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 sha256:2cd8d7f4abcb36472761013475a2b53170c7871f64adae95c328fc400407ef70
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ece527e316fb395cc032b5c0714db37418afd5c4b34a180809245392f561539
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f11f29e04d381fd014e1aa23b15294cf36ccb780f46c71b810daf861c63eadd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97eee80a2d33825e1b8ddabdabad4172541ffa29bd01b12aff8de21076df8d2
+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 +1,334 @@
+{"current_steps": 1, "total_steps": 939, "loss": 0.9383, "lr": 4.2553191489361704e-07, "epoch": 0.003194888178913738, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:52:23"}
+{"current_steps": 2, "total_steps": 939, "loss": 0.8501, "lr": 8.510638297872341e-07, "epoch": 0.006389776357827476, "percentage": 0.21, "elapsed_time": "0:00:29", "remaining_time": "3:48:12"}
+{"current_steps": 3, "total_steps": 939, "loss": 0.887, "lr": 1.276595744680851e-06, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:28:34"}
+{"current_steps": 4, "total_steps": 939, "loss": 0.8099, "lr": 1.7021276595744682e-06, "epoch": 0.012779552715654952, "percentage": 0.43, "elapsed_time": "0:00:52", "remaining_time": "3:25:15"}
+{"current_steps": 5, "total_steps": 939, "loss": 0.876, "lr": 2.1276595744680853e-06, "epoch": 0.01597444089456869, "percentage": 0.53, "elapsed_time": "0:01:04", "remaining_time": "3:20:29"}
+{"current_steps": 6, "total_steps": 939, "loss": 0.8158, "lr": 2.553191489361702e-06, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:14", "remaining_time": "3:13:51"}
+{"current_steps": 7, "total_steps": 939, "loss": 0.8368, "lr": 2.978723404255319e-06, "epoch": 0.022364217252396165, "percentage": 0.75, "elapsed_time": "0:01:26", "remaining_time": "3:11:34"}
+{"current_steps": 8, "total_steps": 939, "loss": 0.7747, "lr": 3.4042553191489363e-06, "epoch": 0.025559105431309903, "percentage": 0.85, "elapsed_time": "0:01:36", "remaining_time": "3:07:38"}
+{"current_steps": 9, "total_steps": 939, "loss": 0.7551, "lr": 3.8297872340425535e-06, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:48", "remaining_time": "3:07:15"}
+{"current_steps": 10, "total_steps": 939, "loss": 0.7211, "lr": 4.255319148936171e-06, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:02:00", "remaining_time": "3:05:50"}
+{"current_steps": 11, "total_steps": 939, "loss": 0.7667, "lr": 4.680851063829788e-06, "epoch": 0.03514376996805112, "percentage": 1.17, "elapsed_time": "0:02:12", "remaining_time": "3:05:41"}
+{"current_steps": 12, "total_steps": 939, "loss": 0.8135, "lr": 5.106382978723404e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:23", "remaining_time": "3:05:11"}
+{"current_steps": 13, "total_steps": 939, "loss": 0.738, "lr": 5.531914893617022e-06, "epoch": 0.04153354632587859, "percentage": 1.38, "elapsed_time": "0:02:31", "remaining_time": "2:59:40"}
+{"current_steps": 14, "total_steps": 939, "loss": 0.7383, "lr": 5.957446808510638e-06, "epoch": 0.04472843450479233, "percentage": 1.49, "elapsed_time": "0:02:40", "remaining_time": "2:56:46"}
+{"current_steps": 15, "total_steps": 939, "loss": 0.6796, "lr": 6.382978723404256e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:51", "remaining_time": "2:56:00"}
+{"current_steps": 16, "total_steps": 939, "loss": 0.6902, "lr": 6.808510638297873e-06, "epoch": 0.051118210862619806, "percentage": 1.7, "elapsed_time": "0:03:00", "remaining_time": "2:53:48"}
+{"current_steps": 17, "total_steps": 939, "loss": 0.6386, "lr": 7.234042553191491e-06, "epoch": 0.054313099041533544, "percentage": 1.81, "elapsed_time": "0:03:12", "remaining_time": "2:53:34"}
+{"current_steps": 18, "total_steps": 939, "loss": 0.6893, "lr": 7.659574468085107e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:24", "remaining_time": "2:54:02"}
+{"current_steps": 19, "total_steps": 939, "loss": 0.6776, "lr": 8.085106382978723e-06, "epoch": 0.06070287539936102, "percentage": 2.02, "elapsed_time": "0:03:36", "remaining_time": "2:54:41"}
+{"current_steps": 20, "total_steps": 939, "loss": 0.6205, "lr": 8.510638297872341e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:03:46", "remaining_time": "2:53:11"}
+{"current_steps": 21, "total_steps": 939, "loss": 0.6056, "lr": 8.936170212765958e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:57", "remaining_time": "2:53:03"}
+{"current_steps": 22, "total_steps": 939, "loss": 0.555, "lr": 9.361702127659576e-06, "epoch": 0.07028753993610223, "percentage": 2.34, "elapsed_time": "0:04:06", "remaining_time": "2:51:21"}
+{"current_steps": 23, "total_steps": 939, "loss": 0.6666, "lr": 9.787234042553192e-06, "epoch": 0.07348242811501597, "percentage": 2.45, "elapsed_time": "0:04:17", "remaining_time": "2:51:10"}
+{"current_steps": 24, "total_steps": 939, "loss": 0.6504, "lr": 1.0212765957446808e-05, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:26", "remaining_time": "2:49:15"}
+{"current_steps": 25, "total_steps": 939, "loss": 0.5772, "lr": 1.0638297872340426e-05, "epoch": 0.07987220447284345, "percentage": 2.66, "elapsed_time": "0:04:36", "remaining_time": "2:48:36"}
+{"current_steps": 26, "total_steps": 939, "loss": 0.6445, "lr": 1.1063829787234044e-05, "epoch": 0.08306709265175719, "percentage": 2.77, "elapsed_time": "0:04:48", "remaining_time": "2:49:00"}
+{"current_steps": 27, "total_steps": 939, "loss": 0.5923, "lr": 1.1489361702127662e-05, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:04:59", "remaining_time": "2:48:46"}
+{"current_steps": 28, "total_steps": 939, "loss": 0.6241, "lr": 1.1914893617021277e-05, "epoch": 0.08945686900958466, "percentage": 2.98, "elapsed_time": "0:05:12", "remaining_time": "2:49:16"}
+{"current_steps": 29, "total_steps": 939, "loss": 0.6283, "lr": 1.2340425531914895e-05, "epoch": 0.0926517571884984, "percentage": 3.09, "elapsed_time": "0:05:20", "remaining_time": "2:47:48"}
+{"current_steps": 30, "total_steps": 939, "loss": 0.6223, "lr": 1.2765957446808513e-05, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:05:30", "remaining_time": "2:47:06"}
+{"current_steps": 31, "total_steps": 939, "loss": 0.5931, "lr": 1.3191489361702127e-05, "epoch": 0.09904153354632587, "percentage": 3.3, "elapsed_time": "0:05:42", "remaining_time": "2:47:10"}
+{"current_steps": 32, "total_steps": 939, "loss": 0.6182, "lr": 1.3617021276595745e-05, "epoch": 0.10223642172523961, "percentage": 3.41, "elapsed_time": "0:05:53", "remaining_time": "2:47:02"}
+{"current_steps": 33, "total_steps": 939, "loss": 0.5675, "lr": 1.4042553191489363e-05, "epoch": 0.10543130990415335, "percentage": 3.51, "elapsed_time": "0:06:02", "remaining_time": "2:45:57"}
+{"current_steps": 34, "total_steps": 939, "loss": 0.596, "lr": 1.4468085106382981e-05, "epoch": 0.10862619808306709, "percentage": 3.62, "elapsed_time": "0:06:14", "remaining_time": "2:46:03"}
+{"current_steps": 35, "total_steps": 939, "loss": 0.5888, "lr": 1.4893617021276596e-05, "epoch": 0.11182108626198083, "percentage": 3.73, "elapsed_time": "0:06:25", "remaining_time": "2:45:51"}
+{"current_steps": 36, "total_steps": 939, "loss": 0.53, "lr": 1.5319148936170214e-05, "epoch": 0.11501597444089456, "percentage": 3.83, "elapsed_time": "0:06:37", "remaining_time": "2:46:17"}
+{"current_steps": 37, "total_steps": 939, "loss": 0.5871, "lr": 1.5744680851063832e-05, "epoch": 0.1182108626198083, "percentage": 3.94, "elapsed_time": "0:06:50", "remaining_time": "2:46:36"}
+{"current_steps": 38, "total_steps": 939, "loss": 0.5879, "lr": 1.6170212765957446e-05, "epoch": 0.12140575079872204, "percentage": 4.05, "elapsed_time": "0:07:00", "remaining_time": "2:46:03"}
+{"current_steps": 39, "total_steps": 939, "loss": 0.5539, "lr": 1.6595744680851064e-05, "epoch": 0.12460063897763578, "percentage": 4.15, "elapsed_time": "0:07:12", "remaining_time": "2:46:24"}
+{"current_steps": 40, "total_steps": 939, "loss": 0.5272, "lr": 1.7021276595744682e-05, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:07:23", "remaining_time": "2:46:06"}
+{"current_steps": 41, "total_steps": 939, "loss": 0.5524, "lr": 1.74468085106383e-05, "epoch": 0.13099041533546327, "percentage": 4.37, "elapsed_time": "0:07:35", "remaining_time": "2:46:20"}
+{"current_steps": 42, "total_steps": 939, "loss": 0.5781, "lr": 1.7872340425531915e-05, "epoch": 0.134185303514377, "percentage": 4.47, "elapsed_time": "0:07:44", "remaining_time": "2:45:30"}
+{"current_steps": 43, "total_steps": 939, "loss": 0.57, "lr": 1.8297872340425533e-05, "epoch": 0.13738019169329074, "percentage": 4.58, "elapsed_time": "0:07:54", "remaining_time": "2:44:49"}
+{"current_steps": 44, "total_steps": 939, "loss": 0.5459, "lr": 1.872340425531915e-05, "epoch": 0.14057507987220447, "percentage": 4.69, "elapsed_time": "0:08:05", "remaining_time": "2:44:35"}
+{"current_steps": 45, "total_steps": 939, "loss": 0.5854, "lr": 1.914893617021277e-05, "epoch": 0.14376996805111822, "percentage": 4.79, "elapsed_time": "0:08:16", "remaining_time": "2:44:31"}
+{"current_steps": 46, "total_steps": 939, "loss": 0.5667, "lr": 1.9574468085106384e-05, "epoch": 0.14696485623003194, "percentage": 4.9, "elapsed_time": "0:08:26", "remaining_time": "2:43:43"}
+{"current_steps": 47, "total_steps": 939, "loss": 0.6011, "lr": 2e-05, "epoch": 0.1501597444089457, "percentage": 5.01, "elapsed_time": "0:08:33", "remaining_time": "2:42:30"}
+{"current_steps": 48, "total_steps": 939, "loss": 0.58, "lr": 2.0425531914893616e-05, "epoch": 0.15335463258785942, "percentage": 5.11, "elapsed_time": "0:08:45", "remaining_time": "2:42:30"}
+{"current_steps": 49, "total_steps": 939, "loss": 0.5729, "lr": 2.0851063829787238e-05, "epoch": 0.15654952076677317, "percentage": 5.22, "elapsed_time": "0:08:55", "remaining_time": "2:42:08"}
+{"current_steps": 50, "total_steps": 939, "loss": 0.5442, "lr": 2.1276595744680852e-05, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:09:06", "remaining_time": "2:42:03"}
+{"current_steps": 51, "total_steps": 939, "loss": 0.5857, "lr": 2.1702127659574467e-05, "epoch": 0.16293929712460065, "percentage": 5.43, "elapsed_time": "0:09:18", "remaining_time": "2:41:56"}
+{"current_steps": 52, "total_steps": 939, "loss": 0.6012, "lr": 2.2127659574468088e-05, "epoch": 0.16613418530351437, "percentage": 5.54, "elapsed_time": "0:09:28", "remaining_time": "2:41:39"}
+{"current_steps": 53, "total_steps": 939, "loss": 0.5524, "lr": 2.2553191489361703e-05, "epoch": 0.16932907348242812, "percentage": 5.64, "elapsed_time": "0:09:35", "remaining_time": "2:40:18"}
+{"current_steps": 54, "total_steps": 939, "loss": 0.5442, "lr": 2.2978723404255324e-05, "epoch": 0.17252396166134185, "percentage": 5.75, "elapsed_time": "0:09:47", "remaining_time": "2:40:32"}
+{"current_steps": 55, "total_steps": 939, "loss": 0.5611, "lr": 2.340425531914894e-05, "epoch": 0.1757188498402556, "percentage": 5.86, "elapsed_time": "0:09:55", "remaining_time": "2:39:29"}
+{"current_steps": 56, "total_steps": 939, "loss": 0.5304, "lr": 2.3829787234042553e-05, "epoch": 0.17891373801916932, "percentage": 5.96, "elapsed_time": "0:10:05", "remaining_time": "2:39:12"}
+{"current_steps": 57, "total_steps": 939, "loss": 0.5587, "lr": 2.4255319148936175e-05, "epoch": 0.18210862619808307, "percentage": 6.07, "elapsed_time": "0:10:16", "remaining_time": "2:39:00"}
+{"current_steps": 58, "total_steps": 939, "loss": 0.5374, "lr": 2.468085106382979e-05, "epoch": 0.1853035143769968, "percentage": 6.18, "elapsed_time": "0:10:26", "remaining_time": "2:38:38"}
+{"current_steps": 59, "total_steps": 939, "loss": 0.5635, "lr": 2.5106382978723404e-05, "epoch": 0.18849840255591055, "percentage": 6.28, "elapsed_time": "0:10:34", "remaining_time": "2:37:37"}
+{"current_steps": 60, "total_steps": 939, "loss": 0.5536, "lr": 2.5531914893617025e-05, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:10:46", "remaining_time": "2:37:44"}
+{"current_steps": 61, "total_steps": 939, "loss": 0.5549, "lr": 2.595744680851064e-05, "epoch": 0.19488817891373802, "percentage": 6.5, "elapsed_time": "0:10:58", "remaining_time": "2:37:58"}
+{"current_steps": 62, "total_steps": 939, "loss": 0.5142, "lr": 2.6382978723404255e-05, "epoch": 0.19808306709265175, "percentage": 6.6, "elapsed_time": "0:11:05", "remaining_time": "2:36:53"}
+{"current_steps": 63, "total_steps": 939, "loss": 0.5533, "lr": 2.6808510638297876e-05, "epoch": 0.2012779552715655, "percentage": 6.71, "elapsed_time": "0:11:13", "remaining_time": "2:36:05"}
+{"current_steps": 64, "total_steps": 939, "loss": 0.5484, "lr": 2.723404255319149e-05, "epoch": 0.20447284345047922, "percentage": 6.82, "elapsed_time": "0:11:23", "remaining_time": "2:35:44"}
+{"current_steps": 65, "total_steps": 939, "loss": 0.5833, "lr": 2.7659574468085112e-05, "epoch": 0.20766773162939298, "percentage": 6.92, "elapsed_time": "0:11:34", "remaining_time": "2:35:38"}
+{"current_steps": 66, "total_steps": 939, "loss": 0.5216, "lr": 2.8085106382978727e-05, "epoch": 0.2108626198083067, "percentage": 7.03, "elapsed_time": "0:11:43", "remaining_time": "2:34:59"}
+{"current_steps": 67, "total_steps": 939, "loss": 0.5304, "lr": 2.851063829787234e-05, "epoch": 0.21405750798722045, "percentage": 7.14, "elapsed_time": "0:11:55", "remaining_time": "2:35:12"}
+{"current_steps": 68, "total_steps": 939, "loss": 0.5217, "lr": 2.8936170212765963e-05, "epoch": 0.21725239616613418, "percentage": 7.24, "elapsed_time": "0:12:01", "remaining_time": "2:33:59"}
+{"current_steps": 69, "total_steps": 939, "loss": 0.5758, "lr": 2.9361702127659577e-05, "epoch": 0.22044728434504793, "percentage": 7.35, "elapsed_time": "0:12:13", "remaining_time": "2:34:05"}
+{"current_steps": 70, "total_steps": 939, "loss": 0.5959, "lr": 2.9787234042553192e-05, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:12:25", "remaining_time": "2:34:17"}
+{"current_steps": 71, "total_steps": 939, "loss": 0.5113, "lr": 3.0212765957446813e-05, "epoch": 0.2268370607028754, "percentage": 7.56, "elapsed_time": "0:12:36", "remaining_time": "2:34:13"}
+{"current_steps": 72, "total_steps": 939, "loss": 0.5343, "lr": 3.063829787234043e-05, "epoch": 0.23003194888178913, "percentage": 7.67, "elapsed_time": "0:12:46", "remaining_time": "2:33:45"}
+{"current_steps": 73, "total_steps": 939, "loss": 0.5368, "lr": 3.1063829787234046e-05, "epoch": 0.23322683706070288, "percentage": 7.77, "elapsed_time": "0:12:57", "remaining_time": "2:33:44"}
+{"current_steps": 74, "total_steps": 939, "loss": 0.5187, "lr": 3.1489361702127664e-05, "epoch": 0.2364217252396166, "percentage": 7.88, "elapsed_time": "0:13:08", "remaining_time": "2:33:35"}
+{"current_steps": 75, "total_steps": 939, "loss": 0.5248, "lr": 3.191489361702128e-05, "epoch": 0.23961661341853036, "percentage": 7.99, "elapsed_time": "0:13:19", "remaining_time": "2:33:28"}
+{"current_steps": 76, "total_steps": 939, "loss": 0.547, "lr": 3.234042553191489e-05, "epoch": 0.24281150159744408, "percentage": 8.09, "elapsed_time": "0:13:30", "remaining_time": "2:33:22"}
+{"current_steps": 77, "total_steps": 939, "loss": 0.4987, "lr": 3.276595744680851e-05, "epoch": 0.24600638977635783, "percentage": 8.2, "elapsed_time": "0:13:38", "remaining_time": "2:32:40"}
+{"current_steps": 78, "total_steps": 939, "loss": 0.5372, "lr": 3.319148936170213e-05, "epoch": 0.24920127795527156, "percentage": 8.31, "elapsed_time": "0:13:50", "remaining_time": "2:32:51"}
+{"current_steps": 79, "total_steps": 939, "loss": 0.5534, "lr": 3.361702127659575e-05, "epoch": 0.2523961661341853, "percentage": 8.41, "elapsed_time": "0:14:02", "remaining_time": "2:32:52"}
+{"current_steps": 80, "total_steps": 939, "loss": 0.5124, "lr": 3.4042553191489365e-05, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:14:11", "remaining_time": "2:32:18"}
+{"current_steps": 81, "total_steps": 939, "loss": 0.5622, "lr": 3.446808510638298e-05, "epoch": 0.25878594249201275, "percentage": 8.63, "elapsed_time": "0:14:22", "remaining_time": "2:32:13"}
+{"current_steps": 82, "total_steps": 939, "loss": 0.5765, "lr": 3.48936170212766e-05, "epoch": 0.26198083067092653, "percentage": 8.73, "elapsed_time": "0:14:29", "remaining_time": "2:31:22"}
+{"current_steps": 83, "total_steps": 939, "loss": 0.5258, "lr": 3.531914893617022e-05, "epoch": 0.26517571884984026, "percentage": 8.84, "elapsed_time": "0:14:39", "remaining_time": "2:31:11"}
+{"current_steps": 84, "total_steps": 939, "loss": 0.4866, "lr": 3.574468085106383e-05, "epoch": 0.268370607028754, "percentage": 8.95, "elapsed_time": "0:14:47", "remaining_time": "2:30:28"}
+{"current_steps": 85, "total_steps": 939, "loss": 0.5806, "lr": 3.617021276595745e-05, "epoch": 0.2715654952076677, "percentage": 9.05, "elapsed_time": "0:14:55", "remaining_time": "2:29:55"}
+{"current_steps": 86, "total_steps": 939, "loss": 0.5617, "lr": 3.6595744680851066e-05, "epoch": 0.2747603833865815, "percentage": 9.16, "elapsed_time": "0:15:07", "remaining_time": "2:30:01"}
+{"current_steps": 87, "total_steps": 939, "loss": 0.5656, "lr": 3.7021276595744684e-05, "epoch": 0.2779552715654952, "percentage": 9.27, "elapsed_time": "0:15:19", "remaining_time": "2:30:04"}
+{"current_steps": 88, "total_steps": 939, "loss": 0.5978, "lr": 3.74468085106383e-05, "epoch": 0.28115015974440893, "percentage": 9.37, "elapsed_time": "0:15:31", "remaining_time": "2:30:10"}
+{"current_steps": 89, "total_steps": 939, "loss": 0.4934, "lr": 3.787234042553192e-05, "epoch": 0.28434504792332266, "percentage": 9.48, "elapsed_time": "0:15:44", "remaining_time": "2:30:17"}
+{"current_steps": 90, "total_steps": 939, "loss": 0.5292, "lr": 3.829787234042554e-05, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:15:55", "remaining_time": "2:30:14"}
+{"current_steps": 91, "total_steps": 939, "loss": 0.5444, "lr": 3.872340425531915e-05, "epoch": 0.29073482428115016, "percentage": 9.69, "elapsed_time": "0:16:06", "remaining_time": "2:30:05"}
+{"current_steps": 92, "total_steps": 939, "loss": 0.5111, "lr": 3.914893617021277e-05, "epoch": 0.2939297124600639, "percentage": 9.8, "elapsed_time": "0:16:17", "remaining_time": "2:30:00"}
+{"current_steps": 93, "total_steps": 939, "loss": 0.5495, "lr": 3.9574468085106385e-05, "epoch": 0.2971246006389776, "percentage": 9.9, "elapsed_time": "0:16:29", "remaining_time": "2:30:02"}
+{"current_steps": 94, "total_steps": 939, "loss": 0.5999, "lr": 4e-05, "epoch": 0.3003194888178914, "percentage": 10.01, "elapsed_time": "0:16:41", "remaining_time": "2:30:04"}
+{"current_steps": 95, "total_steps": 939, "loss": 0.5371, "lr": 3.999986177524551e-05, "epoch": 0.3035143769968051, "percentage": 10.12, "elapsed_time": "0:16:52", "remaining_time": "2:29:56"}
+{"current_steps": 96, "total_steps": 939, "loss": 0.5636, "lr": 3.999944710289265e-05, "epoch": 0.30670926517571884, "percentage": 10.22, "elapsed_time": "0:17:04", "remaining_time": "2:29:59"}
+{"current_steps": 97, "total_steps": 939, "loss": 0.5319, "lr": 3.9998755988673205e-05, "epoch": 0.30990415335463256, "percentage": 10.33, "elapsed_time": "0:17:12", "remaining_time": "2:29:24"}
+{"current_steps": 98, "total_steps": 939, "loss": 0.5626, "lr": 3.9997788442140105e-05, "epoch": 0.31309904153354634, "percentage": 10.44, "elapsed_time": "0:17:21", "remaining_time": "2:28:55"}
+{"current_steps": 99, "total_steps": 939, "loss": 0.5379, "lr": 3.999654447666721e-05, "epoch": 0.31629392971246006, "percentage": 10.54, "elapsed_time": "0:17:29", "remaining_time": "2:28:28"}
+{"current_steps": 100, "total_steps": 939, "loss": 0.5968, "lr": 3.999502410944923e-05, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:17:41", "remaining_time": "2:28:30"}
+{"current_steps": 101, "total_steps": 939, "loss": 0.5493, "lr": 3.99932273615014e-05, "epoch": 0.3226837060702875, "percentage": 10.76, "elapsed_time": "0:17:52", "remaining_time": "2:28:15"}
+{"current_steps": 102, "total_steps": 939, "loss": 0.582, "lr": 3.99911542576592e-05, "epoch": 0.3258785942492013, "percentage": 10.86, "elapsed_time": "0:18:02", "remaining_time": "2:28:02"}
+{"current_steps": 103, "total_steps": 939, "loss": 0.5239, "lr": 3.998880482657809e-05, "epoch": 0.329073482428115, "percentage": 10.97, "elapsed_time": "0:18:15", "remaining_time": "2:28:10"}
+{"current_steps": 104, "total_steps": 939, "loss": 0.5562, "lr": 3.9986179100733e-05, "epoch": 0.33226837060702874, "percentage": 11.08, "elapsed_time": "0:18:27", "remaining_time": "2:28:14"}
+{"current_steps": 105, "total_steps": 939, "loss": 0.5199, "lr": 3.9983277116417974e-05, "epoch": 0.3354632587859425, "percentage": 11.18, "elapsed_time": "0:18:38", "remaining_time": "2:28:06"}
+{"current_steps": 106, "total_steps": 939, "loss": 0.5158, "lr": 3.998009891374561e-05, "epoch": 0.33865814696485624, "percentage": 11.29, "elapsed_time": "0:18:47", "remaining_time": "2:27:39"}
+{"current_steps": 107, "total_steps": 939, "loss": 0.5796, "lr": 3.997664453664654e-05, "epoch": 0.34185303514376997, "percentage": 11.4, "elapsed_time": "0:18:57", "remaining_time": "2:27:24"}
+{"current_steps": 108, "total_steps": 939, "loss": 0.5355, "lr": 3.9972914032868805e-05, "epoch": 0.3450479233226837, "percentage": 11.5, "elapsed_time": "0:19:07", "remaining_time": "2:27:06"}
+{"current_steps": 109, "total_steps": 939, "loss": 0.5459, "lr": 3.99689074539772e-05, "epoch": 0.34824281150159747, "percentage": 11.61, "elapsed_time": "0:19:18", "remaining_time": "2:27:04"}
+{"current_steps": 110, "total_steps": 939, "loss": 0.5503, "lr": 3.996462485535257e-05, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:19:29", "remaining_time": "2:26:50"}
+{"current_steps": 111, "total_steps": 939, "loss": 0.6508, "lr": 3.996006629619103e-05, "epoch": 0.3546325878594249, "percentage": 11.82, "elapsed_time": "0:19:38", "remaining_time": "2:26:32"}
+{"current_steps": 112, "total_steps": 939, "loss": 0.6093, "lr": 3.995523183950314e-05, "epoch": 0.35782747603833864, "percentage": 11.93, "elapsed_time": "0:19:47", "remaining_time": "2:26:09"}
+{"current_steps": 113, "total_steps": 939, "loss": 0.5879, "lr": 3.9950121552113076e-05, "epoch": 0.3610223642172524, "percentage": 12.03, "elapsed_time": "0:19:58", "remaining_time": "2:26:01"}
+{"current_steps": 114, "total_steps": 939, "loss": 0.6371, "lr": 3.994473550465765e-05, "epoch": 0.36421725239616615, "percentage": 12.14, "elapsed_time": "0:20:11", "remaining_time": "2:26:03"}
+{"current_steps": 115, "total_steps": 939, "loss": 0.5058, "lr": 3.993907377158537e-05, "epoch": 0.36741214057507987, "percentage": 12.25, "elapsed_time": "0:20:23", "remaining_time": "2:26:03"}
+{"current_steps": 116, "total_steps": 939, "loss": 0.5475, "lr": 3.993313643115541e-05, "epoch": 0.3706070287539936, "percentage": 12.35, "elapsed_time": "0:20:34", "remaining_time": "2:25:59"}
+{"current_steps": 117, "total_steps": 939, "loss": 0.5131, "lr": 3.992692356543649e-05, "epoch": 0.3738019169329074, "percentage": 12.46, "elapsed_time": "0:20:43", "remaining_time": "2:25:38"}
+{"current_steps": 118, "total_steps": 939, "loss": 0.5351, "lr": 3.992043526030582e-05, "epoch": 0.3769968051118211, "percentage": 12.57, "elapsed_time": "0:20:54", "remaining_time": "2:25:30"}
+{"current_steps": 119, "total_steps": 939, "loss": 0.5241, "lr": 3.991367160544783e-05, "epoch": 0.3801916932907348, "percentage": 12.67, "elapsed_time": "0:21:05", "remaining_time": "2:25:17"}
+{"current_steps": 120, "total_steps": 939, "loss": 0.5341, "lr": 3.990663269435298e-05, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:21:16", "remaining_time": "2:25:14"}
+{"current_steps": 121, "total_steps": 939, "loss": 0.56, "lr": 3.9899318624316424e-05, "epoch": 0.3865814696485623, "percentage": 12.89, "elapsed_time": "0:21:28", "remaining_time": "2:25:09"}
+{"current_steps": 122, "total_steps": 939, "loss": 0.5275, "lr": 3.9891729496436736e-05, "epoch": 0.38977635782747605, "percentage": 12.99, "elapsed_time": "0:21:40", "remaining_time": "2:25:07"}
+{"current_steps": 123, "total_steps": 939, "loss": 0.5726, "lr": 3.988386541561444e-05, "epoch": 0.3929712460063898, "percentage": 13.1, "elapsed_time": "0:21:50", "remaining_time": "2:24:56"}
+{"current_steps": 124, "total_steps": 939, "loss": 0.5689, "lr": 3.9875726490550606e-05, "epoch": 0.3961661341853035, "percentage": 13.21, "elapsed_time": "0:22:01", "remaining_time": "2:24:48"}
+{"current_steps": 125, "total_steps": 939, "loss": 0.5532, "lr": 3.986731283374533e-05, "epoch": 0.3993610223642173, "percentage": 13.31, "elapsed_time": "0:22:14", "remaining_time": "2:24:48"}
+{"current_steps": 126, "total_steps": 939, "loss": 0.6265, "lr": 3.985862456149616e-05, "epoch": 0.402555910543131, "percentage": 13.42, "elapsed_time": "0:22:26", "remaining_time": "2:24:48"}
+{"current_steps": 127, "total_steps": 939, "loss": 0.573, "lr": 3.9849661793896537e-05, "epoch": 0.4057507987220447, "percentage": 13.53, "elapsed_time": "0:22:36", "remaining_time": "2:24:32"}
+{"current_steps": 128, "total_steps": 939, "loss": 0.5177, "lr": 3.984042465483409e-05, "epoch": 0.40894568690095845, "percentage": 13.63, "elapsed_time": "0:22:48", "remaining_time": "2:24:31"}
+{"current_steps": 129, "total_steps": 939, "loss": 0.5476, "lr": 3.983091327198896e-05, "epoch": 0.41214057507987223, "percentage": 13.74, "elapsed_time": "0:22:59", "remaining_time": "2:24:24"}
+{"current_steps": 130, "total_steps": 939, "loss": 0.5868, "lr": 3.982112777683199e-05, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:23:10", "remaining_time": "2:24:13"}
+{"current_steps": 131, "total_steps": 939, "loss": 0.5829, "lr": 3.981106830462296e-05, "epoch": 0.4185303514376997, "percentage": 13.95, "elapsed_time": "0:23:23", "remaining_time": "2:24:19"}
+{"current_steps": 132, "total_steps": 939, "loss": 0.5233, "lr": 3.9800734994408657e-05, "epoch": 0.4217252396166134, "percentage": 14.06, "elapsed_time": "0:23:31", "remaining_time": "2:23:50"}
+{"current_steps": 133, "total_steps": 939, "loss": 0.5452, "lr": 3.9790127989021024e-05, "epoch": 0.4249201277955272, "percentage": 14.16, "elapsed_time": "0:23:42", "remaining_time": "2:23:40"}
+{"current_steps": 134, "total_steps": 939, "loss": 0.6125, "lr": 3.977924743507513e-05, "epoch": 0.4281150159744409, "percentage": 14.27, "elapsed_time": "0:23:52", "remaining_time": "2:23:26"}
+{"current_steps": 135, "total_steps": 939, "loss": 0.5532, "lr": 3.976809348296716e-05, "epoch": 0.43130990415335463, "percentage": 14.38, "elapsed_time": "0:24:03", "remaining_time": "2:23:19"}
+{"current_steps": 136, "total_steps": 939, "loss": 0.5469, "lr": 3.9756666286872345e-05, "epoch": 0.43450479233226835, "percentage": 14.48, "elapsed_time": "0:24:14", "remaining_time": "2:23:10"}
+{"current_steps": 137, "total_steps": 939, "loss": 0.5496, "lr": 3.974496600474282e-05, "epoch": 0.43769968051118213, "percentage": 14.59, "elapsed_time": "0:24:24", "remaining_time": "2:22:50"}
+{"current_steps": 138, "total_steps": 939, "loss": 0.5767, "lr": 3.9732992798305465e-05, "epoch": 0.44089456869009586, "percentage": 14.7, "elapsed_time": "0:24:34", "remaining_time": "2:22:36"}
+{"current_steps": 139, "total_steps": 939, "loss": 0.5746, "lr": 3.972074683305961e-05, "epoch": 0.4440894568690096, "percentage": 14.8, "elapsed_time": "0:24:45", "remaining_time": "2:22:31"}
+{"current_steps": 140, "total_steps": 939, "loss": 0.5332, "lr": 3.9708228278274816e-05, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:24:55", "remaining_time": "2:22:14"}
+{"current_steps": 141, "total_steps": 939, "loss": 0.6213, "lr": 3.96954373069885e-05, "epoch": 0.4504792332268371, "percentage": 15.02, "elapsed_time": "0:25:06", "remaining_time": "2:22:08"}
+{"current_steps": 142, "total_steps": 939, "loss": 0.5389, "lr": 3.968237409600355e-05, "epoch": 0.4536741214057508, "percentage": 15.12, "elapsed_time": "0:25:18", "remaining_time": "2:22:04"}
+{"current_steps": 143, "total_steps": 939, "loss": 0.5514, "lr": 3.9669038825885875e-05, "epoch": 0.45686900958466453, "percentage": 15.23, "elapsed_time": "0:25:29", "remaining_time": "2:21:52"}
+{"current_steps": 144, "total_steps": 939, "loss": 0.5342, "lr": 3.9655431680961924e-05, "epoch": 0.46006389776357826, "percentage": 15.34, "elapsed_time": "0:25:39", "remaining_time": "2:21:38"}
+{"current_steps": 145, "total_steps": 939, "loss": 0.5637, "lr": 3.964155284931612e-05, "epoch": 0.46325878594249204, "percentage": 15.44, "elapsed_time": "0:25:51", "remaining_time": "2:21:34"}
+{"current_steps": 146, "total_steps": 939, "loss": 0.5432, "lr": 3.962740252278827e-05, "epoch": 0.46645367412140576, "percentage": 15.55, "elapsed_time": "0:26:02", "remaining_time": "2:21:27"}
+{"current_steps": 147, "total_steps": 939, "loss": 0.5406, "lr": 3.961298089697093e-05, "epoch": 0.4696485623003195, "percentage": 15.65, "elapsed_time": "0:26:13", "remaining_time": "2:21:17"}
+{"current_steps": 148, "total_steps": 939, "loss": 0.5871, "lr": 3.959828817120665e-05, "epoch": 0.4728434504792332, "percentage": 15.76, "elapsed_time": "0:26:23", "remaining_time": "2:21:05"}
+{"current_steps": 149, "total_steps": 939, "loss": 0.5965, "lr": 3.9583324548585276e-05, "epoch": 0.476038338658147, "percentage": 15.87, "elapsed_time": "0:26:35", "remaining_time": "2:20:57"}
+{"current_steps": 150, "total_steps": 939, "loss": 0.4888, "lr": 3.956809023594112e-05, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:26:45", "remaining_time": "2:20:43"}
+{"current_steps": 151, "total_steps": 939, "loss": 0.568, "lr": 3.955258544385009e-05, "epoch": 0.48242811501597443, "percentage": 16.08, "elapsed_time": "0:26:55", "remaining_time": "2:20:31"}
+{"current_steps": 152, "total_steps": 939, "loss": 0.5329, "lr": 3.95368103866268e-05, "epoch": 0.48562300319488816, "percentage": 16.19, "elapsed_time": "0:27:05", "remaining_time": "2:20:14"}
+{"current_steps": 153, "total_steps": 939, "loss": 0.5458, "lr": 3.9520765282321584e-05, "epoch": 0.48881789137380194, "percentage": 16.29, "elapsed_time": "0:27:17", "remaining_time": "2:20:12"}
+{"current_steps": 154, "total_steps": 939, "loss": 0.534, "lr": 3.9504450352717514e-05, "epoch": 0.49201277955271566, "percentage": 16.4, "elapsed_time": "0:27:29", "remaining_time": "2:20:10"}
+{"current_steps": 155, "total_steps": 939, "loss": 0.5449, "lr": 3.948786582332728e-05, "epoch": 0.4952076677316294, "percentage": 16.51, "elapsed_time": "0:27:41", "remaining_time": "2:20:04"}
+{"current_steps": 156, "total_steps": 939, "loss": 0.5761, "lr": 3.947101192339016e-05, "epoch": 0.4984025559105431, "percentage": 16.61, "elapsed_time": "0:27:50", "remaining_time": "2:19:45"}
+{"current_steps": 157, "total_steps": 939, "loss": 0.5019, "lr": 3.9453888885868756e-05, "epoch": 0.5015974440894568, "percentage": 16.72, "elapsed_time": "0:28:03", "remaining_time": "2:19:43"}
+{"current_steps": 158, "total_steps": 939, "loss": 0.5156, "lr": 3.943649694744584e-05, "epoch": 0.5047923322683706, "percentage": 16.83, "elapsed_time": "0:28:14", "remaining_time": "2:19:37"}
+{"current_steps": 159, "total_steps": 939, "loss": 0.5405, "lr": 3.9418836348521045e-05, "epoch": 0.5079872204472844, "percentage": 16.93, "elapsed_time": "0:28:25", "remaining_time": "2:19:28"}
+{"current_steps": 160, "total_steps": 939, "loss": 0.5227, "lr": 3.940090733320757e-05, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:28:34", "remaining_time": "2:19:09"}
+{"current_steps": 161, "total_steps": 939, "loss": 0.5471, "lr": 3.93827101493288e-05, "epoch": 0.5143769968051118, "percentage": 17.15, "elapsed_time": "0:28:46", "remaining_time": "2:19:02"}
+{"current_steps": 162, "total_steps": 939, "loss": 0.5495, "lr": 3.936424504841485e-05, "epoch": 0.5175718849840255, "percentage": 17.25, "elapsed_time": "0:28:55", "remaining_time": "2:18:43"}
+{"current_steps": 163, "total_steps": 939, "loss": 0.5919, "lr": 3.934551228569913e-05, "epoch": 0.5207667731629393, "percentage": 17.36, "elapsed_time": "0:29:04", "remaining_time": "2:18:23"}
+{"current_steps": 164, "total_steps": 939, "loss": 0.5745, "lr": 3.932651212011479e-05, "epoch": 0.5239616613418531, "percentage": 17.47, "elapsed_time": "0:29:14", "remaining_time": "2:18:09"}
+{"current_steps": 165, "total_steps": 939, "loss": 0.5582, "lr": 3.930724481429114e-05, "epoch": 0.5271565495207667, "percentage": 17.57, "elapsed_time": "0:29:26", "remaining_time": "2:18:06"}
+{"current_steps": 166, "total_steps": 939, "loss": 0.5382, "lr": 3.928771063455007e-05, "epoch": 0.5303514376996805, "percentage": 17.68, "elapsed_time": "0:29:39", "remaining_time": "2:18:07"}
+{"current_steps": 167, "total_steps": 939, "loss": 0.5127, "lr": 3.926790985090228e-05, "epoch": 0.5335463258785943, "percentage": 17.78, "elapsed_time": "0:29:46", "remaining_time": "2:17:40"}
+{"current_steps": 168, "total_steps": 939, "loss": 0.5133, "lr": 3.924784273704363e-05, "epoch": 0.536741214057508, "percentage": 17.89, "elapsed_time": "0:29:58", "remaining_time": "2:17:36"}
+{"current_steps": 169, "total_steps": 939, "loss": 0.5757, "lr": 3.922750957035128e-05, "epoch": 0.5399361022364217, "percentage": 18.0, "elapsed_time": "0:30:10", "remaining_time": "2:17:28"}
+{"current_steps": 170, "total_steps": 939, "loss": 0.5588, "lr": 3.920691063187995e-05, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:30:22", "remaining_time": "2:17:25"}
+{"current_steps": 171, "total_steps": 939, "loss": 0.5652, "lr": 3.918604620635797e-05, "epoch": 0.5463258785942492, "percentage": 18.21, "elapsed_time": "0:30:33", "remaining_time": "2:17:16"}
+{"current_steps": 172, "total_steps": 939, "loss": 0.5586, "lr": 3.916491658218333e-05, "epoch": 0.549520766773163, "percentage": 18.32, "elapsed_time": "0:30:45", "remaining_time": "2:17:08"}
+{"current_steps": 173, "total_steps": 939, "loss": 0.566, "lr": 3.914352205141975e-05, "epoch": 0.5527156549520766, "percentage": 18.42, "elapsed_time": "0:30:55", "remaining_time": "2:16:56"}
+{"current_steps": 174, "total_steps": 939, "loss": 0.6058, "lr": 3.91218629097926e-05, "epoch": 0.5559105431309904, "percentage": 18.53, "elapsed_time": "0:31:03", "remaining_time": "2:16:34"}
+{"current_steps": 175, "total_steps": 939, "loss": 0.5453, "lr": 3.909993945668484e-05, "epoch": 0.5591054313099042, "percentage": 18.64, "elapsed_time": "0:31:15", "remaining_time": "2:16:26"}
+{"current_steps": 176, "total_steps": 939, "loss": 0.5348, "lr": 3.907775199513286e-05, "epoch": 0.5623003194888179, "percentage": 18.74, "elapsed_time": "0:31:26", "remaining_time": "2:16:18"}
+{"current_steps": 177, "total_steps": 939, "loss": 0.5615, "lr": 3.905530083182231e-05, "epoch": 0.5654952076677316, "percentage": 18.85, "elapsed_time": "0:31:35", "remaining_time": "2:15:59"}
+{"current_steps": 178, "total_steps": 939, "loss": 0.5318, "lr": 3.903258627708383e-05, "epoch": 0.5686900958466453, "percentage": 18.96, "elapsed_time": "0:31:46", "remaining_time": "2:15:50"}
+{"current_steps": 179, "total_steps": 939, "loss": 0.531, "lr": 3.90096086448888e-05, "epoch": 0.5718849840255591, "percentage": 19.06, "elapsed_time": "0:31:53", "remaining_time": "2:15:26"}
+{"current_steps": 180, "total_steps": 939, "loss": 0.5679, "lr": 3.898636825284499e-05, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:32:05", "remaining_time": "2:15:17"}
+{"current_steps": 181, "total_steps": 939, "loss": 0.566, "lr": 3.896286542219212e-05, "epoch": 0.5782747603833865, "percentage": 19.28, "elapsed_time": "0:32:17", "remaining_time": "2:15:13"}
+{"current_steps": 182, "total_steps": 939, "loss": 0.5536, "lr": 3.893910047779752e-05, "epoch": 0.5814696485623003, "percentage": 19.38, "elapsed_time": "0:32:27", "remaining_time": "2:15:01"}
+{"current_steps": 183, "total_steps": 939, "loss": 0.5491, "lr": 3.891507374815153e-05, "epoch": 0.5846645367412141, "percentage": 19.49, "elapsed_time": "0:32:39", "remaining_time": "2:14:55"}
+{"current_steps": 184, "total_steps": 939, "loss": 0.5278, "lr": 3.8890785565363046e-05, "epoch": 0.5878594249201278, "percentage": 19.6, "elapsed_time": "0:32:46", "remaining_time": "2:14:28"}
+{"current_steps": 185, "total_steps": 939, "loss": 0.5493, "lr": 3.8866236265154864e-05, "epoch": 0.5910543130990416, "percentage": 19.7, "elapsed_time": "0:32:59", "remaining_time": "2:14:28"}
+{"current_steps": 186, "total_steps": 939, "loss": 0.5118, "lr": 3.8841426186859095e-05, "epoch": 0.5942492012779552, "percentage": 19.81, "elapsed_time": "0:33:11", "remaining_time": "2:14:22"}
+{"current_steps": 187, "total_steps": 939, "loss": 0.5213, "lr": 3.881635567341243e-05, "epoch": 0.597444089456869, "percentage": 19.91, "elapsed_time": "0:33:21", "remaining_time": "2:14:09"}
+{"current_steps": 188, "total_steps": 939, "loss": 0.528, "lr": 3.879102507135142e-05, "epoch": 0.6006389776357828, "percentage": 20.02, "elapsed_time": "0:33:34", "remaining_time": "2:14:07"}
+{"current_steps": 189, "total_steps": 939, "loss": 0.5121, "lr": 3.876543473080771e-05, "epoch": 0.6038338658146964, "percentage": 20.13, "elapsed_time": "0:33:47", "remaining_time": "2:14:06"}
+{"current_steps": 190, "total_steps": 939, "loss": 0.5557, "lr": 3.8739585005503136e-05, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:33:54", "remaining_time": "2:13:41"}
+{"current_steps": 191, "total_steps": 939, "loss": 0.5033, "lr": 3.8713476252744896e-05, "epoch": 0.610223642172524, "percentage": 20.34, "elapsed_time": "0:34:05", "remaining_time": "2:13:30"}
+{"current_steps": 192, "total_steps": 939, "loss": 0.5459, "lr": 3.8687108833420585e-05, "epoch": 0.6134185303514377, "percentage": 20.45, "elapsed_time": "0:34:18", "remaining_time": "2:13:27"}
+{"current_steps": 193, "total_steps": 939, "loss": 0.5761, "lr": 3.866048311199321e-05, "epoch": 0.6166134185303515, "percentage": 20.55, "elapsed_time": "0:34:27", "remaining_time": "2:13:11"}
+{"current_steps": 194, "total_steps": 939, "loss": 0.5597, "lr": 3.863359945649615e-05, "epoch": 0.6198083067092651, "percentage": 20.66, "elapsed_time": "0:34:38", "remaining_time": "2:13:02"}
+{"current_steps": 195, "total_steps": 939, "loss": 0.5415, "lr": 3.860645823852808e-05, "epoch": 0.6230031948881789, "percentage": 20.77, "elapsed_time": "0:34:50", "remaining_time": "2:12:57"}
+{"current_steps": 196, "total_steps": 939, "loss": 0.5435, "lr": 3.85790598332478e-05, "epoch": 0.6261980830670927, "percentage": 20.87, "elapsed_time": "0:35:02", "remaining_time": "2:12:52"}
+{"current_steps": 197, "total_steps": 939, "loss": 0.5485, "lr": 3.8551404619369115e-05, "epoch": 0.6293929712460063, "percentage": 20.98, "elapsed_time": "0:35:13", "remaining_time": "2:12:39"}
+{"current_steps": 198, "total_steps": 939, "loss": 0.5025, "lr": 3.8523492979155534e-05, "epoch": 0.6325878594249201, "percentage": 21.09, "elapsed_time": "0:35:22", "remaining_time": "2:12:22"}
+{"current_steps": 199, "total_steps": 939, "loss": 0.5205, "lr": 3.849532529841502e-05, "epoch": 0.6357827476038339, "percentage": 21.19, "elapsed_time": "0:35:34", "remaining_time": "2:12:17"}
+{"current_steps": 200, "total_steps": 939, "loss": 0.5074, "lr": 3.846690196649464e-05, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:35:45", "remaining_time": "2:12:06"}
+{"current_steps": 201, "total_steps": 939, "loss": 0.5504, "lr": 3.84382233762752e-05, "epoch": 0.6421725239616614, "percentage": 21.41, "elapsed_time": "0:35:57", "remaining_time": "2:12:00"}
+{"current_steps": 202, "total_steps": 939, "loss": 0.5683, "lr": 3.840928992416583e-05, "epoch": 0.645367412140575, "percentage": 21.51, "elapsed_time": "0:36:08", "remaining_time": "2:11:53"}
+{"current_steps": 203, "total_steps": 939, "loss": 0.5101, "lr": 3.8380102010098436e-05, "epoch": 0.6485623003194888, "percentage": 21.62, "elapsed_time": "0:36:20", "remaining_time": "2:11:47"}
+{"current_steps": 204, "total_steps": 939, "loss": 0.564, "lr": 3.835066003752226e-05, "epoch": 0.6517571884984026, "percentage": 21.73, "elapsed_time": "0:36:31", "remaining_time": "2:11:36"}
+{"current_steps": 205, "total_steps": 939, "loss": 0.5227, "lr": 3.832096441339825e-05, "epoch": 0.6549520766773163, "percentage": 21.83, "elapsed_time": "0:36:41", "remaining_time": "2:11:22"}
+{"current_steps": 206, "total_steps": 939, "loss": 0.5564, "lr": 3.829101554819341e-05, "epoch": 0.65814696485623, "percentage": 21.94, "elapsed_time": "0:36:53", "remaining_time": "2:11:17"}
+{"current_steps": 207, "total_steps": 939, "loss": 0.5172, "lr": 3.826081385587523e-05, "epoch": 0.6613418530351438, "percentage": 22.04, "elapsed_time": "0:37:04", "remaining_time": "2:11:06"}
+{"current_steps": 208, "total_steps": 939, "loss": 0.5888, "lr": 3.823035975390585e-05, "epoch": 0.6645367412140575, "percentage": 22.15, "elapsed_time": "0:37:12", "remaining_time": "2:10:44"}
+{"current_steps": 209, "total_steps": 939, "loss": 0.5792, "lr": 3.8199653663236336e-05, "epoch": 0.6677316293929713, "percentage": 22.26, "elapsed_time": "0:37:19", "remaining_time": "2:10:22"}
+{"current_steps": 210, "total_steps": 939, "loss": 0.5196, "lr": 3.8168696008300884e-05, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:37:28", "remaining_time": "2:10:04"}
+{"current_steps": 211, "total_steps": 939, "loss": 0.5444, "lr": 3.813748721701091e-05, "epoch": 0.6741214057507987, "percentage": 22.47, "elapsed_time": "0:37:38", "remaining_time": "2:09:51"}
+{"current_steps": 212, "total_steps": 939, "loss": 0.5673, "lr": 3.8106027720749176e-05, "epoch": 0.6773162939297125, "percentage": 22.58, "elapsed_time": "0:37:47", "remaining_time": "2:09:35"}
+{"current_steps": 213, "total_steps": 939, "loss": 0.5756, "lr": 3.807431795436379e-05, "epoch": 0.6805111821086262, "percentage": 22.68, "elapsed_time": "0:37:59", "remaining_time": "2:09:28"}
+{"current_steps": 214, "total_steps": 939, "loss": 0.5901, "lr": 3.8042358356162215e-05, "epoch": 0.6837060702875399, "percentage": 22.79, "elapsed_time": "0:38:09", "remaining_time": "2:09:16"}
+{"current_steps": 215, "total_steps": 939, "loss": 0.4931, "lr": 3.801014936790522e-05, "epoch": 0.6869009584664537, "percentage": 22.9, "elapsed_time": "0:38:20", "remaining_time": "2:09:07"}
+{"current_steps": 216, "total_steps": 939, "loss": 0.5441, "lr": 3.797769143480075e-05, "epoch": 0.6900958466453674, "percentage": 23.0, "elapsed_time": "0:38:29", "remaining_time": "2:08:48"}
+{"current_steps": 217, "total_steps": 939, "loss": 0.5904, "lr": 3.79449850054978e-05, "epoch": 0.6932907348242812, "percentage": 23.11, "elapsed_time": "0:38:38", "remaining_time": "2:08:34"}
+{"current_steps": 218, "total_steps": 939, "loss": 0.5766, "lr": 3.791203053208017e-05, "epoch": 0.6964856230031949, "percentage": 23.22, "elapsed_time": "0:38:48", "remaining_time": "2:08:21"}
+{"current_steps": 219, "total_steps": 939, "loss": 0.5772, "lr": 3.7878828470060274e-05, "epoch": 0.6996805111821086, "percentage": 23.32, "elapsed_time": "0:38:59", "remaining_time": "2:08:10"}
+{"current_steps": 220, "total_steps": 939, "loss": 0.5679, "lr": 3.7845379278372775e-05, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:39:08", "remaining_time": "2:07:53"}
+{"current_steps": 221, "total_steps": 939, "loss": 0.5432, "lr": 3.781168341936834e-05, "epoch": 0.7060702875399361, "percentage": 23.54, "elapsed_time": "0:39:19", "remaining_time": "2:07:46"}
+{"current_steps": 222, "total_steps": 939, "loss": 0.5682, "lr": 3.777774135880712e-05, "epoch": 0.7092651757188498, "percentage": 23.64, "elapsed_time": "0:39:30", "remaining_time": "2:07:36"}
+{"current_steps": 223, "total_steps": 939, "loss": 0.5121, "lr": 3.774355356585243e-05, "epoch": 0.7124600638977636, "percentage": 23.75, "elapsed_time": "0:39:37", "remaining_time": "2:07:14"}
+{"current_steps": 224, "total_steps": 939, "loss": 0.5196, "lr": 3.7709120513064196e-05, "epoch": 0.7156549520766773, "percentage": 23.86, "elapsed_time": "0:39:46", "remaining_time": "2:06:59"}
+{"current_steps": 225, "total_steps": 939, "loss": 0.5309, "lr": 3.7674442676392456e-05, "epoch": 0.7188498402555911, "percentage": 23.96, "elapsed_time": "0:39:54", "remaining_time": "2:06:39"}
+{"current_steps": 226, "total_steps": 939, "loss": 0.5764, "lr": 3.7639520535170736e-05, "epoch": 0.7220447284345048, "percentage": 24.07, "elapsed_time": "0:40:05", "remaining_time": "2:06:30"}
+{"current_steps": 227, "total_steps": 939, "loss": 0.5711, "lr": 3.760435457210948e-05, "epoch": 0.7252396166134185, "percentage": 24.17, "elapsed_time": "0:40:17", "remaining_time": "2:06:22"}
+{"current_steps": 228, "total_steps": 939, "loss": 0.5355, "lr": 3.7568945273289355e-05, "epoch": 0.7284345047923323, "percentage": 24.28, "elapsed_time": "0:40:28", "remaining_time": "2:06:12"}
+{"current_steps": 229, "total_steps": 939, "loss": 0.5402, "lr": 3.753329312815453e-05, "epoch": 0.731629392971246, "percentage": 24.39, "elapsed_time": "0:40:40", "remaining_time": "2:06:05"}
+{"current_steps": 230, "total_steps": 939, "loss": 0.5323, "lr": 3.749739862950589e-05, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:40:49", "remaining_time": "2:05:50"}
+{"current_steps": 231, "total_steps": 939, "loss": 0.5401, "lr": 3.7461262273494277e-05, "epoch": 0.7380191693290735, "percentage": 24.6, "elapsed_time": "0:41:00", "remaining_time": "2:05:40"}
+{"current_steps": 232, "total_steps": 939, "loss": 0.5489, "lr": 3.742488455961358e-05, "epoch": 0.7412140575079872, "percentage": 24.71, "elapsed_time": "0:41:13", "remaining_time": "2:05:38"}
+{"current_steps": 233, "total_steps": 939, "loss": 0.5277, "lr": 3.738826599069385e-05, "epoch": 0.744408945686901, "percentage": 24.81, "elapsed_time": "0:41:20", "remaining_time": "2:05:16"}
+{"current_steps": 234, "total_steps": 939, "loss": 0.5169, "lr": 3.7351407072894356e-05, "epoch": 0.7476038338658147, "percentage": 24.92, "elapsed_time": "0:41:29", "remaining_time": "2:04:59"}
+{"current_steps": 235, "total_steps": 939, "loss": 0.535, "lr": 3.7314308315696604e-05, "epoch": 0.7507987220447284, "percentage": 25.03, "elapsed_time": "0:41:39", "remaining_time": "2:04:49"}
+{"current_steps": 236, "total_steps": 939, "loss": 0.504, "lr": 3.7276970231897225e-05, "epoch": 0.7539936102236422, "percentage": 25.13, "elapsed_time": "0:41:51", "remaining_time": "2:04:41"}
+{"current_steps": 237, "total_steps": 939, "loss": 0.5613, "lr": 3.723939333760099e-05, "epoch": 0.7571884984025559, "percentage": 25.24, "elapsed_time": "0:42:03", "remaining_time": "2:04:35"}
+{"current_steps": 238, "total_steps": 939, "loss": 0.5244, "lr": 3.720157815221358e-05, "epoch": 0.7603833865814696, "percentage": 25.35, "elapsed_time": "0:42:13", "remaining_time": "2:04:22"}
+{"current_steps": 239, "total_steps": 939, "loss": 0.5426, "lr": 3.716352519843448e-05, "epoch": 0.7635782747603834, "percentage": 25.45, "elapsed_time": "0:42:24", "remaining_time": "2:04:13"}
+{"current_steps": 240, "total_steps": 939, "loss": 0.5104, "lr": 3.71252350022497e-05, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:42:36", "remaining_time": "2:04:05"}
+{"current_steps": 241, "total_steps": 939, "loss": 0.5246, "lr": 3.708670809292455e-05, "epoch": 0.7699680511182109, "percentage": 25.67, "elapsed_time": "0:42:47", "remaining_time": "2:03:56"}
+{"current_steps": 242, "total_steps": 939, "loss": 0.5003, "lr": 3.704794500299627e-05, "epoch": 0.7731629392971247, "percentage": 25.77, "elapsed_time": "0:42:59", "remaining_time": "2:03:49"}
+{"current_steps": 243, "total_steps": 939, "loss": 0.5116, "lr": 3.700894626826674e-05, "epoch": 0.7763578274760383, "percentage": 25.88, "elapsed_time": "0:43:10", "remaining_time": "2:03:40"}
+{"current_steps": 244, "total_steps": 939, "loss": 0.6261, "lr": 3.696971242779499e-05, "epoch": 0.7795527156549521, "percentage": 25.99, "elapsed_time": "0:43:23", "remaining_time": "2:03:34"}
+{"current_steps": 245, "total_steps": 939, "loss": 0.5502, "lr": 3.693024402388984e-05, "epoch": 0.7827476038338658, "percentage": 26.09, "elapsed_time": "0:43:30", "remaining_time": "2:03:15"}
+{"current_steps": 246, "total_steps": 939, "loss": 0.542, "lr": 3.689054160210232e-05, "epoch": 0.7859424920127795, "percentage": 26.2, "elapsed_time": "0:43:43", "remaining_time": "2:03:09"}
+{"current_steps": 247, "total_steps": 939, "loss": 0.5844, "lr": 3.6850605711218176e-05, "epoch": 0.7891373801916933, "percentage": 26.3, "elapsed_time": "0:43:55", "remaining_time": "2:03:03"}
+{"current_steps": 248, "total_steps": 939, "loss": 0.5343, "lr": 3.681043690325029e-05, "epoch": 0.792332268370607, "percentage": 26.41, "elapsed_time": "0:44:04", "remaining_time": "2:02:47"}
+{"current_steps": 249, "total_steps": 939, "loss": 0.5209, "lr": 3.6770035733431014e-05, "epoch": 0.7955271565495208, "percentage": 26.52, "elapsed_time": "0:44:17", "remaining_time": "2:02:43"}
+{"current_steps": 250, "total_steps": 939, "loss": 0.5369, "lr": 3.6729402760204535e-05, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:44:27", "remaining_time": "2:02:30"}
+{"current_steps": 251, "total_steps": 939, "loss": 0.4855, "lr": 3.668853854521913e-05, "epoch": 0.8019169329073482, "percentage": 26.73, "elapsed_time": "0:44:34", "remaining_time": "2:02:12"}
+{"current_steps": 252, "total_steps": 939, "loss": 0.5268, "lr": 3.66474436533194e-05, "epoch": 0.805111821086262, "percentage": 26.84, "elapsed_time": "0:44:46", "remaining_time": "2:02:03"}
+{"current_steps": 253, "total_steps": 939, "loss": 0.5105, "lr": 3.660611865253848e-05, "epoch": 0.8083067092651757, "percentage": 26.94, "elapsed_time": "0:44:57", "remaining_time": "2:01:54"}
+{"current_steps": 254, "total_steps": 939, "loss": 0.4829, "lr": 3.6564564114090175e-05, "epoch": 0.8115015974440895, "percentage": 27.05, "elapsed_time": "0:45:06", "remaining_time": "2:01:39"}
+{"current_steps": 255, "total_steps": 939, "loss": 0.5, "lr": 3.652278061236109e-05, "epoch": 0.8146964856230032, "percentage": 27.16, "elapsed_time": "0:45:18", "remaining_time": "2:01:31"}
+{"current_steps": 256, "total_steps": 939, "loss": 0.5296, "lr": 3.648076872490263e-05, "epoch": 0.8178913738019169, "percentage": 27.26, "elapsed_time": "0:45:28", "remaining_time": "2:01:19"}
+{"current_steps": 257, "total_steps": 939, "loss": 0.507, "lr": 3.6438529032423086e-05, "epoch": 0.8210862619808307, "percentage": 27.37, "elapsed_time": "0:45:39", "remaining_time": "2:01:09"}
+{"current_steps": 258, "total_steps": 939, "loss": 0.5006, "lr": 3.639606211877958e-05, "epoch": 0.8242811501597445, "percentage": 27.48, "elapsed_time": "0:45:51", "remaining_time": "2:01:02"}
+{"current_steps": 259, "total_steps": 939, "loss": 0.5254, "lr": 3.635336857096997e-05, "epoch": 0.8274760383386581, "percentage": 27.58, "elapsed_time": "0:46:02", "remaining_time": "2:00:53"}
+{"current_steps": 260, "total_steps": 939, "loss": 0.5499, "lr": 3.631044897912478e-05, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:46:12", "remaining_time": "2:00:39"}
+{"current_steps": 261, "total_steps": 939, "loss": 0.5311, "lr": 3.6267303936499006e-05, "epoch": 0.8338658146964856, "percentage": 27.8, "elapsed_time": "0:46:22", "remaining_time": "2:00:28"}
+{"current_steps": 262, "total_steps": 939, "loss": 0.5675, "lr": 3.622393403946395e-05, "epoch": 0.8370607028753994, "percentage": 27.9, "elapsed_time": "0:46:32", "remaining_time": "2:00:15"}
+{"current_steps": 263, "total_steps": 939, "loss": 0.5582, "lr": 3.6180339887498953e-05, "epoch": 0.8402555910543131, "percentage": 28.01, "elapsed_time": "0:46:38", "remaining_time": "1:59:52"}
+{"current_steps": 264, "total_steps": 939, "loss": 0.5813, "lr": 3.6136522083183096e-05, "epoch": 0.8434504792332268, "percentage": 28.12, "elapsed_time": "0:46:47", "remaining_time": "1:59:39"}
+{"current_steps": 265, "total_steps": 939, "loss": 0.5302, "lr": 3.6092481232186905e-05, "epoch": 0.8466453674121406, "percentage": 28.22, "elapsed_time": "0:46:57", "remaining_time": "1:59:25"}
+{"current_steps": 266, "total_steps": 939, "loss": 0.4891, "lr": 3.604821794326398e-05, "epoch": 0.8498402555910544, "percentage": 28.33, "elapsed_time": "0:47:05", "remaining_time": "1:59:09"}
+{"current_steps": 267, "total_steps": 939, "loss": 0.5171, "lr": 3.600373282824252e-05, "epoch": 0.853035143769968, "percentage": 28.43, "elapsed_time": "0:47:16", "remaining_time": "1:58:58"}
+{"current_steps": 268, "total_steps": 939, "loss": 0.5085, "lr": 3.595902650201695e-05, "epoch": 0.8562300319488818, "percentage": 28.54, "elapsed_time": "0:47:25", "remaining_time": "1:58:44"}
+{"current_steps": 269, "total_steps": 939, "loss": 0.5324, "lr": 3.591409958253937e-05, "epoch": 0.8594249201277955, "percentage": 28.65, "elapsed_time": "0:47:37", "remaining_time": "1:58:37"}
+{"current_steps": 270, "total_steps": 939, "loss": 0.5752, "lr": 3.5868952690811015e-05, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:47:48", "remaining_time": "1:58:28"}
+{"current_steps": 271, "total_steps": 939, "loss": 0.5599, "lr": 3.582358645087368e-05, "epoch": 0.865814696485623, "percentage": 28.86, "elapsed_time": "0:48:01", "remaining_time": "1:58:21"}
+{"current_steps": 272, "total_steps": 939, "loss": 0.5223, "lr": 3.577800148980112e-05, "epoch": 0.8690095846645367, "percentage": 28.97, "elapsed_time": "0:48:11", "remaining_time": "1:58:11"}
+{"current_steps": 273, "total_steps": 939, "loss": 0.5083, "lr": 3.573219843769033e-05, "epoch": 0.8722044728434505, "percentage": 29.07, "elapsed_time": "0:48:22", "remaining_time": "1:58:01"}
+{"current_steps": 274, "total_steps": 939, "loss": 0.5636, "lr": 3.568617792765287e-05, "epoch": 0.8753993610223643, "percentage": 29.18, "elapsed_time": "0:48:34", "remaining_time": "1:57:52"}
+{"current_steps": 275, "total_steps": 939, "loss": 0.5461, "lr": 3.563994059580611e-05, "epoch": 0.8785942492012779, "percentage": 29.29, "elapsed_time": "0:48:46", "remaining_time": "1:57:46"}
+{"current_steps": 276, "total_steps": 939, "loss": 0.5623, "lr": 3.559348708126445e-05, "epoch": 0.8817891373801917, "percentage": 29.39, "elapsed_time": "0:48:55", "remaining_time": "1:57:31"}
+{"current_steps": 277, "total_steps": 939, "loss": 0.5279, "lr": 3.5546818026130444e-05, "epoch": 0.8849840255591054, "percentage": 29.5, "elapsed_time": "0:49:07", "remaining_time": "1:57:24"}
+{"current_steps": 278, "total_steps": 939, "loss": 0.4966, "lr": 3.549993407548595e-05, "epoch": 0.8881789137380192, "percentage": 29.61, "elapsed_time": "0:49:17", "remaining_time": "1:57:12"}
+{"current_steps": 279, "total_steps": 939, "loss": 0.5365, "lr": 3.545283587738324e-05, "epoch": 0.8913738019169329, "percentage": 29.71, "elapsed_time": "0:49:29", "remaining_time": "1:57:04"}
+{"current_steps": 280, "total_steps": 939, "loss": 0.5672, "lr": 3.5405524082836e-05, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:49:41", "remaining_time": "1:56:57"}
+{"current_steps": 281, "total_steps": 939, "loss": 0.5668, "lr": 3.5357999345810335e-05, "epoch": 0.8977635782747604, "percentage": 29.93, "elapsed_time": "0:49:51", "remaining_time": "1:56:45"}
+{"current_steps": 282, "total_steps": 939, "loss": 0.4955, "lr": 3.5310262323215774e-05, "epoch": 0.9009584664536742, "percentage": 30.03, "elapsed_time": "0:50:04", "remaining_time": "1:56:39"}
+{"current_steps": 283, "total_steps": 939, "loss": 0.5147, "lr": 3.5262313674896125e-05, "epoch": 0.9041533546325878, "percentage": 30.14, "elapsed_time": "0:50:12", "remaining_time": "1:56:22"}
+{"current_steps": 284, "total_steps": 939, "loss": 0.5062, "lr": 3.521415406362041e-05, "epoch": 0.9073482428115016, "percentage": 30.24, "elapsed_time": "0:50:21", "remaining_time": "1:56:08"}
+{"current_steps": 285, "total_steps": 939, "loss": 0.5625, "lr": 3.5165784155073665e-05, "epoch": 0.9105431309904153, "percentage": 30.35, "elapsed_time": "0:50:31", "remaining_time": "1:55:55"}
+{"current_steps": 286, "total_steps": 939, "loss": 0.5424, "lr": 3.511720461784778e-05, "epoch": 0.9137380191693291, "percentage": 30.46, "elapsed_time": "0:50:43", "remaining_time": "1:55:48"}
+{"current_steps": 287, "total_steps": 939, "loss": 0.5632, "lr": 3.50684161234322e-05, "epoch": 0.9169329073482428, "percentage": 30.56, "elapsed_time": "0:50:54", "remaining_time": "1:55:39"}
+{"current_steps": 288, "total_steps": 939, "loss": 0.5372, "lr": 3.50194193462047e-05, "epoch": 0.9201277955271565, "percentage": 30.67, "elapsed_time": "0:51:02", "remaining_time": "1:55:22"}
+{"current_steps": 289, "total_steps": 939, "loss": 0.4861, "lr": 3.497021496342203e-05, "epoch": 0.9233226837060703, "percentage": 30.78, "elapsed_time": "0:51:13", "remaining_time": "1:55:13"}
+{"current_steps": 290, "total_steps": 939, "loss": 0.5801, "lr": 3.4920803655210553e-05, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:51:24", "remaining_time": "1:55:03"}
+{"current_steps": 291, "total_steps": 939, "loss": 0.5207, "lr": 3.4871186104556874e-05, "epoch": 0.9297124600638977, "percentage": 30.99, "elapsed_time": "0:51:36", "remaining_time": "1:54:55"}
+{"current_steps": 292, "total_steps": 939, "loss": 0.5349, "lr": 3.482136299729836e-05, "epoch": 0.9329073482428115, "percentage": 31.1, "elapsed_time": "0:51:45", "remaining_time": "1:54:41"}
+{"current_steps": 293, "total_steps": 939, "loss": 0.5597, "lr": 3.4771335022113705e-05, "epoch": 0.9361022364217252, "percentage": 31.2, "elapsed_time": "0:51:57", "remaining_time": "1:54:32"}
+{"current_steps": 294, "total_steps": 939, "loss": 0.5329, "lr": 3.4721102870513345e-05, "epoch": 0.939297124600639, "percentage": 31.31, "elapsed_time": "0:52:05", "remaining_time": "1:54:17"}
+{"current_steps": 295, "total_steps": 939, "loss": 0.5246, "lr": 3.467066723682998e-05, "epoch": 0.9424920127795527, "percentage": 31.42, "elapsed_time": "0:52:14", "remaining_time": "1:54:02"}
+{"current_steps": 296, "total_steps": 939, "loss": 0.6097, "lr": 3.462002881820891e-05, "epoch": 0.9456869009584664, "percentage": 31.52, "elapsed_time": "0:52:26", "remaining_time": "1:53:56"}
+{"current_steps": 297, "total_steps": 939, "loss": 0.5253, "lr": 3.456918831459844e-05, "epoch": 0.9488817891373802, "percentage": 31.63, "elapsed_time": "0:52:35", "remaining_time": "1:53:41"}
+{"current_steps": 298, "total_steps": 939, "loss": 0.5539, "lr": 3.451814642874017e-05, "epoch": 0.952076677316294, "percentage": 31.74, "elapsed_time": "0:52:44", "remaining_time": "1:53:26"}
+{"current_steps": 299, "total_steps": 939, "loss": 0.5457, "lr": 3.4466903866159326e-05, "epoch": 0.9552715654952076, "percentage": 31.84, "elapsed_time": "0:52:57", "remaining_time": "1:53:20"}
+{"current_steps": 300, "total_steps": 939, "loss": 0.5266, "lr": 3.441546133515496e-05, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:53:09", "remaining_time": "1:53:13"}
+{"current_steps": 301, "total_steps": 939, "loss": 0.5189, "lr": 3.4363819546790216e-05, "epoch": 0.9616613418530351, "percentage": 32.06, "elapsed_time": "0:53:16", "remaining_time": "1:52:54"}
+{"current_steps": 302, "total_steps": 939, "loss": 0.5258, "lr": 3.431197921488242e-05, "epoch": 0.9648562300319489, "percentage": 32.16, "elapsed_time": "0:53:26", "remaining_time": "1:52:42"}
+{"current_steps": 303, "total_steps": 939, "loss": 0.5025, "lr": 3.425994105599331e-05, "epoch": 0.9680511182108626, "percentage": 32.27, "elapsed_time": "0:53:38", "remaining_time": "1:52:35"}
+{"current_steps": 304, "total_steps": 939, "loss": 0.4942, "lr": 3.4207705789419035e-05, "epoch": 0.9712460063897763, "percentage": 32.37, "elapsed_time": "0:53:50", "remaining_time": "1:52:27"}
+{"current_steps": 305, "total_steps": 939, "loss": 0.5128, "lr": 3.41552741371803e-05, "epoch": 0.9744408945686901, "percentage": 32.48, "elapsed_time": "0:53:59", "remaining_time": "1:52:14"}
+{"current_steps": 306, "total_steps": 939, "loss": 0.5036, "lr": 3.4102646824012333e-05, "epoch": 0.9776357827476039, "percentage": 32.59, "elapsed_time": "0:54:10", "remaining_time": "1:52:03"}
+{"current_steps": 307, "total_steps": 939, "loss": 0.5248, "lr": 3.404982457735487e-05, "epoch": 0.9808306709265175, "percentage": 32.69, "elapsed_time": "0:54:15", "remaining_time": "1:51:42"}
+{"current_steps": 308, "total_steps": 939, "loss": 0.5244, "lr": 3.399680812734213e-05, "epoch": 0.9840255591054313, "percentage": 32.8, "elapsed_time": "0:54:26", "remaining_time": "1:51:32"}
+{"current_steps": 309, "total_steps": 939, "loss": 0.5334, "lr": 3.3943598206792665e-05, "epoch": 0.987220447284345, "percentage": 32.91, "elapsed_time": "0:54:35", "remaining_time": "1:51:18"}
+{"current_steps": 310, "total_steps": 939, "loss": 0.506, "lr": 3.3890195551199334e-05, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:54:46", "remaining_time": "1:51:08"}
+{"current_steps": 311, "total_steps": 939, "loss": 0.4884, "lr": 3.3836600898719e-05, "epoch": 0.9936102236421726, "percentage": 33.12, "elapsed_time": "0:54:56", "remaining_time": "1:50:56"}
+{"current_steps": 312, "total_steps": 939, "loss": 0.6063, "lr": 3.3782814990162457e-05, "epoch": 0.9968051118210862, "percentage": 33.23, "elapsed_time": "0:55:06", "remaining_time": "1:50:45"}
+{"current_steps": 313, "total_steps": 939, "loss": 0.5957, "lr": 3.372883856898408e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:55:17", "remaining_time": "1:50:35"}
+{"current_steps": 314, "total_steps": 939, "loss": 0.4153, "lr": 3.367467238127165e-05, "epoch": 1.0031948881789137, "percentage": 33.44, "elapsed_time": "0:56:12", "remaining_time": "1:51:51"}
+{"current_steps": 315, "total_steps": 939, "loss": 0.4178, "lr": 3.3620317175735945e-05, "epoch": 1.0063897763578276, "percentage": 33.55, "elapsed_time": "0:56:23", "remaining_time": "1:51:42"}
+{"current_steps": 316, "total_steps": 939, "loss": 0.3475, "lr": 3.3565773703700474e-05, "epoch": 1.0095846645367412, "percentage": 33.65, "elapsed_time": "0:56:31", "remaining_time": "1:51:25"}
+{"current_steps": 317, "total_steps": 939, "loss": 0.3629, "lr": 3.351104271909104e-05, "epoch": 1.012779552715655, "percentage": 33.76, "elapsed_time": "0:56:43", "remaining_time": "1:51:18"}
+{"current_steps": 318, "total_steps": 939, "loss": 0.3761, "lr": 3.345612497842532e-05, "epoch": 1.0159744408945688, "percentage": 33.87, "elapsed_time": "0:56:53", "remaining_time": "1:51:05"}
+{"current_steps": 319, "total_steps": 939, "loss": 0.3627, "lr": 3.3401021240802446e-05, "epoch": 1.0191693290734825, "percentage": 33.97, "elapsed_time": "0:57:02", "remaining_time": "1:50:52"}
+{"current_steps": 320, "total_steps": 939, "loss": 0.4051, "lr": 3.334573226789249e-05, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:57:14", "remaining_time": "1:50:43"}
+{"current_steps": 321, "total_steps": 939, "loss": 0.3968, "lr": 3.32902588239259e-05, "epoch": 1.0255591054313098, "percentage": 34.19, "elapsed_time": "0:57:26", "remaining_time": "1:50:34"}
+{"current_steps": 322, "total_steps": 939, "loss": 0.4202, "lr": 3.3234601675683005e-05, "epoch": 1.0287539936102237, "percentage": 34.29, "elapsed_time": "0:57:35", "remaining_time": "1:50:20"}
+{"current_steps": 323, "total_steps": 939, "loss": 0.3743, "lr": 3.317876159248337e-05, "epoch": 1.0319488817891374, "percentage": 34.4, "elapsed_time": "0:57:43", "remaining_time": "1:50:05"}
+{"current_steps": 324, "total_steps": 939, "loss": 0.3855, "lr": 3.3122739346175176e-05, "epoch": 1.035143769968051, "percentage": 34.5, "elapsed_time": "0:57:55", "remaining_time": "1:49:56"}
+{"current_steps": 325, "total_steps": 939, "loss": 0.3476, "lr": 3.306653571112454e-05, "epoch": 1.038338658146965, "percentage": 34.61, "elapsed_time": "0:58:03", "remaining_time": "1:49:40"}
+{"current_steps": 326, "total_steps": 939, "loss": 0.3718, "lr": 3.301015146420484e-05, "epoch": 1.0415335463258786, "percentage": 34.72, "elapsed_time": "0:58:14", "remaining_time": "1:49:31"}
+{"current_steps": 327, "total_steps": 939, "loss": 0.4497, "lr": 3.295358738478593e-05, "epoch": 1.0447284345047922, "percentage": 34.82, "elapsed_time": "0:58:26", "remaining_time": "1:49:21"}
+{"current_steps": 328, "total_steps": 939, "loss": 0.3422, "lr": 3.2896844254723414e-05, "epoch": 1.0479233226837061, "percentage": 34.93, "elapsed_time": "0:58:37", "remaining_time": "1:49:11"}
+{"current_steps": 329, "total_steps": 939, "loss": 0.3803, "lr": 3.283992285834782e-05, "epoch": 1.0511182108626198, "percentage": 35.04, "elapsed_time": "0:58:49", "remaining_time": "1:49:03"}
+{"current_steps": 330, "total_steps": 939, "loss": 0.3999, "lr": 3.2782823982453746e-05, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:59:00", "remaining_time": "1:48:54"}
+{"current_steps": 331, "total_steps": 939, "loss": 0.4319, "lr": 3.272554841628901e-05, "epoch": 1.0575079872204474, "percentage": 35.25, "elapsed_time": "0:59:12", "remaining_time": "1:48:45"}
+{"current_steps": 332, "total_steps": 939, "loss": 0.3746, "lr": 3.266809695154371e-05, "epoch": 1.060702875399361, "percentage": 35.36, "elapsed_time": "0:59:23", "remaining_time": "1:48:34"}
+{"current_steps": 333, "total_steps": 939, "loss": 0.3969, "lr": 3.261047038233931e-05, "epoch": 1.0638977635782747, "percentage": 35.46, "elapsed_time": "0:59:31", "remaining_time": "1:48:19"}
+{"current_steps": 334, "total_steps": 939, "loss": 0.3474, "lr": 3.2552669505217646e-05, "epoch": 1.0670926517571886, "percentage": 35.57, "elapsed_time": "0:59:42", "remaining_time": "1:48:09"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ddbc5fed38a1800493530e57c225e378a27f8506e3284c489c1eb075290119
+size 7224