Training in progress, step 400

.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": "secmlr/DS-Clean_QWQ-Clean_Qwen2.5-7B-Instruct_full_sft_1e-5",
+  "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": "4.48.3",
+  "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 sha256:88508681bd5f4d803d491952f4e500a5959476177a909455768e726cd73622c2
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad05aec04b3672c17472f0b9432acad4d1537b612579bc39e7ebafd5066c1338
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b181a40de854afcaf0153080894ee968d945ad32c98cff26e94e0eb5760aa2a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d850c17d0711ae0aa1c69e14c16d9b23a0e7460b0e2f00bd0dd673d49000c2b
+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": "<|im_end|>",
+    "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 +1,209 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,411 @@
+{"current_steps": 1, "total_steps": 987, "loss": 1.2715, "lr": 1.0101010101010103e-07, "epoch": 0.0030379746835443038, "percentage": 0.1, "elapsed_time": "0:00:15", "remaining_time": "4:17:30"}
+{"current_steps": 2, "total_steps": 987, "loss": 1.2093, "lr": 2.0202020202020205e-07, "epoch": 0.0060759493670886075, "percentage": 0.2, "elapsed_time": "0:00:27", "remaining_time": "3:43:30"}
+{"current_steps": 3, "total_steps": 987, "loss": 1.1612, "lr": 3.0303030303030305e-07, "epoch": 0.009113924050632912, "percentage": 0.3, "elapsed_time": "0:00:38", "remaining_time": "3:32:29"}
+{"current_steps": 4, "total_steps": 987, "loss": 1.2536, "lr": 4.040404040404041e-07, "epoch": 0.012151898734177215, "percentage": 0.41, "elapsed_time": "0:00:53", "remaining_time": "3:38:23"}
+{"current_steps": 5, "total_steps": 987, "loss": 1.2661, "lr": 5.05050505050505e-07, "epoch": 0.015189873417721518, "percentage": 0.51, "elapsed_time": "0:01:05", "remaining_time": "3:32:56"}
+{"current_steps": 6, "total_steps": 987, "loss": 1.2054, "lr": 6.060606060606061e-07, "epoch": 0.018227848101265823, "percentage": 0.61, "elapsed_time": "0:01:17", "remaining_time": "3:31:41"}
+{"current_steps": 7, "total_steps": 987, "loss": 1.2581, "lr": 7.070707070707071e-07, "epoch": 0.021265822784810127, "percentage": 0.71, "elapsed_time": "0:01:30", "remaining_time": "3:31:34"}
+{"current_steps": 8, "total_steps": 987, "loss": 1.2837, "lr": 8.080808080808082e-07, "epoch": 0.02430379746835443, "percentage": 0.81, "elapsed_time": "0:01:42", "remaining_time": "3:28:30"}
+{"current_steps": 9, "total_steps": 987, "loss": 1.1936, "lr": 9.090909090909091e-07, "epoch": 0.027341772151898733, "percentage": 0.91, "elapsed_time": "0:01:52", "remaining_time": "3:23:31"}
+{"current_steps": 10, "total_steps": 987, "loss": 1.2754, "lr": 1.01010101010101e-06, "epoch": 0.030379746835443037, "percentage": 1.01, "elapsed_time": "0:02:05", "remaining_time": "3:23:56"}
+{"current_steps": 11, "total_steps": 987, "loss": 1.2239, "lr": 1.111111111111111e-06, "epoch": 0.033417721518987344, "percentage": 1.11, "elapsed_time": "0:02:18", "remaining_time": "3:25:07"}
+{"current_steps": 12, "total_steps": 987, "loss": 1.2018, "lr": 1.2121212121212122e-06, "epoch": 0.03645569620253165, "percentage": 1.22, "elapsed_time": "0:02:29", "remaining_time": "3:22:52"}
+{"current_steps": 13, "total_steps": 987, "loss": 1.1589, "lr": 1.3131313131313134e-06, "epoch": 0.03949367088607595, "percentage": 1.32, "elapsed_time": "0:02:41", "remaining_time": "3:21:22"}
+{"current_steps": 14, "total_steps": 987, "loss": 1.161, "lr": 1.4141414141414143e-06, "epoch": 0.042531645569620254, "percentage": 1.42, "elapsed_time": "0:02:51", "remaining_time": "3:18:43"}
+{"current_steps": 15, "total_steps": 987, "loss": 1.0032, "lr": 1.5151515151515152e-06, "epoch": 0.04556962025316456, "percentage": 1.52, "elapsed_time": "0:03:03", "remaining_time": "3:18:29"}
+{"current_steps": 16, "total_steps": 987, "loss": 1.031, "lr": 1.6161616161616164e-06, "epoch": 0.04860759493670886, "percentage": 1.62, "elapsed_time": "0:03:13", "remaining_time": "3:16:09"}
+{"current_steps": 17, "total_steps": 987, "loss": 1.0449, "lr": 1.7171717171717173e-06, "epoch": 0.051645569620253164, "percentage": 1.72, "elapsed_time": "0:03:20", "remaining_time": "3:10:48"}
+{"current_steps": 18, "total_steps": 987, "loss": 1.0574, "lr": 1.8181818181818183e-06, "epoch": 0.05468354430379747, "percentage": 1.82, "elapsed_time": "0:03:30", "remaining_time": "3:08:34"}
+{"current_steps": 19, "total_steps": 987, "loss": 1.0204, "lr": 1.9191919191919192e-06, "epoch": 0.05772151898734177, "percentage": 1.93, "elapsed_time": "0:03:41", "remaining_time": "3:07:53"}
+{"current_steps": 20, "total_steps": 987, "loss": 0.9535, "lr": 2.02020202020202e-06, "epoch": 0.060759493670886074, "percentage": 2.03, "elapsed_time": "0:03:53", "remaining_time": "3:07:46"}
+{"current_steps": 21, "total_steps": 987, "loss": 0.9261, "lr": 2.1212121212121216e-06, "epoch": 0.06379746835443038, "percentage": 2.13, "elapsed_time": "0:04:05", "remaining_time": "3:08:19"}
+{"current_steps": 22, "total_steps": 987, "loss": 0.9615, "lr": 2.222222222222222e-06, "epoch": 0.06683544303797469, "percentage": 2.23, "elapsed_time": "0:04:15", "remaining_time": "3:06:33"}
+{"current_steps": 23, "total_steps": 987, "loss": 0.9009, "lr": 2.3232323232323234e-06, "epoch": 0.06987341772151899, "percentage": 2.33, "elapsed_time": "0:04:24", "remaining_time": "3:05:06"}
+{"current_steps": 24, "total_steps": 987, "loss": 1.0114, "lr": 2.4242424242424244e-06, "epoch": 0.0729113924050633, "percentage": 2.43, "elapsed_time": "0:04:32", "remaining_time": "3:02:22"}
+{"current_steps": 25, "total_steps": 987, "loss": 0.8631, "lr": 2.5252525252525258e-06, "epoch": 0.0759493670886076, "percentage": 2.53, "elapsed_time": "0:04:44", "remaining_time": "3:02:28"}
+{"current_steps": 26, "total_steps": 987, "loss": 0.8845, "lr": 2.6262626262626267e-06, "epoch": 0.0789873417721519, "percentage": 2.63, "elapsed_time": "0:04:59", "remaining_time": "3:04:45"}
+{"current_steps": 27, "total_steps": 987, "loss": 0.9578, "lr": 2.7272727272727272e-06, "epoch": 0.0820253164556962, "percentage": 2.74, "elapsed_time": "0:05:10", "remaining_time": "3:04:09"}
+{"current_steps": 28, "total_steps": 987, "loss": 0.9361, "lr": 2.8282828282828286e-06, "epoch": 0.08506329113924051, "percentage": 2.84, "elapsed_time": "0:05:21", "remaining_time": "3:03:23"}
+{"current_steps": 29, "total_steps": 987, "loss": 0.9165, "lr": 2.9292929292929295e-06, "epoch": 0.08810126582278481, "percentage": 2.94, "elapsed_time": "0:05:32", "remaining_time": "3:03:07"}
+{"current_steps": 30, "total_steps": 987, "loss": 0.8838, "lr": 3.0303030303030305e-06, "epoch": 0.09113924050632911, "percentage": 3.04, "elapsed_time": "0:05:40", "remaining_time": "3:00:46"}
+{"current_steps": 31, "total_steps": 987, "loss": 0.9255, "lr": 3.131313131313132e-06, "epoch": 0.09417721518987342, "percentage": 3.14, "elapsed_time": "0:05:48", "remaining_time": "2:58:54"}
+{"current_steps": 32, "total_steps": 987, "loss": 0.9086, "lr": 3.232323232323233e-06, "epoch": 0.09721518987341772, "percentage": 3.24, "elapsed_time": "0:05:55", "remaining_time": "2:56:44"}
+{"current_steps": 33, "total_steps": 987, "loss": 0.9455, "lr": 3.3333333333333333e-06, "epoch": 0.10025316455696202, "percentage": 3.34, "elapsed_time": "0:06:05", "remaining_time": "2:56:02"}
+{"current_steps": 34, "total_steps": 987, "loss": 0.883, "lr": 3.4343434343434347e-06, "epoch": 0.10329113924050633, "percentage": 3.44, "elapsed_time": "0:06:15", "remaining_time": "2:55:26"}
+{"current_steps": 35, "total_steps": 987, "loss": 0.9051, "lr": 3.5353535353535356e-06, "epoch": 0.10632911392405063, "percentage": 3.55, "elapsed_time": "0:06:25", "remaining_time": "2:54:42"}
+{"current_steps": 36, "total_steps": 987, "loss": 0.8701, "lr": 3.6363636363636366e-06, "epoch": 0.10936708860759493, "percentage": 3.65, "elapsed_time": "0:06:35", "remaining_time": "2:54:08"}
+{"current_steps": 37, "total_steps": 987, "loss": 0.8791, "lr": 3.737373737373738e-06, "epoch": 0.11240506329113924, "percentage": 3.75, "elapsed_time": "0:06:46", "remaining_time": "2:53:58"}
+{"current_steps": 38, "total_steps": 987, "loss": 0.897, "lr": 3.8383838383838385e-06, "epoch": 0.11544303797468354, "percentage": 3.85, "elapsed_time": "0:06:55", "remaining_time": "2:52:49"}
+{"current_steps": 39, "total_steps": 987, "loss": 0.8636, "lr": 3.93939393939394e-06, "epoch": 0.11848101265822784, "percentage": 3.95, "elapsed_time": "0:07:03", "remaining_time": "2:51:30"}
+{"current_steps": 40, "total_steps": 987, "loss": 0.8969, "lr": 4.04040404040404e-06, "epoch": 0.12151898734177215, "percentage": 4.05, "elapsed_time": "0:07:11", "remaining_time": "2:50:25"}
+{"current_steps": 41, "total_steps": 987, "loss": 0.7474, "lr": 4.141414141414142e-06, "epoch": 0.12455696202531645, "percentage": 4.15, "elapsed_time": "0:07:20", "remaining_time": "2:49:20"}
+{"current_steps": 42, "total_steps": 987, "loss": 0.8376, "lr": 4.242424242424243e-06, "epoch": 0.12759493670886077, "percentage": 4.26, "elapsed_time": "0:07:30", "remaining_time": "2:48:58"}
+{"current_steps": 43, "total_steps": 987, "loss": 0.8653, "lr": 4.343434343434344e-06, "epoch": 0.13063291139240507, "percentage": 4.36, "elapsed_time": "0:07:40", "remaining_time": "2:48:32"}
+{"current_steps": 44, "total_steps": 987, "loss": 0.7882, "lr": 4.444444444444444e-06, "epoch": 0.13367088607594937, "percentage": 4.46, "elapsed_time": "0:07:50", "remaining_time": "2:47:56"}
+{"current_steps": 45, "total_steps": 987, "loss": 0.8823, "lr": 4.5454545454545455e-06, "epoch": 0.13670886075949368, "percentage": 4.56, "elapsed_time": "0:08:02", "remaining_time": "2:48:11"}
+{"current_steps": 46, "total_steps": 987, "loss": 0.8675, "lr": 4.646464646464647e-06, "epoch": 0.13974683544303798, "percentage": 4.66, "elapsed_time": "0:08:11", "remaining_time": "2:47:29"}
+{"current_steps": 47, "total_steps": 987, "loss": 0.8358, "lr": 4.747474747474748e-06, "epoch": 0.14278481012658228, "percentage": 4.76, "elapsed_time": "0:08:19", "remaining_time": "2:46:27"}
+{"current_steps": 48, "total_steps": 987, "loss": 0.8077, "lr": 4.848484848484849e-06, "epoch": 0.1458227848101266, "percentage": 4.86, "elapsed_time": "0:08:27", "remaining_time": "2:45:19"}
+{"current_steps": 49, "total_steps": 987, "loss": 0.8297, "lr": 4.94949494949495e-06, "epoch": 0.1488607594936709, "percentage": 4.96, "elapsed_time": "0:08:39", "remaining_time": "2:45:44"}
+{"current_steps": 50, "total_steps": 987, "loss": 0.823, "lr": 5.0505050505050515e-06, "epoch": 0.1518987341772152, "percentage": 5.07, "elapsed_time": "0:08:49", "remaining_time": "2:45:18"}
+{"current_steps": 51, "total_steps": 987, "loss": 0.8012, "lr": 5.151515151515152e-06, "epoch": 0.1549367088607595, "percentage": 5.17, "elapsed_time": "0:08:58", "remaining_time": "2:44:50"}
+{"current_steps": 52, "total_steps": 987, "loss": 0.8383, "lr": 5.252525252525253e-06, "epoch": 0.1579746835443038, "percentage": 5.27, "elapsed_time": "0:09:09", "remaining_time": "2:44:32"}
+{"current_steps": 53, "total_steps": 987, "loss": 0.7941, "lr": 5.353535353535354e-06, "epoch": 0.1610126582278481, "percentage": 5.37, "elapsed_time": "0:09:22", "remaining_time": "2:45:06"}
+{"current_steps": 54, "total_steps": 987, "loss": 0.8171, "lr": 5.4545454545454545e-06, "epoch": 0.1640506329113924, "percentage": 5.47, "elapsed_time": "0:09:32", "remaining_time": "2:44:51"}
+{"current_steps": 55, "total_steps": 987, "loss": 0.8695, "lr": 5.555555555555557e-06, "epoch": 0.1670886075949367, "percentage": 5.57, "elapsed_time": "0:09:45", "remaining_time": "2:45:15"}
+{"current_steps": 56, "total_steps": 987, "loss": 0.7919, "lr": 5.656565656565657e-06, "epoch": 0.17012658227848101, "percentage": 5.67, "elapsed_time": "0:09:59", "remaining_time": "2:46:02"}
+{"current_steps": 57, "total_steps": 987, "loss": 0.8181, "lr": 5.7575757575757586e-06, "epoch": 0.17316455696202532, "percentage": 5.78, "elapsed_time": "0:10:09", "remaining_time": "2:45:37"}
+{"current_steps": 58, "total_steps": 987, "loss": 0.8249, "lr": 5.858585858585859e-06, "epoch": 0.17620253164556962, "percentage": 5.88, "elapsed_time": "0:10:22", "remaining_time": "2:46:15"}
+{"current_steps": 59, "total_steps": 987, "loss": 0.834, "lr": 5.95959595959596e-06, "epoch": 0.17924050632911392, "percentage": 5.98, "elapsed_time": "0:10:32", "remaining_time": "2:45:55"}
+{"current_steps": 60, "total_steps": 987, "loss": 0.8308, "lr": 6.060606060606061e-06, "epoch": 0.18227848101265823, "percentage": 6.08, "elapsed_time": "0:10:42", "remaining_time": "2:45:20"}
+{"current_steps": 61, "total_steps": 987, "loss": 0.773, "lr": 6.1616161616161615e-06, "epoch": 0.18531645569620253, "percentage": 6.18, "elapsed_time": "0:10:52", "remaining_time": "2:44:59"}
+{"current_steps": 62, "total_steps": 987, "loss": 0.8021, "lr": 6.262626262626264e-06, "epoch": 0.18835443037974683, "percentage": 6.28, "elapsed_time": "0:11:03", "remaining_time": "2:44:53"}
+{"current_steps": 63, "total_steps": 987, "loss": 0.8753, "lr": 6.363636363636364e-06, "epoch": 0.19139240506329114, "percentage": 6.38, "elapsed_time": "0:11:14", "remaining_time": "2:44:55"}
+{"current_steps": 64, "total_steps": 987, "loss": 0.8567, "lr": 6.464646464646466e-06, "epoch": 0.19443037974683544, "percentage": 6.48, "elapsed_time": "0:11:23", "remaining_time": "2:44:12"}
+{"current_steps": 65, "total_steps": 987, "loss": 0.7868, "lr": 6.565656565656566e-06, "epoch": 0.19746835443037974, "percentage": 6.59, "elapsed_time": "0:11:32", "remaining_time": "2:43:36"}
+{"current_steps": 66, "total_steps": 987, "loss": 0.8183, "lr": 6.666666666666667e-06, "epoch": 0.20050632911392405, "percentage": 6.69, "elapsed_time": "0:11:41", "remaining_time": "2:43:13"}
+{"current_steps": 67, "total_steps": 987, "loss": 0.8366, "lr": 6.767676767676769e-06, "epoch": 0.20354430379746835, "percentage": 6.79, "elapsed_time": "0:11:53", "remaining_time": "2:43:20"}
+{"current_steps": 68, "total_steps": 987, "loss": 0.7998, "lr": 6.868686868686869e-06, "epoch": 0.20658227848101265, "percentage": 6.89, "elapsed_time": "0:12:03", "remaining_time": "2:43:02"}
+{"current_steps": 69, "total_steps": 987, "loss": 0.8049, "lr": 6.969696969696971e-06, "epoch": 0.20962025316455696, "percentage": 6.99, "elapsed_time": "0:12:18", "remaining_time": "2:43:43"}
+{"current_steps": 70, "total_steps": 987, "loss": 0.7915, "lr": 7.070707070707071e-06, "epoch": 0.21265822784810126, "percentage": 7.09, "elapsed_time": "0:12:29", "remaining_time": "2:43:42"}
+{"current_steps": 71, "total_steps": 987, "loss": 0.8056, "lr": 7.171717171717172e-06, "epoch": 0.21569620253164556, "percentage": 7.19, "elapsed_time": "0:12:37", "remaining_time": "2:42:47"}
+{"current_steps": 72, "total_steps": 987, "loss": 0.7986, "lr": 7.272727272727273e-06, "epoch": 0.21873417721518987, "percentage": 7.29, "elapsed_time": "0:12:43", "remaining_time": "2:41:45"}
+{"current_steps": 73, "total_steps": 987, "loss": 0.8681, "lr": 7.373737373737374e-06, "epoch": 0.22177215189873417, "percentage": 7.4, "elapsed_time": "0:12:52", "remaining_time": "2:41:08"}
+{"current_steps": 74, "total_steps": 987, "loss": 0.7744, "lr": 7.474747474747476e-06, "epoch": 0.22481012658227847, "percentage": 7.5, "elapsed_time": "0:13:00", "remaining_time": "2:40:31"}
+{"current_steps": 75, "total_steps": 987, "loss": 0.7857, "lr": 7.5757575757575764e-06, "epoch": 0.22784810126582278, "percentage": 7.6, "elapsed_time": "0:13:14", "remaining_time": "2:41:06"}
+{"current_steps": 76, "total_steps": 987, "loss": 0.8095, "lr": 7.676767676767677e-06, "epoch": 0.23088607594936708, "percentage": 7.7, "elapsed_time": "0:13:25", "remaining_time": "2:40:59"}
+{"current_steps": 77, "total_steps": 987, "loss": 0.7742, "lr": 7.77777777777778e-06, "epoch": 0.23392405063291138, "percentage": 7.8, "elapsed_time": "0:13:35", "remaining_time": "2:40:39"}
+{"current_steps": 78, "total_steps": 987, "loss": 0.7522, "lr": 7.87878787878788e-06, "epoch": 0.2369620253164557, "percentage": 7.9, "elapsed_time": "0:13:46", "remaining_time": "2:40:30"}
+{"current_steps": 79, "total_steps": 987, "loss": 0.8157, "lr": 7.97979797979798e-06, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "0:13:54", "remaining_time": "2:39:45"}
+{"current_steps": 80, "total_steps": 987, "loss": 0.8117, "lr": 8.08080808080808e-06, "epoch": 0.2430379746835443, "percentage": 8.11, "elapsed_time": "0:14:09", "remaining_time": "2:40:34"}
+{"current_steps": 81, "total_steps": 987, "loss": 0.7671, "lr": 8.181818181818183e-06, "epoch": 0.2460759493670886, "percentage": 8.21, "elapsed_time": "0:14:18", "remaining_time": "2:40:02"}
+{"current_steps": 82, "total_steps": 987, "loss": 0.8397, "lr": 8.282828282828283e-06, "epoch": 0.2491139240506329, "percentage": 8.31, "elapsed_time": "0:14:29", "remaining_time": "2:39:52"}
+{"current_steps": 83, "total_steps": 987, "loss": 0.7627, "lr": 8.383838383838384e-06, "epoch": 0.2521518987341772, "percentage": 8.41, "elapsed_time": "0:14:38", "remaining_time": "2:39:31"}
+{"current_steps": 84, "total_steps": 987, "loss": 0.8123, "lr": 8.484848484848486e-06, "epoch": 0.25518987341772154, "percentage": 8.51, "elapsed_time": "0:14:48", "remaining_time": "2:39:13"}
+{"current_steps": 85, "total_steps": 987, "loss": 0.7831, "lr": 8.585858585858587e-06, "epoch": 0.2582278481012658, "percentage": 8.61, "elapsed_time": "0:14:58", "remaining_time": "2:38:51"}
+{"current_steps": 86, "total_steps": 987, "loss": 0.7792, "lr": 8.686868686868687e-06, "epoch": 0.26126582278481014, "percentage": 8.71, "elapsed_time": "0:15:08", "remaining_time": "2:38:33"}
+{"current_steps": 87, "total_steps": 987, "loss": 0.7481, "lr": 8.787878787878788e-06, "epoch": 0.2643037974683544, "percentage": 8.81, "elapsed_time": "0:15:14", "remaining_time": "2:37:45"}
+{"current_steps": 88, "total_steps": 987, "loss": 0.7692, "lr": 8.888888888888888e-06, "epoch": 0.26734177215189875, "percentage": 8.92, "elapsed_time": "0:15:22", "remaining_time": "2:37:00"}
+{"current_steps": 89, "total_steps": 987, "loss": 0.7777, "lr": 8.98989898989899e-06, "epoch": 0.270379746835443, "percentage": 9.02, "elapsed_time": "0:15:32", "remaining_time": "2:36:52"}
+{"current_steps": 90, "total_steps": 987, "loss": 0.7863, "lr": 9.090909090909091e-06, "epoch": 0.27341772151898736, "percentage": 9.12, "elapsed_time": "0:15:43", "remaining_time": "2:36:45"}
+{"current_steps": 91, "total_steps": 987, "loss": 0.7787, "lr": 9.191919191919193e-06, "epoch": 0.27645569620253163, "percentage": 9.22, "elapsed_time": "0:15:54", "remaining_time": "2:36:39"}
+{"current_steps": 92, "total_steps": 987, "loss": 0.7489, "lr": 9.292929292929294e-06, "epoch": 0.27949367088607596, "percentage": 9.32, "elapsed_time": "0:16:04", "remaining_time": "2:36:19"}
+{"current_steps": 93, "total_steps": 987, "loss": 0.7824, "lr": 9.393939393939396e-06, "epoch": 0.28253164556962024, "percentage": 9.42, "elapsed_time": "0:16:16", "remaining_time": "2:36:24"}
+{"current_steps": 94, "total_steps": 987, "loss": 0.7366, "lr": 9.494949494949497e-06, "epoch": 0.28556962025316457, "percentage": 9.52, "elapsed_time": "0:16:26", "remaining_time": "2:36:12"}
+{"current_steps": 95, "total_steps": 987, "loss": 0.7596, "lr": 9.595959595959597e-06, "epoch": 0.28860759493670884, "percentage": 9.63, "elapsed_time": "0:16:36", "remaining_time": "2:36:00"}
+{"current_steps": 96, "total_steps": 987, "loss": 0.7449, "lr": 9.696969696969698e-06, "epoch": 0.2916455696202532, "percentage": 9.73, "elapsed_time": "0:16:47", "remaining_time": "2:35:50"}
+{"current_steps": 97, "total_steps": 987, "loss": 0.7852, "lr": 9.797979797979798e-06, "epoch": 0.29468354430379745, "percentage": 9.83, "elapsed_time": "0:16:56", "remaining_time": "2:35:29"}
+{"current_steps": 98, "total_steps": 987, "loss": 0.798, "lr": 9.8989898989899e-06, "epoch": 0.2977215189873418, "percentage": 9.93, "elapsed_time": "0:17:07", "remaining_time": "2:35:25"}
+{"current_steps": 99, "total_steps": 987, "loss": 0.8095, "lr": 1e-05, "epoch": 0.30075949367088606, "percentage": 10.03, "elapsed_time": "0:17:17", "remaining_time": "2:35:08"}
+{"current_steps": 100, "total_steps": 987, "loss": 0.7465, "lr": 9.999968709437563e-06, "epoch": 0.3037974683544304, "percentage": 10.13, "elapsed_time": "0:17:27", "remaining_time": "2:34:52"}
+{"current_steps": 101, "total_steps": 987, "loss": 0.774, "lr": 9.999874838141888e-06, "epoch": 0.30683544303797466, "percentage": 10.23, "elapsed_time": "0:17:37", "remaining_time": "2:34:37"}
+{"current_steps": 102, "total_steps": 987, "loss": 0.7867, "lr": 9.999718387287891e-06, "epoch": 0.309873417721519, "percentage": 10.33, "elapsed_time": "0:17:50", "remaining_time": "2:34:44"}
+{"current_steps": 103, "total_steps": 987, "loss": 0.7392, "lr": 9.999499358833745e-06, "epoch": 0.31291139240506327, "percentage": 10.44, "elapsed_time": "0:18:00", "remaining_time": "2:34:30"}
+{"current_steps": 104, "total_steps": 987, "loss": 0.7829, "lr": 9.99921775552086e-06, "epoch": 0.3159493670886076, "percentage": 10.54, "elapsed_time": "0:18:10", "remaining_time": "2:34:18"}
+{"current_steps": 105, "total_steps": 987, "loss": 0.7264, "lr": 9.998873580873848e-06, "epoch": 0.3189873417721519, "percentage": 10.64, "elapsed_time": "0:18:19", "remaining_time": "2:33:58"}
+{"current_steps": 106, "total_steps": 987, "loss": 0.7611, "lr": 9.998466839200474e-06, "epoch": 0.3220253164556962, "percentage": 10.74, "elapsed_time": "0:18:28", "remaining_time": "2:33:31"}
+{"current_steps": 107, "total_steps": 987, "loss": 0.805, "lr": 9.99799753559161e-06, "epoch": 0.3250632911392405, "percentage": 10.84, "elapsed_time": "0:18:37", "remaining_time": "2:33:13"}
+{"current_steps": 108, "total_steps": 987, "loss": 0.7302, "lr": 9.997465675921163e-06, "epoch": 0.3281012658227848, "percentage": 10.94, "elapsed_time": "0:18:47", "remaining_time": "2:32:58"}
+{"current_steps": 109, "total_steps": 987, "loss": 0.7783, "lr": 9.99687126684601e-06, "epoch": 0.3311392405063291, "percentage": 11.04, "elapsed_time": "0:18:58", "remaining_time": "2:32:47"}
+{"current_steps": 110, "total_steps": 987, "loss": 0.7519, "lr": 9.99621431580591e-06, "epoch": 0.3341772151898734, "percentage": 11.14, "elapsed_time": "0:19:10", "remaining_time": "2:32:56"}
+{"current_steps": 111, "total_steps": 987, "loss": 0.7683, "lr": 9.99549483102341e-06, "epoch": 0.3372151898734177, "percentage": 11.25, "elapsed_time": "0:19:21", "remaining_time": "2:32:43"}
+{"current_steps": 112, "total_steps": 987, "loss": 0.7963, "lr": 9.994712821503737e-06, "epoch": 0.34025316455696203, "percentage": 11.35, "elapsed_time": "0:19:29", "remaining_time": "2:32:17"}
+{"current_steps": 113, "total_steps": 987, "loss": 0.7697, "lr": 9.993868297034709e-06, "epoch": 0.3432911392405063, "percentage": 11.45, "elapsed_time": "0:19:37", "remaining_time": "2:31:44"}
+{"current_steps": 114, "total_steps": 987, "loss": 0.7735, "lr": 9.992961268186575e-06, "epoch": 0.34632911392405064, "percentage": 11.55, "elapsed_time": "0:19:44", "remaining_time": "2:31:12"}
+{"current_steps": 115, "total_steps": 987, "loss": 0.7612, "lr": 9.991991746311916e-06, "epoch": 0.3493670886075949, "percentage": 11.65, "elapsed_time": "0:19:56", "remaining_time": "2:31:11"}
+{"current_steps": 116, "total_steps": 987, "loss": 0.7478, "lr": 9.990959743545487e-06, "epoch": 0.35240506329113924, "percentage": 11.75, "elapsed_time": "0:20:06", "remaining_time": "2:31:02"}
+{"current_steps": 117, "total_steps": 987, "loss": 0.739, "lr": 9.989865272804064e-06, "epoch": 0.3554430379746835, "percentage": 11.85, "elapsed_time": "0:20:17", "remaining_time": "2:30:50"}
+{"current_steps": 118, "total_steps": 987, "loss": 0.7105, "lr": 9.988708347786288e-06, "epoch": 0.35848101265822785, "percentage": 11.96, "elapsed_time": "0:20:30", "remaining_time": "2:30:59"}
+{"current_steps": 119, "total_steps": 987, "loss": 0.7009, "lr": 9.9874889829725e-06, "epoch": 0.3615189873417721, "percentage": 12.06, "elapsed_time": "0:20:39", "remaining_time": "2:30:44"}
+{"current_steps": 120, "total_steps": 987, "loss": 0.7433, "lr": 9.986207193624537e-06, "epoch": 0.36455696202531646, "percentage": 12.16, "elapsed_time": "0:20:51", "remaining_time": "2:30:42"}
+{"current_steps": 121, "total_steps": 987, "loss": 0.8137, "lr": 9.984862995785564e-06, "epoch": 0.3675949367088608, "percentage": 12.26, "elapsed_time": "0:21:03", "remaining_time": "2:30:45"}
+{"current_steps": 122, "total_steps": 987, "loss": 0.7226, "lr": 9.983456406279866e-06, "epoch": 0.37063291139240506, "percentage": 12.36, "elapsed_time": "0:21:13", "remaining_time": "2:30:30"}
+{"current_steps": 123, "total_steps": 987, "loss": 0.7661, "lr": 9.981987442712634e-06, "epoch": 0.3736708860759494, "percentage": 12.46, "elapsed_time": "0:21:26", "remaining_time": "2:30:35"}
+{"current_steps": 124, "total_steps": 987, "loss": 0.7335, "lr": 9.980456123469743e-06, "epoch": 0.37670886075949367, "percentage": 12.56, "elapsed_time": "0:21:40", "remaining_time": "2:30:54"}
+{"current_steps": 125, "total_steps": 987, "loss": 0.798, "lr": 9.978862467717532e-06, "epoch": 0.379746835443038, "percentage": 12.66, "elapsed_time": "0:21:50", "remaining_time": "2:30:34"}
+{"current_steps": 126, "total_steps": 987, "loss": 0.7716, "lr": 9.977206495402554e-06, "epoch": 0.3827848101265823, "percentage": 12.77, "elapsed_time": "0:22:00", "remaining_time": "2:30:22"}
+{"current_steps": 127, "total_steps": 987, "loss": 0.8056, "lr": 9.97548822725133e-06, "epoch": 0.3858227848101266, "percentage": 12.87, "elapsed_time": "0:22:12", "remaining_time": "2:30:22"}
+{"current_steps": 128, "total_steps": 987, "loss": 0.7598, "lr": 9.973707684770095e-06, "epoch": 0.3888607594936709, "percentage": 12.97, "elapsed_time": "0:22:23", "remaining_time": "2:30:14"}
+{"current_steps": 129, "total_steps": 987, "loss": 0.7618, "lr": 9.971864890244514e-06, "epoch": 0.3918987341772152, "percentage": 13.07, "elapsed_time": "0:22:30", "remaining_time": "2:29:43"}
+{"current_steps": 130, "total_steps": 987, "loss": 0.7586, "lr": 9.96995986673942e-06, "epoch": 0.3949367088607595, "percentage": 13.17, "elapsed_time": "0:22:39", "remaining_time": "2:29:23"}
+{"current_steps": 131, "total_steps": 987, "loss": 0.7411, "lr": 9.967992638098517e-06, "epoch": 0.3979746835443038, "percentage": 13.27, "elapsed_time": "0:22:50", "remaining_time": "2:29:16"}
+{"current_steps": 132, "total_steps": 987, "loss": 0.762, "lr": 9.965963228944077e-06, "epoch": 0.4010126582278481, "percentage": 13.37, "elapsed_time": "0:23:00", "remaining_time": "2:29:02"}
+{"current_steps": 133, "total_steps": 987, "loss": 0.7903, "lr": 9.963871664676647e-06, "epoch": 0.4040506329113924, "percentage": 13.48, "elapsed_time": "0:23:12", "remaining_time": "2:29:01"}
+{"current_steps": 134, "total_steps": 987, "loss": 0.7086, "lr": 9.961717971474714e-06, "epoch": 0.4070886075949367, "percentage": 13.58, "elapsed_time": "0:23:23", "remaining_time": "2:28:55"}
+{"current_steps": 135, "total_steps": 987, "loss": 0.7214, "lr": 9.959502176294384e-06, "epoch": 0.41012658227848103, "percentage": 13.68, "elapsed_time": "0:23:33", "remaining_time": "2:28:39"}
+{"current_steps": 136, "total_steps": 987, "loss": 0.7414, "lr": 9.957224306869053e-06, "epoch": 0.4131645569620253, "percentage": 13.78, "elapsed_time": "0:23:43", "remaining_time": "2:28:27"}
+{"current_steps": 137, "total_steps": 987, "loss": 0.7836, "lr": 9.954884391709043e-06, "epoch": 0.41620253164556964, "percentage": 13.88, "elapsed_time": "0:23:56", "remaining_time": "2:28:30"}
+{"current_steps": 138, "total_steps": 987, "loss": 0.7478, "lr": 9.95248246010126e-06, "epoch": 0.4192405063291139, "percentage": 13.98, "elapsed_time": "0:24:03", "remaining_time": "2:28:03"}
+{"current_steps": 139, "total_steps": 987, "loss": 0.7606, "lr": 9.950018542108818e-06, "epoch": 0.42227848101265825, "percentage": 14.08, "elapsed_time": "0:24:12", "remaining_time": "2:27:43"}
+{"current_steps": 140, "total_steps": 987, "loss": 0.725, "lr": 9.947492668570675e-06, "epoch": 0.4253164556962025, "percentage": 14.18, "elapsed_time": "0:24:23", "remaining_time": "2:27:31"}
+{"current_steps": 141, "total_steps": 987, "loss": 0.7558, "lr": 9.944904871101227e-06, "epoch": 0.42835443037974685, "percentage": 14.29, "elapsed_time": "0:24:32", "remaining_time": "2:27:15"}
+{"current_steps": 142, "total_steps": 987, "loss": 0.7417, "lr": 9.94225518208993e-06, "epoch": 0.43139240506329113, "percentage": 14.39, "elapsed_time": "0:24:42", "remaining_time": "2:27:04"}
+{"current_steps": 143, "total_steps": 987, "loss": 0.6828, "lr": 9.939543634700891e-06, "epoch": 0.43443037974683546, "percentage": 14.49, "elapsed_time": "0:24:50", "remaining_time": "2:26:37"}
+{"current_steps": 144, "total_steps": 987, "loss": 0.7945, "lr": 9.936770262872444e-06, "epoch": 0.43746835443037974, "percentage": 14.59, "elapsed_time": "0:25:03", "remaining_time": "2:26:41"}
+{"current_steps": 145, "total_steps": 987, "loss": 0.7532, "lr": 9.933935101316735e-06, "epoch": 0.44050632911392407, "percentage": 14.69, "elapsed_time": "0:25:12", "remaining_time": "2:26:21"}
+{"current_steps": 146, "total_steps": 987, "loss": 0.7403, "lr": 9.931038185519285e-06, "epoch": 0.44354430379746834, "percentage": 14.79, "elapsed_time": "0:25:22", "remaining_time": "2:26:07"}
+{"current_steps": 147, "total_steps": 987, "loss": 0.7232, "lr": 9.928079551738542e-06, "epoch": 0.4465822784810127, "percentage": 14.89, "elapsed_time": "0:25:32", "remaining_time": "2:25:54"}
+{"current_steps": 148, "total_steps": 987, "loss": 0.7788, "lr": 9.925059237005437e-06, "epoch": 0.44962025316455695, "percentage": 14.99, "elapsed_time": "0:25:42", "remaining_time": "2:25:42"}
+{"current_steps": 149, "total_steps": 987, "loss": 0.7531, "lr": 9.9219772791229e-06, "epoch": 0.4526582278481013, "percentage": 15.1, "elapsed_time": "0:25:52", "remaining_time": "2:25:31"}
+{"current_steps": 150, "total_steps": 987, "loss": 0.7865, "lr": 9.91883371666542e-06, "epoch": 0.45569620253164556, "percentage": 15.2, "elapsed_time": "0:26:04", "remaining_time": "2:25:32"}
+{"current_steps": 151, "total_steps": 987, "loss": 0.783, "lr": 9.915628588978522e-06, "epoch": 0.4587341772151899, "percentage": 15.3, "elapsed_time": "0:26:14", "remaining_time": "2:25:14"}
+{"current_steps": 152, "total_steps": 987, "loss": 0.7452, "lr": 9.912361936178312e-06, "epoch": 0.46177215189873416, "percentage": 15.4, "elapsed_time": "0:26:22", "remaining_time": "2:24:52"}
+{"current_steps": 153, "total_steps": 987, "loss": 0.74, "lr": 9.909033799150947e-06, "epoch": 0.4648101265822785, "percentage": 15.5, "elapsed_time": "0:26:30", "remaining_time": "2:24:29"}
+{"current_steps": 154, "total_steps": 987, "loss": 0.733, "lr": 9.90564421955214e-06, "epoch": 0.46784810126582277, "percentage": 15.6, "elapsed_time": "0:26:43", "remaining_time": "2:24:35"}
+{"current_steps": 155, "total_steps": 987, "loss": 0.7717, "lr": 9.902193239806634e-06, "epoch": 0.4708860759493671, "percentage": 15.7, "elapsed_time": "0:26:53", "remaining_time": "2:24:21"}
+{"current_steps": 156, "total_steps": 987, "loss": 0.7391, "lr": 9.898680903107668e-06, "epoch": 0.4739240506329114, "percentage": 15.81, "elapsed_time": "0:27:03", "remaining_time": "2:24:07"}
+{"current_steps": 157, "total_steps": 987, "loss": 0.827, "lr": 9.895107253416434e-06, "epoch": 0.4769620253164557, "percentage": 15.91, "elapsed_time": "0:27:16", "remaining_time": "2:24:12"}
+{"current_steps": 158, "total_steps": 987, "loss": 0.7261, "lr": 9.891472335461537e-06, "epoch": 0.48, "percentage": 16.01, "elapsed_time": "0:27:26", "remaining_time": "2:23:57"}
+{"current_steps": 159, "total_steps": 987, "loss": 0.7388, "lr": 9.887776194738433e-06, "epoch": 0.4830379746835443, "percentage": 16.11, "elapsed_time": "0:27:33", "remaining_time": "2:23:31"}
+{"current_steps": 160, "total_steps": 987, "loss": 0.7581, "lr": 9.884018877508844e-06, "epoch": 0.4860759493670886, "percentage": 16.21, "elapsed_time": "0:27:42", "remaining_time": "2:23:11"}
+{"current_steps": 161, "total_steps": 987, "loss": 0.7631, "lr": 9.8802004308002e-06, "epoch": 0.4891139240506329, "percentage": 16.31, "elapsed_time": "0:27:54", "remaining_time": "2:23:10"}
+{"current_steps": 162, "total_steps": 987, "loss": 0.727, "lr": 9.876320902405041e-06, "epoch": 0.4921518987341772, "percentage": 16.41, "elapsed_time": "0:28:03", "remaining_time": "2:22:53"}
+{"current_steps": 163, "total_steps": 987, "loss": 0.7425, "lr": 9.872380340880416e-06, "epoch": 0.4951898734177215, "percentage": 16.51, "elapsed_time": "0:28:15", "remaining_time": "2:22:48"}
+{"current_steps": 164, "total_steps": 987, "loss": 0.784, "lr": 9.86837879554728e-06, "epoch": 0.4982278481012658, "percentage": 16.62, "elapsed_time": "0:28:27", "remaining_time": "2:22:50"}
+{"current_steps": 165, "total_steps": 987, "loss": 0.7657, "lr": 9.864316316489873e-06, "epoch": 0.5012658227848101, "percentage": 16.72, "elapsed_time": "0:28:44", "remaining_time": "2:23:10"}
+{"current_steps": 166, "total_steps": 987, "loss": 0.7587, "lr": 9.860192954555099e-06, "epoch": 0.5043037974683544, "percentage": 16.82, "elapsed_time": "0:28:54", "remaining_time": "2:22:57"}
+{"current_steps": 167, "total_steps": 987, "loss": 0.7701, "lr": 9.856008761351882e-06, "epoch": 0.5073417721518987, "percentage": 16.92, "elapsed_time": "0:29:05", "remaining_time": "2:22:51"}
+{"current_steps": 168, "total_steps": 987, "loss": 0.7705, "lr": 9.851763789250526e-06, "epoch": 0.5103797468354431, "percentage": 17.02, "elapsed_time": "0:29:14", "remaining_time": "2:22:34"}
+{"current_steps": 169, "total_steps": 987, "loss": 0.7369, "lr": 9.847458091382057e-06, "epoch": 0.5134177215189873, "percentage": 17.12, "elapsed_time": "0:29:23", "remaining_time": "2:22:16"}
+{"current_steps": 170, "total_steps": 987, "loss": 0.7332, "lr": 9.843091721637559e-06, "epoch": 0.5164556962025316, "percentage": 17.22, "elapsed_time": "0:29:32", "remaining_time": "2:21:59"}
+{"current_steps": 171, "total_steps": 987, "loss": 0.736, "lr": 9.838664734667496e-06, "epoch": 0.5194936708860759, "percentage": 17.33, "elapsed_time": "0:29:45", "remaining_time": "2:21:59"}
+{"current_steps": 172, "total_steps": 987, "loss": 0.7453, "lr": 9.834177185881033e-06, "epoch": 0.5225316455696203, "percentage": 17.43, "elapsed_time": "0:29:58", "remaining_time": "2:22:02"}
+{"current_steps": 173, "total_steps": 987, "loss": 0.7801, "lr": 9.829629131445342e-06, "epoch": 0.5255696202531646, "percentage": 17.53, "elapsed_time": "0:30:09", "remaining_time": "2:21:53"}
+{"current_steps": 174, "total_steps": 987, "loss": 0.7916, "lr": 9.825020628284896e-06, "epoch": 0.5286075949367088, "percentage": 17.63, "elapsed_time": "0:30:22", "remaining_time": "2:21:53"}
+{"current_steps": 175, "total_steps": 987, "loss": 0.7729, "lr": 9.820351734080754e-06, "epoch": 0.5316455696202531, "percentage": 17.73, "elapsed_time": "0:30:31", "remaining_time": "2:21:38"}
+{"current_steps": 176, "total_steps": 987, "loss": 0.7414, "lr": 9.81562250726985e-06, "epoch": 0.5346835443037975, "percentage": 17.83, "elapsed_time": "0:30:40", "remaining_time": "2:21:22"}
+{"current_steps": 177, "total_steps": 987, "loss": 0.76, "lr": 9.810833007044247e-06, "epoch": 0.5377215189873418, "percentage": 17.93, "elapsed_time": "0:30:48", "remaining_time": "2:20:58"}
+{"current_steps": 178, "total_steps": 987, "loss": 0.7533, "lr": 9.805983293350413e-06, "epoch": 0.540759493670886, "percentage": 18.03, "elapsed_time": "0:31:00", "remaining_time": "2:20:55"}
+{"current_steps": 179, "total_steps": 987, "loss": 0.7512, "lr": 9.801073426888447e-06, "epoch": 0.5437974683544303, "percentage": 18.14, "elapsed_time": "0:31:12", "remaining_time": "2:20:54"}
+{"current_steps": 180, "total_steps": 987, "loss": 0.7161, "lr": 9.796103469111352e-06, "epoch": 0.5468354430379747, "percentage": 18.24, "elapsed_time": "0:31:23", "remaining_time": "2:20:44"}
+{"current_steps": 181, "total_steps": 987, "loss": 0.7283, "lr": 9.791073482224229e-06, "epoch": 0.549873417721519, "percentage": 18.34, "elapsed_time": "0:31:33", "remaining_time": "2:20:32"}
+{"current_steps": 182, "total_steps": 987, "loss": 0.7019, "lr": 9.785983529183533e-06, "epoch": 0.5529113924050633, "percentage": 18.44, "elapsed_time": "0:31:44", "remaining_time": "2:20:23"}
+{"current_steps": 183, "total_steps": 987, "loss": 0.7223, "lr": 9.780833673696255e-06, "epoch": 0.5559493670886076, "percentage": 18.54, "elapsed_time": "0:31:53", "remaining_time": "2:20:05"}
+{"current_steps": 184, "total_steps": 987, "loss": 0.7753, "lr": 9.775623980219149e-06, "epoch": 0.5589873417721519, "percentage": 18.64, "elapsed_time": "0:32:04", "remaining_time": "2:19:59"}
+{"current_steps": 185, "total_steps": 987, "loss": 0.7879, "lr": 9.77035451395791e-06, "epoch": 0.5620253164556962, "percentage": 18.74, "elapsed_time": "0:32:14", "remaining_time": "2:19:47"}
+{"current_steps": 186, "total_steps": 987, "loss": 0.7154, "lr": 9.76502534086636e-06, "epoch": 0.5650632911392405, "percentage": 18.84, "elapsed_time": "0:32:25", "remaining_time": "2:19:38"}
+{"current_steps": 187, "total_steps": 987, "loss": 0.743, "lr": 9.759636527645633e-06, "epoch": 0.5681012658227849, "percentage": 18.95, "elapsed_time": "0:32:35", "remaining_time": "2:19:26"}
+{"current_steps": 188, "total_steps": 987, "loss": 0.722, "lr": 9.754188141743326e-06, "epoch": 0.5711392405063291, "percentage": 19.05, "elapsed_time": "0:32:44", "remaining_time": "2:19:09"}
+{"current_steps": 189, "total_steps": 987, "loss": 0.769, "lr": 9.74868025135266e-06, "epoch": 0.5741772151898734, "percentage": 19.15, "elapsed_time": "0:32:59", "remaining_time": "2:19:16"}
+{"current_steps": 190, "total_steps": 987, "loss": 0.7497, "lr": 9.743112925411633e-06, "epoch": 0.5772151898734177, "percentage": 19.25, "elapsed_time": "0:33:09", "remaining_time": "2:19:04"}
+{"current_steps": 191, "total_steps": 987, "loss": 0.7256, "lr": 9.737486233602149e-06, "epoch": 0.5802531645569621, "percentage": 19.35, "elapsed_time": "0:33:19", "remaining_time": "2:18:54"}
+{"current_steps": 192, "total_steps": 987, "loss": 0.7028, "lr": 9.731800246349149e-06, "epoch": 0.5832911392405064, "percentage": 19.45, "elapsed_time": "0:33:29", "remaining_time": "2:18:41"}
+{"current_steps": 193, "total_steps": 987, "loss": 0.75, "lr": 9.726055034819726e-06, "epoch": 0.5863291139240506, "percentage": 19.55, "elapsed_time": "0:33:39", "remaining_time": "2:18:29"}
+{"current_steps": 194, "total_steps": 987, "loss": 0.7142, "lr": 9.720250670922242e-06, "epoch": 0.5893670886075949, "percentage": 19.66, "elapsed_time": "0:33:50", "remaining_time": "2:18:18"}
+{"current_steps": 195, "total_steps": 987, "loss": 0.7843, "lr": 9.714387227305422e-06, "epoch": 0.5924050632911393, "percentage": 19.76, "elapsed_time": "0:34:00", "remaining_time": "2:18:08"}
+{"current_steps": 196, "total_steps": 987, "loss": 0.7794, "lr": 9.708464777357444e-06, "epoch": 0.5954430379746836, "percentage": 19.86, "elapsed_time": "0:34:10", "remaining_time": "2:17:55"}
+{"current_steps": 197, "total_steps": 987, "loss": 0.6941, "lr": 9.702483395205023e-06, "epoch": 0.5984810126582278, "percentage": 19.96, "elapsed_time": "0:34:22", "remaining_time": "2:17:51"}
+{"current_steps": 198, "total_steps": 987, "loss": 0.7937, "lr": 9.696443155712488e-06, "epoch": 0.6015189873417721, "percentage": 20.06, "elapsed_time": "0:34:31", "remaining_time": "2:17:36"}
+{"current_steps": 199, "total_steps": 987, "loss": 0.7306, "lr": 9.69034413448083e-06, "epoch": 0.6045569620253165, "percentage": 20.16, "elapsed_time": "0:34:41", "remaining_time": "2:17:22"}
+{"current_steps": 200, "total_steps": 987, "loss": 0.7444, "lr": 9.684186407846774e-06, "epoch": 0.6075949367088608, "percentage": 20.26, "elapsed_time": "0:34:51", "remaining_time": "2:17:10"}
+{"current_steps": 201, "total_steps": 987, "loss": 0.7291, "lr": 9.677970052881811e-06, "epoch": 0.610632911392405, "percentage": 20.36, "elapsed_time": "0:35:02", "remaining_time": "2:17:00"}
+{"current_steps": 202, "total_steps": 987, "loss": 0.7472, "lr": 9.67169514739124e-06, "epoch": 0.6136708860759493, "percentage": 20.47, "elapsed_time": "0:35:12", "remaining_time": "2:16:48"}
+{"current_steps": 203, "total_steps": 987, "loss": 0.6764, "lr": 9.665361769913187e-06, "epoch": 0.6167088607594937, "percentage": 20.57, "elapsed_time": "0:35:22", "remaining_time": "2:16:35"}
+{"current_steps": 204, "total_steps": 987, "loss": 0.7589, "lr": 9.658969999717631e-06, "epoch": 0.619746835443038, "percentage": 20.67, "elapsed_time": "0:35:33", "remaining_time": "2:16:30"}
+{"current_steps": 205, "total_steps": 987, "loss": 0.7312, "lr": 9.652519916805406e-06, "epoch": 0.6227848101265823, "percentage": 20.77, "elapsed_time": "0:35:43", "remaining_time": "2:16:16"}
+{"current_steps": 206, "total_steps": 987, "loss": 0.716, "lr": 9.6460116019072e-06, "epoch": 0.6258227848101265, "percentage": 20.87, "elapsed_time": "0:35:54", "remaining_time": "2:16:09"}
+{"current_steps": 207, "total_steps": 987, "loss": 0.726, "lr": 9.639445136482549e-06, "epoch": 0.6288607594936709, "percentage": 20.97, "elapsed_time": "0:36:02", "remaining_time": "2:15:50"}
+{"current_steps": 208, "total_steps": 987, "loss": 0.7231, "lr": 9.632820602718806e-06, "epoch": 0.6318987341772152, "percentage": 21.07, "elapsed_time": "0:36:17", "remaining_time": "2:15:53"}
+{"current_steps": 209, "total_steps": 987, "loss": 0.7642, "lr": 9.62613808353013e-06, "epoch": 0.6349367088607595, "percentage": 21.18, "elapsed_time": "0:36:23", "remaining_time": "2:15:29"}
+{"current_steps": 210, "total_steps": 987, "loss": 0.7533, "lr": 9.619397662556434e-06, "epoch": 0.6379746835443038, "percentage": 21.28, "elapsed_time": "0:36:30", "remaining_time": "2:15:04"}
+{"current_steps": 211, "total_steps": 987, "loss": 0.7357, "lr": 9.612599424162344e-06, "epoch": 0.6410126582278481, "percentage": 21.38, "elapsed_time": "0:36:47", "remaining_time": "2:15:17"}
+{"current_steps": 212, "total_steps": 987, "loss": 0.7379, "lr": 9.60574345343614e-06, "epoch": 0.6440506329113924, "percentage": 21.48, "elapsed_time": "0:37:00", "remaining_time": "2:15:16"}
+{"current_steps": 213, "total_steps": 987, "loss": 0.7353, "lr": 9.598829836188694e-06, "epoch": 0.6470886075949367, "percentage": 21.58, "elapsed_time": "0:37:13", "remaining_time": "2:15:16"}
+{"current_steps": 214, "total_steps": 987, "loss": 0.7363, "lr": 9.591858658952396e-06, "epoch": 0.650126582278481, "percentage": 21.68, "elapsed_time": "0:37:25", "remaining_time": "2:15:10"}
+{"current_steps": 215, "total_steps": 987, "loss": 0.7145, "lr": 9.584830008980068e-06, "epoch": 0.6531645569620254, "percentage": 21.78, "elapsed_time": "0:37:35", "remaining_time": "2:14:57"}
+{"current_steps": 216, "total_steps": 987, "loss": 0.7563, "lr": 9.577743974243875e-06, "epoch": 0.6562025316455696, "percentage": 21.88, "elapsed_time": "0:37:43", "remaining_time": "2:14:39"}
+{"current_steps": 217, "total_steps": 987, "loss": 0.7046, "lr": 9.570600643434217e-06, "epoch": 0.6592405063291139, "percentage": 21.99, "elapsed_time": "0:37:50", "remaining_time": "2:14:17"}
+{"current_steps": 218, "total_steps": 987, "loss": 0.7466, "lr": 9.563400105958638e-06, "epoch": 0.6622784810126582, "percentage": 22.09, "elapsed_time": "0:37:58", "remaining_time": "2:13:55"}
+{"current_steps": 219, "total_steps": 987, "loss": 0.7257, "lr": 9.55614245194068e-06, "epoch": 0.6653164556962026, "percentage": 22.19, "elapsed_time": "0:38:08", "remaining_time": "2:13:44"}
+{"current_steps": 220, "total_steps": 987, "loss": 0.7217, "lr": 9.548827772218772e-06, "epoch": 0.6683544303797468, "percentage": 22.29, "elapsed_time": "0:38:18", "remaining_time": "2:13:34"}
+{"current_steps": 221, "total_steps": 987, "loss": 0.7111, "lr": 9.541456158345094e-06, "epoch": 0.6713924050632911, "percentage": 22.39, "elapsed_time": "0:38:30", "remaining_time": "2:13:29"}
+{"current_steps": 222, "total_steps": 987, "loss": 0.7823, "lr": 9.534027702584425e-06, "epoch": 0.6744303797468354, "percentage": 22.49, "elapsed_time": "0:38:48", "remaining_time": "2:13:42"}
+{"current_steps": 223, "total_steps": 987, "loss": 0.6862, "lr": 9.526542497912984e-06, "epoch": 0.6774683544303798, "percentage": 22.59, "elapsed_time": "0:38:56", "remaining_time": "2:13:24"}
+{"current_steps": 224, "total_steps": 987, "loss": 0.7292, "lr": 9.51900063801728e-06, "epoch": 0.6805063291139241, "percentage": 22.7, "elapsed_time": "0:39:04", "remaining_time": "2:13:05"}
+{"current_steps": 225, "total_steps": 987, "loss": 0.7449, "lr": 9.511402217292927e-06, "epoch": 0.6835443037974683, "percentage": 22.8, "elapsed_time": "0:39:11", "remaining_time": "2:12:43"}
+{"current_steps": 226, "total_steps": 987, "loss": 0.7606, "lr": 9.503747330843468e-06, "epoch": 0.6865822784810126, "percentage": 22.9, "elapsed_time": "0:39:18", "remaining_time": "2:12:22"}
+{"current_steps": 227, "total_steps": 987, "loss": 0.6848, "lr": 9.496036074479184e-06, "epoch": 0.689620253164557, "percentage": 23.0, "elapsed_time": "0:39:26", "remaining_time": "2:12:03"}
+{"current_steps": 228, "total_steps": 987, "loss": 0.7409, "lr": 9.488268544715897e-06, "epoch": 0.6926582278481013, "percentage": 23.1, "elapsed_time": "0:39:36", "remaining_time": "2:11:50"}
+{"current_steps": 229, "total_steps": 987, "loss": 0.7307, "lr": 9.480444838773753e-06, "epoch": 0.6956962025316455, "percentage": 23.2, "elapsed_time": "0:39:46", "remaining_time": "2:11:38"}
+{"current_steps": 230, "total_steps": 987, "loss": 0.7461, "lr": 9.472565054576017e-06, "epoch": 0.6987341772151898, "percentage": 23.3, "elapsed_time": "0:39:56", "remaining_time": "2:11:28"}
+{"current_steps": 231, "total_steps": 987, "loss": 0.7447, "lr": 9.464629290747844e-06, "epoch": 0.7017721518987342, "percentage": 23.4, "elapsed_time": "0:40:06", "remaining_time": "2:11:16"}
+{"current_steps": 232, "total_steps": 987, "loss": 0.7116, "lr": 9.456637646615035e-06, "epoch": 0.7048101265822785, "percentage": 23.51, "elapsed_time": "0:40:17", "remaining_time": "2:11:07"}
+{"current_steps": 233, "total_steps": 987, "loss": 0.7762, "lr": 9.448590222202808e-06, "epoch": 0.7078481012658228, "percentage": 23.61, "elapsed_time": "0:40:25", "remaining_time": "2:10:49"}
+{"current_steps": 234, "total_steps": 987, "loss": 0.7322, "lr": 9.440487118234536e-06, "epoch": 0.710886075949367, "percentage": 23.71, "elapsed_time": "0:40:32", "remaining_time": "2:10:27"}
+{"current_steps": 235, "total_steps": 987, "loss": 0.7402, "lr": 9.432328436130493e-06, "epoch": 0.7139240506329114, "percentage": 23.81, "elapsed_time": "0:40:41", "remaining_time": "2:10:12"}
+{"current_steps": 236, "total_steps": 987, "loss": 0.7325, "lr": 9.42411427800658e-06, "epoch": 0.7169620253164557, "percentage": 23.91, "elapsed_time": "0:40:49", "remaining_time": "2:09:55"}
+{"current_steps": 237, "total_steps": 987, "loss": 0.721, "lr": 9.415844746673047e-06, "epoch": 0.72, "percentage": 24.01, "elapsed_time": "0:40:59", "remaining_time": "2:09:41"}
+{"current_steps": 238, "total_steps": 987, "loss": 0.7038, "lr": 9.40751994563321e-06, "epoch": 0.7230379746835442, "percentage": 24.11, "elapsed_time": "0:41:08", "remaining_time": "2:09:29"}
+{"current_steps": 239, "total_steps": 987, "loss": 0.7623, "lr": 9.399139979082148e-06, "epoch": 0.7260759493670886, "percentage": 24.21, "elapsed_time": "0:41:18", "remaining_time": "2:09:17"}
+{"current_steps": 240, "total_steps": 987, "loss": 0.7277, "lr": 9.390704951905412e-06, "epoch": 0.7291139240506329, "percentage": 24.32, "elapsed_time": "0:41:28", "remaining_time": "2:09:04"}
+{"current_steps": 241, "total_steps": 987, "loss": 0.7079, "lr": 9.382214969677697e-06, "epoch": 0.7321518987341772, "percentage": 24.42, "elapsed_time": "0:41:37", "remaining_time": "2:08:51"}
+{"current_steps": 242, "total_steps": 987, "loss": 0.7749, "lr": 9.37367013866153e-06, "epoch": 0.7351898734177216, "percentage": 24.52, "elapsed_time": "0:41:47", "remaining_time": "2:08:39"}
+{"current_steps": 243, "total_steps": 987, "loss": 0.7542, "lr": 9.365070565805941e-06, "epoch": 0.7382278481012658, "percentage": 24.62, "elapsed_time": "0:41:54", "remaining_time": "2:08:19"}
+{"current_steps": 244, "total_steps": 987, "loss": 0.7461, "lr": 9.356416358745119e-06, "epoch": 0.7412658227848101, "percentage": 24.72, "elapsed_time": "0:42:02", "remaining_time": "2:08:00"}
+{"current_steps": 245, "total_steps": 987, "loss": 0.7564, "lr": 9.347707625797062e-06, "epoch": 0.7443037974683544, "percentage": 24.82, "elapsed_time": "0:42:12", "remaining_time": "2:07:49"}
+{"current_steps": 246, "total_steps": 987, "loss": 0.7221, "lr": 9.338944475962236e-06, "epoch": 0.7473417721518988, "percentage": 24.92, "elapsed_time": "0:42:23", "remaining_time": "2:07:40"}
+{"current_steps": 247, "total_steps": 987, "loss": 0.7577, "lr": 9.330127018922195e-06, "epoch": 0.7503797468354431, "percentage": 25.03, "elapsed_time": "0:42:36", "remaining_time": "2:07:38"}
+{"current_steps": 248, "total_steps": 987, "loss": 0.7229, "lr": 9.32125536503821e-06, "epoch": 0.7534177215189873, "percentage": 25.13, "elapsed_time": "0:42:45", "remaining_time": "2:07:24"}
+{"current_steps": 249, "total_steps": 987, "loss": 0.7112, "lr": 9.312329625349903e-06, "epoch": 0.7564556962025316, "percentage": 25.23, "elapsed_time": "0:42:54", "remaining_time": "2:07:10"}
+{"current_steps": 250, "total_steps": 987, "loss": 0.7322, "lr": 9.303349911573838e-06, "epoch": 0.759493670886076, "percentage": 25.33, "elapsed_time": "0:43:06", "remaining_time": "2:07:06"}
+{"current_steps": 251, "total_steps": 987, "loss": 0.7206, "lr": 9.294316336102132e-06, "epoch": 0.7625316455696203, "percentage": 25.43, "elapsed_time": "0:43:16", "remaining_time": "2:06:52"}
+{"current_steps": 252, "total_steps": 987, "loss": 0.7861, "lr": 9.285229012001047e-06, "epoch": 0.7655696202531646, "percentage": 25.53, "elapsed_time": "0:43:26", "remaining_time": "2:06:42"}
+{"current_steps": 253, "total_steps": 987, "loss": 0.715, "lr": 9.276088053009578e-06, "epoch": 0.7686075949367088, "percentage": 25.63, "elapsed_time": "0:43:34", "remaining_time": "2:06:24"}
+{"current_steps": 254, "total_steps": 987, "loss": 0.7131, "lr": 9.266893573538023e-06, "epoch": 0.7716455696202532, "percentage": 25.73, "elapsed_time": "0:43:40", "remaining_time": "2:06:03"}
+{"current_steps": 255, "total_steps": 987, "loss": 0.7029, "lr": 9.257645688666557e-06, "epoch": 0.7746835443037975, "percentage": 25.84, "elapsed_time": "0:43:47", "remaining_time": "2:05:42"}
+{"current_steps": 256, "total_steps": 987, "loss": 0.7794, "lr": 9.248344514143786e-06, "epoch": 0.7777215189873418, "percentage": 25.94, "elapsed_time": "0:43:55", "remaining_time": "2:05:26"}
+{"current_steps": 257, "total_steps": 987, "loss": 0.6886, "lr": 9.238990166385304e-06, "epoch": 0.780759493670886, "percentage": 26.04, "elapsed_time": "0:44:05", "remaining_time": "2:05:14"}
+{"current_steps": 258, "total_steps": 987, "loss": 0.6954, "lr": 9.229582762472232e-06, "epoch": 0.7837974683544304, "percentage": 26.14, "elapsed_time": "0:44:17", "remaining_time": "2:05:09"}
+{"current_steps": 259, "total_steps": 987, "loss": 0.7534, "lr": 9.220122420149753e-06, "epoch": 0.7868354430379747, "percentage": 26.24, "elapsed_time": "0:44:27", "remaining_time": "2:04:57"}
+{"current_steps": 260, "total_steps": 987, "loss": 0.6782, "lr": 9.21060925782564e-06, "epoch": 0.789873417721519, "percentage": 26.34, "elapsed_time": "0:44:36", "remaining_time": "2:04:45"}
+{"current_steps": 261, "total_steps": 987, "loss": 0.7083, "lr": 9.201043394568773e-06, "epoch": 0.7929113924050633, "percentage": 26.44, "elapsed_time": "0:44:49", "remaining_time": "2:04:42"}
+{"current_steps": 262, "total_steps": 987, "loss": 0.753, "lr": 9.191424950107648e-06, "epoch": 0.7959493670886076, "percentage": 26.55, "elapsed_time": "0:44:57", "remaining_time": "2:04:24"}
+{"current_steps": 263, "total_steps": 987, "loss": 0.7087, "lr": 9.181754044828882e-06, "epoch": 0.7989873417721519, "percentage": 26.65, "elapsed_time": "0:45:04", "remaining_time": "2:04:05"}
+{"current_steps": 264, "total_steps": 987, "loss": 0.7521, "lr": 9.172030799775698e-06, "epoch": 0.8020253164556962, "percentage": 26.75, "elapsed_time": "0:45:12", "remaining_time": "2:03:49"}
+{"current_steps": 265, "total_steps": 987, "loss": 0.6864, "lr": 9.162255336646422e-06, "epoch": 0.8050632911392405, "percentage": 26.85, "elapsed_time": "0:45:19", "remaining_time": "2:03:29"}
+{"current_steps": 266, "total_steps": 987, "loss": 0.7083, "lr": 9.152427777792947e-06, "epoch": 0.8081012658227849, "percentage": 26.95, "elapsed_time": "0:45:28", "remaining_time": "2:03:17"}
+{"current_steps": 267, "total_steps": 987, "loss": 0.7191, "lr": 9.142548246219212e-06, "epoch": 0.8111392405063291, "percentage": 27.05, "elapsed_time": "0:45:38", "remaining_time": "2:03:04"}
+{"current_steps": 268, "total_steps": 987, "loss": 0.7276, "lr": 9.132616865579655e-06, "epoch": 0.8141772151898734, "percentage": 27.15, "elapsed_time": "0:45:49", "remaining_time": "2:02:57"}
+{"current_steps": 269, "total_steps": 987, "loss": 0.7517, "lr": 9.122633760177674e-06, "epoch": 0.8172151898734177, "percentage": 27.25, "elapsed_time": "0:46:01", "remaining_time": "2:02:51"}
+{"current_steps": 270, "total_steps": 987, "loss": 0.756, "lr": 9.112599054964058e-06, "epoch": 0.8202531645569621, "percentage": 27.36, "elapsed_time": "0:46:11", "remaining_time": "2:02:39"}
+{"current_steps": 271, "total_steps": 987, "loss": 0.6865, "lr": 9.102512875535439e-06, "epoch": 0.8232911392405063, "percentage": 27.46, "elapsed_time": "0:46:19", "remaining_time": "2:02:23"}
+{"current_steps": 272, "total_steps": 987, "loss": 0.6957, "lr": 9.092375348132704e-06, "epoch": 0.8263291139240506, "percentage": 27.56, "elapsed_time": "0:46:26", "remaining_time": "2:02:05"}
+{"current_steps": 273, "total_steps": 987, "loss": 0.6617, "lr": 9.082186599639429e-06, "epoch": 0.8293670886075949, "percentage": 27.66, "elapsed_time": "0:46:34", "remaining_time": "2:01:49"}
+{"current_steps": 274, "total_steps": 987, "loss": 0.7624, "lr": 9.071946757580282e-06, "epoch": 0.8324050632911393, "percentage": 27.76, "elapsed_time": "0:46:47", "remaining_time": "2:01:45"}
+{"current_steps": 275, "total_steps": 987, "loss": 0.7211, "lr": 9.06165595011943e-06, "epoch": 0.8354430379746836, "percentage": 27.86, "elapsed_time": "0:47:01", "remaining_time": "2:01:46"}
+{"current_steps": 276, "total_steps": 987, "loss": 0.7503, "lr": 9.051314306058934e-06, "epoch": 0.8384810126582278, "percentage": 27.96, "elapsed_time": "0:47:11", "remaining_time": "2:01:34"}
+{"current_steps": 277, "total_steps": 987, "loss": 0.759, "lr": 9.040921954837139e-06, "epoch": 0.8415189873417721, "percentage": 28.06, "elapsed_time": "0:47:20", "remaining_time": "2:01:21"}
+{"current_steps": 278, "total_steps": 987, "loss": 0.7452, "lr": 9.030479026527048e-06, "epoch": 0.8445569620253165, "percentage": 28.17, "elapsed_time": "0:47:30", "remaining_time": "2:01:10"}
+{"current_steps": 279, "total_steps": 987, "loss": 0.7302, "lr": 9.019985651834703e-06, "epoch": 0.8475949367088608, "percentage": 28.27, "elapsed_time": "0:47:40", "remaining_time": "2:00:59"}
+{"current_steps": 280, "total_steps": 987, "loss": 0.727, "lr": 9.009441962097543e-06, "epoch": 0.850632911392405, "percentage": 28.37, "elapsed_time": "0:47:48", "remaining_time": "2:00:42"}
+{"current_steps": 281, "total_steps": 987, "loss": 0.7591, "lr": 8.99884808928276e-06, "epoch": 0.8536708860759493, "percentage": 28.47, "elapsed_time": "0:47:56", "remaining_time": "2:00:26"}
+{"current_steps": 282, "total_steps": 987, "loss": 0.7439, "lr": 8.98820416598565e-06, "epoch": 0.8567088607594937, "percentage": 28.57, "elapsed_time": "0:48:06", "remaining_time": "2:00:17"}
+{"current_steps": 283, "total_steps": 987, "loss": 0.7565, "lr": 8.97751032542795e-06, "epoch": 0.859746835443038, "percentage": 28.67, "elapsed_time": "0:48:14", "remaining_time": "2:00:01"}
+{"current_steps": 284, "total_steps": 987, "loss": 0.7034, "lr": 8.966766701456177e-06, "epoch": 0.8627848101265823, "percentage": 28.77, "elapsed_time": "0:48:25", "remaining_time": "1:59:51"}
+{"current_steps": 285, "total_steps": 987, "loss": 0.724, "lr": 8.955973428539943e-06, "epoch": 0.8658227848101265, "percentage": 28.88, "elapsed_time": "0:48:35", "remaining_time": "1:59:42"}
+{"current_steps": 286, "total_steps": 987, "loss": 0.7179, "lr": 8.945130641770281e-06, "epoch": 0.8688607594936709, "percentage": 28.98, "elapsed_time": "0:48:45", "remaining_time": "1:59:30"}
+{"current_steps": 287, "total_steps": 987, "loss": 0.731, "lr": 8.93423847685795e-06, "epoch": 0.8718987341772152, "percentage": 29.08, "elapsed_time": "0:49:01", "remaining_time": "1:59:33"}
+{"current_steps": 288, "total_steps": 987, "loss": 0.7071, "lr": 8.923297070131738e-06, "epoch": 0.8749367088607595, "percentage": 29.18, "elapsed_time": "0:49:12", "remaining_time": "1:59:26"}
+{"current_steps": 289, "total_steps": 987, "loss": 0.7153, "lr": 8.91230655853675e-06, "epoch": 0.8779746835443037, "percentage": 29.28, "elapsed_time": "0:49:20", "remaining_time": "1:59:09"}
+{"current_steps": 290, "total_steps": 987, "loss": 0.74, "lr": 8.901267079632703e-06, "epoch": 0.8810126582278481, "percentage": 29.38, "elapsed_time": "0:49:27", "remaining_time": "1:58:51"}
+{"current_steps": 291, "total_steps": 987, "loss": 0.7491, "lr": 8.890178771592198e-06, "epoch": 0.8840506329113924, "percentage": 29.48, "elapsed_time": "0:49:34", "remaining_time": "1:58:34"}
+{"current_steps": 292, "total_steps": 987, "loss": 0.7055, "lr": 8.879041773198996e-06, "epoch": 0.8870886075949367, "percentage": 29.58, "elapsed_time": "0:49:42", "remaining_time": "1:58:19"}
+{"current_steps": 293, "total_steps": 987, "loss": 0.687, "lr": 8.86785622384627e-06, "epoch": 0.890126582278481, "percentage": 29.69, "elapsed_time": "0:49:53", "remaining_time": "1:58:10"}
+{"current_steps": 294, "total_steps": 987, "loss": 0.745, "lr": 8.856622263534875e-06, "epoch": 0.8931645569620253, "percentage": 29.79, "elapsed_time": "0:50:03", "remaining_time": "1:57:58"}
+{"current_steps": 295, "total_steps": 987, "loss": 0.7713, "lr": 8.845340032871584e-06, "epoch": 0.8962025316455696, "percentage": 29.89, "elapsed_time": "0:50:12", "remaining_time": "1:57:47"}
+{"current_steps": 296, "total_steps": 987, "loss": 0.7472, "lr": 8.834009673067337e-06, "epoch": 0.8992405063291139, "percentage": 29.99, "elapsed_time": "0:50:22", "remaining_time": "1:57:35"}
+{"current_steps": 297, "total_steps": 987, "loss": 0.7249, "lr": 8.822631325935463e-06, "epoch": 0.9022784810126582, "percentage": 30.09, "elapsed_time": "0:50:32", "remaining_time": "1:57:25"}
+{"current_steps": 298, "total_steps": 987, "loss": 0.7491, "lr": 8.811205133889917e-06, "epoch": 0.9053164556962026, "percentage": 30.19, "elapsed_time": "0:50:46", "remaining_time": "1:57:23"}
+{"current_steps": 299, "total_steps": 987, "loss": 0.7172, "lr": 8.799731239943488e-06, "epoch": 0.9083544303797468, "percentage": 30.29, "elapsed_time": "0:50:56", "remaining_time": "1:57:13"}
+{"current_steps": 300, "total_steps": 987, "loss": 0.7573, "lr": 8.788209787706014e-06, "epoch": 0.9113924050632911, "percentage": 30.4, "elapsed_time": "0:51:03", "remaining_time": "1:56:54"}
+{"current_steps": 301, "total_steps": 987, "loss": 0.6943, "lr": 8.776640921382585e-06, "epoch": 0.9144303797468355, "percentage": 30.5, "elapsed_time": "0:51:12", "remaining_time": "1:56:43"}
+{"current_steps": 302, "total_steps": 987, "loss": 0.6878, "lr": 8.765024785771732e-06, "epoch": 0.9174683544303798, "percentage": 30.6, "elapsed_time": "0:51:22", "remaining_time": "1:56:32"}
+{"current_steps": 303, "total_steps": 987, "loss": 0.7261, "lr": 8.753361526263622e-06, "epoch": 0.920506329113924, "percentage": 30.7, "elapsed_time": "0:51:35", "remaining_time": "1:56:27"}
+{"current_steps": 304, "total_steps": 987, "loss": 0.7324, "lr": 8.741651288838237e-06, "epoch": 0.9235443037974683, "percentage": 30.8, "elapsed_time": "0:51:44", "remaining_time": "1:56:15"}
+{"current_steps": 305, "total_steps": 987, "loss": 0.6935, "lr": 8.729894220063542e-06, "epoch": 0.9265822784810127, "percentage": 30.9, "elapsed_time": "0:51:56", "remaining_time": "1:56:07"}
+{"current_steps": 306, "total_steps": 987, "loss": 0.7483, "lr": 8.718090467093654e-06, "epoch": 0.929620253164557, "percentage": 31.0, "elapsed_time": "0:52:05", "remaining_time": "1:55:56"}
+{"current_steps": 307, "total_steps": 987, "loss": 0.7327, "lr": 8.706240177667003e-06, "epoch": 0.9326582278481013, "percentage": 31.1, "elapsed_time": "0:52:13", "remaining_time": "1:55:40"}
+{"current_steps": 308, "total_steps": 987, "loss": 0.7143, "lr": 8.694343500104474e-06, "epoch": 0.9356962025316455, "percentage": 31.21, "elapsed_time": "0:52:21", "remaining_time": "1:55:25"}
+{"current_steps": 309, "total_steps": 987, "loss": 0.7508, "lr": 8.682400583307562e-06, "epoch": 0.9387341772151899, "percentage": 31.31, "elapsed_time": "0:52:29", "remaining_time": "1:55:10"}
+{"current_steps": 310, "total_steps": 987, "loss": 0.6685, "lr": 8.670411576756502e-06, "epoch": 0.9417721518987342, "percentage": 31.41, "elapsed_time": "0:52:36", "remaining_time": "1:54:54"}
+{"current_steps": 311, "total_steps": 987, "loss": 0.7384, "lr": 8.658376630508391e-06, "epoch": 0.9448101265822785, "percentage": 31.51, "elapsed_time": "0:52:45", "remaining_time": "1:54:41"}
+{"current_steps": 312, "total_steps": 987, "loss": 0.6916, "lr": 8.646295895195334e-06, "epoch": 0.9478481012658228, "percentage": 31.61, "elapsed_time": "0:52:56", "remaining_time": "1:54:32"}
+{"current_steps": 313, "total_steps": 987, "loss": 0.7618, "lr": 8.634169522022522e-06, "epoch": 0.9508860759493671, "percentage": 31.71, "elapsed_time": "0:53:05", "remaining_time": "1:54:20"}
+{"current_steps": 314, "total_steps": 987, "loss": 0.685, "lr": 8.621997662766378e-06, "epoch": 0.9539240506329114, "percentage": 31.81, "elapsed_time": "0:53:15", "remaining_time": "1:54:08"}
+{"current_steps": 315, "total_steps": 987, "loss": 0.7715, "lr": 8.609780469772623e-06, "epoch": 0.9569620253164557, "percentage": 31.91, "elapsed_time": "0:53:25", "remaining_time": "1:53:58"}
+{"current_steps": 316, "total_steps": 987, "loss": 0.7225, "lr": 8.597518095954399e-06, "epoch": 0.96, "percentage": 32.02, "elapsed_time": "0:53:35", "remaining_time": "1:53:47"}
+{"current_steps": 317, "total_steps": 987, "loss": 0.6919, "lr": 8.585210694790333e-06, "epoch": 0.9630379746835444, "percentage": 32.12, "elapsed_time": "0:53:44", "remaining_time": "1:53:34"}
+{"current_steps": 318, "total_steps": 987, "loss": 0.749, "lr": 8.572858420322626e-06, "epoch": 0.9660759493670886, "percentage": 32.22, "elapsed_time": "0:53:52", "remaining_time": "1:53:21"}
+{"current_steps": 319, "total_steps": 987, "loss": 0.7202, "lr": 8.56046142715513e-06, "epoch": 0.9691139240506329, "percentage": 32.32, "elapsed_time": "0:54:00", "remaining_time": "1:53:05"}
+{"current_steps": 320, "total_steps": 987, "loss": 0.7242, "lr": 8.548019870451391e-06, "epoch": 0.9721518987341772, "percentage": 32.42, "elapsed_time": "0:54:08", "remaining_time": "1:52:50"}
+{"current_steps": 321, "total_steps": 987, "loss": 0.699, "lr": 8.535533905932739e-06, "epoch": 0.9751898734177216, "percentage": 32.52, "elapsed_time": "0:54:19", "remaining_time": "1:52:42"}
+{"current_steps": 322, "total_steps": 987, "loss": 0.7342, "lr": 8.523003689876312e-06, "epoch": 0.9782278481012658, "percentage": 32.62, "elapsed_time": "0:54:29", "remaining_time": "1:52:31"}
+{"current_steps": 323, "total_steps": 987, "loss": 0.6986, "lr": 8.510429379113114e-06, "epoch": 0.9812658227848101, "percentage": 32.73, "elapsed_time": "0:54:41", "remaining_time": "1:52:25"}
+{"current_steps": 324, "total_steps": 987, "loss": 0.7206, "lr": 8.497811131026046e-06, "epoch": 0.9843037974683544, "percentage": 32.83, "elapsed_time": "0:54:53", "remaining_time": "1:52:18"}
+{"current_steps": 325, "total_steps": 987, "loss": 0.6682, "lr": 8.485149103547943e-06, "epoch": 0.9873417721518988, "percentage": 32.93, "elapsed_time": "0:55:02", "remaining_time": "1:52:06"}
+{"current_steps": 326, "total_steps": 987, "loss": 0.7281, "lr": 8.472443455159586e-06, "epoch": 0.990379746835443, "percentage": 33.03, "elapsed_time": "0:55:09", "remaining_time": "1:51:50"}
+{"current_steps": 327, "total_steps": 987, "loss": 0.7449, "lr": 8.459694344887732e-06, "epoch": 0.9934177215189873, "percentage": 33.13, "elapsed_time": "0:55:16", "remaining_time": "1:51:34"}
+{"current_steps": 328, "total_steps": 987, "loss": 0.6661, "lr": 8.446901932303112e-06, "epoch": 0.9964556962025316, "percentage": 33.23, "elapsed_time": "0:55:24", "remaining_time": "1:51:18"}
+{"current_steps": 329, "total_steps": 987, "loss": 0.6925, "lr": 8.434066377518437e-06, "epoch": 0.999493670886076, "percentage": 33.33, "elapsed_time": "0:55:31", "remaining_time": "1:51:03"}
+{"current_steps": 330, "total_steps": 987, "loss": 0.7072, "lr": 8.421187841186402e-06, "epoch": 1.0, "percentage": 33.43, "elapsed_time": "0:55:33", "remaining_time": "1:50:35"}
+{"current_steps": 331, "total_steps": 987, "loss": 0.5878, "lr": 8.408266484497664e-06, "epoch": 1.0030379746835443, "percentage": 33.54, "elapsed_time": "0:55:42", "remaining_time": "1:50:24"}
+{"current_steps": 332, "total_steps": 987, "loss": 0.5245, "lr": 8.395302469178832e-06, "epoch": 1.0060759493670886, "percentage": 33.64, "elapsed_time": "0:55:53", "remaining_time": "1:50:16"}
+{"current_steps": 333, "total_steps": 987, "loss": 0.5884, "lr": 8.382295957490435e-06, "epoch": 1.0091139240506328, "percentage": 33.74, "elapsed_time": "0:56:06", "remaining_time": "1:50:10"}
+{"current_steps": 334, "total_steps": 987, "loss": 0.5912, "lr": 8.369247112224901e-06, "epoch": 1.0121518987341773, "percentage": 33.84, "elapsed_time": "0:56:15", "remaining_time": "1:49:59"}
+{"current_steps": 335, "total_steps": 987, "loss": 0.6168, "lr": 8.356156096704516e-06, "epoch": 1.0151898734177216, "percentage": 33.94, "elapsed_time": "0:56:25", "remaining_time": "1:49:49"}
+{"current_steps": 336, "total_steps": 987, "loss": 0.5443, "lr": 8.343023074779368e-06, "epoch": 1.0182278481012659, "percentage": 34.04, "elapsed_time": "0:56:33", "remaining_time": "1:49:35"}
+{"current_steps": 337, "total_steps": 987, "loss": 0.5769, "lr": 8.329848210825322e-06, "epoch": 1.0212658227848102, "percentage": 34.14, "elapsed_time": "0:56:43", "remaining_time": "1:49:25"}
+{"current_steps": 338, "total_steps": 987, "loss": 0.5507, "lr": 8.316631669741934e-06, "epoch": 1.0243037974683544, "percentage": 34.25, "elapsed_time": "0:56:51", "remaining_time": "1:49:10"}
+{"current_steps": 339, "total_steps": 987, "loss": 0.5182, "lr": 8.303373616950408e-06, "epoch": 1.0273417721518987, "percentage": 34.35, "elapsed_time": "0:56:58", "remaining_time": "1:48:54"}
+{"current_steps": 340, "total_steps": 987, "loss": 0.5391, "lr": 8.290074218391515e-06, "epoch": 1.030379746835443, "percentage": 34.45, "elapsed_time": "0:57:10", "remaining_time": "1:48:48"}
+{"current_steps": 341, "total_steps": 987, "loss": 0.5657, "lr": 8.27673364052352e-06, "epoch": 1.0334177215189873, "percentage": 34.55, "elapsed_time": "0:57:20", "remaining_time": "1:48:37"}
+{"current_steps": 342, "total_steps": 987, "loss": 0.5656, "lr": 8.263352050320094e-06, "epoch": 1.0364556962025318, "percentage": 34.65, "elapsed_time": "0:57:29", "remaining_time": "1:48:26"}
+{"current_steps": 343, "total_steps": 987, "loss": 0.5628, "lr": 8.249929615268234e-06, "epoch": 1.039493670886076, "percentage": 34.75, "elapsed_time": "0:57:39", "remaining_time": "1:48:15"}
+{"current_steps": 344, "total_steps": 987, "loss": 0.5692, "lr": 8.236466503366155e-06, "epoch": 1.0425316455696203, "percentage": 34.85, "elapsed_time": "0:57:51", "remaining_time": "1:48:08"}
+{"current_steps": 345, "total_steps": 987, "loss": 0.5971, "lr": 8.222962883121196e-06, "epoch": 1.0455696202531646, "percentage": 34.95, "elapsed_time": "0:58:00", "remaining_time": "1:47:56"}
+{"current_steps": 346, "total_steps": 987, "loss": 0.5534, "lr": 8.209418923547706e-06, "epoch": 1.0486075949367089, "percentage": 35.06, "elapsed_time": "0:58:09", "remaining_time": "1:47:44"}
+{"current_steps": 347, "total_steps": 987, "loss": 0.5548, "lr": 8.195834794164925e-06, "epoch": 1.0516455696202531, "percentage": 35.16, "elapsed_time": "0:58:17", "remaining_time": "1:47:30"}
+{"current_steps": 348, "total_steps": 987, "loss": 0.5465, "lr": 8.182210664994879e-06, "epoch": 1.0546835443037974, "percentage": 35.26, "elapsed_time": "0:58:24", "remaining_time": "1:47:14"}
+{"current_steps": 349, "total_steps": 987, "loss": 0.566, "lr": 8.168546706560231e-06, "epoch": 1.0577215189873417, "percentage": 35.36, "elapsed_time": "0:58:31", "remaining_time": "1:46:59"}
+{"current_steps": 350, "total_steps": 987, "loss": 0.5618, "lr": 8.154843089882159e-06, "epoch": 1.0607594936708862, "percentage": 35.46, "elapsed_time": "0:58:41", "remaining_time": "1:46:49"}
+{"current_steps": 351, "total_steps": 987, "loss": 0.5758, "lr": 8.141099986478212e-06, "epoch": 1.0637974683544305, "percentage": 35.56, "elapsed_time": "0:58:53", "remaining_time": "1:46:41"}
+{"current_steps": 352, "total_steps": 987, "loss": 0.5528, "lr": 8.127317568360164e-06, "epoch": 1.0668354430379747, "percentage": 35.66, "elapsed_time": "0:59:03", "remaining_time": "1:46:31"}
+{"current_steps": 353, "total_steps": 987, "loss": 0.5814, "lr": 8.113496008031863e-06, "epoch": 1.069873417721519, "percentage": 35.76, "elapsed_time": "0:59:12", "remaining_time": "1:46:20"}
+{"current_steps": 354, "total_steps": 987, "loss": 0.5173, "lr": 8.099635478487064e-06, "epoch": 1.0729113924050633, "percentage": 35.87, "elapsed_time": "0:59:22", "remaining_time": "1:46:09"}
+{"current_steps": 355, "total_steps": 987, "loss": 0.562, "lr": 8.085736153207277e-06, "epoch": 1.0759493670886076, "percentage": 35.97, "elapsed_time": "0:59:30", "remaining_time": "1:45:55"}
+{"current_steps": 356, "total_steps": 987, "loss": 0.5522, "lr": 8.07179820615958e-06, "epoch": 1.0789873417721518, "percentage": 36.07, "elapsed_time": "0:59:41", "remaining_time": "1:45:48"}
+{"current_steps": 357, "total_steps": 987, "loss": 0.6107, "lr": 8.057821811794457e-06, "epoch": 1.082025316455696, "percentage": 36.17, "elapsed_time": "0:59:48", "remaining_time": "1:45:33"}
+{"current_steps": 358, "total_steps": 987, "loss": 0.5735, "lr": 8.043807145043604e-06, "epoch": 1.0850632911392406, "percentage": 36.27, "elapsed_time": "0:59:56", "remaining_time": "1:45:19"}
+{"current_steps": 359, "total_steps": 987, "loss": 0.5334, "lr": 8.029754381317741e-06, "epoch": 1.0881012658227849, "percentage": 36.37, "elapsed_time": "1:00:04", "remaining_time": "1:45:05"}
+{"current_steps": 360, "total_steps": 987, "loss": 0.5773, "lr": 8.015663696504424e-06, "epoch": 1.0911392405063292, "percentage": 36.47, "elapsed_time": "1:00:14", "remaining_time": "1:44:55"}
+{"current_steps": 361, "total_steps": 987, "loss": 0.5568, "lr": 8.001535266965829e-06, "epoch": 1.0941772151898734, "percentage": 36.58, "elapsed_time": "1:00:28", "remaining_time": "1:44:51"}
+{"current_steps": 362, "total_steps": 987, "loss": 0.5424, "lr": 7.987369269536563e-06, "epoch": 1.0972151898734177, "percentage": 36.68, "elapsed_time": "1:00:38", "remaining_time": "1:44:41"}
+{"current_steps": 363, "total_steps": 987, "loss": 0.549, "lr": 7.973165881521435e-06, "epoch": 1.100253164556962, "percentage": 36.78, "elapsed_time": "1:00:49", "remaining_time": "1:44:33"}
+{"current_steps": 364, "total_steps": 987, "loss": 0.5304, "lr": 7.958925280693243e-06, "epoch": 1.1032911392405063, "percentage": 36.88, "elapsed_time": "1:00:59", "remaining_time": "1:44:22"}
+{"current_steps": 365, "total_steps": 987, "loss": 0.571, "lr": 7.944647645290555e-06, "epoch": 1.1063291139240505, "percentage": 36.98, "elapsed_time": "1:01:06", "remaining_time": "1:44:08"}
+{"current_steps": 366, "total_steps": 987, "loss": 0.5493, "lr": 7.930333154015467e-06, "epoch": 1.109367088607595, "percentage": 37.08, "elapsed_time": "1:01:15", "remaining_time": "1:43:55"}
+{"current_steps": 367, "total_steps": 987, "loss": 0.606, "lr": 7.915981986031367e-06, "epoch": 1.1124050632911393, "percentage": 37.18, "elapsed_time": "1:01:26", "remaining_time": "1:43:47"}
+{"current_steps": 368, "total_steps": 987, "loss": 0.5572, "lr": 7.901594320960709e-06, "epoch": 1.1154430379746836, "percentage": 37.28, "elapsed_time": "1:01:36", "remaining_time": "1:43:37"}
+{"current_steps": 369, "total_steps": 987, "loss": 0.5733, "lr": 7.887170338882742e-06, "epoch": 1.1184810126582279, "percentage": 37.39, "elapsed_time": "1:01:45", "remaining_time": "1:43:26"}
+{"current_steps": 370, "total_steps": 987, "loss": 0.585, "lr": 7.872710220331271e-06, "epoch": 1.1215189873417721, "percentage": 37.49, "elapsed_time": "1:01:55", "remaining_time": "1:43:16"}
+{"current_steps": 371, "total_steps": 987, "loss": 0.5445, "lr": 7.858214146292394e-06, "epoch": 1.1245569620253164, "percentage": 37.59, "elapsed_time": "1:02:05", "remaining_time": "1:43:05"}
+{"current_steps": 372, "total_steps": 987, "loss": 0.5742, "lr": 7.843682298202235e-06, "epoch": 1.1275949367088607, "percentage": 37.69, "elapsed_time": "1:02:17", "remaining_time": "1:42:58"}
+{"current_steps": 373, "total_steps": 987, "loss": 0.5644, "lr": 7.829114857944672e-06, "epoch": 1.130632911392405, "percentage": 37.79, "elapsed_time": "1:02:29", "remaining_time": "1:42:52"}
+{"current_steps": 374, "total_steps": 987, "loss": 0.5616, "lr": 7.814512007849069e-06, "epoch": 1.1336708860759495, "percentage": 37.89, "elapsed_time": "1:02:38", "remaining_time": "1:42:40"}
+{"current_steps": 375, "total_steps": 987, "loss": 0.5645, "lr": 7.799873930687979e-06, "epoch": 1.1367088607594937, "percentage": 37.99, "elapsed_time": "1:02:49", "remaining_time": "1:42:31"}
+{"current_steps": 376, "total_steps": 987, "loss": 0.5798, "lr": 7.785200809674869e-06, "epoch": 1.139746835443038, "percentage": 38.1, "elapsed_time": "1:02:56", "remaining_time": "1:42:16"}
+{"current_steps": 377, "total_steps": 987, "loss": 0.5695, "lr": 7.770492828461824e-06, "epoch": 1.1427848101265823, "percentage": 38.2, "elapsed_time": "1:03:07", "remaining_time": "1:42:08"}
+{"current_steps": 378, "total_steps": 987, "loss": 0.5783, "lr": 7.755750171137245e-06, "epoch": 1.1458227848101266, "percentage": 38.3, "elapsed_time": "1:03:19", "remaining_time": "1:42:00"}
+{"current_steps": 379, "total_steps": 987, "loss": 0.5589, "lr": 7.74097302222355e-06, "epoch": 1.1488607594936708, "percentage": 38.4, "elapsed_time": "1:03:28", "remaining_time": "1:41:48"}
+{"current_steps": 380, "total_steps": 987, "loss": 0.5548, "lr": 7.726161566674856e-06, "epoch": 1.1518987341772151, "percentage": 38.5, "elapsed_time": "1:03:38", "remaining_time": "1:41:38"}
+{"current_steps": 381, "total_steps": 987, "loss": 0.5759, "lr": 7.711315989874677e-06, "epoch": 1.1549367088607596, "percentage": 38.6, "elapsed_time": "1:03:49", "remaining_time": "1:41:31"}
+{"current_steps": 382, "total_steps": 987, "loss": 0.5391, "lr": 7.696436477633588e-06, "epoch": 1.1579746835443039, "percentage": 38.7, "elapsed_time": "1:03:57", "remaining_time": "1:41:18"}
+{"current_steps": 383, "total_steps": 987, "loss": 0.5883, "lr": 7.681523216186912e-06, "epoch": 1.1610126582278482, "percentage": 38.8, "elapsed_time": "1:04:11", "remaining_time": "1:41:13"}
+{"current_steps": 384, "total_steps": 987, "loss": 0.5509, "lr": 7.666576392192389e-06, "epoch": 1.1640506329113924, "percentage": 38.91, "elapsed_time": "1:04:20", "remaining_time": "1:41:01"}
+{"current_steps": 385, "total_steps": 987, "loss": 0.529, "lr": 7.651596192727826e-06, "epoch": 1.1670886075949367, "percentage": 39.01, "elapsed_time": "1:04:28", "remaining_time": "1:40:48"}
+{"current_steps": 386, "total_steps": 987, "loss": 0.5022, "lr": 7.636582805288771e-06, "epoch": 1.170126582278481, "percentage": 39.11, "elapsed_time": "1:04:37", "remaining_time": "1:40:37"}
+{"current_steps": 387, "total_steps": 987, "loss": 0.5648, "lr": 7.621536417786159e-06, "epoch": 1.1731645569620253, "percentage": 39.21, "elapsed_time": "1:04:47", "remaining_time": "1:40:26"}
+{"current_steps": 388, "total_steps": 987, "loss": 0.5873, "lr": 7.606457218543961e-06, "epoch": 1.1762025316455695, "percentage": 39.31, "elapsed_time": "1:04:58", "remaining_time": "1:40:18"}
+{"current_steps": 389, "total_steps": 987, "loss": 0.5474, "lr": 7.5913453962968296e-06, "epoch": 1.1792405063291138, "percentage": 39.41, "elapsed_time": "1:05:08", "remaining_time": "1:40:08"}
+{"current_steps": 390, "total_steps": 987, "loss": 0.5545, "lr": 7.576201140187727e-06, "epoch": 1.1822784810126583, "percentage": 39.51, "elapsed_time": "1:05:18", "remaining_time": "1:39:57"}
+{"current_steps": 391, "total_steps": 987, "loss": 0.5828, "lr": 7.5610246397655715e-06, "epoch": 1.1853164556962026, "percentage": 39.61, "elapsed_time": "1:05:28", "remaining_time": "1:39:47"}
+{"current_steps": 392, "total_steps": 987, "loss": 0.5873, "lr": 7.54581608498286e-06, "epoch": 1.1883544303797469, "percentage": 39.72, "elapsed_time": "1:05:37", "remaining_time": "1:39:35"}
+{"current_steps": 393, "total_steps": 987, "loss": 0.5592, "lr": 7.530575666193283e-06, "epoch": 1.1913924050632911, "percentage": 39.82, "elapsed_time": "1:05:43", "remaining_time": "1:39:20"}
+{"current_steps": 394, "total_steps": 987, "loss": 0.5807, "lr": 7.515303574149348e-06, "epoch": 1.1944303797468354, "percentage": 39.92, "elapsed_time": "1:05:50", "remaining_time": "1:39:06"}
+{"current_steps": 395, "total_steps": 987, "loss": 0.5337, "lr": 7.500000000000001e-06, "epoch": 1.1974683544303797, "percentage": 40.02, "elapsed_time": "1:05:58", "remaining_time": "1:38:51"}
+{"current_steps": 396, "total_steps": 987, "loss": 0.5438, "lr": 7.484665135288214e-06, "epoch": 1.200506329113924, "percentage": 40.12, "elapsed_time": "1:06:09", "remaining_time": "1:38:44"}
+{"current_steps": 397, "total_steps": 987, "loss": 0.5476, "lr": 7.469299171948608e-06, "epoch": 1.2035443037974685, "percentage": 40.22, "elapsed_time": "1:06:19", "remaining_time": "1:38:34"}
+{"current_steps": 398, "total_steps": 987, "loss": 0.5564, "lr": 7.453902302305032e-06, "epoch": 1.2065822784810127, "percentage": 40.32, "elapsed_time": "1:06:28", "remaining_time": "1:38:22"}
+{"current_steps": 399, "total_steps": 987, "loss": 0.5283, "lr": 7.438474719068174e-06, "epoch": 1.209620253164557, "percentage": 40.43, "elapsed_time": "1:06:39", "remaining_time": "1:38:13"}
+{"current_steps": 400, "total_steps": 987, "loss": 0.5426, "lr": 7.423016615333135e-06, "epoch": 1.2126582278481013, "percentage": 40.53, "elapsed_time": "1:06:49", "remaining_time": "1:38:03"}
+{"current_steps": 401, "total_steps": 987, "loss": 0.5555, "lr": 7.4075281845770196e-06, "epoch": 1.2156962025316456, "percentage": 40.63, "elapsed_time": "1:08:24", "remaining_time": "1:39:58"}
+{"current_steps": 402, "total_steps": 987, "loss": 0.5727, "lr": 7.392009620656513e-06, "epoch": 1.2187341772151898, "percentage": 40.73, "elapsed_time": "1:08:35", "remaining_time": "1:39:48"}
+{"current_steps": 403, "total_steps": 987, "loss": 0.5825, "lr": 7.37646111780545e-06, "epoch": 1.2217721518987341, "percentage": 40.83, "elapsed_time": "1:08:45", "remaining_time": "1:39:39"}
+{"current_steps": 404, "total_steps": 987, "loss": 0.5587, "lr": 7.360882870632393e-06, "epoch": 1.2248101265822784, "percentage": 40.93, "elapsed_time": "1:08:58", "remaining_time": "1:39:32"}
+{"current_steps": 405, "total_steps": 987, "loss": 0.5642, "lr": 7.3452750741181855e-06, "epoch": 1.2278481012658227, "percentage": 41.03, "elapsed_time": "1:09:13", "remaining_time": "1:39:28"}
+{"current_steps": 406, "total_steps": 987, "loss": 0.5167, "lr": 7.329637923613522e-06, "epoch": 1.2308860759493672, "percentage": 41.13, "elapsed_time": "1:09:30", "remaining_time": "1:39:27"}
+{"current_steps": 407, "total_steps": 987, "loss": 0.5418, "lr": 7.313971614836496e-06, "epoch": 1.2339240506329114, "percentage": 41.24, "elapsed_time": "1:09:42", "remaining_time": "1:39:19"}
+{"current_steps": 408, "total_steps": 987, "loss": 0.5826, "lr": 7.298276343870152e-06, "epoch": 1.2369620253164557, "percentage": 41.34, "elapsed_time": "1:09:51", "remaining_time": "1:39:08"}
+{"current_steps": 409, "total_steps": 987, "loss": 0.5518, "lr": 7.282552307160033e-06, "epoch": 1.24, "percentage": 41.44, "elapsed_time": "1:10:09", "remaining_time": "1:39:08"}
+{"current_steps": 410, "total_steps": 987, "loss": 0.5499, "lr": 7.26679970151172e-06, "epoch": 1.2430379746835443, "percentage": 41.54, "elapsed_time": "1:10:24", "remaining_time": "1:39:05"}
+{"current_steps": 411, "total_steps": 987, "loss": 0.579, "lr": 7.251018724088367e-06, "epoch": 1.2460759493670885, "percentage": 41.64, "elapsed_time": "1:10:38", "remaining_time": "1:39:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75f1dddfa49ebb7ceb819b7808e202978a303dbf72577a612cc8983e782db08
+size 8248