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 sha256:58d072d84dec72b35ca1d0fe0121ce59237bf41e470a7ed565098d4878d07bfb
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d19fb7c555a0220ef93174d881cbd10a49370eaaaf35c4902c8667deb9e22d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6366376c1b13817be97f94e8e366a9fac87910b1b929ae97189715a59f7f14
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e29313491a69cf036aba27e2abb0170ebb0d86371561938ff7ec7c4f5eec26
+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 +1,255 @@
+{"current_steps": 1, "total_steps": 1235, "loss": 0.8014, "lr": 3.2258064516129035e-07, "epoch": 0.004048582995951417, "percentage": 0.08, "elapsed_time": "0:00:36", "remaining_time": "12:25:26"}
+{"current_steps": 2, "total_steps": 1235, "loss": 0.8239, "lr": 6.451612903225807e-07, "epoch": 0.008097165991902834, "percentage": 0.16, "elapsed_time": "0:00:58", "remaining_time": "9:57:12"}
+{"current_steps": 3, "total_steps": 1235, "loss": 0.8091, "lr": 9.67741935483871e-07, "epoch": 0.012145748987854251, "percentage": 0.24, "elapsed_time": "0:01:19", "remaining_time": "9:01:08"}
+{"current_steps": 4, "total_steps": 1235, "loss": 0.7885, "lr": 1.2903225806451614e-06, "epoch": 0.016194331983805668, "percentage": 0.32, "elapsed_time": "0:01:42", "remaining_time": "8:44:42"}
+{"current_steps": 5, "total_steps": 1235, "loss": 0.7789, "lr": 1.6129032258064516e-06, "epoch": 0.020242914979757085, "percentage": 0.4, "elapsed_time": "0:02:05", "remaining_time": "8:35:16"}
+{"current_steps": 6, "total_steps": 1235, "loss": 0.7965, "lr": 1.935483870967742e-06, "epoch": 0.024291497975708502, "percentage": 0.49, "elapsed_time": "0:02:28", "remaining_time": "8:26:57"}
+{"current_steps": 7, "total_steps": 1235, "loss": 0.7465, "lr": 2.2580645161290324e-06, "epoch": 0.02834008097165992, "percentage": 0.57, "elapsed_time": "0:02:51", "remaining_time": "8:20:01"}
+{"current_steps": 8, "total_steps": 1235, "loss": 0.7283, "lr": 2.580645161290323e-06, "epoch": 0.032388663967611336, "percentage": 0.65, "elapsed_time": "0:03:14", "remaining_time": "8:17:12"}
+{"current_steps": 9, "total_steps": 1235, "loss": 0.7176, "lr": 2.903225806451613e-06, "epoch": 0.03643724696356275, "percentage": 0.73, "elapsed_time": "0:03:36", "remaining_time": "8:11:24"}
+{"current_steps": 10, "total_steps": 1235, "loss": 0.7035, "lr": 3.225806451612903e-06, "epoch": 0.04048582995951417, "percentage": 0.81, "elapsed_time": "0:04:00", "remaining_time": "8:11:41"}
+{"current_steps": 11, "total_steps": 1235, "loss": 0.7034, "lr": 3.548387096774194e-06, "epoch": 0.044534412955465584, "percentage": 0.89, "elapsed_time": "0:04:24", "remaining_time": "8:10:13"}
+{"current_steps": 12, "total_steps": 1235, "loss": 0.6933, "lr": 3.870967741935484e-06, "epoch": 0.048582995951417005, "percentage": 0.97, "elapsed_time": "0:04:46", "remaining_time": "8:06:41"}
+{"current_steps": 13, "total_steps": 1235, "loss": 0.6838, "lr": 4.193548387096774e-06, "epoch": 0.05263157894736842, "percentage": 1.05, "elapsed_time": "0:05:06", "remaining_time": "8:00:12"}
+{"current_steps": 14, "total_steps": 1235, "loss": 0.6837, "lr": 4.516129032258065e-06, "epoch": 0.05668016194331984, "percentage": 1.13, "elapsed_time": "0:05:28", "remaining_time": "7:58:05"}
+{"current_steps": 15, "total_steps": 1235, "loss": 0.6697, "lr": 4.838709677419355e-06, "epoch": 0.06072874493927125, "percentage": 1.21, "elapsed_time": "0:05:51", "remaining_time": "7:56:26"}
+{"current_steps": 16, "total_steps": 1235, "loss": 0.6388, "lr": 5.161290322580646e-06, "epoch": 0.06477732793522267, "percentage": 1.3, "elapsed_time": "0:06:15", "remaining_time": "7:56:20"}
+{"current_steps": 17, "total_steps": 1235, "loss": 0.6441, "lr": 5.483870967741935e-06, "epoch": 0.06882591093117409, "percentage": 1.38, "elapsed_time": "0:06:38", "remaining_time": "7:56:02"}
+{"current_steps": 18, "total_steps": 1235, "loss": 0.5922, "lr": 5.806451612903226e-06, "epoch": 0.0728744939271255, "percentage": 1.46, "elapsed_time": "0:07:01", "remaining_time": "7:54:45"}
+{"current_steps": 19, "total_steps": 1235, "loss": 0.6266, "lr": 6.129032258064517e-06, "epoch": 0.07692307692307693, "percentage": 1.54, "elapsed_time": "0:07:25", "remaining_time": "7:54:52"}
+{"current_steps": 20, "total_steps": 1235, "loss": 0.617, "lr": 6.451612903225806e-06, "epoch": 0.08097165991902834, "percentage": 1.62, "elapsed_time": "0:07:48", "remaining_time": "7:54:20"}
+{"current_steps": 21, "total_steps": 1235, "loss": 0.5728, "lr": 6.774193548387097e-06, "epoch": 0.08502024291497975, "percentage": 1.7, "elapsed_time": "0:08:12", "remaining_time": "7:54:05"}
+{"current_steps": 22, "total_steps": 1235, "loss": 0.5816, "lr": 7.096774193548388e-06, "epoch": 0.08906882591093117, "percentage": 1.78, "elapsed_time": "0:08:34", "remaining_time": "7:52:39"}
+{"current_steps": 23, "total_steps": 1235, "loss": 0.5799, "lr": 7.4193548387096784e-06, "epoch": 0.0931174089068826, "percentage": 1.86, "elapsed_time": "0:08:55", "remaining_time": "7:50:07"}
+{"current_steps": 24, "total_steps": 1235, "loss": 0.5412, "lr": 7.741935483870968e-06, "epoch": 0.09716599190283401, "percentage": 1.94, "elapsed_time": "0:09:17", "remaining_time": "7:49:12"}
+{"current_steps": 25, "total_steps": 1235, "loss": 0.5629, "lr": 8.064516129032258e-06, "epoch": 0.10121457489878542, "percentage": 2.02, "elapsed_time": "0:09:39", "remaining_time": "7:47:38"}
+{"current_steps": 26, "total_steps": 1235, "loss": 0.5518, "lr": 8.387096774193549e-06, "epoch": 0.10526315789473684, "percentage": 2.11, "elapsed_time": "0:10:02", "remaining_time": "7:46:34"}
+{"current_steps": 27, "total_steps": 1235, "loss": 0.539, "lr": 8.70967741935484e-06, "epoch": 0.10931174089068826, "percentage": 2.19, "elapsed_time": "0:10:23", "remaining_time": "7:44:35"}
+{"current_steps": 28, "total_steps": 1235, "loss": 0.5456, "lr": 9.03225806451613e-06, "epoch": 0.11336032388663968, "percentage": 2.27, "elapsed_time": "0:10:45", "remaining_time": "7:43:53"}
+{"current_steps": 29, "total_steps": 1235, "loss": 0.5472, "lr": 9.35483870967742e-06, "epoch": 0.11740890688259109, "percentage": 2.35, "elapsed_time": "0:11:08", "remaining_time": "7:43:10"}
+{"current_steps": 30, "total_steps": 1235, "loss": 0.5156, "lr": 9.67741935483871e-06, "epoch": 0.1214574898785425, "percentage": 2.43, "elapsed_time": "0:11:30", "remaining_time": "7:41:56"}
+{"current_steps": 31, "total_steps": 1235, "loss": 0.5264, "lr": 1e-05, "epoch": 0.12550607287449392, "percentage": 2.51, "elapsed_time": "0:11:52", "remaining_time": "7:41:12"}
+{"current_steps": 32, "total_steps": 1235, "loss": 0.5389, "lr": 1.0322580645161291e-05, "epoch": 0.12955465587044535, "percentage": 2.59, "elapsed_time": "0:12:15", "remaining_time": "7:40:50"}
+{"current_steps": 33, "total_steps": 1235, "loss": 0.5295, "lr": 1.0645161290322582e-05, "epoch": 0.13360323886639677, "percentage": 2.67, "elapsed_time": "0:12:36", "remaining_time": "7:39:29"}
+{"current_steps": 34, "total_steps": 1235, "loss": 0.5204, "lr": 1.096774193548387e-05, "epoch": 0.13765182186234817, "percentage": 2.75, "elapsed_time": "0:12:59", "remaining_time": "7:38:54"}
+{"current_steps": 35, "total_steps": 1235, "loss": 0.5154, "lr": 1.1290322580645164e-05, "epoch": 0.1417004048582996, "percentage": 2.83, "elapsed_time": "0:13:22", "remaining_time": "7:38:33"}
+{"current_steps": 36, "total_steps": 1235, "loss": 0.5302, "lr": 1.1612903225806453e-05, "epoch": 0.145748987854251, "percentage": 2.91, "elapsed_time": "0:15:46", "remaining_time": "8:45:12"}
+{"current_steps": 37, "total_steps": 1235, "loss": 0.4965, "lr": 1.1935483870967743e-05, "epoch": 0.14979757085020243, "percentage": 3.0, "elapsed_time": "0:16:08", "remaining_time": "8:42:50"}
+{"current_steps": 38, "total_steps": 1235, "loss": 0.5346, "lr": 1.2258064516129034e-05, "epoch": 0.15384615384615385, "percentage": 3.08, "elapsed_time": "0:16:31", "remaining_time": "8:40:19"}
+{"current_steps": 39, "total_steps": 1235, "loss": 0.4916, "lr": 1.2580645161290324e-05, "epoch": 0.15789473684210525, "percentage": 3.16, "elapsed_time": "0:16:53", "remaining_time": "8:37:55"}
+{"current_steps": 40, "total_steps": 1235, "loss": 0.5064, "lr": 1.2903225806451613e-05, "epoch": 0.16194331983805668, "percentage": 3.24, "elapsed_time": "0:17:16", "remaining_time": "8:36:13"}
+{"current_steps": 41, "total_steps": 1235, "loss": 0.5222, "lr": 1.3225806451612903e-05, "epoch": 0.1659919028340081, "percentage": 3.32, "elapsed_time": "0:17:39", "remaining_time": "8:34:21"}
+{"current_steps": 42, "total_steps": 1235, "loss": 0.4955, "lr": 1.3548387096774194e-05, "epoch": 0.1700404858299595, "percentage": 3.4, "elapsed_time": "0:18:03", "remaining_time": "8:32:46"}
+{"current_steps": 43, "total_steps": 1235, "loss": 0.4952, "lr": 1.3870967741935486e-05, "epoch": 0.17408906882591094, "percentage": 3.48, "elapsed_time": "0:18:25", "remaining_time": "8:30:37"}
+{"current_steps": 44, "total_steps": 1235, "loss": 0.4992, "lr": 1.4193548387096776e-05, "epoch": 0.17813765182186234, "percentage": 3.56, "elapsed_time": "0:18:48", "remaining_time": "8:29:13"}
+{"current_steps": 45, "total_steps": 1235, "loss": 0.475, "lr": 1.4516129032258066e-05, "epoch": 0.18218623481781376, "percentage": 3.64, "elapsed_time": "0:19:11", "remaining_time": "8:27:27"}
+{"current_steps": 46, "total_steps": 1235, "loss": 0.4738, "lr": 1.4838709677419357e-05, "epoch": 0.1862348178137652, "percentage": 3.72, "elapsed_time": "0:19:33", "remaining_time": "8:25:25"}
+{"current_steps": 47, "total_steps": 1235, "loss": 0.4891, "lr": 1.5161290322580646e-05, "epoch": 0.1902834008097166, "percentage": 3.81, "elapsed_time": "0:19:56", "remaining_time": "8:24:00"}
+{"current_steps": 48, "total_steps": 1235, "loss": 0.4857, "lr": 1.5483870967741936e-05, "epoch": 0.19433198380566802, "percentage": 3.89, "elapsed_time": "0:20:19", "remaining_time": "8:22:44"}
+{"current_steps": 49, "total_steps": 1235, "loss": 0.4981, "lr": 1.5806451612903226e-05, "epoch": 0.19838056680161945, "percentage": 3.97, "elapsed_time": "0:20:43", "remaining_time": "8:21:26"}
+{"current_steps": 50, "total_steps": 1235, "loss": 0.4792, "lr": 1.6129032258064517e-05, "epoch": 0.20242914979757085, "percentage": 4.05, "elapsed_time": "0:21:04", "remaining_time": "8:19:34"}
+{"current_steps": 51, "total_steps": 1235, "loss": 0.4926, "lr": 1.6451612903225807e-05, "epoch": 0.20647773279352227, "percentage": 4.13, "elapsed_time": "0:21:27", "remaining_time": "8:18:14"}
+{"current_steps": 52, "total_steps": 1235, "loss": 0.4833, "lr": 1.6774193548387098e-05, "epoch": 0.21052631578947367, "percentage": 4.21, "elapsed_time": "0:21:50", "remaining_time": "8:17:01"}
+{"current_steps": 53, "total_steps": 1235, "loss": 0.485, "lr": 1.7096774193548388e-05, "epoch": 0.2145748987854251, "percentage": 4.29, "elapsed_time": "0:22:14", "remaining_time": "8:15:57"}
+{"current_steps": 54, "total_steps": 1235, "loss": 0.4948, "lr": 1.741935483870968e-05, "epoch": 0.21862348178137653, "percentage": 4.37, "elapsed_time": "0:22:37", "remaining_time": "8:14:58"}
+{"current_steps": 55, "total_steps": 1235, "loss": 0.455, "lr": 1.774193548387097e-05, "epoch": 0.22267206477732793, "percentage": 4.45, "elapsed_time": "0:22:58", "remaining_time": "8:13:05"}
+{"current_steps": 56, "total_steps": 1235, "loss": 0.4856, "lr": 1.806451612903226e-05, "epoch": 0.22672064777327935, "percentage": 4.53, "elapsed_time": "0:23:22", "remaining_time": "8:12:00"}
+{"current_steps": 57, "total_steps": 1235, "loss": 0.4727, "lr": 1.838709677419355e-05, "epoch": 0.23076923076923078, "percentage": 4.62, "elapsed_time": "0:23:44", "remaining_time": "8:10:40"}
+{"current_steps": 58, "total_steps": 1235, "loss": 0.4866, "lr": 1.870967741935484e-05, "epoch": 0.23481781376518218, "percentage": 4.7, "elapsed_time": "0:24:05", "remaining_time": "8:09:02"}
+{"current_steps": 59, "total_steps": 1235, "loss": 0.4698, "lr": 1.903225806451613e-05, "epoch": 0.2388663967611336, "percentage": 4.78, "elapsed_time": "0:24:29", "remaining_time": "8:08:03"}
+{"current_steps": 60, "total_steps": 1235, "loss": 0.472, "lr": 1.935483870967742e-05, "epoch": 0.242914979757085, "percentage": 4.86, "elapsed_time": "0:24:52", "remaining_time": "8:06:59"}
+{"current_steps": 61, "total_steps": 1235, "loss": 0.4689, "lr": 1.967741935483871e-05, "epoch": 0.24696356275303644, "percentage": 4.94, "elapsed_time": "0:25:14", "remaining_time": "8:05:39"}
+{"current_steps": 62, "total_steps": 1235, "loss": 0.4722, "lr": 2e-05, "epoch": 0.25101214574898784, "percentage": 5.02, "elapsed_time": "0:25:35", "remaining_time": "8:04:15"}
+{"current_steps": 63, "total_steps": 1235, "loss": 0.4712, "lr": 2.0322580645161292e-05, "epoch": 0.2550607287449393, "percentage": 5.1, "elapsed_time": "0:25:58", "remaining_time": "8:03:21"}
+{"current_steps": 64, "total_steps": 1235, "loss": 0.4579, "lr": 2.0645161290322582e-05, "epoch": 0.2591093117408907, "percentage": 5.18, "elapsed_time": "0:26:21", "remaining_time": "8:02:14"}
+{"current_steps": 65, "total_steps": 1235, "loss": 0.4776, "lr": 2.0967741935483873e-05, "epoch": 0.2631578947368421, "percentage": 5.26, "elapsed_time": "0:26:43", "remaining_time": "8:00:57"}
+{"current_steps": 66, "total_steps": 1235, "loss": 0.4599, "lr": 2.1290322580645163e-05, "epoch": 0.26720647773279355, "percentage": 5.34, "elapsed_time": "0:27:06", "remaining_time": "8:00:02"}
+{"current_steps": 67, "total_steps": 1235, "loss": 0.4464, "lr": 2.161290322580645e-05, "epoch": 0.27125506072874495, "percentage": 5.43, "elapsed_time": "0:27:26", "remaining_time": "7:58:30"}
+{"current_steps": 68, "total_steps": 1235, "loss": 0.4581, "lr": 2.193548387096774e-05, "epoch": 0.27530364372469635, "percentage": 5.51, "elapsed_time": "0:27:49", "remaining_time": "7:57:34"}
+{"current_steps": 69, "total_steps": 1235, "loss": 0.4805, "lr": 2.225806451612903e-05, "epoch": 0.2793522267206478, "percentage": 5.59, "elapsed_time": "0:28:12", "remaining_time": "7:56:48"}
+{"current_steps": 70, "total_steps": 1235, "loss": 0.4559, "lr": 2.2580645161290328e-05, "epoch": 0.2834008097165992, "percentage": 5.67, "elapsed_time": "0:28:34", "remaining_time": "7:55:32"}
+{"current_steps": 71, "total_steps": 1235, "loss": 0.4601, "lr": 2.2903225806451615e-05, "epoch": 0.2874493927125506, "percentage": 5.75, "elapsed_time": "0:28:56", "remaining_time": "7:54:31"}
+{"current_steps": 72, "total_steps": 1235, "loss": 0.4687, "lr": 2.3225806451612906e-05, "epoch": 0.291497975708502, "percentage": 5.83, "elapsed_time": "0:29:18", "remaining_time": "7:53:20"}
+{"current_steps": 73, "total_steps": 1235, "loss": 0.4769, "lr": 2.3548387096774196e-05, "epoch": 0.29554655870445345, "percentage": 5.91, "elapsed_time": "0:29:41", "remaining_time": "7:52:34"}
+{"current_steps": 74, "total_steps": 1235, "loss": 0.4634, "lr": 2.3870967741935486e-05, "epoch": 0.29959514170040485, "percentage": 5.99, "elapsed_time": "0:30:02", "remaining_time": "7:51:27"}
+{"current_steps": 75, "total_steps": 1235, "loss": 0.4528, "lr": 2.4193548387096777e-05, "epoch": 0.30364372469635625, "percentage": 6.07, "elapsed_time": "0:30:25", "remaining_time": "7:50:40"}
+{"current_steps": 76, "total_steps": 1235, "loss": 0.4472, "lr": 2.4516129032258067e-05, "epoch": 0.3076923076923077, "percentage": 6.15, "elapsed_time": "0:30:47", "remaining_time": "7:49:41"}
+{"current_steps": 77, "total_steps": 1235, "loss": 0.4737, "lr": 2.4838709677419358e-05, "epoch": 0.3117408906882591, "percentage": 6.23, "elapsed_time": "0:31:10", "remaining_time": "7:48:57"}
+{"current_steps": 78, "total_steps": 1235, "loss": 0.4689, "lr": 2.5161290322580648e-05, "epoch": 0.3157894736842105, "percentage": 6.32, "elapsed_time": "0:31:32", "remaining_time": "7:47:56"}
+{"current_steps": 79, "total_steps": 1235, "loss": 0.4579, "lr": 2.548387096774194e-05, "epoch": 0.31983805668016196, "percentage": 6.4, "elapsed_time": "0:31:55", "remaining_time": "7:47:09"}
+{"current_steps": 80, "total_steps": 1235, "loss": 0.4764, "lr": 2.5806451612903226e-05, "epoch": 0.32388663967611336, "percentage": 6.48, "elapsed_time": "0:32:15", "remaining_time": "7:45:38"}
+{"current_steps": 81, "total_steps": 1235, "loss": 0.4574, "lr": 2.6129032258064516e-05, "epoch": 0.32793522267206476, "percentage": 6.56, "elapsed_time": "0:32:37", "remaining_time": "7:44:46"}
+{"current_steps": 82, "total_steps": 1235, "loss": 0.4628, "lr": 2.6451612903225806e-05, "epoch": 0.3319838056680162, "percentage": 6.64, "elapsed_time": "0:33:00", "remaining_time": "7:44:01"}
+{"current_steps": 83, "total_steps": 1235, "loss": 0.4565, "lr": 2.6774193548387097e-05, "epoch": 0.3360323886639676, "percentage": 6.72, "elapsed_time": "0:33:23", "remaining_time": "7:43:30"}
+{"current_steps": 84, "total_steps": 1235, "loss": 0.4523, "lr": 2.7096774193548387e-05, "epoch": 0.340080971659919, "percentage": 6.8, "elapsed_time": "0:33:47", "remaining_time": "7:42:57"}
+{"current_steps": 85, "total_steps": 1235, "loss": 0.456, "lr": 2.7419354838709678e-05, "epoch": 0.3441295546558704, "percentage": 6.88, "elapsed_time": "0:34:10", "remaining_time": "7:42:25"}
+{"current_steps": 86, "total_steps": 1235, "loss": 0.457, "lr": 2.774193548387097e-05, "epoch": 0.3481781376518219, "percentage": 6.96, "elapsed_time": "0:34:34", "remaining_time": "7:41:58"}
+{"current_steps": 87, "total_steps": 1235, "loss": 0.4736, "lr": 2.8064516129032262e-05, "epoch": 0.3522267206477733, "percentage": 7.04, "elapsed_time": "0:34:57", "remaining_time": "7:41:21"}
+{"current_steps": 88, "total_steps": 1235, "loss": 0.455, "lr": 2.8387096774193552e-05, "epoch": 0.3562753036437247, "percentage": 7.13, "elapsed_time": "0:35:20", "remaining_time": "7:40:32"}
+{"current_steps": 89, "total_steps": 1235, "loss": 0.4564, "lr": 2.8709677419354843e-05, "epoch": 0.3603238866396761, "percentage": 7.21, "elapsed_time": "0:35:42", "remaining_time": "7:39:42"}
+{"current_steps": 90, "total_steps": 1235, "loss": 0.4533, "lr": 2.9032258064516133e-05, "epoch": 0.3643724696356275, "percentage": 7.29, "elapsed_time": "0:36:02", "remaining_time": "7:38:36"}
+{"current_steps": 91, "total_steps": 1235, "loss": 0.4542, "lr": 2.9354838709677423e-05, "epoch": 0.3684210526315789, "percentage": 7.37, "elapsed_time": "0:36:25", "remaining_time": "7:37:56"}
+{"current_steps": 92, "total_steps": 1235, "loss": 0.4448, "lr": 2.9677419354838714e-05, "epoch": 0.3724696356275304, "percentage": 7.45, "elapsed_time": "0:36:48", "remaining_time": "7:37:13"}
+{"current_steps": 93, "total_steps": 1235, "loss": 0.4506, "lr": 3.0000000000000004e-05, "epoch": 0.3765182186234818, "percentage": 7.53, "elapsed_time": "0:37:09", "remaining_time": "7:36:15"}
+{"current_steps": 94, "total_steps": 1235, "loss": 0.4537, "lr": 3.032258064516129e-05, "epoch": 0.3805668016194332, "percentage": 7.61, "elapsed_time": "0:37:32", "remaining_time": "7:35:35"}
+{"current_steps": 95, "total_steps": 1235, "loss": 0.4366, "lr": 3.0645161290322585e-05, "epoch": 0.38461538461538464, "percentage": 7.69, "elapsed_time": "0:37:54", "remaining_time": "7:34:53"}
+{"current_steps": 96, "total_steps": 1235, "loss": 0.4533, "lr": 3.096774193548387e-05, "epoch": 0.38866396761133604, "percentage": 7.77, "elapsed_time": "0:38:17", "remaining_time": "7:34:13"}
+{"current_steps": 97, "total_steps": 1235, "loss": 0.4531, "lr": 3.1290322580645166e-05, "epoch": 0.39271255060728744, "percentage": 7.85, "elapsed_time": "0:38:39", "remaining_time": "7:33:30"}
+{"current_steps": 98, "total_steps": 1235, "loss": 0.448, "lr": 3.161290322580645e-05, "epoch": 0.3967611336032389, "percentage": 7.94, "elapsed_time": "0:39:02", "remaining_time": "7:32:54"}
+{"current_steps": 99, "total_steps": 1235, "loss": 0.4464, "lr": 3.193548387096774e-05, "epoch": 0.4008097165991903, "percentage": 8.02, "elapsed_time": "0:39:25", "remaining_time": "7:32:21"}
+{"current_steps": 100, "total_steps": 1235, "loss": 0.4652, "lr": 3.2258064516129034e-05, "epoch": 0.4048582995951417, "percentage": 8.1, "elapsed_time": "0:39:47", "remaining_time": "7:31:39"}
+{"current_steps": 101, "total_steps": 1235, "loss": 0.442, "lr": 3.258064516129033e-05, "epoch": 0.4089068825910931, "percentage": 8.18, "elapsed_time": "0:40:11", "remaining_time": "7:31:13"}
+{"current_steps": 102, "total_steps": 1235, "loss": 0.4477, "lr": 3.2903225806451614e-05, "epoch": 0.41295546558704455, "percentage": 8.26, "elapsed_time": "0:40:34", "remaining_time": "7:30:37"}
+{"current_steps": 103, "total_steps": 1235, "loss": 0.4646, "lr": 3.322580645161291e-05, "epoch": 0.41700404858299595, "percentage": 8.34, "elapsed_time": "0:40:55", "remaining_time": "7:29:49"}
+{"current_steps": 104, "total_steps": 1235, "loss": 0.4471, "lr": 3.3548387096774195e-05, "epoch": 0.42105263157894735, "percentage": 8.42, "elapsed_time": "0:41:18", "remaining_time": "7:29:09"}
+{"current_steps": 105, "total_steps": 1235, "loss": 0.4562, "lr": 3.387096774193549e-05, "epoch": 0.4251012145748988, "percentage": 8.5, "elapsed_time": "0:41:40", "remaining_time": "7:28:33"}
+{"current_steps": 106, "total_steps": 1235, "loss": 0.4525, "lr": 3.4193548387096776e-05, "epoch": 0.4291497975708502, "percentage": 8.58, "elapsed_time": "0:42:02", "remaining_time": "7:27:42"}
+{"current_steps": 107, "total_steps": 1235, "loss": 0.4455, "lr": 3.451612903225807e-05, "epoch": 0.4331983805668016, "percentage": 8.66, "elapsed_time": "0:42:24", "remaining_time": "7:27:08"}
+{"current_steps": 108, "total_steps": 1235, "loss": 0.4394, "lr": 3.483870967741936e-05, "epoch": 0.43724696356275305, "percentage": 8.74, "elapsed_time": "0:42:48", "remaining_time": "7:26:38"}
+{"current_steps": 109, "total_steps": 1235, "loss": 0.4344, "lr": 3.516129032258065e-05, "epoch": 0.44129554655870445, "percentage": 8.83, "elapsed_time": "0:43:10", "remaining_time": "7:26:04"}
+{"current_steps": 110, "total_steps": 1235, "loss": 0.4221, "lr": 3.548387096774194e-05, "epoch": 0.44534412955465585, "percentage": 8.91, "elapsed_time": "0:43:32", "remaining_time": "7:25:16"}
+{"current_steps": 111, "total_steps": 1235, "loss": 0.4554, "lr": 3.5806451612903225e-05, "epoch": 0.4493927125506073, "percentage": 8.99, "elapsed_time": "0:43:53", "remaining_time": "7:24:31"}
+{"current_steps": 112, "total_steps": 1235, "loss": 0.4494, "lr": 3.612903225806452e-05, "epoch": 0.4534412955465587, "percentage": 9.07, "elapsed_time": "0:44:16", "remaining_time": "7:23:57"}
+{"current_steps": 113, "total_steps": 1235, "loss": 0.4408, "lr": 3.6451612903225805e-05, "epoch": 0.4574898785425101, "percentage": 9.15, "elapsed_time": "0:44:38", "remaining_time": "7:23:19"}
+{"current_steps": 114, "total_steps": 1235, "loss": 0.458, "lr": 3.67741935483871e-05, "epoch": 0.46153846153846156, "percentage": 9.23, "elapsed_time": "0:44:59", "remaining_time": "7:22:25"}
+{"current_steps": 115, "total_steps": 1235, "loss": 0.4552, "lr": 3.7096774193548386e-05, "epoch": 0.46558704453441296, "percentage": 9.31, "elapsed_time": "0:45:21", "remaining_time": "7:21:48"}
+{"current_steps": 116, "total_steps": 1235, "loss": 0.4615, "lr": 3.741935483870968e-05, "epoch": 0.46963562753036436, "percentage": 9.39, "elapsed_time": "0:45:43", "remaining_time": "7:21:09"}
+{"current_steps": 117, "total_steps": 1235, "loss": 0.4439, "lr": 3.7741935483870974e-05, "epoch": 0.47368421052631576, "percentage": 9.47, "elapsed_time": "0:46:06", "remaining_time": "7:20:37"}
+{"current_steps": 118, "total_steps": 1235, "loss": 0.4396, "lr": 3.806451612903226e-05, "epoch": 0.4777327935222672, "percentage": 9.55, "elapsed_time": "0:46:28", "remaining_time": "7:20:00"}
+{"current_steps": 119, "total_steps": 1235, "loss": 0.447, "lr": 3.8387096774193555e-05, "epoch": 0.4817813765182186, "percentage": 9.64, "elapsed_time": "0:46:51", "remaining_time": "7:19:29"}
+{"current_steps": 120, "total_steps": 1235, "loss": 0.4601, "lr": 3.870967741935484e-05, "epoch": 0.48582995951417, "percentage": 9.72, "elapsed_time": "0:47:14", "remaining_time": "7:18:58"}
+{"current_steps": 121, "total_steps": 1235, "loss": 0.4572, "lr": 3.9032258064516135e-05, "epoch": 0.4898785425101215, "percentage": 9.8, "elapsed_time": "0:47:37", "remaining_time": "7:18:24"}
+{"current_steps": 122, "total_steps": 1235, "loss": 0.441, "lr": 3.935483870967742e-05, "epoch": 0.4939271255060729, "percentage": 9.88, "elapsed_time": "0:48:00", "remaining_time": "7:18:01"}
+{"current_steps": 123, "total_steps": 1235, "loss": 0.4522, "lr": 3.9677419354838716e-05, "epoch": 0.4979757085020243, "percentage": 9.96, "elapsed_time": "0:48:23", "remaining_time": "7:17:33"}
+{"current_steps": 124, "total_steps": 1235, "loss": 0.4435, "lr": 4e-05, "epoch": 0.5020242914979757, "percentage": 10.04, "elapsed_time": "0:48:47", "remaining_time": "7:17:06"}
+{"current_steps": 125, "total_steps": 1235, "loss": 0.4419, "lr": 3.9999920040266474e-05, "epoch": 0.5060728744939271, "percentage": 10.12, "elapsed_time": "0:49:09", "remaining_time": "7:16:33"}
+{"current_steps": 126, "total_steps": 1235, "loss": 0.4513, "lr": 3.999968016170525e-05, "epoch": 0.5101214574898786, "percentage": 10.2, "elapsed_time": "0:49:31", "remaining_time": "7:15:51"}
+{"current_steps": 127, "total_steps": 1235, "loss": 0.4481, "lr": 3.9999280366234394e-05, "epoch": 0.5141700404858299, "percentage": 10.28, "elapsed_time": "0:49:54", "remaining_time": "7:15:26"}
+{"current_steps": 128, "total_steps": 1235, "loss": 0.4344, "lr": 3.999872065705065e-05, "epoch": 0.5182186234817814, "percentage": 10.36, "elapsed_time": "0:50:15", "remaining_time": "7:14:40"}
+{"current_steps": 129, "total_steps": 1235, "loss": 0.4515, "lr": 3.999800103862945e-05, "epoch": 0.5222672064777328, "percentage": 10.45, "elapsed_time": "0:50:38", "remaining_time": "7:14:08"}
+{"current_steps": 130, "total_steps": 1235, "loss": 0.4588, "lr": 3.9997121516724834e-05, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "0:51:01", "remaining_time": "7:13:39"}
+{"current_steps": 131, "total_steps": 1235, "loss": 0.4397, "lr": 3.999608209836944e-05, "epoch": 0.5303643724696356, "percentage": 10.61, "elapsed_time": "0:51:23", "remaining_time": "7:13:02"}
+{"current_steps": 132, "total_steps": 1235, "loss": 0.443, "lr": 3.999488279187443e-05, "epoch": 0.5344129554655871, "percentage": 10.69, "elapsed_time": "0:51:45", "remaining_time": "7:12:29"}
+{"current_steps": 133, "total_steps": 1235, "loss": 0.4528, "lr": 3.9993523606829425e-05, "epoch": 0.5384615384615384, "percentage": 10.77, "elapsed_time": "0:52:05", "remaining_time": "7:11:39"}
+{"current_steps": 134, "total_steps": 1235, "loss": 0.438, "lr": 3.9992004554102435e-05, "epoch": 0.5425101214574899, "percentage": 10.85, "elapsed_time": "0:52:28", "remaining_time": "7:11:09"}
+{"current_steps": 135, "total_steps": 1235, "loss": 0.4418, "lr": 3.999032564583976e-05, "epoch": 0.5465587044534413, "percentage": 10.93, "elapsed_time": "0:52:49", "remaining_time": "7:10:29"}
+{"current_steps": 136, "total_steps": 1235, "loss": 0.4489, "lr": 3.998848689546591e-05, "epoch": 0.5506072874493927, "percentage": 11.01, "elapsed_time": "0:53:12", "remaining_time": "7:09:59"}
+{"current_steps": 137, "total_steps": 1235, "loss": 0.4274, "lr": 3.9986488317683496e-05, "epoch": 0.5546558704453441, "percentage": 11.09, "elapsed_time": "0:53:35", "remaining_time": "7:09:31"}
+{"current_steps": 138, "total_steps": 1235, "loss": 0.4397, "lr": 3.9984329928473067e-05, "epoch": 0.5587044534412956, "percentage": 11.17, "elapsed_time": "0:53:58", "remaining_time": "7:09:01"}
+{"current_steps": 139, "total_steps": 1235, "loss": 0.4707, "lr": 3.998201174509306e-05, "epoch": 0.562753036437247, "percentage": 11.26, "elapsed_time": "0:54:21", "remaining_time": "7:08:34"}
+{"current_steps": 140, "total_steps": 1235, "loss": 0.4414, "lr": 3.997953378607961e-05, "epoch": 0.5668016194331984, "percentage": 11.34, "elapsed_time": "0:54:42", "remaining_time": "7:07:55"}
+{"current_steps": 141, "total_steps": 1235, "loss": 0.4446, "lr": 3.9976896071246403e-05, "epoch": 0.5708502024291497, "percentage": 11.42, "elapsed_time": "0:55:05", "remaining_time": "7:07:23"}
+{"current_steps": 142, "total_steps": 1235, "loss": 0.4371, "lr": 3.997409862168454e-05, "epoch": 0.5748987854251012, "percentage": 11.5, "elapsed_time": "0:55:27", "remaining_time": "7:06:49"}
+{"current_steps": 143, "total_steps": 1235, "loss": 0.4415, "lr": 3.997114145976237e-05, "epoch": 0.5789473684210527, "percentage": 11.58, "elapsed_time": "0:55:49", "remaining_time": "7:06:20"}
+{"current_steps": 144, "total_steps": 1235, "loss": 0.4383, "lr": 3.9968024609125245e-05, "epoch": 0.582995951417004, "percentage": 11.66, "elapsed_time": "0:56:12", "remaining_time": "7:05:49"}
+{"current_steps": 145, "total_steps": 1235, "loss": 0.4448, "lr": 3.996474809469545e-05, "epoch": 0.5870445344129555, "percentage": 11.74, "elapsed_time": "0:56:34", "remaining_time": "7:05:20"}
+{"current_steps": 146, "total_steps": 1235, "loss": 0.4437, "lr": 3.996131194267189e-05, "epoch": 0.5910931174089069, "percentage": 11.82, "elapsed_time": "0:56:56", "remaining_time": "7:04:46"}
+{"current_steps": 147, "total_steps": 1235, "loss": 0.4319, "lr": 3.995771618052995e-05, "epoch": 0.5951417004048583, "percentage": 11.9, "elapsed_time": "0:57:19", "remaining_time": "7:04:20"}
+{"current_steps": 148, "total_steps": 1235, "loss": 0.447, "lr": 3.9953960837021256e-05, "epoch": 0.5991902834008097, "percentage": 11.98, "elapsed_time": "0:57:41", "remaining_time": "7:03:40"}
+{"current_steps": 149, "total_steps": 1235, "loss": 0.4425, "lr": 3.995004594217343e-05, "epoch": 0.6032388663967612, "percentage": 12.06, "elapsed_time": "0:58:04", "remaining_time": "7:03:16"}
+{"current_steps": 150, "total_steps": 1235, "loss": 0.4328, "lr": 3.994597152728987e-05, "epoch": 0.6072874493927125, "percentage": 12.15, "elapsed_time": "0:58:27", "remaining_time": "7:02:48"}
+{"current_steps": 151, "total_steps": 1235, "loss": 0.4262, "lr": 3.994173762494947e-05, "epoch": 0.611336032388664, "percentage": 12.23, "elapsed_time": "0:58:49", "remaining_time": "7:02:17"}
+{"current_steps": 152, "total_steps": 1235, "loss": 0.431, "lr": 3.9937344269006424e-05, "epoch": 0.6153846153846154, "percentage": 12.31, "elapsed_time": "0:59:12", "remaining_time": "7:01:50"}
+{"current_steps": 153, "total_steps": 1235, "loss": 0.4397, "lr": 3.993279149458988e-05, "epoch": 0.6194331983805668, "percentage": 12.39, "elapsed_time": "0:59:35", "remaining_time": "7:01:24"}
+{"current_steps": 154, "total_steps": 1235, "loss": 0.4511, "lr": 3.9928079338103695e-05, "epoch": 0.6234817813765182, "percentage": 12.47, "elapsed_time": "0:59:58", "remaining_time": "7:01:01"}
+{"current_steps": 155, "total_steps": 1235, "loss": 0.4389, "lr": 3.992320783722616e-05, "epoch": 0.6275303643724697, "percentage": 12.55, "elapsed_time": "1:00:20", "remaining_time": "7:00:24"}
+{"current_steps": 156, "total_steps": 1235, "loss": 0.4331, "lr": 3.991817703090965e-05, "epoch": 0.631578947368421, "percentage": 12.63, "elapsed_time": "1:00:41", "remaining_time": "6:59:45"}
+{"current_steps": 157, "total_steps": 1235, "loss": 0.4362, "lr": 3.991298695938038e-05, "epoch": 0.6356275303643725, "percentage": 12.71, "elapsed_time": "1:01:02", "remaining_time": "6:59:05"}
+{"current_steps": 158, "total_steps": 1235, "loss": 0.4279, "lr": 3.9907637664138e-05, "epoch": 0.6396761133603239, "percentage": 12.79, "elapsed_time": "1:01:24", "remaining_time": "6:58:36"}
+{"current_steps": 159, "total_steps": 1235, "loss": 0.4408, "lr": 3.990212918795534e-05, "epoch": 0.6437246963562753, "percentage": 12.87, "elapsed_time": "1:01:47", "remaining_time": "6:58:10"}
+{"current_steps": 160, "total_steps": 1235, "loss": 0.4431, "lr": 3.9896461574878036e-05, "epoch": 0.6477732793522267, "percentage": 12.96, "elapsed_time": "1:02:10", "remaining_time": "6:57:41"}
+{"current_steps": 161, "total_steps": 1235, "loss": 0.4341, "lr": 3.989063487022416e-05, "epoch": 0.6518218623481782, "percentage": 13.04, "elapsed_time": "1:02:36", "remaining_time": "6:57:35"}
+{"current_steps": 162, "total_steps": 1235, "loss": 0.4217, "lr": 3.9884649120583903e-05, "epoch": 0.6558704453441295, "percentage": 13.12, "elapsed_time": "1:02:56", "remaining_time": "6:56:51"}
+{"current_steps": 163, "total_steps": 1235, "loss": 0.4411, "lr": 3.987850437381915e-05, "epoch": 0.659919028340081, "percentage": 13.2, "elapsed_time": "1:03:17", "remaining_time": "6:56:17"}
+{"current_steps": 164, "total_steps": 1235, "loss": 0.4457, "lr": 3.987220067906313e-05, "epoch": 0.6639676113360324, "percentage": 13.28, "elapsed_time": "1:03:40", "remaining_time": "6:55:47"}
+{"current_steps": 165, "total_steps": 1235, "loss": 0.437, "lr": 3.986573808672002e-05, "epoch": 0.6680161943319838, "percentage": 13.36, "elapsed_time": "1:04:03", "remaining_time": "6:55:23"}
+{"current_steps": 166, "total_steps": 1235, "loss": 0.4355, "lr": 3.9859116648464534e-05, "epoch": 0.6720647773279352, "percentage": 13.44, "elapsed_time": "1:04:28", "remaining_time": "6:55:12"}
+{"current_steps": 167, "total_steps": 1235, "loss": 0.4357, "lr": 3.985233641724152e-05, "epoch": 0.6761133603238867, "percentage": 13.52, "elapsed_time": "1:04:51", "remaining_time": "6:54:49"}
+{"current_steps": 168, "total_steps": 1235, "loss": 0.4359, "lr": 3.984539744726554e-05, "epoch": 0.680161943319838, "percentage": 13.6, "elapsed_time": "1:05:15", "remaining_time": "6:54:28"}
+{"current_steps": 169, "total_steps": 1235, "loss": 0.4302, "lr": 3.983829979402038e-05, "epoch": 0.6842105263157895, "percentage": 13.68, "elapsed_time": "1:05:40", "remaining_time": "6:54:15"}
+{"current_steps": 170, "total_steps": 1235, "loss": 0.4541, "lr": 3.983104351425871e-05, "epoch": 0.6882591093117408, "percentage": 13.77, "elapsed_time": "1:06:04", "remaining_time": "6:53:54"}
+{"current_steps": 171, "total_steps": 1235, "loss": 0.4206, "lr": 3.982362866600154e-05, "epoch": 0.6923076923076923, "percentage": 13.85, "elapsed_time": "1:06:26", "remaining_time": "6:53:25"}
+{"current_steps": 172, "total_steps": 1235, "loss": 0.4493, "lr": 3.9816055308537806e-05, "epoch": 0.6963562753036437, "percentage": 13.93, "elapsed_time": "1:06:50", "remaining_time": "6:53:07"}
+{"current_steps": 173, "total_steps": 1235, "loss": 0.4486, "lr": 3.980832350242388e-05, "epoch": 0.7004048582995951, "percentage": 14.01, "elapsed_time": "1:07:12", "remaining_time": "6:52:32"}
+{"current_steps": 174, "total_steps": 1235, "loss": 0.4405, "lr": 3.980043330948306e-05, "epoch": 0.7044534412955465, "percentage": 14.09, "elapsed_time": "1:07:34", "remaining_time": "6:52:04"}
+{"current_steps": 175, "total_steps": 1235, "loss": 0.4417, "lr": 3.9792384792805124e-05, "epoch": 0.708502024291498, "percentage": 14.17, "elapsed_time": "1:07:57", "remaining_time": "6:51:40"}
+{"current_steps": 176, "total_steps": 1235, "loss": 0.4323, "lr": 3.978417801674579e-05, "epoch": 0.7125506072874493, "percentage": 14.25, "elapsed_time": "1:08:20", "remaining_time": "6:51:10"}
+{"current_steps": 177, "total_steps": 1235, "loss": 0.4276, "lr": 3.9775813046926244e-05, "epoch": 0.7165991902834008, "percentage": 14.33, "elapsed_time": "1:08:44", "remaining_time": "6:50:55"}
+{"current_steps": 178, "total_steps": 1235, "loss": 0.4219, "lr": 3.976728995023254e-05, "epoch": 0.7206477732793523, "percentage": 14.41, "elapsed_time": "1:09:07", "remaining_time": "6:50:30"}
+{"current_steps": 179, "total_steps": 1235, "loss": 0.4318, "lr": 3.975860879481514e-05, "epoch": 0.7246963562753036, "percentage": 14.49, "elapsed_time": "1:09:29", "remaining_time": "6:49:57"}
+{"current_steps": 180, "total_steps": 1235, "loss": 0.4258, "lr": 3.974976965008833e-05, "epoch": 0.728744939271255, "percentage": 14.57, "elapsed_time": "1:09:51", "remaining_time": "6:49:25"}
+{"current_steps": 181, "total_steps": 1235, "loss": 0.4367, "lr": 3.9740772586729674e-05, "epoch": 0.7327935222672065, "percentage": 14.66, "elapsed_time": "1:10:13", "remaining_time": "6:48:58"}
+{"current_steps": 182, "total_steps": 1235, "loss": 0.4299, "lr": 3.973161767667946e-05, "epoch": 0.7368421052631579, "percentage": 14.74, "elapsed_time": "1:10:35", "remaining_time": "6:48:22"}
+{"current_steps": 183, "total_steps": 1235, "loss": 0.4088, "lr": 3.972230499314009e-05, "epoch": 0.7408906882591093, "percentage": 14.82, "elapsed_time": "1:10:57", "remaining_time": "6:47:54"}
+{"current_steps": 184, "total_steps": 1235, "loss": 0.4264, "lr": 3.9712834610575545e-05, "epoch": 0.7449392712550608, "percentage": 14.9, "elapsed_time": "1:11:20", "remaining_time": "6:47:28"}
+{"current_steps": 185, "total_steps": 1235, "loss": 0.4214, "lr": 3.9703206604710746e-05, "epoch": 0.7489878542510121, "percentage": 14.98, "elapsed_time": "1:11:42", "remaining_time": "6:46:57"}
+{"current_steps": 186, "total_steps": 1235, "loss": 0.4314, "lr": 3.969342105253098e-05, "epoch": 0.7530364372469636, "percentage": 15.06, "elapsed_time": "1:12:05", "remaining_time": "6:46:34"}
+{"current_steps": 187, "total_steps": 1235, "loss": 0.4304, "lr": 3.9683478032281246e-05, "epoch": 0.757085020242915, "percentage": 15.14, "elapsed_time": "1:12:27", "remaining_time": "6:46:06"}
+{"current_steps": 188, "total_steps": 1235, "loss": 0.4269, "lr": 3.967337762346568e-05, "epoch": 0.7611336032388664, "percentage": 15.22, "elapsed_time": "1:12:50", "remaining_time": "6:45:37"}
+{"current_steps": 189, "total_steps": 1235, "loss": 0.4418, "lr": 3.9663119906846885e-05, "epoch": 0.7651821862348178, "percentage": 15.3, "elapsed_time": "1:13:15", "remaining_time": "6:45:26"}
+{"current_steps": 190, "total_steps": 1235, "loss": 0.4383, "lr": 3.965270496444528e-05, "epoch": 0.7692307692307693, "percentage": 15.38, "elapsed_time": "1:13:38", "remaining_time": "6:45:00"}
+{"current_steps": 191, "total_steps": 1235, "loss": 0.4302, "lr": 3.9642132879538465e-05, "epoch": 0.7732793522267206, "percentage": 15.47, "elapsed_time": "1:14:03", "remaining_time": "6:44:48"}
+{"current_steps": 192, "total_steps": 1235, "loss": 0.4295, "lr": 3.9631403736660566e-05, "epoch": 0.7773279352226721, "percentage": 15.55, "elapsed_time": "1:14:24", "remaining_time": "6:44:13"}
+{"current_steps": 193, "total_steps": 1235, "loss": 0.442, "lr": 3.962051762160151e-05, "epoch": 0.7813765182186235, "percentage": 15.63, "elapsed_time": "1:14:48", "remaining_time": "6:43:51"}
+{"current_steps": 194, "total_steps": 1235, "loss": 0.4468, "lr": 3.960947462140638e-05, "epoch": 0.7854251012145749, "percentage": 15.71, "elapsed_time": "1:15:10", "remaining_time": "6:43:21"}
+{"current_steps": 195, "total_steps": 1235, "loss": 0.4298, "lr": 3.959827482437472e-05, "epoch": 0.7894736842105263, "percentage": 15.79, "elapsed_time": "1:15:32", "remaining_time": "6:42:51"}
+{"current_steps": 196, "total_steps": 1235, "loss": 0.4326, "lr": 3.958691832005981e-05, "epoch": 0.7935222672064778, "percentage": 15.87, "elapsed_time": "1:15:50", "remaining_time": "6:42:01"}
+{"current_steps": 197, "total_steps": 1235, "loss": 0.4257, "lr": 3.9575405199267944e-05, "epoch": 0.7975708502024291, "percentage": 15.95, "elapsed_time": "1:16:13", "remaining_time": "6:41:35"}
+{"current_steps": 198, "total_steps": 1235, "loss": 0.4227, "lr": 3.956373555405774e-05, "epoch": 0.8016194331983806, "percentage": 16.03, "elapsed_time": "1:16:34", "remaining_time": "6:41:02"}
+{"current_steps": 199, "total_steps": 1235, "loss": 0.4231, "lr": 3.955190947773937e-05, "epoch": 0.805668016194332, "percentage": 16.11, "elapsed_time": "1:16:55", "remaining_time": "6:40:31"}
+{"current_steps": 200, "total_steps": 1235, "loss": 0.4271, "lr": 3.9539927064873824e-05, "epoch": 0.8097165991902834, "percentage": 16.19, "elapsed_time": "1:17:18", "remaining_time": "6:40:03"}
+{"current_steps": 201, "total_steps": 1235, "loss": 0.4176, "lr": 3.952778841127214e-05, "epoch": 0.8137651821862348, "percentage": 16.28, "elapsed_time": "1:17:39", "remaining_time": "6:39:31"}
+{"current_steps": 202, "total_steps": 1235, "loss": 0.427, "lr": 3.95154936139947e-05, "epoch": 0.8178137651821862, "percentage": 16.36, "elapsed_time": "1:18:02", "remaining_time": "6:39:03"}
+{"current_steps": 203, "total_steps": 1235, "loss": 0.4312, "lr": 3.950304277135034e-05, "epoch": 0.8218623481781376, "percentage": 16.44, "elapsed_time": "1:18:23", "remaining_time": "6:38:33"}
+{"current_steps": 204, "total_steps": 1235, "loss": 0.4184, "lr": 3.94904359828957e-05, "epoch": 0.8259109311740891, "percentage": 16.52, "elapsed_time": "1:18:46", "remaining_time": "6:38:08"}
+{"current_steps": 205, "total_steps": 1235, "loss": 0.4329, "lr": 3.94776733494343e-05, "epoch": 0.8299595141700404, "percentage": 16.6, "elapsed_time": "1:19:09", "remaining_time": "6:37:44"}
+{"current_steps": 206, "total_steps": 1235, "loss": 0.4269, "lr": 3.9464754973015826e-05, "epoch": 0.8340080971659919, "percentage": 16.68, "elapsed_time": "1:19:31", "remaining_time": "6:37:13"}
+{"current_steps": 207, "total_steps": 1235, "loss": 0.4215, "lr": 3.9451680956935275e-05, "epoch": 0.8380566801619433, "percentage": 16.76, "elapsed_time": "1:19:54", "remaining_time": "6:36:49"}
+{"current_steps": 208, "total_steps": 1235, "loss": 0.4128, "lr": 3.943845140573213e-05, "epoch": 0.8421052631578947, "percentage": 16.84, "elapsed_time": "1:20:16", "remaining_time": "6:36:21"}
+{"current_steps": 209, "total_steps": 1235, "loss": 0.4428, "lr": 3.942506642518952e-05, "epoch": 0.8461538461538461, "percentage": 16.92, "elapsed_time": "1:20:44", "remaining_time": "6:36:21"}
+{"current_steps": 210, "total_steps": 1235, "loss": 0.4267, "lr": 3.9411526122333396e-05, "epoch": 0.8502024291497976, "percentage": 17.0, "elapsed_time": "1:21:06", "remaining_time": "6:35:55"}
+{"current_steps": 211, "total_steps": 1235, "loss": 0.4336, "lr": 3.939783060543167e-05, "epoch": 0.854251012145749, "percentage": 17.09, "elapsed_time": "1:21:32", "remaining_time": "6:35:43"}
+{"current_steps": 212, "total_steps": 1235, "loss": 0.4207, "lr": 3.938397998399333e-05, "epoch": 0.8582995951417004, "percentage": 17.17, "elapsed_time": "1:21:55", "remaining_time": "6:35:21"}
+{"current_steps": 213, "total_steps": 1235, "loss": 0.4277, "lr": 3.936997436876756e-05, "epoch": 0.8623481781376519, "percentage": 17.25, "elapsed_time": "1:22:20", "remaining_time": "6:35:07"}
+{"current_steps": 214, "total_steps": 1235, "loss": 0.4211, "lr": 3.935581387174289e-05, "epoch": 0.8663967611336032, "percentage": 17.33, "elapsed_time": "1:22:45", "remaining_time": "6:34:49"}
+{"current_steps": 215, "total_steps": 1235, "loss": 0.4141, "lr": 3.9341498606146295e-05, "epoch": 0.8704453441295547, "percentage": 17.41, "elapsed_time": "1:23:08", "remaining_time": "6:34:24"}
+{"current_steps": 216, "total_steps": 1235, "loss": 0.4142, "lr": 3.932702868644224e-05, "epoch": 0.8744939271255061, "percentage": 17.49, "elapsed_time": "1:23:31", "remaining_time": "6:34:03"}
+{"current_steps": 217, "total_steps": 1235, "loss": 0.4147, "lr": 3.931240422833181e-05, "epoch": 0.8785425101214575, "percentage": 17.57, "elapsed_time": "1:23:56", "remaining_time": "6:33:46"}
+{"current_steps": 218, "total_steps": 1235, "loss": 0.4364, "lr": 3.9297625348751806e-05, "epoch": 0.8825910931174089, "percentage": 17.65, "elapsed_time": "1:24:20", "remaining_time": "6:33:27"}
+{"current_steps": 219, "total_steps": 1235, "loss": 0.4098, "lr": 3.9282692165873744e-05, "epoch": 0.8866396761133604, "percentage": 17.73, "elapsed_time": "1:24:41", "remaining_time": "6:32:52"}
+{"current_steps": 220, "total_steps": 1235, "loss": 0.4312, "lr": 3.9267604799102945e-05, "epoch": 0.8906882591093117, "percentage": 17.81, "elapsed_time": "1:25:04", "remaining_time": "6:32:28"}
+{"current_steps": 221, "total_steps": 1235, "loss": 0.4232, "lr": 3.9252363369077615e-05, "epoch": 0.8947368421052632, "percentage": 17.89, "elapsed_time": "1:25:27", "remaining_time": "6:32:05"}
+{"current_steps": 222, "total_steps": 1235, "loss": 0.4289, "lr": 3.9236967997667796e-05, "epoch": 0.8987854251012146, "percentage": 17.98, "elapsed_time": "1:25:51", "remaining_time": "6:31:46"}
+{"current_steps": 223, "total_steps": 1235, "loss": 0.428, "lr": 3.9221418807974496e-05, "epoch": 0.902834008097166, "percentage": 18.06, "elapsed_time": "1:26:13", "remaining_time": "6:31:19"}
+{"current_steps": 224, "total_steps": 1235, "loss": 0.4171, "lr": 3.92057159243286e-05, "epoch": 0.9068825910931174, "percentage": 18.14, "elapsed_time": "1:26:35", "remaining_time": "6:30:48"}
+{"current_steps": 225, "total_steps": 1235, "loss": 0.4187, "lr": 3.9189859472289956e-05, "epoch": 0.9109311740890689, "percentage": 18.22, "elapsed_time": "1:26:57", "remaining_time": "6:30:20"}
+{"current_steps": 226, "total_steps": 1235, "loss": 0.4149, "lr": 3.9173849578646324e-05, "epoch": 0.9149797570850202, "percentage": 18.3, "elapsed_time": "1:27:19", "remaining_time": "6:29:50"}
+{"current_steps": 227, "total_steps": 1235, "loss": 0.4322, "lr": 3.9157686371412395e-05, "epoch": 0.9190283400809717, "percentage": 18.38, "elapsed_time": "1:27:46", "remaining_time": "6:29:43"}
+{"current_steps": 228, "total_steps": 1235, "loss": 0.4186, "lr": 3.914136997982874e-05, "epoch": 0.9230769230769231, "percentage": 18.46, "elapsed_time": "1:28:08", "remaining_time": "6:29:16"}
+{"current_steps": 229, "total_steps": 1235, "loss": 0.4271, "lr": 3.912490053436079e-05, "epoch": 0.9271255060728745, "percentage": 18.54, "elapsed_time": "1:28:31", "remaining_time": "6:28:51"}
+{"current_steps": 230, "total_steps": 1235, "loss": 0.4155, "lr": 3.9108278166697805e-05, "epoch": 0.9311740890688259, "percentage": 18.62, "elapsed_time": "1:28:53", "remaining_time": "6:28:25"}
+{"current_steps": 231, "total_steps": 1235, "loss": 0.4302, "lr": 3.909150300975178e-05, "epoch": 0.9352226720647774, "percentage": 18.7, "elapsed_time": "1:29:15", "remaining_time": "6:27:55"}
+{"current_steps": 232, "total_steps": 1235, "loss": 0.4302, "lr": 3.907457519765642e-05, "epoch": 0.9392712550607287, "percentage": 18.79, "elapsed_time": "1:29:38", "remaining_time": "6:27:31"}
+{"current_steps": 233, "total_steps": 1235, "loss": 0.4168, "lr": 3.905749486576607e-05, "epoch": 0.9433198380566802, "percentage": 18.87, "elapsed_time": "1:29:59", "remaining_time": "6:26:59"}
+{"current_steps": 234, "total_steps": 1235, "loss": 0.4527, "lr": 3.90402621506546e-05, "epoch": 0.9473684210526315, "percentage": 18.95, "elapsed_time": "1:30:21", "remaining_time": "6:26:33"}
+{"current_steps": 235, "total_steps": 1235, "loss": 0.4148, "lr": 3.902287719011435e-05, "epoch": 0.951417004048583, "percentage": 19.03, "elapsed_time": "1:30:44", "remaining_time": "6:26:06"}
+{"current_steps": 236, "total_steps": 1235, "loss": 0.4327, "lr": 3.900534012315499e-05, "epoch": 0.9554655870445344, "percentage": 19.11, "elapsed_time": "1:31:05", "remaining_time": "6:25:34"}
+{"current_steps": 237, "total_steps": 1235, "loss": 0.4233, "lr": 3.8987651090002454e-05, "epoch": 0.9595141700404858, "percentage": 19.19, "elapsed_time": "1:31:35", "remaining_time": "6:25:40"}
+{"current_steps": 238, "total_steps": 1235, "loss": 0.4174, "lr": 3.896981023209777e-05, "epoch": 0.9635627530364372, "percentage": 19.27, "elapsed_time": "1:32:01", "remaining_time": "6:25:29"}
+{"current_steps": 239, "total_steps": 1235, "loss": 0.4233, "lr": 3.8951817692095966e-05, "epoch": 0.9676113360323887, "percentage": 19.35, "elapsed_time": "1:32:22", "remaining_time": "6:24:59"}
+{"current_steps": 240, "total_steps": 1235, "loss": 0.4327, "lr": 3.893367361386491e-05, "epoch": 0.97165991902834, "percentage": 19.43, "elapsed_time": "1:32:47", "remaining_time": "6:24:42"}
+{"current_steps": 241, "total_steps": 1235, "loss": 0.4362, "lr": 3.891537814248417e-05, "epoch": 0.9757085020242915, "percentage": 19.51, "elapsed_time": "1:33:10", "remaining_time": "6:24:19"}
+{"current_steps": 242, "total_steps": 1235, "loss": 0.4363, "lr": 3.889693142424384e-05, "epoch": 0.979757085020243, "percentage": 19.6, "elapsed_time": "1:33:33", "remaining_time": "6:23:53"}
+{"current_steps": 243, "total_steps": 1235, "loss": 0.4121, "lr": 3.8878333606643405e-05, "epoch": 0.9838056680161943, "percentage": 19.68, "elapsed_time": "1:33:58", "remaining_time": "6:23:37"}
+{"current_steps": 244, "total_steps": 1235, "loss": 0.4186, "lr": 3.885958483839049e-05, "epoch": 0.9878542510121457, "percentage": 19.76, "elapsed_time": "1:34:19", "remaining_time": "6:23:06"}
+{"current_steps": 245, "total_steps": 1235, "loss": 0.4359, "lr": 3.8840685269399786e-05, "epoch": 0.9919028340080972, "percentage": 19.84, "elapsed_time": "1:34:41", "remaining_time": "6:22:39"}
+{"current_steps": 246, "total_steps": 1235, "loss": 0.4177, "lr": 3.882163505079171e-05, "epoch": 0.9959514170040485, "percentage": 19.92, "elapsed_time": "1:35:03", "remaining_time": "6:22:11"}
+{"current_steps": 247, "total_steps": 1235, "loss": 0.4233, "lr": 3.880243433489132e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:35:26", "remaining_time": "6:21:47"}
+{"current_steps": 248, "total_steps": 1235, "loss": 0.3872, "lr": 3.878308327522702e-05, "epoch": 1.0040485829959513, "percentage": 20.08, "elapsed_time": "1:37:26", "remaining_time": "6:27:46"}
+{"current_steps": 249, "total_steps": 1235, "loss": 0.3878, "lr": 3.876358202652936e-05, "epoch": 1.008097165991903, "percentage": 20.16, "elapsed_time": "1:37:47", "remaining_time": "6:27:15"}
+{"current_steps": 250, "total_steps": 1235, "loss": 0.3805, "lr": 3.8743930744729835e-05, "epoch": 1.0121457489878543, "percentage": 20.24, "elapsed_time": "1:38:10", "remaining_time": "6:26:48"}
+{"current_steps": 251, "total_steps": 1235, "loss": 0.3864, "lr": 3.8724129586959535e-05, "epoch": 1.0161943319838056, "percentage": 20.32, "elapsed_time": "1:38:31", "remaining_time": "6:26:13"}
+{"current_steps": 252, "total_steps": 1235, "loss": 0.3741, "lr": 3.870417871154801e-05, "epoch": 1.0202429149797572, "percentage": 20.4, "elapsed_time": "1:38:54", "remaining_time": "6:25:48"}
+{"current_steps": 253, "total_steps": 1235, "loss": 0.3852, "lr": 3.868407827802192e-05, "epoch": 1.0242914979757085, "percentage": 20.49, "elapsed_time": "1:39:22", "remaining_time": "6:25:42"}
+{"current_steps": 254, "total_steps": 1235, "loss": 0.3877, "lr": 3.8663828447103804e-05, "epoch": 1.0283400809716599, "percentage": 20.57, "elapsed_time": "1:39:44", "remaining_time": "6:25:13"}
+{"current_steps": 255, "total_steps": 1235, "loss": 0.3677, "lr": 3.8643429380710765e-05, "epoch": 1.0323886639676114, "percentage": 20.65, "elapsed_time": "1:40:11", "remaining_time": "6:25:02"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9282730de29b5b55446a66648519aa7fafda2fa7f35f3429d872d7123ab073a0
+size 7224