "remaining_time": "11:11:11"}
+{"current_steps": 126, "total_steps": 1955, "loss": 0.5252, "lr": 2.5714285714285718e-05, "epoch": 0.32225063938618925, "percentage": 6.45, "elapsed_time": "0:46:14", "remaining_time": "11:11:16"}
+{"current_steps": 127, "total_steps": 1955, "loss": 0.5163, "lr": 2.5918367346938778e-05, "epoch": 0.3248081841432225, "percentage": 6.5, "elapsed_time": "0:46:34", "remaining_time": "11:10:23"}
+{"current_steps": 128, "total_steps": 1955, "loss": 0.5229, "lr": 2.6122448979591835e-05, "epoch": 0.3273657289002558, "percentage": 6.55, "elapsed_time": "0:46:56", "remaining_time": "11:09:59"}
+{"current_steps": 129, "total_steps": 1955, "loss": 0.541, "lr": 2.63265306122449e-05, "epoch": 0.329923273657289, "percentage": 6.6, "elapsed_time": "0:47:14", "remaining_time": "11:08:42"}
+{"current_steps": 130, "total_steps": 1955, "loss": 0.4992, "lr": 2.653061224489796e-05, "epoch": 0.33248081841432225, "percentage": 6.65, "elapsed_time": "0:47:36", "remaining_time": "11:08:19"}
+{"current_steps": 131, "total_steps": 1955, "loss": 0.4802, "lr": 2.6734693877551023e-05, "epoch": 0.3350383631713555, "percentage": 6.7, "elapsed_time": "0:47:54", "remaining_time": "11:07:03"}
+{"current_steps": 132, "total_steps": 1955, "loss": 0.5109, "lr": 2.6938775510204084e-05, "epoch": 0.3375959079283887, "percentage": 6.75, "elapsed_time": "0:48:18", "remaining_time": "11:07:04"}
+{"current_steps": 133, "total_steps": 1955, "loss": 0.5062, "lr": 2.7142857142857148e-05, "epoch": 0.340153452685422, "percentage": 6.8, "elapsed_time": "0:48:41", "remaining_time": "11:06:56"}
+{"current_steps": 134, "total_steps": 1955, "loss": 0.5238, "lr": 2.7346938775510205e-05, "epoch": 0.34271099744245526, "percentage": 6.85, "elapsed_time": "0:49:02", "remaining_time": "11:06:33"}
+{"current_steps": 135, "total_steps": 1955, "loss": 0.5395, "lr": 2.755102040816327e-05, "epoch": 0.3452685421994885, "percentage": 6.91, "elapsed_time": "0:49:25", "remaining_time": "11:06:17"}
+{"current_steps": 136, "total_steps": 1955, "loss": 0.5101, "lr": 2.775510204081633e-05, "epoch": 0.34782608695652173, "percentage": 6.96, "elapsed_time": "0:49:47", "remaining_time": "11:06:03"}
+{"current_steps": 137, "total_steps": 1955, "loss": 0.5065, "lr": 2.7959183673469393e-05, "epoch": 0.35038363171355497, "percentage": 7.01, "elapsed_time": "0:50:10", "remaining_time": "11:05:54"}
+{"current_steps": 138, "total_steps": 1955, "loss": 0.5056, "lr": 2.816326530612245e-05, "epoch": 0.35294117647058826, "percentage": 7.06, "elapsed_time": "0:50:34", "remaining_time": "11:05:59"}
+{"current_steps": 139, "total_steps": 1955, "loss": 0.4966, "lr": 2.836734693877551e-05, "epoch": 0.3554987212276215, "percentage": 7.11, "elapsed_time": "0:50:55", "remaining_time": "11:05:15"}
+{"current_steps": 140, "total_steps": 1955, "loss": 0.5085, "lr": 2.8571428571428574e-05, "epoch": 0.35805626598465473, "percentage": 7.16, "elapsed_time": "0:51:18", "remaining_time": "11:05:12"}
+{"current_steps": 141, "total_steps": 1955, "loss": 0.5302, "lr": 2.8775510204081635e-05, "epoch": 0.36061381074168797, "percentage": 7.21, "elapsed_time": "0:51:41", "remaining_time": "11:05:05"}
+{"current_steps": 142, "total_steps": 1955, "loss": 0.4989, "lr": 2.89795918367347e-05, "epoch": 0.3631713554987212, "percentage": 7.26, "elapsed_time": "0:52:03", "remaining_time": "11:04:38"}
+{"current_steps": 143, "total_steps": 1955, "loss": 0.4725, "lr": 2.9183673469387756e-05, "epoch": 0.3657289002557545, "percentage": 7.31, "elapsed_time": "0:52:22", "remaining_time": "11:03:35"}
+{"current_steps": 144, "total_steps": 1955, "loss": 0.5106, "lr": 2.938775510204082e-05, "epoch": 0.36828644501278773, "percentage": 7.37, "elapsed_time": "0:52:45", "remaining_time": "11:03:32"}
+{"current_steps": 145, "total_steps": 1955, "loss": 0.511, "lr": 2.959183673469388e-05, "epoch": 0.37084398976982097, "percentage": 7.42, "elapsed_time": "0:53:05", "remaining_time": "11:02:48"}
+{"current_steps": 146, "total_steps": 1955, "loss": 0.5298, "lr": 2.9795918367346944e-05, "epoch": 0.3734015345268542, "percentage": 7.47, "elapsed_time": "0:53:26", "remaining_time": "11:02:12"}
+{"current_steps": 147, "total_steps": 1955, "loss": 0.4871, "lr": 3.0000000000000004e-05, "epoch": 0.37595907928388744, "percentage": 7.52, "elapsed_time": "0:53:48", "remaining_time": "11:01:46"}
+{"current_steps": 148, "total_steps": 1955, "loss": 0.5152, "lr": 3.020408163265306e-05, "epoch": 0.37851662404092073, "percentage": 7.57, "elapsed_time": "0:54:09", "remaining_time": "11:01:10"}
+{"current_steps": 149, "total_steps": 1955, "loss": 0.5261, "lr": 3.0408163265306125e-05, "epoch": 0.38107416879795397, "percentage": 7.62, "elapsed_time": "0:54:31", "remaining_time": "11:00:56"}
+{"current_steps": 150, "total_steps": 1955, "loss": 0.5029, "lr": 3.061224489795918e-05, "epoch": 0.3836317135549872, "percentage": 7.67, "elapsed_time": "0:54:53", "remaining_time": "11:00:26"}
+{"current_steps": 151, "total_steps": 1955, "loss": 0.4885, "lr": 3.0816326530612246e-05, "epoch": 0.38618925831202044, "percentage": 7.72, "elapsed_time": "0:55:17", "remaining_time": "11:00:37"}
+{"current_steps": 152, "total_steps": 1955, "loss": 0.5274, "lr": 3.102040816326531e-05, "epoch": 0.3887468030690537, "percentage": 7.77, "elapsed_time": "0:55:37", "remaining_time": "10:59:45"}
+{"current_steps": 153, "total_steps": 1955, "loss": 0.5043, "lr": 3.1224489795918374e-05, "epoch": 0.391304347826087, "percentage": 7.83, "elapsed_time": "0:55:57", "remaining_time": "10:59:06"}
+{"current_steps": 154, "total_steps": 1955, "loss": 0.4935, "lr": 3.142857142857143e-05, "epoch": 0.3938618925831202, "percentage": 7.88, "elapsed_time": "0:56:16", "remaining_time": "10:58:02"}
+{"current_steps": 155, "total_steps": 1955, "loss": 0.503, "lr": 3.1632653061224494e-05, "epoch": 0.39641943734015345, "percentage": 7.93, "elapsed_time": "0:56:35", "remaining_time": "10:57:07"}
+{"current_steps": 156, "total_steps": 1955, "loss": 0.4717, "lr": 3.183673469387755e-05, "epoch": 0.3989769820971867, "percentage": 7.98, "elapsed_time": "0:56:56", "remaining_time": "10:56:41"}
+{"current_steps": 157, "total_steps": 1955, "loss": 0.4699, "lr": 3.2040816326530615e-05, "epoch": 0.40153452685422, "percentage": 8.03, "elapsed_time": "0:57:15", "remaining_time": "10:55:47"}
+{"current_steps": 158, "total_steps": 1955, "loss": 0.5213, "lr": 3.224489795918368e-05, "epoch": 0.4040920716112532, "percentage": 8.08, "elapsed_time": "0:57:38", "remaining_time": "10:55:30"}
+{"current_steps": 159, "total_steps": 1955, "loss": 0.4953, "lr": 3.2448979591836736e-05, "epoch": 0.40664961636828645, "percentage": 8.13, "elapsed_time": "0:58:01", "remaining_time": "10:55:22"}
+{"current_steps": 160, "total_steps": 1955, "loss": 0.4912, "lr": 3.26530612244898e-05, "epoch": 0.4092071611253197, "percentage": 8.18, "elapsed_time": "0:58:25", "remaining_time": "10:55:22"}
+{"current_steps": 161, "total_steps": 1955, "loss": 0.5346, "lr": 3.285714285714286e-05, "epoch": 0.4117647058823529, "percentage": 8.24, "elapsed_time": "0:58:48", "remaining_time": "10:55:20"}
+{"current_steps": 162, "total_steps": 1955, "loss": 0.5075, "lr": 3.306122448979592e-05, "epoch": 0.4143222506393862, "percentage": 8.29, "elapsed_time": "0:59:11", "remaining_time": "10:55:11"}
+{"current_steps": 163, "total_steps": 1955, "loss": 0.5068, "lr": 3.3265306122448985e-05, "epoch": 0.41687979539641945, "percentage": 8.34, "elapsed_time": "0:59:34", "remaining_time": "10:54:53"}
+{"current_steps": 164, "total_steps": 1955, "loss": 0.5258, "lr": 3.346938775510204e-05, "epoch": 0.4194373401534527, "percentage": 8.39, "elapsed_time": "0:59:54", "remaining_time": "10:54:16"}
+{"current_steps": 165, "total_steps": 1955, "loss": 0.5077, "lr": 3.3673469387755106e-05, "epoch": 0.4219948849104859, "percentage": 8.44, "elapsed_time": "1:00:14", "remaining_time": "10:53:37"}
+{"current_steps": 166, "total_steps": 1955, "loss": 0.5092, "lr": 3.387755102040817e-05, "epoch": 0.42455242966751916, "percentage": 8.49, "elapsed_time": "1:00:37", "remaining_time": "10:53:17"}
+{"current_steps": 167, "total_steps": 1955, "loss": 0.5111, "lr": 3.408163265306123e-05, "epoch": 0.42710997442455245, "percentage": 8.54, "elapsed_time": "1:00:58", "remaining_time": "10:52:50"}
+{"current_steps": 168, "total_steps": 1955, "loss": 0.5014, "lr": 3.4285714285714284e-05, "epoch": 0.4296675191815857, "percentage": 8.59, "elapsed_time": "1:01:21", "remaining_time": "10:52:36"}
+{"current_steps": 169, "total_steps": 1955, "loss": 0.4808, "lr": 3.448979591836735e-05, "epoch": 0.4322250639386189, "percentage": 8.64, "elapsed_time": "1:01:45", "remaining_time": "10:52:41"}
+{"current_steps": 170, "total_steps": 1955, "loss": 0.523, "lr": 3.469387755102041e-05, "epoch": 0.43478260869565216, "percentage": 8.7, "elapsed_time": "1:02:03", "remaining_time": "10:51:41"}
+{"current_steps": 171, "total_steps": 1955, "loss": 0.5066, "lr": 3.4897959183673475e-05, "epoch": 0.4373401534526854, "percentage": 8.75, "elapsed_time": "1:02:27", "remaining_time": "10:51:40"}
+{"current_steps": 172, "total_steps": 1955, "loss": 0.5098, "lr": 3.510204081632653e-05, "epoch": 0.4398976982097187, "percentage": 8.8, "elapsed_time": "1:02:52", "remaining_time": "10:51:42"}
+{"current_steps": 173, "total_steps": 1955, "loss": 0.5031, "lr": 3.5306122448979596e-05, "epoch": 0.4424552429667519, "percentage": 8.85, "elapsed_time": "1:03:15", "remaining_time": "10:51:38"}
+{"current_steps": 174, "total_steps": 1955, "loss": 0.5052, "lr": 3.551020408163265e-05, "epoch": 0.44501278772378516, "percentage": 8.9, "elapsed_time": "1:03:40", "remaining_time": "10:51:40"}
+{"current_steps": 175, "total_steps": 1955, "loss": 0.488, "lr": 3.571428571428572e-05, "epoch": 0.4475703324808184, "percentage": 8.95, "elapsed_time": "1:03:59", "remaining_time": "10:50:52"}
+{"current_steps": 176, "total_steps": 1955, "loss": 0.5243, "lr": 3.591836734693878e-05, "epoch": 0.45012787723785164, "percentage": 9.0, "elapsed_time": "1:04:24", "remaining_time": "10:51:02"}
+{"current_steps": 177, "total_steps": 1955, "loss": 0.5101, "lr": 3.612244897959184e-05, "epoch": 0.45268542199488493, "percentage": 9.05, "elapsed_time": "1:04:48", "remaining_time": "10:50:57"}
+{"current_steps": 178, "total_steps": 1955, "loss": 0.5077, "lr": 3.63265306122449e-05, "epoch": 0.45524296675191817, "percentage": 9.1, "elapsed_time": "1:05:05", "remaining_time": "10:49:53"}
+{"current_steps": 179, "total_steps": 1955, "loss": 0.5181, "lr": 3.653061224489796e-05, "epoch": 0.4578005115089514, "percentage": 9.16, "elapsed_time": "1:05:31", "remaining_time": "10:50:06"}
+{"current_steps": 180, "total_steps": 1955, "loss": 0.5018, "lr": 3.673469387755102e-05, "epoch": 0.46035805626598464, "percentage": 9.21, "elapsed_time": "1:05:50", "remaining_time": "10:49:17"}
+{"current_steps": 181, "total_steps": 1955, "loss": 0.5044, "lr": 3.6938775510204086e-05, "epoch": 0.4629156010230179, "percentage": 9.26, "elapsed_time": "1:06:12", "remaining_time": "10:48:56"}
+{"current_steps": 182, "total_steps": 1955, "loss": 0.5093, "lr": 3.714285714285715e-05, "epoch": 0.46547314578005117, "percentage": 9.31, "elapsed_time": "1:06:34", "remaining_time": "10:48:30"}
+{"current_steps": 183, "total_steps": 1955, "loss": 0.539, "lr": 3.734693877551021e-05, "epoch": 0.4680306905370844, "percentage": 9.36, "elapsed_time": "1:06:55", "remaining_time": "10:48:04"}
+{"current_steps": 184, "total_steps": 1955, "loss": 0.472, "lr": 3.755102040816327e-05, "epoch": 0.47058823529411764, "percentage": 9.41, "elapsed_time": "1:07:18", "remaining_time": "10:47:46"}
+{"current_steps": 185, "total_steps": 1955, "loss": 0.5202, "lr": 3.775510204081633e-05, "epoch": 0.4731457800511509, "percentage": 9.46, "elapsed_time": "1:07:40", "remaining_time": "10:47:24"}
+{"current_steps": 186, "total_steps": 1955, "loss": 0.5115, "lr": 3.795918367346939e-05, "epoch": 0.47570332480818417, "percentage": 9.51, "elapsed_time": "1:08:03", "remaining_time": "10:47:17"}
+{"current_steps": 187, "total_steps": 1955, "loss": 0.5145, "lr": 3.816326530612245e-05, "epoch": 0.4782608695652174, "percentage": 9.57, "elapsed_time": "1:08:26", "remaining_time": "10:47:04"}
+{"current_steps": 188, "total_steps": 1955, "loss": 0.5201, "lr": 3.836734693877551e-05, "epoch": 0.48081841432225064, "percentage": 9.62, "elapsed_time": "1:08:47", "remaining_time": "10:46:35"}
+{"current_steps": 189, "total_steps": 1955, "loss": 0.5366, "lr": 3.857142857142858e-05, "epoch": 0.4833759590792839, "percentage": 9.67, "elapsed_time": "1:09:11", "remaining_time": "10:46:28"}
+{"current_steps": 190, "total_steps": 1955, "loss": 0.5075, "lr": 3.8775510204081634e-05, "epoch": 0.4859335038363171, "percentage": 9.72, "elapsed_time": "1:09:34", "remaining_time": "10:46:18"}
+{"current_steps": 191, "total_steps": 1955, "loss": 0.4898, "lr": 3.89795918367347e-05, "epoch": 0.4884910485933504, "percentage": 9.77, "elapsed_time": "1:09:58", "remaining_time": "10:46:16"}
+{"current_steps": 192, "total_steps": 1955, "loss": 0.5213, "lr": 3.9183673469387755e-05, "epoch": 0.49104859335038364, "percentage": 9.82, "elapsed_time": "1:10:18", "remaining_time": "10:45:32"}
+{"current_steps": 193, "total_steps": 1955, "loss": 0.521, "lr": 3.938775510204082e-05, "epoch": 0.4936061381074169, "percentage": 9.87, "elapsed_time": "1:10:40", "remaining_time": "10:45:16"}
+{"current_steps": 194, "total_steps": 1955, "loss": 0.4832, "lr": 3.959183673469388e-05, "epoch": 0.4961636828644501, "percentage": 9.92, "elapsed_time": "1:11:02", "remaining_time": "10:44:50"}
+{"current_steps": 195, "total_steps": 1955, "loss": 0.4869, "lr": 3.9795918367346946e-05, "epoch": 0.49872122762148335, "percentage": 9.97, "elapsed_time": "1:11:22", "remaining_time": "10:44:14"}
+{"current_steps": 196, "total_steps": 1955, "loss": 0.4761, "lr": 4e-05, "epoch": 0.5012787723785166, "percentage": 10.03, "elapsed_time": "1:11:44", "remaining_time": "10:43:47"}
+{"current_steps": 197, "total_steps": 1955, "loss": 0.4753, "lr": 3.9999968101669686e-05, "epoch": 0.5038363171355499, "percentage": 10.08, "elapsed_time": "1:12:05", "remaining_time": "10:43:21"}
+{"current_steps": 198, "total_steps": 1955, "loss": 0.5139, "lr": 3.999987240678048e-05, "epoch": 0.5063938618925832, "percentage": 10.13, "elapsed_time": "1:12:26", "remaining_time": "10:42:50"}
+{"current_steps": 199, "total_steps": 1955, "loss": 0.5223, "lr": 3.9999712915637624e-05, "epoch": 0.5089514066496164, "percentage": 10.18, "elapsed_time": "1:12:49", "remaining_time": "10:42:38"}
+{"current_steps": 200, "total_steps": 1955, "loss": 0.5003, "lr": 3.9999489628749886e-05, "epoch": 0.5115089514066496, "percentage": 10.23, "elapsed_time": "1:13:10", "remaining_time": "10:42:03"}
+{"current_steps": 201, "total_steps": 1955, "loss": 0.509, "lr": 3.99992025468295e-05, "epoch": 0.5140664961636828, "percentage": 10.28, "elapsed_time": "1:13:35", "remaining_time": "10:42:11"}
+{"current_steps": 202, "total_steps": 1955, "loss": 0.5065, "lr": 3.9998851670792225e-05, "epoch": 0.5166240409207161, "percentage": 10.33, "elapsed_time": "1:13:58", "remaining_time": "10:42:01"}
+{"current_steps": 203, "total_steps": 1955, "loss": 0.4726, "lr": 3.999843700175729e-05, "epoch": 0.5191815856777494, "percentage": 10.38, "elapsed_time": "1:14:21", "remaining_time": "10:41:47"}
+{"current_steps": 204, "total_steps": 1955, "loss": 0.4894, "lr": 3.999795854104741e-05, "epoch": 0.5217391304347826, "percentage": 10.43, "elapsed_time": "1:14:41", "remaining_time": "10:41:09"}
+{"current_steps": 205, "total_steps": 1955, "loss": 0.5022, "lr": 3.99974162901888e-05, "epoch": 0.5242966751918159, "percentage": 10.49, "elapsed_time": "1:15:03", "remaining_time": "10:40:48"}
+{"current_steps": 206, "total_steps": 1955, "loss": 0.488, "lr": 3.999681025091116e-05, "epoch": 0.5268542199488491, "percentage": 10.54, "elapsed_time": "1:15:27", "remaining_time": "10:40:38"}
+{"current_steps": 207, "total_steps": 1955, "loss": 0.4968, "lr": 3.9996140425147647e-05, "epoch": 0.5294117647058824, "percentage": 10.59, "elapsed_time": "1:15:48", "remaining_time": "10:40:13"}
+{"current_steps": 208, "total_steps": 1955, "loss": 0.4876, "lr": 3.9995406815034885e-05, "epoch": 0.5319693094629157, "percentage": 10.64, "elapsed_time": "1:16:11", "remaining_time": "10:39:56"}
+{"current_steps": 209, "total_steps": 1955, "loss": 0.4954, "lr": 3.999460942291298e-05, "epoch": 0.5345268542199488, "percentage": 10.69, "elapsed_time": "1:16:36", "remaining_time": "10:39:55"}
+{"current_steps": 210, "total_steps": 1955, "loss": 0.5089, "lr": 3.999374825132548e-05, "epoch": 0.5370843989769821, "percentage": 10.74, "elapsed_time": "1:16:58", "remaining_time": "10:39:40"}
+{"current_steps": 211, "total_steps": 1955, "loss": 0.4716, "lr": 3.9992823303019366e-05, "epoch": 0.5396419437340153, "percentage": 10.79, "elapsed_time": "1:17:22", "remaining_time": "10:39:35"}
+{"current_steps": 212, "total_steps": 1955, "loss": 0.4892, "lr": 3.999183458094508e-05, "epoch": 0.5421994884910486, "percentage": 10.84, "elapsed_time": "1:17:43", "remaining_time": "10:39:02"}
+{"current_steps": 213, "total_steps": 1955, "loss": 0.5119, "lr": 3.9990782088256484e-05, "epoch": 0.5447570332480819, "percentage": 10.9, "elapsed_time": "1:18:03", "remaining_time": "10:38:27"}
+{"current_steps": 214, "total_steps": 1955, "loss": 0.5106, "lr": 3.9989665828310834e-05, "epoch": 0.5473145780051151, "percentage": 10.95, "elapsed_time": "1:18:27", "remaining_time": "10:38:15"}
+{"current_steps": 215, "total_steps": 1955, "loss": 0.4526, "lr": 3.9988485804668836e-05, "epoch": 0.5498721227621484, "percentage": 11.0, "elapsed_time": "1:18:47", "remaining_time": "10:37:39"}
+{"current_steps": 216, "total_steps": 1955, "loss": 0.4712, "lr": 3.998724202109455e-05, "epoch": 0.5524296675191815, "percentage": 11.05, "elapsed_time": "1:19:11", "remaining_time": "10:37:32"}
+{"current_steps": 217, "total_steps": 1955, "loss": 0.5023, "lr": 3.9985934481555455e-05, "epoch": 0.5549872122762148, "percentage": 11.1, "elapsed_time": "1:19:32", "remaining_time": "10:37:03"}
+{"current_steps": 218, "total_steps": 1955, "loss": 0.4683, "lr": 3.998456319022237e-05, "epoch": 0.5575447570332481, "percentage": 11.15, "elapsed_time": "1:19:53", "remaining_time": "10:36:31"}
+{"current_steps": 219, "total_steps": 1955, "loss": 0.5068, "lr": 3.998312815146949e-05, "epoch": 0.5601023017902813, "percentage": 11.2, "elapsed_time": "1:20:15", "remaining_time": "10:36:14"}
+{"current_steps": 220, "total_steps": 1955, "loss": 0.5505, "lr": 3.9981629369874354e-05, "epoch": 0.5626598465473146, "percentage": 11.25, "elapsed_time": "1:20:38", "remaining_time": "10:36:01"}
+{"current_steps": 221, "total_steps": 1955, "loss": 0.5232, "lr": 3.998006685021781e-05, "epoch": 0.5652173913043478, "percentage": 11.3, "elapsed_time": "1:20:59", "remaining_time": "10:35:31"}
+{"current_steps": 222, "total_steps": 1955, "loss": 0.5064, "lr": 3.997844059748406e-05, "epoch": 0.5677749360613811, "percentage": 11.36, "elapsed_time": "1:21:19", "remaining_time": "10:34:52"}
+{"current_steps": 223, "total_steps": 1955, "loss": 0.476, "lr": 3.997675061686055e-05, "epoch": 0.5703324808184144, "percentage": 11.41, "elapsed_time": "1:21:38", "remaining_time": "10:34:05"}
+{"current_steps": 224, "total_steps": 1955, "loss": 0.4885, "lr": 3.997499691373805e-05, "epoch": 0.5728900255754475, "percentage": 11.46, "elapsed_time": "1:21:53", "remaining_time": "10:32:48"}
+{"current_steps": 225, "total_steps": 1955, "loss": 0.5041, "lr": 3.997317949371059e-05, "epoch": 0.5754475703324808, "percentage": 11.51, "elapsed_time": "1:22:16", "remaining_time": "10:32:37"}
+{"current_steps": 226, "total_steps": 1955, "loss": 0.5026, "lr": 3.997129836257542e-05, "epoch": 0.578005115089514, "percentage": 11.56, "elapsed_time": "1:22:35", "remaining_time": "10:31:49"}
+{"current_steps": 227, "total_steps": 1955, "loss": 0.5264, "lr": 3.996935352633304e-05, "epoch": 0.5805626598465473, "percentage": 11.61, "elapsed_time": "1:22:58", "remaining_time": "10:31:41"}
+{"current_steps": 228, "total_steps": 1955, "loss": 0.4746, "lr": 3.996734499118715e-05, "epoch": 0.5831202046035806, "percentage": 11.66, "elapsed_time": "1:23:21", "remaining_time": "10:31:23"}
+{"current_steps": 229, "total_steps": 1955, "loss": 0.5162, "lr": 3.9965272763544655e-05, "epoch": 0.5856777493606138, "percentage": 11.71, "elapsed_time": "1:23:41", "remaining_time": "10:30:44"}
+{"current_steps": 230, "total_steps": 1955, "loss": 0.4801, "lr": 3.99631368500156e-05, "epoch": 0.5882352941176471, "percentage": 11.76, "elapsed_time": "1:24:02", "remaining_time": "10:30:15"}
+{"current_steps": 231, "total_steps": 1955, "loss": 0.4675, "lr": 3.996093725741321e-05, "epoch": 0.5907928388746803, "percentage": 11.82, "elapsed_time": "1:24:25", "remaining_time": "10:30:05"}
+{"current_steps": 232, "total_steps": 1955, "loss": 0.5005, "lr": 3.995867399275379e-05, "epoch": 0.5933503836317136, "percentage": 11.87, "elapsed_time": "1:24:47", "remaining_time": "10:29:46"}
+{"current_steps": 233, "total_steps": 1955, "loss": 0.5102, "lr": 3.99563470632568e-05, "epoch": 0.5959079283887468, "percentage": 11.92, "elapsed_time": "1:25:14", "remaining_time": "10:29:57"}
+{"current_steps": 234, "total_steps": 1955, "loss": 0.511, "lr": 3.995395647634474e-05, "epoch": 0.59846547314578, "percentage": 11.97, "elapsed_time": "1:25:37", "remaining_time": "10:29:47"}
+{"current_steps": 235, "total_steps": 1955, "loss": 0.5135, "lr": 3.99515022396432e-05, "epoch": 0.6010230179028133, "percentage": 12.02, "elapsed_time": "1:25:59", "remaining_time": "10:29:25"}
+{"current_steps": 236, "total_steps": 1955, "loss": 0.5197, "lr": 3.994898436098078e-05, "epoch": 0.6035805626598465, "percentage": 12.07, "elapsed_time": "1:26:21", "remaining_time": "10:29:02"}
+{"current_steps": 237, "total_steps": 1955, "loss": 0.4989, "lr": 3.994640284838909e-05, "epoch": 0.6061381074168798, "percentage": 12.12, "elapsed_time": "1:26:42", "remaining_time": "10:28:32"}
+{"current_steps": 238, "total_steps": 1955, "loss": 0.4981, "lr": 3.994375771010272e-05, "epoch": 0.6086956521739131, "percentage": 12.17, "elapsed_time": "1:27:04", "remaining_time": "10:28:12"}
+{"current_steps": 239, "total_steps": 1955, "loss": 0.5143, "lr": 3.994104895455922e-05, "epoch": 0.6112531969309463, "percentage": 12.23, "elapsed_time": "1:27:27", "remaining_time": "10:27:54"}
+{"current_steps": 240, "total_steps": 1955, "loss": 0.4935, "lr": 3.993827659039908e-05, "epoch": 0.6138107416879796, "percentage": 12.28, "elapsed_time": "1:27:50", "remaining_time": "10:27:39"}
+{"current_steps": 241, "total_steps": 1955, "loss": 0.4863, "lr": 3.993544062646566e-05, "epoch": 0.6163682864450127, "percentage": 12.33, "elapsed_time": "1:28:11", "remaining_time": "10:27:11"}
+{"current_steps": 242, "total_steps": 1955, "loss": 0.4569, "lr": 3.9932541071805236e-05, "epoch": 0.618925831202046, "percentage": 12.38, "elapsed_time": "1:28:31", "remaining_time": "10:26:36"}
+{"current_steps": 243, "total_steps": 1955, "loss": 0.4866, "lr": 3.9929577935666876e-05, "epoch": 0.6214833759590793, "percentage": 12.43, "elapsed_time": "1:28:50", "remaining_time": "10:25:56"}
+{"current_steps": 244, "total_steps": 1955, "loss": 0.4849, "lr": 3.992655122750251e-05, "epoch": 0.6240409207161125, "percentage": 12.48, "elapsed_time": "1:29:13", "remaining_time": "10:25:41"}
+{"current_steps": 245, "total_steps": 1955, "loss": 0.4703, "lr": 3.992346095696682e-05, "epoch": 0.6265984654731458, "percentage": 12.53, "elapsed_time": "1:29:35", "remaining_time": "10:25:17"}
+{"current_steps": 246, "total_steps": 1955, "loss": 0.476, "lr": 3.992030713391726e-05, "epoch": 0.629156010230179, "percentage": 12.58, "elapsed_time": "1:29:57", "remaining_time": "10:24:57"}
+{"current_steps": 247, "total_steps": 1955, "loss": 0.5034, "lr": 3.9917089768414e-05, "epoch": 0.6317135549872123, "percentage": 12.63, "elapsed_time": "1:30:15", "remaining_time": "10:24:05"}
+{"current_steps": 248, "total_steps": 1955, "loss": 0.4993, "lr": 3.991380887071989e-05, "epoch": 0.6342710997442456, "percentage": 12.69, "elapsed_time": "1:30:38", "remaining_time": "10:23:53"}
+{"current_steps": 249, "total_steps": 1955, "loss": 0.4923, "lr": 3.991046445130045e-05, "epoch": 0.6368286445012787, "percentage": 12.74, "elapsed_time": "1:31:00", "remaining_time": "10:23:31"}
+{"current_steps": 250, "total_steps": 1955, "loss": 0.4991, "lr": 3.9907056520823824e-05, "epoch": 0.639386189258312, "percentage": 12.79, "elapsed_time": "1:31:19", "remaining_time": "10:22:50"}
+{"current_steps": 251, "total_steps": 1955, "loss": 0.4963, "lr": 3.9903585090160736e-05, "epoch": 0.6419437340153452, "percentage": 12.84, "elapsed_time": "1:31:41", "remaining_time": "10:22:28"}
+{"current_steps": 252, "total_steps": 1955, "loss": 0.5077, "lr": 3.990005017038446e-05, "epoch": 0.6445012787723785, "percentage": 12.89, "elapsed_time": "1:32:03", "remaining_time": "10:22:09"}
+{"current_steps": 253, "total_steps": 1955, "loss": 0.5077, "lr": 3.989645177277083e-05, "epoch": 0.6470588235294118, "percentage": 12.94, "elapsed_time": "1:32:26", "remaining_time": "10:21:49"}
+{"current_steps": 254, "total_steps": 1955, "loss": 0.487, "lr": 3.989278990879811e-05, "epoch": 0.649616368286445, "percentage": 12.99, "elapsed_time": "1:32:46", "remaining_time": "10:21:21"}
+{"current_steps": 255, "total_steps": 1955, "loss": 0.4792, "lr": 3.988906459014704e-05, "epoch": 0.6521739130434783, "percentage": 13.04, "elapsed_time": "1:33:08", "remaining_time": "10:20:58"}
+{"current_steps": 256, "total_steps": 1955, "loss": 0.4981, "lr": 3.9885275828700756e-05, "epoch": 0.6547314578005116, "percentage": 13.09, "elapsed_time": "1:33:33", "remaining_time": "10:20:51"}
+{"current_steps": 257, "total_steps": 1955, "loss": 0.5144, "lr": 3.988142363654479e-05, "epoch": 0.6572890025575447, "percentage": 13.15, "elapsed_time": "1:33:52", "remaining_time": "10:20:17"}
+{"current_steps": 258, "total_steps": 1955, "loss": 0.4974, "lr": 3.987750802596698e-05, "epoch": 0.659846547314578, "percentage": 13.2, "elapsed_time": "1:34:13", "remaining_time": "10:19:43"}
+{"current_steps": 259, "total_steps": 1955, "loss": 0.5004, "lr": 3.987352900945748e-05, "epoch": 0.6624040920716112, "percentage": 13.25, "elapsed_time": "1:34:36", "remaining_time": "10:19:31"}
+{"current_steps": 260, "total_steps": 1955, "loss": 0.5016, "lr": 3.986948659970868e-05, "epoch": 0.6649616368286445, "percentage": 13.3, "elapsed_time": "1:34:58", "remaining_time": "10:19:07"}
+{"current_steps": 261, "total_steps": 1955, "loss": 0.4982, "lr": 3.98653808096152e-05, "epoch": 0.6675191815856778, "percentage": 13.35, "elapsed_time": "1:35:18", "remaining_time": "10:18:34"}
+{"current_steps": 262, "total_steps": 1955, "loss": 0.5306, "lr": 3.986121165227381e-05, "epoch": 0.670076726342711, "percentage": 13.4, "elapsed_time": "1:35:38", "remaining_time": "10:17:58"}
+{"current_steps": 263, "total_steps": 1955, "loss": 0.5045, "lr": 3.985697914098344e-05, "epoch": 0.6726342710997443, "percentage": 13.45, "elapsed_time": "1:35:57", "remaining_time": "10:17:21"}
+{"current_steps": 264, "total_steps": 1955, "loss": 0.4734, "lr": 3.985268328924509e-05, "epoch": 0.6751918158567775, "percentage": 13.5, "elapsed_time": "1:36:20", "remaining_time": "10:17:07"}
+{"current_steps": 265, "total_steps": 1955, "loss": 0.488, "lr": 3.984832411076181e-05, "epoch": 0.6777493606138107, "percentage": 13.55, "elapsed_time": "1:36:42", "remaining_time": "10:16:47"}
+{"current_steps": 266, "total_steps": 1955, "loss": 0.4904, "lr": 3.984390161943865e-05, "epoch": 0.680306905370844, "percentage": 13.61, "elapsed_time": "1:37:04", "remaining_time": "10:16:24"}
+{"current_steps": 267, "total_steps": 1955, "loss": 0.5122, "lr": 3.983941582938262e-05, "epoch": 0.6828644501278772, "percentage": 13.66, "elapsed_time": "1:37:27", "remaining_time": "10:16:09"}
+{"current_steps": 268, "total_steps": 1955, "loss": 0.4784, "lr": 3.983486675490264e-05, "epoch": 0.6854219948849105, "percentage": 13.71, "elapsed_time": "1:37:49", "remaining_time": "10:15:45"}
+{"current_steps": 269, "total_steps": 1955, "loss": 0.4762, "lr": 3.98302544105095e-05, "epoch": 0.6879795396419437, "percentage": 13.76, "elapsed_time": "1:38:13", "remaining_time": "10:15:36"}
+{"current_steps": 270, "total_steps": 1955, "loss": 0.5144, "lr": 3.9825578810915815e-05, "epoch": 0.690537084398977, "percentage": 13.81, "elapsed_time": "1:38:36", "remaining_time": "10:15:22"}
+{"current_steps": 271, "total_steps": 1955, "loss": 0.5182, "lr": 3.982083997103595e-05, "epoch": 0.6930946291560103, "percentage": 13.86, "elapsed_time": "1:38:57", "remaining_time": "10:14:58"}
+{"current_steps": 272, "total_steps": 1955, "loss": 0.5065, "lr": 3.9816037905986035e-05, "epoch": 0.6956521739130435, "percentage": 13.91, "elapsed_time": "1:39:15", "remaining_time": "10:14:12"}
+{"current_steps": 273, "total_steps": 1955, "loss": 0.4784, "lr": 3.9811172631083835e-05, "epoch": 0.6982097186700768, "percentage": 13.96, "elapsed_time": "1:39:37", "remaining_time": "10:13:46"}
+{"current_steps": 274, "total_steps": 1955, "loss": 0.5325, "lr": 3.980624416184877e-05, "epoch": 0.7007672634271099, "percentage": 14.02, "elapsed_time": "1:39:58", "remaining_time": "10:13:20"}
+{"current_steps": 275, "total_steps": 1955, "loss": 0.4551, "lr": 3.980125251400185e-05, "epoch": 0.7033248081841432, "percentage": 14.07, "elapsed_time": "1:40:21", "remaining_time": "10:13:05"}
+{"current_steps": 276, "total_steps": 1955, "loss": 0.4997, "lr": 3.9796197703465574e-05, "epoch": 0.7058823529411765, "percentage": 14.12, "elapsed_time": "1:40:42", "remaining_time": "10:12:37"}
+{"current_steps": 277, "total_steps": 1955, "loss": 0.525, "lr": 3.979107974636396e-05, "epoch": 0.7084398976982097, "percentage": 14.17, "elapsed_time": "1:41:03", "remaining_time": "10:12:10"}
+{"current_steps": 278, "total_steps": 1955, "loss": 0.4542, "lr": 3.978589865902243e-05, "epoch": 0.710997442455243, "percentage": 14.22, "elapsed_time": "1:41:19", "remaining_time": "10:11:15"}
+{"current_steps": 279, "total_steps": 1955, "loss": 0.4527, "lr": 3.978065445796778e-05, "epoch": 0.7135549872122762, "percentage": 14.27, "elapsed_time": "1:41:39", "remaining_time": "10:10:41"}
+{"current_steps": 280, "total_steps": 1955, "loss": 0.5231, "lr": 3.977534715992816e-05, "epoch": 0.7161125319693095, "percentage": 14.32, "elapsed_time": "1:42:01", "remaining_time": "10:10:18"}
+{"current_steps": 281, "total_steps": 1955, "loss": 0.5022, "lr": 3.976997678183294e-05, "epoch": 0.7186700767263428, "percentage": 14.37, "elapsed_time": "1:42:21", "remaining_time": "10:09:45"}
+{"current_steps": 282, "total_steps": 1955, "loss": 0.5042, "lr": 3.9764543340812745e-05, "epoch": 0.7212276214833759, "percentage": 14.42, "elapsed_time": "1:42:44", "remaining_time": "10:09:33"}
+{"current_steps": 283, "total_steps": 1955, "loss": 0.4853, "lr": 3.9759046854199336e-05, "epoch": 0.7237851662404092, "percentage": 14.48, "elapsed_time": "1:43:07", "remaining_time": "10:09:18"}
+{"current_steps": 284, "total_steps": 1955, "loss": 0.4992, "lr": 3.975348733952559e-05, "epoch": 0.7263427109974424, "percentage": 14.53, "elapsed_time": "1:43:31", "remaining_time": "10:09:04"}
+{"current_steps": 285, "total_steps": 1955, "loss": 0.5127, "lr": 3.974786481452543e-05, "epoch": 0.7289002557544757, "percentage": 14.58, "elapsed_time": "1:43:52", "remaining_time": "10:08:41"}
+{"current_steps": 286, "total_steps": 1955, "loss": 0.4683, "lr": 3.9742179297133774e-05, "epoch": 0.731457800511509, "percentage": 14.63, "elapsed_time": "1:44:10", "remaining_time": "10:07:54"}
+{"current_steps": 287, "total_steps": 1955, "loss": 0.4597, "lr": 3.973643080548647e-05, "epoch": 0.7340153452685422, "percentage": 14.68, "elapsed_time": "1:44:34", "remaining_time": "10:07:47"}
+{"current_steps": 288, "total_steps": 1955, "loss": 0.5261, "lr": 3.973061935792025e-05, "epoch": 0.7365728900255755, "percentage": 14.73, "elapsed_time": "1:44:53", "remaining_time": "10:07:08"}
+{"current_steps": 289, "total_steps": 1955, "loss": 0.4669, "lr": 3.972474497297266e-05, "epoch": 0.7391304347826086, "percentage": 14.78, "elapsed_time": "1:45:17", "remaining_time": "10:06:57"}
+{"current_steps": 290, "total_steps": 1955, "loss": 0.4872, "lr": 3.971880766938201e-05, "epoch": 0.7416879795396419, "percentage": 14.83, "elapsed_time": "1:45:39", "remaining_time": "10:06:38"}
+{"current_steps": 291, "total_steps": 1955, "loss": 0.5228, "lr": 3.97128074660873e-05, "epoch": 0.7442455242966752, "percentage": 14.88, "elapsed_time": "1:46:01", "remaining_time": "10:06:15"}
+{"current_steps": 292, "total_steps": 1955, "loss": 0.4919, "lr": 3.970674438222818e-05, "epoch": 0.7468030690537084, "percentage": 14.94, "elapsed_time": "1:46:23", "remaining_time": "10:05:55"}
+{"current_steps": 293, "total_steps": 1955, "loss": 0.4755, "lr": 3.9700618437144875e-05, "epoch": 0.7493606138107417, "percentage": 14.99, "elapsed_time": "1:46:45", "remaining_time": "10:05:34"}
+{"current_steps": 294, "total_steps": 1955, "loss": 0.4945, "lr": 3.969442965037814e-05, "epoch": 0.7519181585677749, "percentage": 15.04, "elapsed_time": "1:47:07", "remaining_time": "10:05:13"}
+{"current_steps": 295, "total_steps": 1955, "loss": 0.4884, "lr": 3.9688178041669146e-05, "epoch": 0.7544757033248082, "percentage": 15.09, "elapsed_time": "1:47:24", "remaining_time": "10:04:23"}
+{"current_steps": 296, "total_steps": 1955, "loss": 0.4583, "lr": 3.9681863630959493e-05, "epoch": 0.7570332480818415, "percentage": 15.14, "elapsed_time": "1:47:42", "remaining_time": "10:03:42"}
+{"current_steps": 297, "total_steps": 1955, "loss": 0.5337, "lr": 3.967548643839111e-05, "epoch": 0.7595907928388747, "percentage": 15.19, "elapsed_time": "1:48:05", "remaining_time": "10:03:23"}
+{"current_steps": 298, "total_steps": 1955, "loss": 0.5107, "lr": 3.966904648430616e-05, "epoch": 0.7621483375959079, "percentage": 15.24, "elapsed_time": "1:48:26", "remaining_time": "10:02:57"}
+{"current_steps": 299, "total_steps": 1955, "loss": 0.4987, "lr": 3.966254378924702e-05, "epoch": 0.7647058823529411, "percentage": 15.29, "elapsed_time": "1:48:47", "remaining_time": "10:02:32"}
+{"current_steps": 300, "total_steps": 1955, "loss": 0.5417, "lr": 3.965597837395621e-05, "epoch": 0.7672634271099744, "percentage": 15.35, "elapsed_time": "1:49:06", "remaining_time": "10:01:57"}
+{"current_steps": 301, "total_steps": 1955, "loss": 0.49, "lr": 3.9649350259376305e-05, "epoch": 0.7698209718670077, "percentage": 15.4, "elapsed_time": "1:49:29", "remaining_time": "10:01:38"}
+{"current_steps": 302, "total_steps": 1955, "loss": 0.4719, "lr": 3.9642659466649885e-05, "epoch": 0.7723785166240409, "percentage": 15.45, "elapsed_time": "1:49:51", "remaining_time": "10:01:16"}
+{"current_steps": 303, "total_steps": 1955, "loss": 0.4972, "lr": 3.9635906017119465e-05, "epoch": 0.7749360613810742, "percentage": 15.5, "elapsed_time": "1:50:08", "remaining_time": "10:00:28"}
+{"current_steps": 304, "total_steps": 1955, "loss": 0.4767, "lr": 3.9629089932327416e-05, "epoch": 0.7774936061381074, "percentage": 15.55, "elapsed_time": "1:50:31", "remaining_time": "10:00:14"}
+{"current_steps": 305, "total_steps": 1955, "loss": 0.4813, "lr": 3.9622211234015916e-05, "epoch": 0.7800511508951407, "percentage": 15.6, "elapsed_time": "1:50:55", "remaining_time": "10:00:03"}
+{"current_steps": 306, "total_steps": 1955, "loss": 0.4788, "lr": 3.961526994412686e-05, "epoch": 0.782608695652174, "percentage": 15.65, "elapsed_time": "1:51:17", "remaining_time": "9:59:43"}
+{"current_steps": 307, "total_steps": 1955, "loss": 0.4932, "lr": 3.96082660848018e-05, "epoch": 0.7851662404092071, "percentage": 15.7, "elapsed_time": "1:51:42", "remaining_time": "9:59:37"}
+{"current_steps": 308, "total_steps": 1955, "loss": 0.4813, "lr": 3.9601199678381884e-05, "epoch": 0.7877237851662404, "percentage": 15.75, "elapsed_time": "1:52:06", "remaining_time": "9:59:27"}
+{"current_steps": 309, "total_steps": 1955, "loss": 0.4627, "lr": 3.959407074740776e-05, "epoch": 0.7902813299232737, "percentage": 15.81, "elapsed_time": "1:52:26", "remaining_time": "9:58:59"}
+{"current_steps": 310, "total_steps": 1955, "loss": 0.5, "lr": 3.958687931461954e-05, "epoch": 0.7928388746803069, "percentage": 15.86, "elapsed_time": "1:52:49", "remaining_time": "9:58:40"}
+{"current_steps": 311, "total_steps": 1955, "loss": 0.4918, "lr": 3.957962540295669e-05, "epoch": 0.7953964194373402, "percentage": 15.91, "elapsed_time": "1:53:11", "remaining_time": "9:58:20"}
+{"current_steps": 312, "total_steps": 1955, "loss": 0.4835, "lr": 3.9572309035557974e-05, "epoch": 0.7979539641943734, "percentage": 15.96, "elapsed_time": "1:53:34", "remaining_time": "9:58:04"}
+{"current_steps": 313, "total_steps": 1955, "loss": 0.4868, "lr": 3.956493023576139e-05, "epoch": 0.8005115089514067, "percentage": 16.01, "elapsed_time": "1:53:55", "remaining_time": "9:57:40"}
+{"current_steps": 314, "total_steps": 1955, "loss": 0.5004, "lr": 3.955748902710406e-05, "epoch": 0.80306905370844, "percentage": 16.06, "elapsed_time": "1:54:19", "remaining_time": "9:57:26"}
+{"current_steps": 315, "total_steps": 1955, "loss": 0.5095, "lr": 3.954998543332221e-05, "epoch": 0.8056265984654731, "percentage": 16.11, "elapsed_time": "1:54:41", "remaining_time": "9:57:05"}
+{"current_steps": 316, "total_steps": 1955, "loss": 0.4951, "lr": 3.9542419478351043e-05, "epoch": 0.8081841432225064, "percentage": 16.16, "elapsed_time": "1:55:01", "remaining_time": "9:56:36"}
+{"current_steps": 317, "total_steps": 1955, "loss": 0.4935, "lr": 3.953479118632471e-05, "epoch": 0.8107416879795396, "percentage": 16.21, "elapsed_time": "1:55:22", "remaining_time": "9:56:12"}
+{"current_steps": 318, "total_steps": 1955, "loss": 0.4696, "lr": 3.952710058157617e-05, "epoch": 0.8132992327365729, "percentage": 16.27, "elapsed_time": "1:55:45", "remaining_time": "9:55:53"}
+{"current_steps": 319, "total_steps": 1955, "loss": 0.4752, "lr": 3.9519347688637185e-05, "epoch": 0.8158567774936062, "percentage": 16.32, "elapsed_time": "1:56:09", "remaining_time": "9:55:45"}
+{"current_steps": 320, "total_steps": 1955, "loss": 0.4811, "lr": 3.951153253223817e-05, "epoch": 0.8184143222506394, "percentage": 16.37, "elapsed_time": "1:56:30", "remaining_time": "9:55:16"}
+{"current_steps": 321, "total_steps": 1955, "loss": 0.4954, "lr": 3.950365513730818e-05, "epoch": 0.8209718670076727, "percentage": 16.42, "elapsed_time": "1:56:53", "remaining_time": "9:54:59"}
+{"current_steps": 322, "total_steps": 1955, "loss": 0.4789, "lr": 3.949571552897479e-05, "epoch": 0.8235294117647058, "percentage": 16.47, "elapsed_time": "1:57:12", "remaining_time": "9:54:27"}
+{"current_steps": 323, "total_steps": 1955, "loss": 0.4526, "lr": 3.948771373256402e-05, "epoch": 0.8260869565217391, "percentage": 16.52, "elapsed_time": "1:57:32", "remaining_time": "9:53:54"}
+{"current_steps": 324, "total_steps": 1955, "loss": 0.4845, "lr": 3.947964977360027e-05, "epoch": 0.8286445012787724, "percentage": 16.57, "elapsed_time": "1:57:52", "remaining_time": "9:53:24"}
+{"current_steps": 325, "total_steps": 1955, "loss": 0.4607, "lr": 3.947152367780621e-05, "epoch": 0.8312020460358056, "percentage": 16.62, "elapsed_time": "1:58:16", "remaining_time": "9:53:09"}
+{"current_steps": 326, "total_steps": 1955, "loss": 0.5179, "lr": 3.946333547110275e-05, "epoch": 0.8337595907928389, "percentage": 16.68, "elapsed_time": "1:58:35", "remaining_time": "9:52:34"}
+{"current_steps": 327, "total_steps": 1955, "loss": 0.4559, "lr": 3.945508517960889e-05, "epoch": 0.8363171355498721, "percentage": 16.73, "elapsed_time": "1:58:57", "remaining_time": "9:52:17"}
+{"current_steps": 328, "total_steps": 1955, "loss": 0.4762, "lr": 3.944677282964169e-05, "epoch": 0.8388746803069054, "percentage": 16.78, "elapsed_time": "1:59:17", "remaining_time": "9:51:45"}
+{"current_steps": 329, "total_steps": 1955, "loss": 0.4988, "lr": 3.943839844771614e-05, "epoch": 0.8414322250639387, "percentage": 16.83, "elapsed_time": "1:59:39", "remaining_time": "9:51:24"}
+{"current_steps": 330, "total_steps": 1955, "loss": 0.5063, "lr": 3.942996206054513e-05, "epoch": 0.8439897698209718, "percentage": 16.88, "elapsed_time": "1:59:59", "remaining_time": "9:50:51"}
+{"current_steps": 331, "total_steps": 1955, "loss": 0.4961, "lr": 3.942146369503933e-05, "epoch": 0.8465473145780051, "percentage": 16.93, "elapsed_time": "2:00:19", "remaining_time": "9:50:19"}
+{"current_steps": 332, "total_steps": 1955, "loss": 0.4765, "lr": 3.941290337830711e-05, "epoch": 0.8491048593350383, "percentage": 16.98, "elapsed_time": "2:00:42", "remaining_time": "9:50:07"}
+{"current_steps": 333, "total_steps": 1955, "loss": 0.4672, "lr": 3.940428113765445e-05, "epoch": 0.8516624040920716, "percentage": 17.03, "elapsed_time": "2:01:04", "remaining_time": "9:49:45"}
+{"current_steps": 334, "total_steps": 1955, "loss": 0.5004, "lr": 3.9395597000584844e-05, "epoch": 0.8542199488491049, "percentage": 17.08, "elapsed_time": "2:01:24", "remaining_time": "9:49:16"}
+{"current_steps": 335, "total_steps": 1955, "loss": 0.4704, "lr": 3.938685099479926e-05, "epoch": 0.8567774936061381, "percentage": 17.14, "elapsed_time": "2:01:49", "remaining_time": "9:49:06"}
+{"current_steps": 336, "total_steps": 1955, "loss": 0.4756, "lr": 3.9378043148195975e-05, "epoch": 0.8593350383631714, "percentage": 17.19, "elapsed_time": "2:02:09", "remaining_time": "9:48:38"}
+{"current_steps": 337, "total_steps": 1955, "loss": 0.4936, "lr": 3.936917348887057e-05, "epoch": 0.8618925831202046, "percentage": 17.24, "elapsed_time": "2:02:31", "remaining_time": "9:48:14"}
+{"current_steps": 338, "total_steps": 1955, "loss": 0.4699, "lr": 3.9360242045115764e-05, "epoch": 0.8644501278772379, "percentage": 17.29, "elapsed_time": "2:02:55", "remaining_time": "9:48:02"}
+{"current_steps": 339, "total_steps": 1955, "loss": 0.4774, "lr": 3.935124884542137e-05, "epoch": 0.8670076726342711, "percentage": 17.34, "elapsed_time": "2:03:15", "remaining_time": "9:47:35"}
+{"current_steps": 340, "total_steps": 1955, "loss": 0.4648, "lr": 3.9342193918474205e-05, "epoch": 0.8695652173913043, "percentage": 17.39, "elapsed_time": "2:03:39", "remaining_time": "9:47:21"}
+{"current_steps": 341, "total_steps": 1955, "loss": 0.465, "lr": 3.9333077293157956e-05, "epoch": 0.8721227621483376, "percentage": 17.44, "elapsed_time": "2:03:59", "remaining_time": "9:46:52"}
+{"current_steps": 342, "total_steps": 1955, "loss": 0.5018, "lr": 3.9323898998553155e-05, "epoch": 0.8746803069053708, "percentage": 17.49, "elapsed_time": "2:04:21", "remaining_time": "9:46:31"}
+{"current_steps": 343, "total_steps": 1955, "loss": 0.4873, "lr": 3.931465906393702e-05, "epoch": 0.8772378516624041, "percentage": 17.54, "elapsed_time": "2:04:44", "remaining_time": "9:46:16"}
+{"current_steps": 344, "total_steps": 1955, "loss": 0.4502, "lr": 3.93053575187834e-05, "epoch": 0.8797953964194374, "percentage": 17.6, "elapsed_time": "2:05:00", "remaining_time": "9:45:24"}
+{"current_steps": 345, "total_steps": 1955, "loss": 0.4649, "lr": 3.929599439276268e-05, "epoch": 0.8823529411764706, "percentage": 17.65, "elapsed_time": "2:05:23", "remaining_time": "9:45:07"}
+{"current_steps": 346, "total_steps": 1955, "loss": 0.4879, "lr": 3.928656971574165e-05, "epoch": 0.8849104859335039, "percentage": 17.7, "elapsed_time": "2:05:44", "remaining_time": "9:44:45"}
+{"current_steps": 347, "total_steps": 1955, "loss": 0.5072, "lr": 3.9277083517783465e-05, "epoch": 0.887468030690537, "percentage": 17.75, "elapsed_time": "2:06:07", "remaining_time": "9:44:26"}
+{"current_steps": 348, "total_steps": 1955, "loss": 0.4696, "lr": 3.926753582914752e-05, "epoch": 0.8900255754475703, "percentage": 17.8, "elapsed_time": "2:06:32", "remaining_time": "9:44:18"}
+{"current_steps": 349, "total_steps": 1955, "loss": 0.5515, "lr": 3.925792668028934e-05, "epoch": 0.8925831202046036, "percentage": 17.85, "elapsed_time": "2:06:53", "remaining_time": "9:43:55"}
+{"current_steps": 350, "total_steps": 1955, "loss": 0.4926, "lr": 3.9248256101860504e-05, "epoch": 0.8951406649616368, "percentage": 17.9, "elapsed_time": "2:07:12", "remaining_time": "9:43:22"}
+{"current_steps": 351, "total_steps": 1955, "loss": 0.486, "lr": 3.9238524124708545e-05, "epoch": 0.8976982097186701, "percentage": 17.95, "elapsed_time": "2:07:33", "remaining_time": "9:42:54"}
+{"current_steps": 352, "total_steps": 1955, "loss": 0.4958, "lr": 3.922873077987685e-05, "epoch": 0.9002557544757033, "percentage": 18.01, "elapsed_time": "2:07:53", "remaining_time": "9:42:23"}
+{"current_steps": 353, "total_steps": 1955, "loss": 0.4658, "lr": 3.921887609860455e-05, "epoch": 0.9028132992327366, "percentage": 18.06, "elapsed_time": "2:08:17", "remaining_time": "9:42:11"}
+{"current_steps": 354, "total_steps": 1955, "loss": 0.5137, "lr": 3.920896011232643e-05, "epoch": 0.9053708439897699, "percentage": 18.11, "elapsed_time": "2:08:35", "remaining_time": "9:41:34"}
+{"current_steps": 355, "total_steps": 1955, "loss": 0.4834, "lr": 3.919898285267283e-05, "epoch": 0.907928388746803, "percentage": 18.16, "elapsed_time": "2:08:56", "remaining_time": "9:41:08"}
+{"current_steps": 356, "total_steps": 1955, "loss": 0.4999, "lr": 3.918894435146955e-05, "epoch": 0.9104859335038363, "percentage": 18.21, "elapsed_time": "2:09:17", "remaining_time": "9:40:45"}
+{"current_steps": 357, "total_steps": 1955, "loss": 0.4647, "lr": 3.9178844640737726e-05, "epoch": 0.9130434782608695, "percentage": 18.26, "elapsed_time": "2:09:40", "remaining_time": "9:40:28"}
+{"current_steps": 358, "total_steps": 1955, "loss": 0.4707, "lr": 3.916868375269375e-05, "epoch": 0.9156010230179028, "percentage": 18.31, "elapsed_time": "2:10:04", "remaining_time": "9:40:16"}
+{"current_steps": 359, "total_steps": 1955, "loss": 0.4714, "lr": 3.915846171974916e-05, "epoch": 0.9181585677749361, "percentage": 18.36, "elapsed_time": "2:10:26", "remaining_time": "9:39:52"}
+{"current_steps": 360, "total_steps": 1955, "loss": 0.4898, "lr": 3.914817857451054e-05, "epoch": 0.9207161125319693, "percentage": 18.41, "elapsed_time": "2:10:47", "remaining_time": "9:39:26"}
+{"current_steps": 361, "total_steps": 1955, "loss": 0.4877, "lr": 3.913783434977939e-05, "epoch": 0.9232736572890026, "percentage": 18.47, "elapsed_time": "2:11:09", "remaining_time": "9:39:09"}
+{"current_steps": 362, "total_steps": 1955, "loss": 0.4838, "lr": 3.9127429078552074e-05, "epoch": 0.9258312020460358, "percentage": 18.52, "elapsed_time": "2:11:32", "remaining_time": "9:38:50"}
+{"current_steps": 363, "total_steps": 1955, "loss": 0.4961, "lr": 3.9116962794019663e-05, "epoch": 0.928388746803069, "percentage": 18.57, "elapsed_time": "2:11:55", "remaining_time": "9:38:33"}
+{"current_steps": 364, "total_steps": 1955, "loss": 0.4473, "lr": 3.9106435529567856e-05, "epoch": 0.9309462915601023, "percentage": 18.62, "elapsed_time": "2:12:18", "remaining_time": "9:38:16"}
+{"current_steps": 365, "total_steps": 1955, "loss": 0.4889, "lr": 3.909584731877688e-05, "epoch": 0.9335038363171355, "percentage": 18.67, "elapsed_time": "2:12:39", "remaining_time": "9:37:54"}
+{"current_steps": 366, "total_steps": 1955, "loss": 0.4743, "lr": 3.9085198195421354e-05, "epoch": 0.9360613810741688, "percentage": 18.72, "elapsed_time": "2:13:02", "remaining_time": "9:37:35"}
+{"current_steps": 367, "total_steps": 1955, "loss": 0.4685, "lr": 3.907448819347019e-05, "epoch": 0.9386189258312021, "percentage": 18.77, "elapsed_time": "2:13:22", "remaining_time": "9:37:04"}
+{"current_steps": 368, "total_steps": 1955, "loss": 0.4797, "lr": 3.906371734708653e-05, "epoch": 0.9411764705882353, "percentage": 18.82, "elapsed_time": "2:13:43", "remaining_time": "9:36:40"}
+{"current_steps": 369, "total_steps": 1955, "loss": 0.4996, "lr": 3.905288569062756e-05, "epoch": 0.9437340153452686, "percentage": 18.87, "elapsed_time": "2:14:05", "remaining_time": "9:36:21"}
+{"current_steps": 370, "total_steps": 1955, "loss": 0.4927, "lr": 3.9041993258644456e-05, "epoch": 0.9462915601023018, "percentage": 18.93, "elapsed_time": "2:14:28", "remaining_time": "9:36:04"}
+{"current_steps": 371, "total_steps": 1955, "loss": 0.4658, "lr": 3.9031040085882265e-05, "epoch": 0.948849104859335, "percentage": 18.98, "elapsed_time": "2:14:52", "remaining_time": "9:35:52"}
+{"current_steps": 372, "total_steps": 1955, "loss": 0.4702, "lr": 3.902002620727977e-05, "epoch": 0.9514066496163683, "percentage": 19.03, "elapsed_time": "2:15:07", "remaining_time": "9:35:00"}
+{"current_steps": 373, "total_steps": 1955, "loss": 0.4917, "lr": 3.900895165796941e-05, "epoch": 0.9539641943734015, "percentage": 19.08, "elapsed_time": "2:15:30", "remaining_time": "9:34:42"}
+{"current_steps": 374, "total_steps": 1955, "loss": 0.4648, "lr": 3.8997816473277144e-05, "epoch": 0.9565217391304348, "percentage": 19.13, "elapsed_time": "2:15:51", "remaining_time": "9:34:17"}
+{"current_steps": 375, "total_steps": 1955, "loss": 0.5054, "lr": 3.898662068872236e-05, "epoch": 0.959079283887468, "percentage": 19.18, "elapsed_time": "2:16:10", "remaining_time": "9:33:43"}
+{"current_steps": 376, "total_steps": 1955, "loss": 0.4792, "lr": 3.897536434001773e-05, "epoch": 0.9616368286445013, "percentage": 19.23, "elapsed_time": "2:16:35", "remaining_time": "9:33:34"}
+{"current_steps": 377, "total_steps": 1955, "loss": 0.5003, "lr": 3.896404746306914e-05, "epoch": 0.9641943734015346, "percentage": 19.28, "elapsed_time": "2:16:58", "remaining_time": "9:33:19"}
+{"current_steps": 378, "total_steps": 1955, "loss": 0.5123, "lr": 3.895267009397553e-05, "epoch": 0.9667519181585678, "percentage": 19.34, "elapsed_time": "2:17:22", "remaining_time": "9:33:06"}
+{"current_steps": 379, "total_steps": 1955, "loss": 0.4543, "lr": 3.894123226902881e-05, "epoch": 0.969309462915601, "percentage": 19.39, "elapsed_time": "2:17:42", "remaining_time": "9:32:37"}
+{"current_steps": 380, "total_steps": 1955, "loss": 0.469, "lr": 3.892973402471373e-05, "epoch": 0.9718670076726342, "percentage": 19.44, "elapsed_time": "2:18:03", "remaining_time": "9:32:11"}
+{"current_steps": 381, "total_steps": 1955, "loss": 0.4544, "lr": 3.891817539770777e-05, "epoch": 0.9744245524296675, "percentage": 19.49, "elapsed_time": "2:18:24", "remaining_time": "9:31:47"}
+{"current_steps": 382, "total_steps": 1955, "loss": 0.5424, "lr": 3.890655642488102e-05, "epoch": 0.9769820971867008, "percentage": 19.54, "elapsed_time": "2:18:45", "remaining_time": "9:31:24"}
+{"current_steps": 383, "total_steps": 1955, "loss": 0.5016, "lr": 3.889487714329606e-05, "epoch": 0.979539641943734, "percentage": 19.59, "elapsed_time": "2:19:07", "remaining_time": "9:31:01"}
+{"current_steps": 384, "total_steps": 1955, "loss": 0.4588, "lr": 3.8883137590207863e-05, "epoch": 0.9820971867007673, "percentage": 19.64, "elapsed_time": "2:19:30", "remaining_time": "9:30:44"}
+{"current_steps": 385, "total_steps": 1955, "loss": 0.4623, "lr": 3.8871337803063626e-05, "epoch": 0.9846547314578005, "percentage": 19.69, "elapsed_time": "2:19:54", "remaining_time": "9:30:33"}
+{"current_steps": 386, "total_steps": 1955, "loss": 0.4688, "lr": 3.885947781950271e-05, "epoch": 0.9872122762148338, "percentage": 19.74, "elapsed_time": "2:20:18", "remaining_time": "9:30:20"}
+{"current_steps": 387, "total_steps": 1955, "loss": 0.4696, "lr": 3.884755767735647e-05, "epoch": 0.989769820971867, "percentage": 19.8, "elapsed_time": "2:20:36", "remaining_time": "9:29:40"}
+{"current_steps": 388, "total_steps": 1955, "loss": 0.4888, "lr": 3.883557741464819e-05, "epoch": 0.9923273657289002, "percentage": 19.85, "elapsed_time": "2:20:58", "remaining_time": "9:29:22"}
+{"current_steps": 389, "total_steps": 1955, "loss": 0.5048, "lr": 3.882353706959289e-05, "epoch": 0.9948849104859335, "percentage": 19.9, "elapsed_time": "2:21:21", "remaining_time": "9:29:05"}
+{"current_steps": 390, "total_steps": 1955, "loss": 0.4626, "lr": 3.8811436680597266e-05, "epoch": 0.9974424552429667, "percentage": 19.95, "elapsed_time": "2:21:46", "remaining_time": "9:28:55"}
+{"current_steps": 391, "total_steps": 1955, "loss": 0.4768, "lr": 3.8799276286259535e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "2:22:09", "remaining_time": "9:28:36"}
+{"current_steps": 392, "total_steps": 1955, "loss": 0.4003, "lr": 3.878705592536933e-05, "epoch": 1.0025575447570332, "percentage": 20.05, "elapsed_time": "2:23:13", "remaining_time": "9:31:04"}
+{"current_steps": 393, "total_steps": 1955, "loss": 0.4111, "lr": 3.877477563690756e-05, "epoch": 1.0051150895140666, "percentage": 20.1, "elapsed_time": "2:23:32", "remaining_time": "9:30:32"}
+{"current_steps": 394, "total_steps": 1955, "loss": 0.4555, "lr": 3.87624354600463e-05, "epoch": 1.0076726342710998, "percentage": 20.15, "elapsed_time": "2:23:55", "remaining_time": "9:30:13"}
+{"current_steps": 395, "total_steps": 1955, "loss": 0.4177, "lr": 3.8750035434148644e-05, "epoch": 1.010230179028133, "percentage": 20.2, "elapsed_time": "2:24:18", "remaining_time": "9:29:53"}
+{"current_steps": 396, "total_steps": 1955, "loss": 0.4034, "lr": 3.8737575598768605e-05, "epoch": 1.0127877237851663, "percentage": 20.26, "elapsed_time": "2:24:38", "remaining_time": "9:29:25"}
+{"current_steps": 397, "total_steps": 1955, "loss": 0.3993, "lr": 3.872505599365098e-05, "epoch": 1.0153452685421995, "percentage": 20.31, "elapsed_time": "2:24:56", "remaining_time": "9:28:47"}
+{"current_steps": 398, "total_steps": 1955, "loss": 0.4413, "lr": 3.871247665873123e-05, "epoch": 1.0179028132992327, "percentage": 20.36, "elapsed_time": "2:25:20", "remaining_time": "9:28:33"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4b2503653384ce72e0d3e2cdcdeb594e4403c12f0947535ce8de87d4f5f980
+size 7160