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 sha256:3163bec82cac4d3eeea8a94b857de1493b4f14ac248dc06b7957138c3a242f80
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b6eca00394cc39b45959b6b0a5ac718a244f48494e589c8ba9f188113e5810
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f1c04d813bb7778402975982e12267eaeffcccee67c981232b48c633b4ad5e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a8c4ebe1decdeb1093ae8a2a29c1eddaf9fe003db5e1f3a1fd17dedb3fe4d9
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,329 @@
+{"current_steps": 1, "total_steps": 939, "loss": 0.9383, "lr": 1.0638297872340426e-07, "epoch": 0.003194888178913738, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:52:42"}
+{"current_steps": 2, "total_steps": 939, "loss": 0.8501, "lr": 2.1276595744680852e-07, "epoch": 0.006389776357827476, "percentage": 0.21, "elapsed_time": "0:00:29", "remaining_time": "3:48:52"}
+{"current_steps": 3, "total_steps": 939, "loss": 0.8875, "lr": 3.1914893617021275e-07, "epoch": 0.009584664536741214, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:29:41"}
+{"current_steps": 4, "total_steps": 939, "loss": 0.8129, "lr": 4.2553191489361704e-07, "epoch": 0.012779552715654952, "percentage": 0.43, "elapsed_time": "0:00:52", "remaining_time": "3:26:04"}
+{"current_steps": 5, "total_steps": 939, "loss": 0.8894, "lr": 5.319148936170213e-07, "epoch": 0.01597444089456869, "percentage": 0.53, "elapsed_time": "0:01:04", "remaining_time": "3:21:30"}
+{"current_steps": 6, "total_steps": 939, "loss": 0.8576, "lr": 6.382978723404255e-07, "epoch": 0.019169329073482427, "percentage": 0.64, "elapsed_time": "0:01:15", "remaining_time": "3:14:51"}
+{"current_steps": 7, "total_steps": 939, "loss": 0.8891, "lr": 7.446808510638298e-07, "epoch": 0.022364217252396165, "percentage": 0.75, "elapsed_time": "0:01:26", "remaining_time": "3:12:28"}
+{"current_steps": 8, "total_steps": 939, "loss": 0.8551, "lr": 8.510638297872341e-07, "epoch": 0.025559105431309903, "percentage": 0.85, "elapsed_time": "0:01:37", "remaining_time": "3:08:09"}
+{"current_steps": 9, "total_steps": 939, "loss": 0.8428, "lr": 9.574468085106384e-07, "epoch": 0.02875399361022364, "percentage": 0.96, "elapsed_time": "0:01:49", "remaining_time": "3:07:46"}
+{"current_steps": 10, "total_steps": 939, "loss": 0.8059, "lr": 1.0638297872340427e-06, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:02:00", "remaining_time": "3:06:20"}
+{"current_steps": 11, "total_steps": 939, "loss": 0.8492, "lr": 1.170212765957447e-06, "epoch": 0.03514376996805112, "percentage": 1.17, "elapsed_time": "0:02:12", "remaining_time": "3:06:10"}
+{"current_steps": 12, "total_steps": 939, "loss": 0.879, "lr": 1.276595744680851e-06, "epoch": 0.038338658146964855, "percentage": 1.28, "elapsed_time": "0:02:24", "remaining_time": "3:05:45"}
+{"current_steps": 13, "total_steps": 939, "loss": 0.824, "lr": 1.3829787234042555e-06, "epoch": 0.04153354632587859, "percentage": 1.38, "elapsed_time": "0:02:31", "remaining_time": "3:00:11"}
+{"current_steps": 14, "total_steps": 939, "loss": 0.7959, "lr": 1.4893617021276596e-06, "epoch": 0.04472843450479233, "percentage": 1.49, "elapsed_time": "0:02:41", "remaining_time": "2:57:28"}
+{"current_steps": 15, "total_steps": 939, "loss": 0.7458, "lr": 1.595744680851064e-06, "epoch": 0.04792332268370607, "percentage": 1.6, "elapsed_time": "0:02:52", "remaining_time": "2:56:37"}
+{"current_steps": 16, "total_steps": 939, "loss": 0.7691, "lr": 1.7021276595744682e-06, "epoch": 0.051118210862619806, "percentage": 1.7, "elapsed_time": "0:03:01", "remaining_time": "2:54:24"}
+{"current_steps": 17, "total_steps": 939, "loss": 0.7256, "lr": 1.8085106382978727e-06, "epoch": 0.054313099041533544, "percentage": 1.81, "elapsed_time": "0:03:12", "remaining_time": "2:54:12"}
+{"current_steps": 18, "total_steps": 939, "loss": 0.7825, "lr": 1.9148936170212767e-06, "epoch": 0.05750798722044728, "percentage": 1.92, "elapsed_time": "0:03:24", "remaining_time": "2:54:42"}
+{"current_steps": 19, "total_steps": 939, "loss": 0.7727, "lr": 2.021276595744681e-06, "epoch": 0.06070287539936102, "percentage": 2.02, "elapsed_time": "0:03:37", "remaining_time": "2:55:16"}
+{"current_steps": 20, "total_steps": 939, "loss": 0.7154, "lr": 2.1276595744680853e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:03:46", "remaining_time": "2:53:39"}
+{"current_steps": 21, "total_steps": 939, "loss": 0.7033, "lr": 2.2340425531914894e-06, "epoch": 0.0670926517571885, "percentage": 2.24, "elapsed_time": "0:03:58", "remaining_time": "2:53:30"}
+{"current_steps": 22, "total_steps": 939, "loss": 0.6523, "lr": 2.340425531914894e-06, "epoch": 0.07028753993610223, "percentage": 2.34, "elapsed_time": "0:04:07", "remaining_time": "2:51:52"}
+{"current_steps": 23, "total_steps": 939, "loss": 0.7746, "lr": 2.446808510638298e-06, "epoch": 0.07348242811501597, "percentage": 2.45, "elapsed_time": "0:04:18", "remaining_time": "2:51:42"}
+{"current_steps": 24, "total_steps": 939, "loss": 0.7548, "lr": 2.553191489361702e-06, "epoch": 0.07667731629392971, "percentage": 2.56, "elapsed_time": "0:04:27", "remaining_time": "2:49:46"}
+{"current_steps": 25, "total_steps": 939, "loss": 0.6684, "lr": 2.6595744680851065e-06, "epoch": 0.07987220447284345, "percentage": 2.66, "elapsed_time": "0:04:37", "remaining_time": "2:49:09"}
+{"current_steps": 26, "total_steps": 939, "loss": 0.7405, "lr": 2.765957446808511e-06, "epoch": 0.08306709265175719, "percentage": 2.77, "elapsed_time": "0:04:49", "remaining_time": "2:49:24"}
+{"current_steps": 27, "total_steps": 939, "loss": 0.6736, "lr": 2.8723404255319155e-06, "epoch": 0.08626198083067092, "percentage": 2.88, "elapsed_time": "0:05:00", "remaining_time": "2:49:11"}
+{"current_steps": 28, "total_steps": 939, "loss": 0.6973, "lr": 2.978723404255319e-06, "epoch": 0.08945686900958466, "percentage": 2.98, "elapsed_time": "0:05:13", "remaining_time": "2:49:44"}
+{"current_steps": 29, "total_steps": 939, "loss": 0.7071, "lr": 3.0851063829787237e-06, "epoch": 0.0926517571884984, "percentage": 3.09, "elapsed_time": "0:05:21", "remaining_time": "2:48:17"}
+{"current_steps": 30, "total_steps": 939, "loss": 0.6911, "lr": 3.191489361702128e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:05:31", "remaining_time": "2:47:35"}
+{"current_steps": 31, "total_steps": 939, "loss": 0.6605, "lr": 3.297872340425532e-06, "epoch": 0.09904153354632587, "percentage": 3.3, "elapsed_time": "0:05:43", "remaining_time": "2:47:40"}
+{"current_steps": 32, "total_steps": 939, "loss": 0.6891, "lr": 3.4042553191489363e-06, "epoch": 0.10223642172523961, "percentage": 3.41, "elapsed_time": "0:05:54", "remaining_time": "2:47:33"}
+{"current_steps": 33, "total_steps": 939, "loss": 0.6334, "lr": 3.510638297872341e-06, "epoch": 0.10543130990415335, "percentage": 3.51, "elapsed_time": "0:06:03", "remaining_time": "2:46:28"}
+{"current_steps": 34, "total_steps": 939, "loss": 0.6557, "lr": 3.6170212765957453e-06, "epoch": 0.10862619808306709, "percentage": 3.62, "elapsed_time": "0:06:15", "remaining_time": "2:46:33"}
+{"current_steps": 35, "total_steps": 939, "loss": 0.6491, "lr": 3.723404255319149e-06, "epoch": 0.11182108626198083, "percentage": 3.73, "elapsed_time": "0:06:26", "remaining_time": "2:46:22"}
+{"current_steps": 36, "total_steps": 939, "loss": 0.5842, "lr": 3.8297872340425535e-06, "epoch": 0.11501597444089456, "percentage": 3.83, "elapsed_time": "0:06:38", "remaining_time": "2:46:47"}
+{"current_steps": 37, "total_steps": 939, "loss": 0.6432, "lr": 3.936170212765958e-06, "epoch": 0.1182108626198083, "percentage": 3.94, "elapsed_time": "0:06:51", "remaining_time": "2:47:05"}
+{"current_steps": 38, "total_steps": 939, "loss": 0.6392, "lr": 4.042553191489362e-06, "epoch": 0.12140575079872204, "percentage": 4.05, "elapsed_time": "0:07:01", "remaining_time": "2:46:33"}
+{"current_steps": 39, "total_steps": 939, "loss": 0.6042, "lr": 4.148936170212766e-06, "epoch": 0.12460063897763578, "percentage": 4.15, "elapsed_time": "0:07:14", "remaining_time": "2:46:55"}
+{"current_steps": 40, "total_steps": 939, "loss": 0.5756, "lr": 4.255319148936171e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:07:24", "remaining_time": "2:46:37"}
+{"current_steps": 41, "total_steps": 939, "loss": 0.6, "lr": 4.361702127659575e-06, "epoch": 0.13099041533546327, "percentage": 4.37, "elapsed_time": "0:07:36", "remaining_time": "2:46:49"}
+{"current_steps": 42, "total_steps": 939, "loss": 0.6201, "lr": 4.468085106382979e-06, "epoch": 0.134185303514377, "percentage": 4.47, "elapsed_time": "0:07:46", "remaining_time": "2:46:01"}
+{"current_steps": 43, "total_steps": 939, "loss": 0.6119, "lr": 4.574468085106383e-06, "epoch": 0.13738019169329074, "percentage": 4.58, "elapsed_time": "0:07:56", "remaining_time": "2:45:20"}
+{"current_steps": 44, "total_steps": 939, "loss": 0.5856, "lr": 4.680851063829788e-06, "epoch": 0.14057507987220447, "percentage": 4.69, "elapsed_time": "0:08:06", "remaining_time": "2:45:04"}
+{"current_steps": 45, "total_steps": 939, "loss": 0.6272, "lr": 4.787234042553192e-06, "epoch": 0.14376996805111822, "percentage": 4.79, "elapsed_time": "0:08:18", "remaining_time": "2:45:00"}
+{"current_steps": 46, "total_steps": 939, "loss": 0.5995, "lr": 4.893617021276596e-06, "epoch": 0.14696485623003194, "percentage": 4.9, "elapsed_time": "0:08:27", "remaining_time": "2:44:10"}
+{"current_steps": 47, "total_steps": 939, "loss": 0.6345, "lr": 5e-06, "epoch": 0.1501597444089457, "percentage": 5.01, "elapsed_time": "0:08:35", "remaining_time": "2:42:56"}
+{"current_steps": 48, "total_steps": 939, "loss": 0.6101, "lr": 5.106382978723404e-06, "epoch": 0.15335463258785942, "percentage": 5.11, "elapsed_time": "0:08:46", "remaining_time": "2:42:54"}
+{"current_steps": 49, "total_steps": 939, "loss": 0.6044, "lr": 5.212765957446809e-06, "epoch": 0.15654952076677317, "percentage": 5.22, "elapsed_time": "0:08:56", "remaining_time": "2:42:32"}
+{"current_steps": 50, "total_steps": 939, "loss": 0.5714, "lr": 5.319148936170213e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:09:08", "remaining_time": "2:42:28"}
+{"current_steps": 51, "total_steps": 939, "loss": 0.6129, "lr": 5.425531914893617e-06, "epoch": 0.16293929712460065, "percentage": 5.43, "elapsed_time": "0:09:19", "remaining_time": "2:42:20"}
+{"current_steps": 52, "total_steps": 939, "loss": 0.6297, "lr": 5.531914893617022e-06, "epoch": 0.16613418530351437, "percentage": 5.54, "elapsed_time": "0:09:29", "remaining_time": "2:42:02"}
+{"current_steps": 53, "total_steps": 939, "loss": 0.5753, "lr": 5.638297872340426e-06, "epoch": 0.16932907348242812, "percentage": 5.64, "elapsed_time": "0:09:36", "remaining_time": "2:40:42"}
+{"current_steps": 54, "total_steps": 939, "loss": 0.5689, "lr": 5.744680851063831e-06, "epoch": 0.17252396166134185, "percentage": 5.75, "elapsed_time": "0:09:49", "remaining_time": "2:40:56"}
+{"current_steps": 55, "total_steps": 939, "loss": 0.5864, "lr": 5.851063829787235e-06, "epoch": 0.1757188498402556, "percentage": 5.86, "elapsed_time": "0:09:56", "remaining_time": "2:39:51"}
+{"current_steps": 56, "total_steps": 939, "loss": 0.549, "lr": 5.957446808510638e-06, "epoch": 0.17891373801916932, "percentage": 5.96, "elapsed_time": "0:10:07", "remaining_time": "2:39:35"}
+{"current_steps": 57, "total_steps": 939, "loss": 0.5829, "lr": 6.063829787234044e-06, "epoch": 0.18210862619808307, "percentage": 6.07, "elapsed_time": "0:10:18", "remaining_time": "2:39:24"}
+{"current_steps": 58, "total_steps": 939, "loss": 0.5608, "lr": 6.170212765957447e-06, "epoch": 0.1853035143769968, "percentage": 6.18, "elapsed_time": "0:10:28", "remaining_time": "2:39:03"}
+{"current_steps": 59, "total_steps": 939, "loss": 0.5806, "lr": 6.276595744680851e-06, "epoch": 0.18849840255591055, "percentage": 6.28, "elapsed_time": "0:10:35", "remaining_time": "2:38:01"}
+{"current_steps": 60, "total_steps": 939, "loss": 0.5736, "lr": 6.382978723404256e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:10:47", "remaining_time": "2:38:07"}
+{"current_steps": 61, "total_steps": 939, "loss": 0.5716, "lr": 6.48936170212766e-06, "epoch": 0.19488817891373802, "percentage": 6.5, "elapsed_time": "0:11:00", "remaining_time": "2:38:20"}
+{"current_steps": 62, "total_steps": 939, "loss": 0.5287, "lr": 6.595744680851064e-06, "epoch": 0.19808306709265175, "percentage": 6.6, "elapsed_time": "0:11:07", "remaining_time": "2:37:16"}
+{"current_steps": 63, "total_steps": 939, "loss": 0.5664, "lr": 6.702127659574469e-06, "epoch": 0.2012779552715655, "percentage": 6.71, "elapsed_time": "0:11:15", "remaining_time": "2:36:27"}
+{"current_steps": 64, "total_steps": 939, "loss": 0.5622, "lr": 6.808510638297873e-06, "epoch": 0.20447284345047922, "percentage": 6.82, "elapsed_time": "0:11:25", "remaining_time": "2:36:07"}
+{"current_steps": 65, "total_steps": 939, "loss": 0.5966, "lr": 6.914893617021278e-06, "epoch": 0.20766773162939298, "percentage": 6.92, "elapsed_time": "0:11:36", "remaining_time": "2:36:00"}
+{"current_steps": 66, "total_steps": 939, "loss": 0.5325, "lr": 7.021276595744682e-06, "epoch": 0.2108626198083067, "percentage": 7.03, "elapsed_time": "0:11:44", "remaining_time": "2:35:20"}
+{"current_steps": 67, "total_steps": 939, "loss": 0.5378, "lr": 7.127659574468085e-06, "epoch": 0.21405750798722045, "percentage": 7.14, "elapsed_time": "0:11:57", "remaining_time": "2:35:32"}
+{"current_steps": 68, "total_steps": 939, "loss": 0.5294, "lr": 7.234042553191491e-06, "epoch": 0.21725239616613418, "percentage": 7.24, "elapsed_time": "0:12:02", "remaining_time": "2:34:19"}
+{"current_steps": 69, "total_steps": 939, "loss": 0.5835, "lr": 7.340425531914894e-06, "epoch": 0.22044728434504793, "percentage": 7.35, "elapsed_time": "0:12:14", "remaining_time": "2:34:25"}
+{"current_steps": 70, "total_steps": 939, "loss": 0.6016, "lr": 7.446808510638298e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:12:27", "remaining_time": "2:34:36"}
+{"current_steps": 71, "total_steps": 939, "loss": 0.5148, "lr": 7.553191489361703e-06, "epoch": 0.2268370607028754, "percentage": 7.56, "elapsed_time": "0:12:38", "remaining_time": "2:34:31"}
+{"current_steps": 72, "total_steps": 939, "loss": 0.5407, "lr": 7.659574468085107e-06, "epoch": 0.23003194888178913, "percentage": 7.67, "elapsed_time": "0:12:47", "remaining_time": "2:34:03"}
+{"current_steps": 73, "total_steps": 939, "loss": 0.541, "lr": 7.765957446808511e-06, "epoch": 0.23322683706070288, "percentage": 7.77, "elapsed_time": "0:12:59", "remaining_time": "2:34:02"}
+{"current_steps": 74, "total_steps": 939, "loss": 0.5215, "lr": 7.872340425531916e-06, "epoch": 0.2364217252396166, "percentage": 7.88, "elapsed_time": "0:13:09", "remaining_time": "2:33:53"}
+{"current_steps": 75, "total_steps": 939, "loss": 0.5259, "lr": 7.97872340425532e-06, "epoch": 0.23961661341853036, "percentage": 7.99, "elapsed_time": "0:13:20", "remaining_time": "2:33:45"}
+{"current_steps": 76, "total_steps": 939, "loss": 0.5485, "lr": 8.085106382978723e-06, "epoch": 0.24281150159744408, "percentage": 8.09, "elapsed_time": "0:13:31", "remaining_time": "2:33:37"}
+{"current_steps": 77, "total_steps": 939, "loss": 0.498, "lr": 8.191489361702128e-06, "epoch": 0.24600638977635783, "percentage": 8.2, "elapsed_time": "0:13:39", "remaining_time": "2:32:55"}
+{"current_steps": 78, "total_steps": 939, "loss": 0.5384, "lr": 8.297872340425532e-06, "epoch": 0.24920127795527156, "percentage": 8.31, "elapsed_time": "0:13:52", "remaining_time": "2:33:05"}
+{"current_steps": 79, "total_steps": 939, "loss": 0.5514, "lr": 8.404255319148937e-06, "epoch": 0.2523961661341853, "percentage": 8.41, "elapsed_time": "0:14:03", "remaining_time": "2:33:07"}
+{"current_steps": 80, "total_steps": 939, "loss": 0.5093, "lr": 8.510638297872341e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:14:12", "remaining_time": "2:32:32"}
+{"current_steps": 81, "total_steps": 939, "loss": 0.5594, "lr": 8.617021276595746e-06, "epoch": 0.25878594249201275, "percentage": 8.63, "elapsed_time": "0:14:23", "remaining_time": "2:32:27"}
+{"current_steps": 82, "total_steps": 939, "loss": 0.5729, "lr": 8.72340425531915e-06, "epoch": 0.26198083067092653, "percentage": 8.73, "elapsed_time": "0:14:30", "remaining_time": "2:31:36"}
+{"current_steps": 83, "total_steps": 939, "loss": 0.5233, "lr": 8.829787234042555e-06, "epoch": 0.26517571884984026, "percentage": 8.84, "elapsed_time": "0:14:40", "remaining_time": "2:31:25"}
+{"current_steps": 84, "total_steps": 939, "loss": 0.4808, "lr": 8.936170212765958e-06, "epoch": 0.268370607028754, "percentage": 8.95, "elapsed_time": "0:14:48", "remaining_time": "2:30:43"}
+{"current_steps": 85, "total_steps": 939, "loss": 0.5767, "lr": 9.042553191489362e-06, "epoch": 0.2715654952076677, "percentage": 9.05, "elapsed_time": "0:14:56", "remaining_time": "2:30:10"}
+{"current_steps": 86, "total_steps": 939, "loss": 0.5543, "lr": 9.148936170212767e-06, "epoch": 0.2747603833865815, "percentage": 9.16, "elapsed_time": "0:15:08", "remaining_time": "2:30:15"}
+{"current_steps": 87, "total_steps": 939, "loss": 0.5555, "lr": 9.255319148936171e-06, "epoch": 0.2779552715654952, "percentage": 9.27, "elapsed_time": "0:15:20", "remaining_time": "2:30:17"}
+{"current_steps": 88, "total_steps": 939, "loss": 0.5871, "lr": 9.361702127659576e-06, "epoch": 0.28115015974440893, "percentage": 9.37, "elapsed_time": "0:15:33", "remaining_time": "2:30:23"}
+{"current_steps": 89, "total_steps": 939, "loss": 0.4884, "lr": 9.46808510638298e-06, "epoch": 0.28434504792332266, "percentage": 9.48, "elapsed_time": "0:15:45", "remaining_time": "2:30:30"}
+{"current_steps": 90, "total_steps": 939, "loss": 0.5232, "lr": 9.574468085106385e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:15:57", "remaining_time": "2:30:28"}
+{"current_steps": 91, "total_steps": 939, "loss": 0.5364, "lr": 9.680851063829787e-06, "epoch": 0.29073482428115016, "percentage": 9.69, "elapsed_time": "0:16:07", "remaining_time": "2:30:18"}
+{"current_steps": 92, "total_steps": 939, "loss": 0.502, "lr": 9.787234042553192e-06, "epoch": 0.2939297124600639, "percentage": 9.8, "elapsed_time": "0:16:18", "remaining_time": "2:30:13"}
+{"current_steps": 93, "total_steps": 939, "loss": 0.5379, "lr": 9.893617021276596e-06, "epoch": 0.2971246006389776, "percentage": 9.9, "elapsed_time": "0:16:30", "remaining_time": "2:30:14"}
+{"current_steps": 94, "total_steps": 939, "loss": 0.5857, "lr": 1e-05, "epoch": 0.3003194888178914, "percentage": 10.01, "elapsed_time": "0:16:42", "remaining_time": "2:30:15"}
+{"current_steps": 95, "total_steps": 939, "loss": 0.5236, "lr": 9.999965443811378e-06, "epoch": 0.3035143769968051, "percentage": 10.12, "elapsed_time": "0:16:54", "remaining_time": "2:30:08"}
+{"current_steps": 96, "total_steps": 939, "loss": 0.5526, "lr": 9.999861775723162e-06, "epoch": 0.30670926517571884, "percentage": 10.22, "elapsed_time": "0:17:06", "remaining_time": "2:30:12"}
+{"current_steps": 97, "total_steps": 939, "loss": 0.518, "lr": 9.999688997168301e-06, "epoch": 0.30990415335463256, "percentage": 10.33, "elapsed_time": "0:17:14", "remaining_time": "2:29:38"}
+{"current_steps": 98, "total_steps": 939, "loss": 0.5433, "lr": 9.999447110535026e-06, "epoch": 0.31309904153354634, "percentage": 10.44, "elapsed_time": "0:17:22", "remaining_time": "2:29:09"}
+{"current_steps": 99, "total_steps": 939, "loss": 0.5233, "lr": 9.999136119166803e-06, "epoch": 0.31629392971246006, "percentage": 10.54, "elapsed_time": "0:17:31", "remaining_time": "2:28:43"}
+{"current_steps": 100, "total_steps": 939, "loss": 0.5787, "lr": 9.998756027362308e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:17:43", "remaining_time": "2:28:44"}
+{"current_steps": 101, "total_steps": 939, "loss": 0.5398, "lr": 9.99830684037535e-06, "epoch": 0.3226837060702875, "percentage": 10.76, "elapsed_time": "0:17:53", "remaining_time": "2:28:30"}
+{"current_steps": 102, "total_steps": 939, "loss": 0.5612, "lr": 9.9977885644148e-06, "epoch": 0.3258785942492013, "percentage": 10.86, "elapsed_time": "0:18:04", "remaining_time": "2:28:17"}
+{"current_steps": 103, "total_steps": 939, "loss": 0.506, "lr": 9.997201206644522e-06, "epoch": 0.329073482428115, "percentage": 10.97, "elapsed_time": "0:18:17", "remaining_time": "2:28:25"}
+{"current_steps": 104, "total_steps": 939, "loss": 0.5465, "lr": 9.99654477518325e-06, "epoch": 0.33226837060702874, "percentage": 11.08, "elapsed_time": "0:18:29", "remaining_time": "2:28:29"}
+{"current_steps": 105, "total_steps": 939, "loss": 0.5071, "lr": 9.995819279104494e-06, "epoch": 0.3354632587859425, "percentage": 11.18, "elapsed_time": "0:18:40", "remaining_time": "2:28:21"}
+{"current_steps": 106, "total_steps": 939, "loss": 0.5008, "lr": 9.995024728436402e-06, "epoch": 0.33865814696485624, "percentage": 11.29, "elapsed_time": "0:18:49", "remaining_time": "2:27:55"}
+{"current_steps": 107, "total_steps": 939, "loss": 0.5627, "lr": 9.994161134161635e-06, "epoch": 0.34185303514376997, "percentage": 11.4, "elapsed_time": "0:18:59", "remaining_time": "2:27:39"}
+{"current_steps": 108, "total_steps": 939, "loss": 0.5221, "lr": 9.993228508217201e-06, "epoch": 0.3450479233226837, "percentage": 11.5, "elapsed_time": "0:19:09", "remaining_time": "2:27:21"}
+{"current_steps": 109, "total_steps": 939, "loss": 0.5327, "lr": 9.9922268634943e-06, "epoch": 0.34824281150159747, "percentage": 11.61, "elapsed_time": "0:19:20", "remaining_time": "2:27:19"}
+{"current_steps": 110, "total_steps": 939, "loss": 0.5285, "lr": 9.991156213838143e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:19:31", "remaining_time": "2:27:05"}
+{"current_steps": 111, "total_steps": 939, "loss": 0.6163, "lr": 9.990016574047757e-06, "epoch": 0.3546325878594249, "percentage": 11.82, "elapsed_time": "0:19:40", "remaining_time": "2:26:47"}
+{"current_steps": 112, "total_steps": 939, "loss": 0.5783, "lr": 9.988807959875785e-06, "epoch": 0.35782747603833864, "percentage": 11.93, "elapsed_time": "0:19:49", "remaining_time": "2:26:23"}
+{"current_steps": 113, "total_steps": 939, "loss": 0.5686, "lr": 9.987530388028269e-06, "epoch": 0.3610223642172524, "percentage": 12.03, "elapsed_time": "0:20:00", "remaining_time": "2:26:16"}
+{"current_steps": 114, "total_steps": 939, "loss": 0.6109, "lr": 9.986183876164412e-06, "epoch": 0.36421725239616615, "percentage": 12.14, "elapsed_time": "0:20:12", "remaining_time": "2:26:18"}
+{"current_steps": 115, "total_steps": 939, "loss": 0.4905, "lr": 9.984768442896342e-06, "epoch": 0.36741214057507987, "percentage": 12.25, "elapsed_time": "0:20:24", "remaining_time": "2:26:17"}
+{"current_steps": 116, "total_steps": 939, "loss": 0.5219, "lr": 9.983284107788852e-06, "epoch": 0.3706070287539936, "percentage": 12.35, "elapsed_time": "0:20:36", "remaining_time": "2:26:13"}
+{"current_steps": 117, "total_steps": 939, "loss": 0.4976, "lr": 9.981730891359123e-06, "epoch": 0.3738019169329074, "percentage": 12.46, "elapsed_time": "0:20:45", "remaining_time": "2:25:53"}
+{"current_steps": 118, "total_steps": 939, "loss": 0.518, "lr": 9.980108815076456e-06, "epoch": 0.3769968051118211, "percentage": 12.57, "elapsed_time": "0:20:56", "remaining_time": "2:25:44"}
+{"current_steps": 119, "total_steps": 939, "loss": 0.5111, "lr": 9.978417901361958e-06, "epoch": 0.3801916932907348, "percentage": 12.67, "elapsed_time": "0:21:07", "remaining_time": "2:25:31"}
+{"current_steps": 120, "total_steps": 939, "loss": 0.5197, "lr": 9.976658173588244e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:21:19", "remaining_time": "2:25:29"}
+{"current_steps": 121, "total_steps": 939, "loss": 0.5394, "lr": 9.974829656079106e-06, "epoch": 0.3865814696485623, "percentage": 12.89, "elapsed_time": "0:21:30", "remaining_time": "2:25:24"}
+{"current_steps": 122, "total_steps": 939, "loss": 0.5117, "lr": 9.972932374109184e-06, "epoch": 0.38977635782747605, "percentage": 12.99, "elapsed_time": "0:21:42", "remaining_time": "2:25:22"}
+{"current_steps": 123, "total_steps": 939, "loss": 0.5527, "lr": 9.97096635390361e-06, "epoch": 0.3929712460063898, "percentage": 13.1, "elapsed_time": "0:21:53", "remaining_time": "2:25:12"}
+{"current_steps": 124, "total_steps": 939, "loss": 0.5466, "lr": 9.968931622637652e-06, "epoch": 0.3961661341853035, "percentage": 13.21, "elapsed_time": "0:22:04", "remaining_time": "2:25:04"}
+{"current_steps": 125, "total_steps": 939, "loss": 0.5412, "lr": 9.966828208436332e-06, "epoch": 0.3993610223642173, "percentage": 13.31, "elapsed_time": "0:22:16", "remaining_time": "2:25:04"}
+{"current_steps": 126, "total_steps": 939, "loss": 0.602, "lr": 9.96465614037404e-06, "epoch": 0.402555910543131, "percentage": 13.42, "elapsed_time": "0:22:29", "remaining_time": "2:25:05"}
+{"current_steps": 127, "total_steps": 939, "loss": 0.5469, "lr": 9.962415448474134e-06, "epoch": 0.4057507987220447, "percentage": 13.53, "elapsed_time": "0:22:39", "remaining_time": "2:24:49"}
+{"current_steps": 128, "total_steps": 939, "loss": 0.5003, "lr": 9.960106163708522e-06, "epoch": 0.40894568690095845, "percentage": 13.63, "elapsed_time": "0:22:51", "remaining_time": "2:24:47"}
+{"current_steps": 129, "total_steps": 939, "loss": 0.5305, "lr": 9.95772831799724e-06, "epoch": 0.41214057507987223, "percentage": 13.74, "elapsed_time": "0:23:02", "remaining_time": "2:24:41"}
+{"current_steps": 130, "total_steps": 939, "loss": 0.5667, "lr": 9.955281944207998e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:23:13", "remaining_time": "2:24:30"}
+{"current_steps": 131, "total_steps": 939, "loss": 0.5512, "lr": 9.95276707615574e-06, "epoch": 0.4185303514376997, "percentage": 13.95, "elapsed_time": "0:23:26", "remaining_time": "2:24:34"}
+{"current_steps": 132, "total_steps": 939, "loss": 0.5074, "lr": 9.950183748602164e-06, "epoch": 0.4217252396166134, "percentage": 14.06, "elapsed_time": "0:23:34", "remaining_time": "2:24:05"}
+{"current_steps": 133, "total_steps": 939, "loss": 0.5252, "lr": 9.947531997255256e-06, "epoch": 0.4249201277955272, "percentage": 14.16, "elapsed_time": "0:23:45", "remaining_time": "2:23:56"}
+{"current_steps": 134, "total_steps": 939, "loss": 0.5889, "lr": 9.944811858768782e-06, "epoch": 0.4281150159744409, "percentage": 14.27, "elapsed_time": "0:23:55", "remaining_time": "2:23:42"}
+{"current_steps": 135, "total_steps": 939, "loss": 0.532, "lr": 9.94202337074179e-06, "epoch": 0.43130990415335463, "percentage": 14.38, "elapsed_time": "0:24:06", "remaining_time": "2:23:35"}
+{"current_steps": 136, "total_steps": 939, "loss": 0.5234, "lr": 9.939166571718086e-06, "epoch": 0.43450479233226835, "percentage": 14.48, "elapsed_time": "0:24:17", "remaining_time": "2:23:26"}
+{"current_steps": 137, "total_steps": 939, "loss": 0.5283, "lr": 9.936241501185706e-06, "epoch": 0.43769968051118213, "percentage": 14.59, "elapsed_time": "0:24:26", "remaining_time": "2:23:06"}
+{"current_steps": 138, "total_steps": 939, "loss": 0.5404, "lr": 9.933248199576366e-06, "epoch": 0.44089456869009586, "percentage": 14.7, "elapsed_time": "0:24:36", "remaining_time": "2:22:52"}
+{"current_steps": 139, "total_steps": 939, "loss": 0.5509, "lr": 9.930186708264902e-06, "epoch": 0.4440894568690096, "percentage": 14.8, "elapsed_time": "0:24:48", "remaining_time": "2:22:47"}
+{"current_steps": 140, "total_steps": 939, "loss": 0.5155, "lr": 9.927057069568704e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:24:58", "remaining_time": "2:22:31"}
+{"current_steps": 141, "total_steps": 939, "loss": 0.5829, "lr": 9.923859326747125e-06, "epoch": 0.4504792332268371, "percentage": 15.02, "elapsed_time": "0:25:09", "remaining_time": "2:22:24"}
+{"current_steps": 142, "total_steps": 939, "loss": 0.52, "lr": 9.920593524000887e-06, "epoch": 0.4536741214057508, "percentage": 15.12, "elapsed_time": "0:25:21", "remaining_time": "2:22:20"}
+{"current_steps": 143, "total_steps": 939, "loss": 0.5283, "lr": 9.917259706471469e-06, "epoch": 0.45686900958466453, "percentage": 15.23, "elapsed_time": "0:25:32", "remaining_time": "2:22:08"}
+{"current_steps": 144, "total_steps": 939, "loss": 0.5155, "lr": 9.913857920240481e-06, "epoch": 0.46006389776357826, "percentage": 15.34, "elapsed_time": "0:25:42", "remaining_time": "2:21:54"}
+{"current_steps": 145, "total_steps": 939, "loss": 0.5403, "lr": 9.91038821232903e-06, "epoch": 0.46325878594249204, "percentage": 15.44, "elapsed_time": "0:25:54", "remaining_time": "2:21:50"}
+{"current_steps": 146, "total_steps": 939, "loss": 0.5234, "lr": 9.906850630697068e-06, "epoch": 0.46645367412140576, "percentage": 15.55, "elapsed_time": "0:26:05", "remaining_time": "2:21:43"}
+{"current_steps": 147, "total_steps": 939, "loss": 0.5187, "lr": 9.903245224242732e-06, "epoch": 0.4696485623003195, "percentage": 15.65, "elapsed_time": "0:26:16", "remaining_time": "2:21:33"}
+{"current_steps": 148, "total_steps": 939, "loss": 0.5577, "lr": 9.899572042801662e-06, "epoch": 0.4728434504792332, "percentage": 15.76, "elapsed_time": "0:26:26", "remaining_time": "2:21:20"}
+{"current_steps": 149, "total_steps": 939, "loss": 0.5622, "lr": 9.895831137146319e-06, "epoch": 0.476038338658147, "percentage": 15.87, "elapsed_time": "0:26:38", "remaining_time": "2:21:13"}
+{"current_steps": 150, "total_steps": 939, "loss": 0.4704, "lr": 9.89202255898528e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:26:48", "remaining_time": "2:21:00"}
+{"current_steps": 151, "total_steps": 939, "loss": 0.5426, "lr": 9.888146360962523e-06, "epoch": 0.48242811501597443, "percentage": 16.08, "elapsed_time": "0:26:58", "remaining_time": "2:20:47"}
+{"current_steps": 152, "total_steps": 939, "loss": 0.5051, "lr": 9.8842025966567e-06, "epoch": 0.48562300319488816, "percentage": 16.19, "elapsed_time": "0:27:08", "remaining_time": "2:20:31"}
+{"current_steps": 153, "total_steps": 939, "loss": 0.5203, "lr": 9.880191320580396e-06, "epoch": 0.48881789137380194, "percentage": 16.29, "elapsed_time": "0:27:20", "remaining_time": "2:20:29"}
+{"current_steps": 154, "total_steps": 939, "loss": 0.5137, "lr": 9.876112588179378e-06, "epoch": 0.49201277955271566, "percentage": 16.4, "elapsed_time": "0:27:33", "remaining_time": "2:20:27"}
+{"current_steps": 155, "total_steps": 939, "loss": 0.5207, "lr": 9.87196645583182e-06, "epoch": 0.4952076677316294, "percentage": 16.51, "elapsed_time": "0:27:45", "remaining_time": "2:20:21"}
+{"current_steps": 156, "total_steps": 939, "loss": 0.5505, "lr": 9.86775298084754e-06, "epoch": 0.4984025559105431, "percentage": 16.61, "elapsed_time": "0:27:54", "remaining_time": "2:20:03"}
+{"current_steps": 157, "total_steps": 939, "loss": 0.474, "lr": 9.863472221467189e-06, "epoch": 0.5015974440894568, "percentage": 16.72, "elapsed_time": "0:28:06", "remaining_time": "2:19:59"}
+{"current_steps": 158, "total_steps": 939, "loss": 0.4911, "lr": 9.85912423686146e-06, "epoch": 0.5047923322683706, "percentage": 16.83, "elapsed_time": "0:28:18", "remaining_time": "2:19:54"}
+{"current_steps": 159, "total_steps": 939, "loss": 0.5203, "lr": 9.854709087130261e-06, "epoch": 0.5079872204472844, "percentage": 16.93, "elapsed_time": "0:28:29", "remaining_time": "2:19:44"}
+{"current_steps": 160, "total_steps": 939, "loss": 0.5028, "lr": 9.850226833301893e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:28:38", "remaining_time": "2:19:25"}
+{"current_steps": 161, "total_steps": 939, "loss": 0.5262, "lr": 9.8456775373322e-06, "epoch": 0.5143769968051118, "percentage": 17.15, "elapsed_time": "0:28:49", "remaining_time": "2:19:18"}
+{"current_steps": 162, "total_steps": 939, "loss": 0.5206, "lr": 9.841061262103713e-06, "epoch": 0.5175718849840255, "percentage": 17.25, "elapsed_time": "0:28:58", "remaining_time": "2:18:59"}
+{"current_steps": 163, "total_steps": 939, "loss": 0.5538, "lr": 9.836378071424782e-06, "epoch": 0.5207667731629393, "percentage": 17.36, "elapsed_time": "0:29:07", "remaining_time": "2:18:39"}
+{"current_steps": 164, "total_steps": 939, "loss": 0.543, "lr": 9.831628030028698e-06, "epoch": 0.5239616613418531, "percentage": 17.47, "elapsed_time": "0:29:17", "remaining_time": "2:18:25"}
+{"current_steps": 165, "total_steps": 939, "loss": 0.5294, "lr": 9.826811203572785e-06, "epoch": 0.5271565495207667, "percentage": 17.57, "elapsed_time": "0:29:29", "remaining_time": "2:18:21"}
+{"current_steps": 166, "total_steps": 939, "loss": 0.5156, "lr": 9.821927658637518e-06, "epoch": 0.5303514376996805, "percentage": 17.68, "elapsed_time": "0:29:43", "remaining_time": "2:18:22"}
+{"current_steps": 167, "total_steps": 939, "loss": 0.4903, "lr": 9.81697746272557e-06, "epoch": 0.5335463258785943, "percentage": 17.78, "elapsed_time": "0:29:50", "remaining_time": "2:17:55"}
+{"current_steps": 168, "total_steps": 939, "loss": 0.4907, "lr": 9.811960684260907e-06, "epoch": 0.536741214057508, "percentage": 17.89, "elapsed_time": "0:30:02", "remaining_time": "2:17:51"}
+{"current_steps": 169, "total_steps": 939, "loss": 0.5494, "lr": 9.80687739258782e-06, "epoch": 0.5399361022364217, "percentage": 18.0, "elapsed_time": "0:30:13", "remaining_time": "2:17:43"}
+{"current_steps": 170, "total_steps": 939, "loss": 0.5349, "lr": 9.801727657969988e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:30:26", "remaining_time": "2:17:40"}
+{"current_steps": 171, "total_steps": 939, "loss": 0.5363, "lr": 9.796511551589492e-06, "epoch": 0.5463258785942492, "percentage": 18.21, "elapsed_time": "0:30:37", "remaining_time": "2:17:31"}
+{"current_steps": 172, "total_steps": 939, "loss": 0.5323, "lr": 9.791229145545832e-06, "epoch": 0.549520766773163, "percentage": 18.32, "elapsed_time": "0:30:48", "remaining_time": "2:17:23"}
+{"current_steps": 173, "total_steps": 939, "loss": 0.542, "lr": 9.785880512854937e-06, "epoch": 0.5527156549520766, "percentage": 18.42, "elapsed_time": "0:30:59", "remaining_time": "2:17:12"}
+{"current_steps": 174, "total_steps": 939, "loss": 0.5699, "lr": 9.78046572744815e-06, "epoch": 0.5559105431309904, "percentage": 18.53, "elapsed_time": "0:31:07", "remaining_time": "2:16:50"}
+{"current_steps": 175, "total_steps": 939, "loss": 0.518, "lr": 9.77498486417121e-06, "epoch": 0.5591054313099042, "percentage": 18.64, "elapsed_time": "0:31:18", "remaining_time": "2:16:42"}
+{"current_steps": 176, "total_steps": 939, "loss": 0.5058, "lr": 9.769437998783216e-06, "epoch": 0.5623003194888179, "percentage": 18.74, "elapsed_time": "0:31:30", "remaining_time": "2:16:35"}
+{"current_steps": 177, "total_steps": 939, "loss": 0.5356, "lr": 9.763825207955577e-06, "epoch": 0.5654952076677316, "percentage": 18.85, "elapsed_time": "0:31:39", "remaining_time": "2:16:15"}
+{"current_steps": 178, "total_steps": 939, "loss": 0.5093, "lr": 9.758146569270957e-06, "epoch": 0.5686900958466453, "percentage": 18.96, "elapsed_time": "0:31:50", "remaining_time": "2:16:06"}
+{"current_steps": 179, "total_steps": 939, "loss": 0.5041, "lr": 9.7524021612222e-06, "epoch": 0.5718849840255591, "percentage": 19.06, "elapsed_time": "0:31:57", "remaining_time": "2:15:42"}
+{"current_steps": 180, "total_steps": 939, "loss": 0.5406, "lr": 9.746592063211247e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:32:08", "remaining_time": "2:15:33"}
+{"current_steps": 181, "total_steps": 939, "loss": 0.5403, "lr": 9.74071635554803e-06, "epoch": 0.5782747603833865, "percentage": 19.28, "elapsed_time": "0:32:21", "remaining_time": "2:15:29"}
+{"current_steps": 182, "total_steps": 939, "loss": 0.5193, "lr": 9.73477511944938e-06, "epoch": 0.5814696485623003, "percentage": 19.38, "elapsed_time": "0:32:31", "remaining_time": "2:15:17"}
+{"current_steps": 183, "total_steps": 939, "loss": 0.5198, "lr": 9.728768437037882e-06, "epoch": 0.5846645367412141, "percentage": 19.49, "elapsed_time": "0:32:43", "remaining_time": "2:15:11"}
+{"current_steps": 184, "total_steps": 939, "loss": 0.5051, "lr": 9.722696391340762e-06, "epoch": 0.5878594249201278, "percentage": 19.6, "elapsed_time": "0:32:50", "remaining_time": "2:14:44"}
+{"current_steps": 185, "total_steps": 939, "loss": 0.5204, "lr": 9.716559066288716e-06, "epoch": 0.5910543130990416, "percentage": 19.7, "elapsed_time": "0:33:03", "remaining_time": "2:14:44"}
+{"current_steps": 186, "total_steps": 939, "loss": 0.4819, "lr": 9.710356546714774e-06, "epoch": 0.5942492012779552, "percentage": 19.81, "elapsed_time": "0:33:15", "remaining_time": "2:14:38"}
+{"current_steps": 187, "total_steps": 939, "loss": 0.4975, "lr": 9.704088918353108e-06, "epoch": 0.597444089456869, "percentage": 19.91, "elapsed_time": "0:33:25", "remaining_time": "2:14:25"}
+{"current_steps": 188, "total_steps": 939, "loss": 0.506, "lr": 9.697756267837856e-06, "epoch": 0.6006389776357828, "percentage": 20.02, "elapsed_time": "0:33:38", "remaining_time": "2:14:23"}
+{"current_steps": 189, "total_steps": 939, "loss": 0.4885, "lr": 9.691358682701927e-06, "epoch": 0.6038338658146964, "percentage": 20.13, "elapsed_time": "0:33:51", "remaining_time": "2:14:21"}
+{"current_steps": 190, "total_steps": 939, "loss": 0.5204, "lr": 9.684896251375784e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:33:58", "remaining_time": "2:13:57"}
+{"current_steps": 191, "total_steps": 939, "loss": 0.4774, "lr": 9.678369063186224e-06, "epoch": 0.610223642172524, "percentage": 20.34, "elapsed_time": "0:34:09", "remaining_time": "2:13:46"}
+{"current_steps": 192, "total_steps": 939, "loss": 0.5183, "lr": 9.671777208355146e-06, "epoch": 0.6134185303514377, "percentage": 20.45, "elapsed_time": "0:34:22", "remaining_time": "2:13:42"}
+{"current_steps": 193, "total_steps": 939, "loss": 0.5393, "lr": 9.665120777998303e-06, "epoch": 0.6166134185303515, "percentage": 20.55, "elapsed_time": "0:34:31", "remaining_time": "2:13:27"}
+{"current_steps": 194, "total_steps": 939, "loss": 0.5264, "lr": 9.658399864124037e-06, "epoch": 0.6198083067092651, "percentage": 20.66, "elapsed_time": "0:34:42", "remaining_time": "2:13:17"}
+{"current_steps": 195, "total_steps": 939, "loss": 0.5184, "lr": 9.65161455963202e-06, "epoch": 0.6230031948881789, "percentage": 20.77, "elapsed_time": "0:34:54", "remaining_time": "2:13:12"}
+{"current_steps": 196, "total_steps": 939, "loss": 0.5213, "lr": 9.64476495831195e-06, "epoch": 0.6261980830670927, "percentage": 20.87, "elapsed_time": "0:35:06", "remaining_time": "2:13:07"}
+{"current_steps": 197, "total_steps": 939, "loss": 0.5167, "lr": 9.637851154842279e-06, "epoch": 0.6293929712460063, "percentage": 20.98, "elapsed_time": "0:35:17", "remaining_time": "2:12:54"}
+{"current_steps": 198, "total_steps": 939, "loss": 0.4814, "lr": 9.630873244788884e-06, "epoch": 0.6325878594249201, "percentage": 21.09, "elapsed_time": "0:35:26", "remaining_time": "2:12:36"}
+{"current_steps": 199, "total_steps": 939, "loss": 0.487, "lr": 9.623831324603755e-06, "epoch": 0.6357827476038339, "percentage": 21.19, "elapsed_time": "0:35:38", "remaining_time": "2:12:31"}
+{"current_steps": 200, "total_steps": 939, "loss": 0.4843, "lr": 9.61672549162366e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:35:49", "remaining_time": "2:12:21"}
+{"current_steps": 201, "total_steps": 939, "loss": 0.5234, "lr": 9.6095558440688e-06, "epoch": 0.6421725239616614, "percentage": 21.41, "elapsed_time": "0:36:01", "remaining_time": "2:12:15"}
+{"current_steps": 202, "total_steps": 939, "loss": 0.535, "lr": 9.602322481041457e-06, "epoch": 0.645367412140575, "percentage": 21.51, "elapsed_time": "0:36:12", "remaining_time": "2:12:07"}
+{"current_steps": 203, "total_steps": 939, "loss": 0.4762, "lr": 9.595025502524609e-06, "epoch": 0.6485623003194888, "percentage": 21.62, "elapsed_time": "0:36:24", "remaining_time": "2:12:01"}
+{"current_steps": 204, "total_steps": 939, "loss": 0.5302, "lr": 9.587665009380565e-06, "epoch": 0.6517571884984026, "percentage": 21.73, "elapsed_time": "0:36:35", "remaining_time": "2:11:50"}
+{"current_steps": 205, "total_steps": 939, "loss": 0.4887, "lr": 9.580241103349562e-06, "epoch": 0.6549520766773163, "percentage": 21.83, "elapsed_time": "0:36:45", "remaining_time": "2:11:37"}
+{"current_steps": 206, "total_steps": 939, "loss": 0.5172, "lr": 9.572753887048353e-06, "epoch": 0.65814696485623, "percentage": 21.94, "elapsed_time": "0:36:57", "remaining_time": "2:11:31"}
+{"current_steps": 207, "total_steps": 939, "loss": 0.4967, "lr": 9.565203463968808e-06, "epoch": 0.6613418530351438, "percentage": 22.04, "elapsed_time": "0:37:08", "remaining_time": "2:11:20"}
+{"current_steps": 208, "total_steps": 939, "loss": 0.5581, "lr": 9.557589938476462e-06, "epoch": 0.6645367412140575, "percentage": 22.15, "elapsed_time": "0:37:16", "remaining_time": "2:10:58"}
+{"current_steps": 209, "total_steps": 939, "loss": 0.547, "lr": 9.549913415809084e-06, "epoch": 0.6677316293929713, "percentage": 22.26, "elapsed_time": "0:37:23", "remaining_time": "2:10:36"}
+{"current_steps": 210, "total_steps": 939, "loss": 0.4954, "lr": 9.542174002075221e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:37:32", "remaining_time": "2:10:18"}
+{"current_steps": 211, "total_steps": 939, "loss": 0.5166, "lr": 9.534371804252727e-06, "epoch": 0.6741214057507987, "percentage": 22.47, "elapsed_time": "0:37:42", "remaining_time": "2:10:05"}
+{"current_steps": 212, "total_steps": 939, "loss": 0.5348, "lr": 9.526506930187294e-06, "epoch": 0.6773162939297125, "percentage": 22.58, "elapsed_time": "0:37:51", "remaining_time": "2:09:49"}
+{"current_steps": 213, "total_steps": 939, "loss": 0.5431, "lr": 9.518579488590947e-06, "epoch": 0.6805111821086262, "percentage": 22.68, "elapsed_time": "0:38:03", "remaining_time": "2:09:42"}
+{"current_steps": 214, "total_steps": 939, "loss": 0.5562, "lr": 9.510589589040554e-06, "epoch": 0.6837060702875399, "percentage": 22.79, "elapsed_time": "0:38:13", "remaining_time": "2:09:30"}
+{"current_steps": 215, "total_steps": 939, "loss": 0.4647, "lr": 9.502537341976305e-06, "epoch": 0.6869009584664537, "percentage": 22.9, "elapsed_time": "0:38:25", "remaining_time": "2:09:22"}
+{"current_steps": 216, "total_steps": 939, "loss": 0.5153, "lr": 9.494422858700188e-06, "epoch": 0.6900958466453674, "percentage": 23.0, "elapsed_time": "0:38:33", "remaining_time": "2:09:03"}
+{"current_steps": 217, "total_steps": 939, "loss": 0.5555, "lr": 9.48624625137445e-06, "epoch": 0.6932907348242812, "percentage": 23.11, "elapsed_time": "0:38:43", "remaining_time": "2:08:49"}
+{"current_steps": 218, "total_steps": 939, "loss": 0.5471, "lr": 9.478007633020043e-06, "epoch": 0.6964856230031949, "percentage": 23.22, "elapsed_time": "0:38:52", "remaining_time": "2:08:35"}
+{"current_steps": 219, "total_steps": 939, "loss": 0.5439, "lr": 9.469707117515068e-06, "epoch": 0.6996805111821086, "percentage": 23.32, "elapsed_time": "0:39:03", "remaining_time": "2:08:25"}
+{"current_steps": 220, "total_steps": 939, "loss": 0.5397, "lr": 9.461344819593194e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:39:12", "remaining_time": "2:08:08"}
+{"current_steps": 221, "total_steps": 939, "loss": 0.5103, "lr": 9.452920854842085e-06, "epoch": 0.7060702875399361, "percentage": 23.54, "elapsed_time": "0:39:24", "remaining_time": "2:08:01"}
+{"current_steps": 222, "total_steps": 939, "loss": 0.5386, "lr": 9.44443533970178e-06, "epoch": 0.7092651757188498, "percentage": 23.64, "elapsed_time": "0:39:35", "remaining_time": "2:07:50"}
+{"current_steps": 223, "total_steps": 939, "loss": 0.4815, "lr": 9.435888391463108e-06, "epoch": 0.7124600638977636, "percentage": 23.75, "elapsed_time": "0:39:42", "remaining_time": "2:07:29"}
+{"current_steps": 224, "total_steps": 939, "loss": 0.4967, "lr": 9.427280128266049e-06, "epoch": 0.7156549520766773, "percentage": 23.86, "elapsed_time": "0:39:51", "remaining_time": "2:07:13"}
+{"current_steps": 225, "total_steps": 939, "loss": 0.502, "lr": 9.418610669098114e-06, "epoch": 0.7188498402555911, "percentage": 23.96, "elapsed_time": "0:39:59", "remaining_time": "2:06:54"}
+{"current_steps": 226, "total_steps": 939, "loss": 0.5471, "lr": 9.409880133792684e-06, "epoch": 0.7220447284345048, "percentage": 24.07, "elapsed_time": "0:40:10", "remaining_time": "2:06:45"}
+{"current_steps": 227, "total_steps": 939, "loss": 0.5415, "lr": 9.40108864302737e-06, "epoch": 0.7252396166134185, "percentage": 24.17, "elapsed_time": "0:40:22", "remaining_time": "2:06:37"}
+{"current_steps": 228, "total_steps": 939, "loss": 0.5131, "lr": 9.392236318322339e-06, "epoch": 0.7284345047923323, "percentage": 24.28, "elapsed_time": "0:40:33", "remaining_time": "2:06:27"}
+{"current_steps": 229, "total_steps": 939, "loss": 0.5174, "lr": 9.383323282038632e-06, "epoch": 0.731629392971246, "percentage": 24.39, "elapsed_time": "0:40:44", "remaining_time": "2:06:20"}
+{"current_steps": 230, "total_steps": 939, "loss": 0.5025, "lr": 9.374349657376473e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:40:54", "remaining_time": "2:06:05"}
+{"current_steps": 231, "total_steps": 939, "loss": 0.5119, "lr": 9.365315568373569e-06, "epoch": 0.7380191693290735, "percentage": 24.6, "elapsed_time": "0:41:05", "remaining_time": "2:05:55"}
+{"current_steps": 232, "total_steps": 939, "loss": 0.5222, "lr": 9.356221139903395e-06, "epoch": 0.7412140575079872, "percentage": 24.71, "elapsed_time": "0:41:18", "remaining_time": "2:05:52"}
+{"current_steps": 233, "total_steps": 939, "loss": 0.4956, "lr": 9.347066497673462e-06, "epoch": 0.744408945686901, "percentage": 24.81, "elapsed_time": "0:41:25", "remaining_time": "2:05:31"}
+{"current_steps": 234, "total_steps": 939, "loss": 0.4948, "lr": 9.337851768223589e-06, "epoch": 0.7476038338658147, "percentage": 24.92, "elapsed_time": "0:41:34", "remaining_time": "2:05:14"}
+{"current_steps": 235, "total_steps": 939, "loss": 0.5117, "lr": 9.328577078924151e-06, "epoch": 0.7507987220447284, "percentage": 25.03, "elapsed_time": "0:41:44", "remaining_time": "2:05:04"}
+{"current_steps": 236, "total_steps": 939, "loss": 0.4821, "lr": 9.319242557974306e-06, "epoch": 0.7539936102236422, "percentage": 25.13, "elapsed_time": "0:41:56", "remaining_time": "2:04:56"}
+{"current_steps": 237, "total_steps": 939, "loss": 0.5237, "lr": 9.309848334400247e-06, "epoch": 0.7571884984025559, "percentage": 25.24, "elapsed_time": "0:42:08", "remaining_time": "2:04:50"}
+{"current_steps": 238, "total_steps": 939, "loss": 0.5017, "lr": 9.300394538053395e-06, "epoch": 0.7603833865814696, "percentage": 25.35, "elapsed_time": "0:42:18", "remaining_time": "2:04:36"}
+{"current_steps": 239, "total_steps": 939, "loss": 0.5127, "lr": 9.29088129960862e-06, "epoch": 0.7635782747603834, "percentage": 25.45, "elapsed_time": "0:42:29", "remaining_time": "2:04:28"}
+{"current_steps": 240, "total_steps": 939, "loss": 0.4893, "lr": 9.281308750562426e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:42:41", "remaining_time": "2:04:20"}
+{"current_steps": 241, "total_steps": 939, "loss": 0.4983, "lr": 9.271677023231137e-06, "epoch": 0.7699680511182109, "percentage": 25.67, "elapsed_time": "0:42:52", "remaining_time": "2:04:11"}
+{"current_steps": 242, "total_steps": 939, "loss": 0.4765, "lr": 9.261986250749068e-06, "epoch": 0.7731629392971247, "percentage": 25.77, "elapsed_time": "0:43:04", "remaining_time": "2:04:04"}
+{"current_steps": 243, "total_steps": 939, "loss": 0.4874, "lr": 9.252236567066686e-06, "epoch": 0.7763578274760383, "percentage": 25.88, "elapsed_time": "0:43:16", "remaining_time": "2:03:56"}
+{"current_steps": 244, "total_steps": 939, "loss": 0.5903, "lr": 9.242428106948748e-06, "epoch": 0.7795527156549521, "percentage": 25.99, "elapsed_time": "0:43:28", "remaining_time": "2:03:49"}
+{"current_steps": 245, "total_steps": 939, "loss": 0.5189, "lr": 9.23256100597246e-06, "epoch": 0.7827476038338658, "percentage": 26.09, "elapsed_time": "0:43:36", "remaining_time": "2:03:30"}
+{"current_steps": 246, "total_steps": 939, "loss": 0.5151, "lr": 9.22263540052558e-06, "epoch": 0.7859424920127795, "percentage": 26.2, "elapsed_time": "0:43:48", "remaining_time": "2:03:24"}
+{"current_steps": 247, "total_steps": 939, "loss": 0.5593, "lr": 9.212651427804544e-06, "epoch": 0.7891373801916933, "percentage": 26.3, "elapsed_time": "0:44:00", "remaining_time": "2:03:18"}
+{"current_steps": 248, "total_steps": 939, "loss": 0.5106, "lr": 9.202609225812572e-06, "epoch": 0.792332268370607, "percentage": 26.41, "elapsed_time": "0:44:09", "remaining_time": "2:03:02"}
+{"current_steps": 249, "total_steps": 939, "loss": 0.4975, "lr": 9.192508933357753e-06, "epoch": 0.7955271565495208, "percentage": 26.52, "elapsed_time": "0:44:22", "remaining_time": "2:02:58"}
+{"current_steps": 250, "total_steps": 939, "loss": 0.5089, "lr": 9.182350690051134e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:44:32", "remaining_time": "2:02:45"}
+{"current_steps": 251, "total_steps": 939, "loss": 0.4621, "lr": 9.172134636304783e-06, "epoch": 0.8019169329073482, "percentage": 26.73, "elapsed_time": "0:44:40", "remaining_time": "2:02:27"}
+{"current_steps": 252, "total_steps": 939, "loss": 0.5013, "lr": 9.16186091332985e-06, "epoch": 0.805111821086262, "percentage": 26.84, "elapsed_time": "0:44:51", "remaining_time": "2:02:18"}
+{"current_steps": 253, "total_steps": 939, "loss": 0.4925, "lr": 9.15152966313462e-06, "epoch": 0.8083067092651757, "percentage": 26.94, "elapsed_time": "0:45:03", "remaining_time": "2:02:09"}
+{"current_steps": 254, "total_steps": 939, "loss": 0.4612, "lr": 9.141141028522544e-06, "epoch": 0.8115015974440895, "percentage": 27.05, "elapsed_time": "0:45:12", "remaining_time": "2:01:54"}
+{"current_steps": 255, "total_steps": 939, "loss": 0.4837, "lr": 9.130695153090272e-06, "epoch": 0.8146964856230032, "percentage": 27.16, "elapsed_time": "0:45:23", "remaining_time": "2:01:46"}
+{"current_steps": 256, "total_steps": 939, "loss": 0.5045, "lr": 9.120192181225658e-06, "epoch": 0.8178913738019169, "percentage": 27.26, "elapsed_time": "0:45:33", "remaining_time": "2:01:34"}
+{"current_steps": 257, "total_steps": 939, "loss": 0.4874, "lr": 9.109632258105771e-06, "epoch": 0.8210862619808307, "percentage": 27.37, "elapsed_time": "0:45:44", "remaining_time": "2:01:24"}
+{"current_steps": 258, "total_steps": 939, "loss": 0.4771, "lr": 9.099015529694894e-06, "epoch": 0.8242811501597445, "percentage": 27.48, "elapsed_time": "0:45:56", "remaining_time": "2:01:16"}
+{"current_steps": 259, "total_steps": 939, "loss": 0.4943, "lr": 9.088342142742493e-06, "epoch": 0.8274760383386581, "percentage": 27.58, "elapsed_time": "0:46:08", "remaining_time": "2:01:07"}
+{"current_steps": 260, "total_steps": 939, "loss": 0.5186, "lr": 9.077612244781196e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:46:17", "remaining_time": "2:00:53"}
+{"current_steps": 261, "total_steps": 939, "loss": 0.5066, "lr": 9.066825984124751e-06, "epoch": 0.8338658146964856, "percentage": 27.8, "elapsed_time": "0:46:28", "remaining_time": "2:00:42"}
+{"current_steps": 262, "total_steps": 939, "loss": 0.5428, "lr": 9.055983509865988e-06, "epoch": 0.8370607028753994, "percentage": 27.9, "elapsed_time": "0:46:38", "remaining_time": "2:00:30"}
+{"current_steps": 263, "total_steps": 939, "loss": 0.5276, "lr": 9.045084971874738e-06, "epoch": 0.8402555910543131, "percentage": 28.01, "elapsed_time": "0:46:43", "remaining_time": "2:00:07"}
+{"current_steps": 264, "total_steps": 939, "loss": 0.5562, "lr": 9.034130520795774e-06, "epoch": 0.8434504792332268, "percentage": 28.12, "elapsed_time": "0:46:53", "remaining_time": "1:59:53"}
+{"current_steps": 265, "total_steps": 939, "loss": 0.504, "lr": 9.023120308046726e-06, "epoch": 0.8466453674121406, "percentage": 28.22, "elapsed_time": "0:47:03", "remaining_time": "1:59:40"}
+{"current_steps": 266, "total_steps": 939, "loss": 0.4649, "lr": 9.012054485815995e-06, "epoch": 0.8498402555910544, "percentage": 28.33, "elapsed_time": "0:47:11", "remaining_time": "1:59:23"}
+{"current_steps": 267, "total_steps": 939, "loss": 0.4908, "lr": 9.00093320706063e-06, "epoch": 0.853035143769968, "percentage": 28.43, "elapsed_time": "0:47:22", "remaining_time": "1:59:12"}
+{"current_steps": 268, "total_steps": 939, "loss": 0.483, "lr": 8.989756625504237e-06, "epoch": 0.8562300319488818, "percentage": 28.54, "elapsed_time": "0:47:31", "remaining_time": "1:58:58"}
+{"current_steps": 269, "total_steps": 939, "loss": 0.5018, "lr": 8.978524895634842e-06, "epoch": 0.8594249201277955, "percentage": 28.65, "elapsed_time": "0:47:43", "remaining_time": "1:58:51"}
+{"current_steps": 270, "total_steps": 939, "loss": 0.5439, "lr": 8.967238172702754e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:47:54", "remaining_time": "1:58:42"}
+{"current_steps": 271, "total_steps": 939, "loss": 0.5334, "lr": 8.95589661271842e-06, "epoch": 0.865814696485623, "percentage": 28.86, "elapsed_time": "0:48:06", "remaining_time": "1:58:36"}
+{"current_steps": 272, "total_steps": 939, "loss": 0.4968, "lr": 8.94450037245028e-06, "epoch": 0.8690095846645367, "percentage": 28.97, "elapsed_time": "0:48:17", "remaining_time": "1:58:25"}
+{"current_steps": 273, "total_steps": 939, "loss": 0.4893, "lr": 8.933049609422582e-06, "epoch": 0.8722044728434505, "percentage": 29.07, "elapsed_time": "0:48:28", "remaining_time": "1:58:15"}
+{"current_steps": 274, "total_steps": 939, "loss": 0.5345, "lr": 8.921544481913218e-06, "epoch": 0.8753993610223643, "percentage": 29.18, "elapsed_time": "0:48:40", "remaining_time": "1:58:07"}
+{"current_steps": 275, "total_steps": 939, "loss": 0.5156, "lr": 8.909985148951528e-06, "epoch": 0.8785942492012779, "percentage": 29.29, "elapsed_time": "0:48:52", "remaining_time": "1:58:00"}
+{"current_steps": 276, "total_steps": 939, "loss": 0.529, "lr": 8.898371770316113e-06, "epoch": 0.8817891373801917, "percentage": 29.39, "elapsed_time": "0:49:01", "remaining_time": "1:57:45"}
+{"current_steps": 277, "total_steps": 939, "loss": 0.5067, "lr": 8.886704506532611e-06, "epoch": 0.8849840255591054, "percentage": 29.5, "elapsed_time": "0:49:13", "remaining_time": "1:57:39"}
+{"current_steps": 278, "total_steps": 939, "loss": 0.4631, "lr": 8.874983518871488e-06, "epoch": 0.8881789137380192, "percentage": 29.61, "elapsed_time": "0:49:23", "remaining_time": "1:57:27"}
+{"current_steps": 279, "total_steps": 939, "loss": 0.5109, "lr": 8.86320896934581e-06, "epoch": 0.8913738019169329, "percentage": 29.71, "elapsed_time": "0:49:35", "remaining_time": "1:57:19"}
+{"current_steps": 280, "total_steps": 939, "loss": 0.5404, "lr": 8.851381020709e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:49:47", "remaining_time": "1:57:12"}
+{"current_steps": 281, "total_steps": 939, "loss": 0.544, "lr": 8.839499836452584e-06, "epoch": 0.8977635782747604, "percentage": 29.93, "elapsed_time": "0:49:58", "remaining_time": "1:57:00"}
+{"current_steps": 282, "total_steps": 939, "loss": 0.4744, "lr": 8.827565580803944e-06, "epoch": 0.9009584664536742, "percentage": 30.03, "elapsed_time": "0:50:10", "remaining_time": "1:56:54"}
+{"current_steps": 283, "total_steps": 939, "loss": 0.4917, "lr": 8.815578418724031e-06, "epoch": 0.9041533546325878, "percentage": 30.14, "elapsed_time": "0:50:18", "remaining_time": "1:56:37"}
+{"current_steps": 284, "total_steps": 939, "loss": 0.4877, "lr": 8.803538515905102e-06, "epoch": 0.9073482428115016, "percentage": 30.24, "elapsed_time": "0:50:27", "remaining_time": "1:56:23"}
+{"current_steps": 285, "total_steps": 939, "loss": 0.5375, "lr": 8.791446038768416e-06, "epoch": 0.9105431309904153, "percentage": 30.35, "elapsed_time": "0:50:37", "remaining_time": "1:56:10"}
+{"current_steps": 286, "total_steps": 939, "loss": 0.5083, "lr": 8.779301154461945e-06, "epoch": 0.9137380191693291, "percentage": 30.46, "elapsed_time": "0:50:49", "remaining_time": "1:56:02"}
+{"current_steps": 287, "total_steps": 939, "loss": 0.5355, "lr": 8.76710403085805e-06, "epoch": 0.9169329073482428, "percentage": 30.56, "elapsed_time": "0:51:01", "remaining_time": "1:55:54"}
+{"current_steps": 288, "total_steps": 939, "loss": 0.5028, "lr": 8.754854836551174e-06, "epoch": 0.9201277955271565, "percentage": 30.67, "elapsed_time": "0:51:08", "remaining_time": "1:55:37"}
+{"current_steps": 289, "total_steps": 939, "loss": 0.465, "lr": 8.742553740855507e-06, "epoch": 0.9233226837060703, "percentage": 30.78, "elapsed_time": "0:51:20", "remaining_time": "1:55:28"}
+{"current_steps": 290, "total_steps": 939, "loss": 0.5438, "lr": 8.730200913802638e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:51:31", "remaining_time": "1:55:18"}
+{"current_steps": 291, "total_steps": 939, "loss": 0.4949, "lr": 8.717796526139218e-06, "epoch": 0.9297124600638977, "percentage": 30.99, "elapsed_time": "0:51:43", "remaining_time": "1:55:10"}
+{"current_steps": 292, "total_steps": 939, "loss": 0.5081, "lr": 8.70534074932459e-06, "epoch": 0.9329073482428115, "percentage": 31.1, "elapsed_time": "0:51:52", "remaining_time": "1:54:56"}
+{"current_steps": 293, "total_steps": 939, "loss": 0.5278, "lr": 8.692833755528426e-06, "epoch": 0.9361022364217252, "percentage": 31.2, "elapsed_time": "0:52:03", "remaining_time": "1:54:47"}
+{"current_steps": 294, "total_steps": 939, "loss": 0.5033, "lr": 8.680275717628336e-06, "epoch": 0.939297124600639, "percentage": 31.31, "elapsed_time": "0:52:12", "remaining_time": "1:54:31"}
+{"current_steps": 295, "total_steps": 939, "loss": 0.5002, "lr": 8.667666809207495e-06, "epoch": 0.9424920127795527, "percentage": 31.42, "elapsed_time": "0:52:21", "remaining_time": "1:54:17"}
+{"current_steps": 296, "total_steps": 939, "loss": 0.5699, "lr": 8.655007204552228e-06, "epoch": 0.9456869009584664, "percentage": 31.52, "elapsed_time": "0:52:33", "remaining_time": "1:54:10"}
+{"current_steps": 297, "total_steps": 939, "loss": 0.4943, "lr": 8.64229707864961e-06, "epoch": 0.9488817891373802, "percentage": 31.63, "elapsed_time": "0:52:42", "remaining_time": "1:53:55"}
+{"current_steps": 298, "total_steps": 939, "loss": 0.5194, "lr": 8.629536607185042e-06, "epoch": 0.952076677316294, "percentage": 31.74, "elapsed_time": "0:52:51", "remaining_time": "1:53:41"}
+{"current_steps": 299, "total_steps": 939, "loss": 0.5146, "lr": 8.616725966539831e-06, "epoch": 0.9552715654952076, "percentage": 31.84, "elapsed_time": "0:53:03", "remaining_time": "1:53:34"}
+{"current_steps": 300, "total_steps": 939, "loss": 0.5002, "lr": 8.60386533378874e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:53:15", "remaining_time": "1:53:27"}
+{"current_steps": 301, "total_steps": 939, "loss": 0.4845, "lr": 8.590954886697554e-06, "epoch": 0.9616613418530351, "percentage": 32.06, "elapsed_time": "0:53:22", "remaining_time": "1:53:08"}
+{"current_steps": 302, "total_steps": 939, "loss": 0.4975, "lr": 8.577994803720605e-06, "epoch": 0.9648562300319489, "percentage": 32.16, "elapsed_time": "0:53:32", "remaining_time": "1:52:56"}
+{"current_steps": 303, "total_steps": 939, "loss": 0.4797, "lr": 8.564985263998327e-06, "epoch": 0.9680511182108626, "percentage": 32.27, "elapsed_time": "0:53:45", "remaining_time": "1:52:49"}
+{"current_steps": 304, "total_steps": 939, "loss": 0.4639, "lr": 8.551926447354759e-06, "epoch": 0.9712460063897763, "percentage": 32.37, "elapsed_time": "0:53:57", "remaining_time": "1:52:41"}
+{"current_steps": 305, "total_steps": 939, "loss": 0.4892, "lr": 8.538818534295076e-06, "epoch": 0.9744408945686901, "percentage": 32.48, "elapsed_time": "0:54:06", "remaining_time": "1:52:28"}
+{"current_steps": 306, "total_steps": 939, "loss": 0.484, "lr": 8.525661706003083e-06, "epoch": 0.9776357827476039, "percentage": 32.59, "elapsed_time": "0:54:16", "remaining_time": "1:52:17"}
+{"current_steps": 307, "total_steps": 939, "loss": 0.4956, "lr": 8.512456144338717e-06, "epoch": 0.9808306709265175, "percentage": 32.69, "elapsed_time": "0:54:22", "remaining_time": "1:51:56"}
+{"current_steps": 308, "total_steps": 939, "loss": 0.4973, "lr": 8.499202031835532e-06, "epoch": 0.9840255591054313, "percentage": 32.8, "elapsed_time": "0:54:33", "remaining_time": "1:51:46"}
+{"current_steps": 309, "total_steps": 939, "loss": 0.5086, "lr": 8.485899551698166e-06, "epoch": 0.987220447284345, "percentage": 32.91, "elapsed_time": "0:54:42", "remaining_time": "1:51:32"}
+{"current_steps": 310, "total_steps": 939, "loss": 0.4838, "lr": 8.472548887799833e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:54:53", "remaining_time": "1:51:22"}
+{"current_steps": 311, "total_steps": 939, "loss": 0.4707, "lr": 8.45915022467975e-06, "epoch": 0.9936102236421726, "percentage": 33.12, "elapsed_time": "0:55:03", "remaining_time": "1:51:10"}
+{"current_steps": 312, "total_steps": 939, "loss": 0.5721, "lr": 8.445703747540614e-06, "epoch": 0.9968051118210862, "percentage": 33.23, "elapsed_time": "0:55:13", "remaining_time": "1:50:58"}
+{"current_steps": 313, "total_steps": 939, "loss": 0.5683, "lr": 8.43220964224602e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:55:24", "remaining_time": "1:50:49"}
+{"current_steps": 314, "total_steps": 939, "loss": 0.4403, "lr": 8.418668095317912e-06, "epoch": 1.0031948881789137, "percentage": 33.44, "elapsed_time": "0:56:18", "remaining_time": "1:52:05"}
+{"current_steps": 315, "total_steps": 939, "loss": 0.4496, "lr": 8.405079293933986e-06, "epoch": 1.0063897763578276, "percentage": 33.55, "elapsed_time": "0:56:30", "remaining_time": "1:51:56"}
+{"current_steps": 316, "total_steps": 939, "loss": 0.3808, "lr": 8.391443425925118e-06, "epoch": 1.0095846645367412, "percentage": 33.65, "elapsed_time": "0:56:37", "remaining_time": "1:51:38"}
+{"current_steps": 317, "total_steps": 939, "loss": 0.3941, "lr": 8.37776067977276e-06, "epoch": 1.012779552715655, "percentage": 33.76, "elapsed_time": "0:56:50", "remaining_time": "1:51:31"}
+{"current_steps": 318, "total_steps": 939, "loss": 0.41, "lr": 8.36403124460633e-06, "epoch": 1.0159744408945688, "percentage": 33.87, "elapsed_time": "0:57:00", "remaining_time": "1:51:19"}
+{"current_steps": 319, "total_steps": 939, "loss": 0.4023, "lr": 8.350255310200611e-06, "epoch": 1.0191693290734825, "percentage": 33.97, "elapsed_time": "0:57:09", "remaining_time": "1:51:05"}
+{"current_steps": 320, "total_steps": 939, "loss": 0.4308, "lr": 8.336433066973122e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:57:21", "remaining_time": "1:50:56"}
+{"current_steps": 321, "total_steps": 939, "loss": 0.4339, "lr": 8.322564705981476e-06, "epoch": 1.0255591054313098, "percentage": 34.19, "elapsed_time": "0:57:33", "remaining_time": "1:50:48"}
+{"current_steps": 322, "total_steps": 939, "loss": 0.4639, "lr": 8.308650418920751e-06, "epoch": 1.0287539936102237, "percentage": 34.29, "elapsed_time": "0:57:42", "remaining_time": "1:50:33"}
+{"current_steps": 323, "total_steps": 939, "loss": 0.4138, "lr": 8.294690398120843e-06, "epoch": 1.0319488817891374, "percentage": 34.4, "elapsed_time": "0:57:50", "remaining_time": "1:50:18"}
+{"current_steps": 324, "total_steps": 939, "loss": 0.4181, "lr": 8.280684836543794e-06, "epoch": 1.035143769968051, "percentage": 34.5, "elapsed_time": "0:58:02", "remaining_time": "1:50:09"}
+{"current_steps": 325, "total_steps": 939, "loss": 0.3765, "lr": 8.266633927781135e-06, "epoch": 1.038338658146965, "percentage": 34.61, "elapsed_time": "0:58:10", "remaining_time": "1:49:53"}
+{"current_steps": 326, "total_steps": 939, "loss": 0.4155, "lr": 8.25253786605121e-06, "epoch": 1.0415335463258786, "percentage": 34.72, "elapsed_time": "0:58:21", "remaining_time": "1:49:44"}
+{"current_steps": 327, "total_steps": 939, "loss": 0.4796, "lr": 8.238396846196483e-06, "epoch": 1.0447284345047922, "percentage": 34.82, "elapsed_time": "0:58:33", "remaining_time": "1:49:34"}
+{"current_steps": 328, "total_steps": 939, "loss": 0.3758, "lr": 8.224211063680854e-06, "epoch": 1.0479233226837061, "percentage": 34.93, "elapsed_time": "0:58:44", "remaining_time": "1:49:25"}
+{"current_steps": 329, "total_steps": 939, "loss": 0.4103, "lr": 8.209980714586955e-06, "epoch": 1.0511182108626198, "percentage": 35.04, "elapsed_time": "0:58:56", "remaining_time": "1:49:16"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da6965553a7372621d2aa16abae70276df82529c7c7e4682e7a93baf410eedf
+size 7224