Training in progress, epoch 1

.gitattributes

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

added_tokens.json

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

config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724aa098416af47a30887fcaf4ccdbf115b125c69cf25ada1508d97f518ded5e
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8865f5028f1c69ba2b41346fa9c2002b186bb88e0b6f87330b5033dfce0c3121
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145c504927de5b9c19399f8e8027088aa289ab018f5dbb39856eb9433fb2c59d
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73a48acd8cf3c57077fb9c2067c9a6cf947a898285d7bc56ec1c37fee65870f
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_log.jsonl

@@ -0,0 +1,353 @@
+{"current_steps": 1, "total_steps": 1730, "loss": 1.1688, "lr": 1.1560693641618497e-07, "epoch": 0.002890173410404624, "percentage": 0.06, "elapsed_time": "0:00:32", "remaining_time": "15:36:34"}
+{"current_steps": 2, "total_steps": 1730, "loss": 1.152, "lr": 2.3121387283236994e-07, "epoch": 0.005780346820809248, "percentage": 0.12, "elapsed_time": "0:00:56", "remaining_time": "13:33:41"}
+{"current_steps": 3, "total_steps": 1730, "loss": 1.1394, "lr": 3.468208092485549e-07, "epoch": 0.008670520231213872, "percentage": 0.17, "elapsed_time": "0:01:18", "remaining_time": "12:32:06"}
+{"current_steps": 4, "total_steps": 1730, "loss": 1.1456, "lr": 4.624277456647399e-07, "epoch": 0.011560693641618497, "percentage": 0.23, "elapsed_time": "0:01:43", "remaining_time": "12:23:49"}
+{"current_steps": 5, "total_steps": 1730, "loss": 1.1535, "lr": 5.780346820809249e-07, "epoch": 0.014450867052023121, "percentage": 0.29, "elapsed_time": "0:02:07", "remaining_time": "12:15:18"}
+{"current_steps": 6, "total_steps": 1730, "loss": 1.1366, "lr": 6.936416184971098e-07, "epoch": 0.017341040462427744, "percentage": 0.35, "elapsed_time": "0:02:32", "remaining_time": "12:09:40"}
+{"current_steps": 7, "total_steps": 1730, "loss": 1.1601, "lr": 8.092485549132949e-07, "epoch": 0.02023121387283237, "percentage": 0.4, "elapsed_time": "0:02:55", "remaining_time": "11:59:38"}
+{"current_steps": 8, "total_steps": 1730, "loss": 1.0901, "lr": 9.248554913294798e-07, "epoch": 0.023121387283236993, "percentage": 0.46, "elapsed_time": "0:03:19", "remaining_time": "11:55:02"}
+{"current_steps": 9, "total_steps": 1730, "loss": 1.0838, "lr": 1.040462427745665e-06, "epoch": 0.02601156069364162, "percentage": 0.52, "elapsed_time": "0:03:42", "remaining_time": "11:49:35"}
+{"current_steps": 10, "total_steps": 1730, "loss": 1.0948, "lr": 1.1560693641618499e-06, "epoch": 0.028901734104046242, "percentage": 0.58, "elapsed_time": "0:04:06", "remaining_time": "11:45:22"}
+{"current_steps": 11, "total_steps": 1730, "loss": 1.0693, "lr": 1.2716763005780348e-06, "epoch": 0.031791907514450865, "percentage": 0.64, "elapsed_time": "0:04:30", "remaining_time": "11:43:53"}
+{"current_steps": 12, "total_steps": 1730, "loss": 1.0612, "lr": 1.3872832369942195e-06, "epoch": 0.03468208092485549, "percentage": 0.69, "elapsed_time": "0:04:53", "remaining_time": "11:40:22"}
+{"current_steps": 13, "total_steps": 1730, "loss": 1.071, "lr": 1.502890173410405e-06, "epoch": 0.03757225433526012, "percentage": 0.75, "elapsed_time": "0:05:17", "remaining_time": "11:39:56"}
+{"current_steps": 14, "total_steps": 1730, "loss": 1.0341, "lr": 1.6184971098265898e-06, "epoch": 0.04046242774566474, "percentage": 0.81, "elapsed_time": "0:05:42", "remaining_time": "11:39:48"}
+{"current_steps": 15, "total_steps": 1730, "loss": 1.0408, "lr": 1.7341040462427746e-06, "epoch": 0.04335260115606936, "percentage": 0.87, "elapsed_time": "0:06:06", "remaining_time": "11:38:30"}
+{"current_steps": 16, "total_steps": 1730, "loss": 1.0101, "lr": 1.8497109826589595e-06, "epoch": 0.046242774566473986, "percentage": 0.92, "elapsed_time": "0:06:30", "remaining_time": "11:37:31"}
+{"current_steps": 17, "total_steps": 1730, "loss": 0.9826, "lr": 1.965317919075145e-06, "epoch": 0.049132947976878616, "percentage": 0.98, "elapsed_time": "0:06:55", "remaining_time": "11:37:31"}
+{"current_steps": 18, "total_steps": 1730, "loss": 0.9661, "lr": 2.08092485549133e-06, "epoch": 0.05202312138728324, "percentage": 1.04, "elapsed_time": "0:07:19", "remaining_time": "11:37:17"}
+{"current_steps": 19, "total_steps": 1730, "loss": 0.9596, "lr": 2.1965317919075148e-06, "epoch": 0.05491329479768786, "percentage": 1.1, "elapsed_time": "0:07:43", "remaining_time": "11:36:11"}
+{"current_steps": 20, "total_steps": 1730, "loss": 0.9482, "lr": 2.3121387283236997e-06, "epoch": 0.057803468208092484, "percentage": 1.16, "elapsed_time": "0:08:06", "remaining_time": "11:33:07"}
+{"current_steps": 21, "total_steps": 1730, "loss": 0.9411, "lr": 2.4277456647398847e-06, "epoch": 0.06069364161849711, "percentage": 1.21, "elapsed_time": "0:08:30", "remaining_time": "11:32:53"}
+{"current_steps": 22, "total_steps": 1730, "loss": 0.9384, "lr": 2.5433526011560696e-06, "epoch": 0.06358381502890173, "percentage": 1.27, "elapsed_time": "0:08:54", "remaining_time": "11:31:12"}
+{"current_steps": 23, "total_steps": 1730, "loss": 0.9385, "lr": 2.658959537572254e-06, "epoch": 0.06647398843930635, "percentage": 1.33, "elapsed_time": "0:09:18", "remaining_time": "11:30:58"}
+{"current_steps": 24, "total_steps": 1730, "loss": 0.9346, "lr": 2.774566473988439e-06, "epoch": 0.06936416184971098, "percentage": 1.39, "elapsed_time": "0:09:38", "remaining_time": "11:25:17"}
+{"current_steps": 25, "total_steps": 1730, "loss": 0.8848, "lr": 2.890173410404625e-06, "epoch": 0.07225433526011561, "percentage": 1.45, "elapsed_time": "0:10:02", "remaining_time": "11:25:08"}
+{"current_steps": 26, "total_steps": 1730, "loss": 0.8725, "lr": 3.00578034682081e-06, "epoch": 0.07514450867052024, "percentage": 1.5, "elapsed_time": "0:10:28", "remaining_time": "11:26:00"}
+{"current_steps": 27, "total_steps": 1730, "loss": 0.8621, "lr": 3.1213872832369948e-06, "epoch": 0.07803468208092486, "percentage": 1.56, "elapsed_time": "0:10:51", "remaining_time": "11:24:45"}
+{"current_steps": 28, "total_steps": 1730, "loss": 0.8399, "lr": 3.2369942196531797e-06, "epoch": 0.08092485549132948, "percentage": 1.62, "elapsed_time": "0:11:14", "remaining_time": "11:23:03"}
+{"current_steps": 29, "total_steps": 1730, "loss": 0.8481, "lr": 3.3526011560693642e-06, "epoch": 0.0838150289017341, "percentage": 1.68, "elapsed_time": "0:11:39", "remaining_time": "11:23:23"}
+{"current_steps": 30, "total_steps": 1730, "loss": 0.8354, "lr": 3.468208092485549e-06, "epoch": 0.08670520231213873, "percentage": 1.73, "elapsed_time": "0:12:03", "remaining_time": "11:22:55"}
+{"current_steps": 31, "total_steps": 1730, "loss": 0.8387, "lr": 3.583815028901734e-06, "epoch": 0.08959537572254335, "percentage": 1.79, "elapsed_time": "0:12:26", "remaining_time": "11:21:51"}
+{"current_steps": 32, "total_steps": 1730, "loss": 0.8525, "lr": 3.699421965317919e-06, "epoch": 0.09248554913294797, "percentage": 1.85, "elapsed_time": "0:12:50", "remaining_time": "11:21:19"}
+{"current_steps": 33, "total_steps": 1730, "loss": 0.851, "lr": 3.815028901734104e-06, "epoch": 0.0953757225433526, "percentage": 1.91, "elapsed_time": "0:13:14", "remaining_time": "11:21:21"}
+{"current_steps": 34, "total_steps": 1730, "loss": 0.8317, "lr": 3.93063583815029e-06, "epoch": 0.09826589595375723, "percentage": 1.97, "elapsed_time": "0:13:39", "remaining_time": "11:21:28"}
+{"current_steps": 35, "total_steps": 1730, "loss": 0.8313, "lr": 4.046242774566474e-06, "epoch": 0.10115606936416185, "percentage": 2.02, "elapsed_time": "0:14:03", "remaining_time": "11:20:27"}
+{"current_steps": 36, "total_steps": 1730, "loss": 0.8044, "lr": 4.16184971098266e-06, "epoch": 0.10404624277456648, "percentage": 2.08, "elapsed_time": "0:14:25", "remaining_time": "11:18:47"}
+{"current_steps": 37, "total_steps": 1730, "loss": 0.8237, "lr": 4.277456647398844e-06, "epoch": 0.1069364161849711, "percentage": 2.14, "elapsed_time": "0:14:49", "remaining_time": "11:18:40"}
+{"current_steps": 38, "total_steps": 1730, "loss": 0.806, "lr": 4.3930635838150296e-06, "epoch": 0.10982658959537572, "percentage": 2.2, "elapsed_time": "0:15:14", "remaining_time": "11:18:42"}
+{"current_steps": 39, "total_steps": 1730, "loss": 0.8056, "lr": 4.508670520231214e-06, "epoch": 0.11271676300578035, "percentage": 2.25, "elapsed_time": "0:15:37", "remaining_time": "11:17:30"}
+{"current_steps": 40, "total_steps": 1730, "loss": 0.7844, "lr": 4.6242774566473994e-06, "epoch": 0.11560693641618497, "percentage": 2.31, "elapsed_time": "0:16:01", "remaining_time": "11:17:18"}
+{"current_steps": 41, "total_steps": 1730, "loss": 0.8, "lr": 4.739884393063584e-06, "epoch": 0.11849710982658959, "percentage": 2.37, "elapsed_time": "0:16:26", "remaining_time": "11:17:18"}
+{"current_steps": 42, "total_steps": 1730, "loss": 0.7943, "lr": 4.855491329479769e-06, "epoch": 0.12138728323699421, "percentage": 2.43, "elapsed_time": "0:16:51", "remaining_time": "11:17:15"}
+{"current_steps": 43, "total_steps": 1730, "loss": 0.789, "lr": 4.971098265895954e-06, "epoch": 0.12427745664739884, "percentage": 2.49, "elapsed_time": "0:17:14", "remaining_time": "11:16:34"}
+{"current_steps": 44, "total_steps": 1730, "loss": 0.7821, "lr": 5.086705202312139e-06, "epoch": 0.12716763005780346, "percentage": 2.54, "elapsed_time": "0:17:36", "remaining_time": "11:14:30"}
+{"current_steps": 45, "total_steps": 1730, "loss": 0.7866, "lr": 5.202312138728324e-06, "epoch": 0.13005780346820808, "percentage": 2.6, "elapsed_time": "0:18:00", "remaining_time": "11:14:30"}
+{"current_steps": 46, "total_steps": 1730, "loss": 0.7666, "lr": 5.317919075144508e-06, "epoch": 0.1329479768786127, "percentage": 2.66, "elapsed_time": "0:18:24", "remaining_time": "11:13:51"}
+{"current_steps": 47, "total_steps": 1730, "loss": 0.7692, "lr": 5.433526011560694e-06, "epoch": 0.13583815028901733, "percentage": 2.72, "elapsed_time": "0:18:47", "remaining_time": "11:13:01"}
+{"current_steps": 48, "total_steps": 1730, "loss": 0.7589, "lr": 5.549132947976878e-06, "epoch": 0.13872832369942195, "percentage": 2.77, "elapsed_time": "0:19:13", "remaining_time": "11:13:35"}
+{"current_steps": 49, "total_steps": 1730, "loss": 0.7591, "lr": 5.664739884393064e-06, "epoch": 0.1416184971098266, "percentage": 2.83, "elapsed_time": "0:19:38", "remaining_time": "11:13:57"}
+{"current_steps": 50, "total_steps": 1730, "loss": 0.7683, "lr": 5.78034682080925e-06, "epoch": 0.14450867052023122, "percentage": 2.89, "elapsed_time": "0:20:02", "remaining_time": "11:13:14"}
+{"current_steps": 51, "total_steps": 1730, "loss": 0.7353, "lr": 5.895953757225434e-06, "epoch": 0.14739884393063585, "percentage": 2.95, "elapsed_time": "0:20:27", "remaining_time": "11:13:38"}
+{"current_steps": 52, "total_steps": 1730, "loss": 0.7644, "lr": 6.01156069364162e-06, "epoch": 0.15028901734104047, "percentage": 3.01, "elapsed_time": "0:20:49", "remaining_time": "11:12:11"}
+{"current_steps": 53, "total_steps": 1730, "loss": 0.752, "lr": 6.127167630057804e-06, "epoch": 0.1531791907514451, "percentage": 3.06, "elapsed_time": "0:21:13", "remaining_time": "11:11:25"}
+{"current_steps": 54, "total_steps": 1730, "loss": 0.7639, "lr": 6.2427745664739895e-06, "epoch": 0.15606936416184972, "percentage": 3.12, "elapsed_time": "0:21:36", "remaining_time": "11:10:41"}
+{"current_steps": 55, "total_steps": 1730, "loss": 0.7509, "lr": 6.358381502890174e-06, "epoch": 0.15895953757225434, "percentage": 3.18, "elapsed_time": "0:22:00", "remaining_time": "11:10:21"}
+{"current_steps": 56, "total_steps": 1730, "loss": 0.7484, "lr": 6.473988439306359e-06, "epoch": 0.16184971098265896, "percentage": 3.24, "elapsed_time": "0:22:25", "remaining_time": "11:10:10"}
+{"current_steps": 57, "total_steps": 1730, "loss": 0.7408, "lr": 6.589595375722544e-06, "epoch": 0.16473988439306358, "percentage": 3.29, "elapsed_time": "0:22:48", "remaining_time": "11:09:14"}
+{"current_steps": 58, "total_steps": 1730, "loss": 0.7599, "lr": 6.7052023121387284e-06, "epoch": 0.1676300578034682, "percentage": 3.35, "elapsed_time": "0:23:12", "remaining_time": "11:09:03"}
+{"current_steps": 59, "total_steps": 1730, "loss": 0.7253, "lr": 6.820809248554914e-06, "epoch": 0.17052023121387283, "percentage": 3.41, "elapsed_time": "0:23:35", "remaining_time": "11:08:17"}
+{"current_steps": 60, "total_steps": 1730, "loss": 0.7493, "lr": 6.936416184971098e-06, "epoch": 0.17341040462427745, "percentage": 3.47, "elapsed_time": "0:23:58", "remaining_time": "11:07:16"}
+{"current_steps": 61, "total_steps": 1730, "loss": 0.7491, "lr": 7.052023121387284e-06, "epoch": 0.17630057803468208, "percentage": 3.53, "elapsed_time": "0:24:22", "remaining_time": "11:07:00"}
+{"current_steps": 62, "total_steps": 1730, "loss": 0.7437, "lr": 7.167630057803468e-06, "epoch": 0.1791907514450867, "percentage": 3.58, "elapsed_time": "0:24:46", "remaining_time": "11:06:20"}
+{"current_steps": 63, "total_steps": 1730, "loss": 0.7516, "lr": 7.283236994219654e-06, "epoch": 0.18208092485549132, "percentage": 3.64, "elapsed_time": "0:25:09", "remaining_time": "11:05:36"}
+{"current_steps": 64, "total_steps": 1730, "loss": 0.7288, "lr": 7.398843930635838e-06, "epoch": 0.18497109826589594, "percentage": 3.7, "elapsed_time": "0:25:33", "remaining_time": "11:05:23"}
+{"current_steps": 65, "total_steps": 1730, "loss": 0.7576, "lr": 7.5144508670520235e-06, "epoch": 0.18786127167630057, "percentage": 3.76, "elapsed_time": "0:25:58", "remaining_time": "11:05:12"}
+{"current_steps": 66, "total_steps": 1730, "loss": 0.7289, "lr": 7.630057803468209e-06, "epoch": 0.1907514450867052, "percentage": 3.82, "elapsed_time": "0:26:22", "remaining_time": "11:04:46"}
+{"current_steps": 67, "total_steps": 1730, "loss": 0.7267, "lr": 7.745664739884393e-06, "epoch": 0.1936416184971098, "percentage": 3.87, "elapsed_time": "0:26:44", "remaining_time": "11:03:55"}
+{"current_steps": 68, "total_steps": 1730, "loss": 0.7516, "lr": 7.86127167630058e-06, "epoch": 0.19653179190751446, "percentage": 3.93, "elapsed_time": "0:27:09", "remaining_time": "11:03:50"}
+{"current_steps": 69, "total_steps": 1730, "loss": 0.7149, "lr": 7.976878612716764e-06, "epoch": 0.1994219653179191, "percentage": 3.99, "elapsed_time": "0:27:36", "remaining_time": "11:04:40"}
+{"current_steps": 70, "total_steps": 1730, "loss": 0.7229, "lr": 8.092485549132949e-06, "epoch": 0.2023121387283237, "percentage": 4.05, "elapsed_time": "0:28:01", "remaining_time": "11:04:33"}
+{"current_steps": 71, "total_steps": 1730, "loss": 0.7367, "lr": 8.208092485549133e-06, "epoch": 0.20520231213872833, "percentage": 4.1, "elapsed_time": "0:28:25", "remaining_time": "11:04:10"}
+{"current_steps": 72, "total_steps": 1730, "loss": 0.7394, "lr": 8.32369942196532e-06, "epoch": 0.20809248554913296, "percentage": 4.16, "elapsed_time": "0:28:49", "remaining_time": "11:03:52"}
+{"current_steps": 73, "total_steps": 1730, "loss": 0.7383, "lr": 8.439306358381504e-06, "epoch": 0.21098265895953758, "percentage": 4.22, "elapsed_time": "0:29:14", "remaining_time": "11:03:47"}
+{"current_steps": 74, "total_steps": 1730, "loss": 0.7222, "lr": 8.554913294797688e-06, "epoch": 0.2138728323699422, "percentage": 4.28, "elapsed_time": "0:29:38", "remaining_time": "11:03:15"}
+{"current_steps": 75, "total_steps": 1730, "loss": 0.7311, "lr": 8.670520231213873e-06, "epoch": 0.21676300578034682, "percentage": 4.34, "elapsed_time": "0:30:03", "remaining_time": "11:03:15"}
+{"current_steps": 76, "total_steps": 1730, "loss": 0.7182, "lr": 8.786127167630059e-06, "epoch": 0.21965317919075145, "percentage": 4.39, "elapsed_time": "0:30:26", "remaining_time": "11:02:34"}
+{"current_steps": 77, "total_steps": 1730, "loss": 0.7141, "lr": 8.901734104046244e-06, "epoch": 0.22254335260115607, "percentage": 4.45, "elapsed_time": "0:30:51", "remaining_time": "11:02:28"}
+{"current_steps": 78, "total_steps": 1730, "loss": 0.7138, "lr": 9.017341040462428e-06, "epoch": 0.2254335260115607, "percentage": 4.51, "elapsed_time": "0:31:15", "remaining_time": "11:01:53"}
+{"current_steps": 79, "total_steps": 1730, "loss": 0.7006, "lr": 9.132947976878613e-06, "epoch": 0.22832369942196531, "percentage": 4.57, "elapsed_time": "0:31:38", "remaining_time": "11:01:06"}
+{"current_steps": 80, "total_steps": 1730, "loss": 0.7094, "lr": 9.248554913294799e-06, "epoch": 0.23121387283236994, "percentage": 4.62, "elapsed_time": "0:32:02", "remaining_time": "11:00:45"}
+{"current_steps": 81, "total_steps": 1730, "loss": 0.7294, "lr": 9.364161849710983e-06, "epoch": 0.23410404624277456, "percentage": 4.68, "elapsed_time": "0:32:25", "remaining_time": "10:59:58"}
+{"current_steps": 82, "total_steps": 1730, "loss": 0.734, "lr": 9.479768786127168e-06, "epoch": 0.23699421965317918, "percentage": 4.74, "elapsed_time": "0:32:47", "remaining_time": "10:59:11"}
+{"current_steps": 83, "total_steps": 1730, "loss": 0.7166, "lr": 9.595375722543352e-06, "epoch": 0.2398843930635838, "percentage": 4.8, "elapsed_time": "0:33:10", "remaining_time": "10:58:13"}
+{"current_steps": 84, "total_steps": 1730, "loss": 0.7245, "lr": 9.710982658959539e-06, "epoch": 0.24277456647398843, "percentage": 4.86, "elapsed_time": "0:33:33", "remaining_time": "10:57:31"}
+{"current_steps": 85, "total_steps": 1730, "loss": 0.7045, "lr": 9.826589595375723e-06, "epoch": 0.24566473988439305, "percentage": 4.91, "elapsed_time": "0:33:55", "remaining_time": "10:56:39"}
+{"current_steps": 86, "total_steps": 1730, "loss": 0.7053, "lr": 9.942196531791908e-06, "epoch": 0.24855491329479767, "percentage": 4.97, "elapsed_time": "0:34:20", "remaining_time": "10:56:20"}
+{"current_steps": 87, "total_steps": 1730, "loss": 0.6994, "lr": 1.0057803468208094e-05, "epoch": 0.2514450867052023, "percentage": 5.03, "elapsed_time": "0:34:47", "remaining_time": "10:57:04"}
+{"current_steps": 88, "total_steps": 1730, "loss": 0.694, "lr": 1.0173410404624278e-05, "epoch": 0.2543352601156069, "percentage": 5.09, "elapsed_time": "0:35:11", "remaining_time": "10:56:37"}
+{"current_steps": 89, "total_steps": 1730, "loss": 0.7096, "lr": 1.0289017341040463e-05, "epoch": 0.25722543352601157, "percentage": 5.14, "elapsed_time": "0:35:33", "remaining_time": "10:55:42"}
+{"current_steps": 90, "total_steps": 1730, "loss": 0.7114, "lr": 1.0404624277456647e-05, "epoch": 0.26011560693641617, "percentage": 5.2, "elapsed_time": "0:35:56", "remaining_time": "10:54:55"}
+{"current_steps": 91, "total_steps": 1730, "loss": 0.7306, "lr": 1.0520231213872834e-05, "epoch": 0.2630057803468208, "percentage": 5.26, "elapsed_time": "0:36:17", "remaining_time": "10:53:46"}
+{"current_steps": 92, "total_steps": 1730, "loss": 0.6958, "lr": 1.0635838150289017e-05, "epoch": 0.2658959537572254, "percentage": 5.32, "elapsed_time": "0:36:40", "remaining_time": "10:53:01"}
+{"current_steps": 93, "total_steps": 1730, "loss": 0.7386, "lr": 1.0751445086705203e-05, "epoch": 0.26878612716763006, "percentage": 5.38, "elapsed_time": "0:37:04", "remaining_time": "10:52:30"}
+{"current_steps": 94, "total_steps": 1730, "loss": 0.7083, "lr": 1.0867052023121387e-05, "epoch": 0.27167630057803466, "percentage": 5.43, "elapsed_time": "0:37:26", "remaining_time": "10:51:40"}
+{"current_steps": 95, "total_steps": 1730, "loss": 0.7364, "lr": 1.0982658959537573e-05, "epoch": 0.2745664739884393, "percentage": 5.49, "elapsed_time": "0:37:49", "remaining_time": "10:50:56"}
+{"current_steps": 96, "total_steps": 1730, "loss": 0.7149, "lr": 1.1098265895953756e-05, "epoch": 0.2774566473988439, "percentage": 5.55, "elapsed_time": "0:38:13", "remaining_time": "10:50:33"}
+{"current_steps": 97, "total_steps": 1730, "loss": 0.6983, "lr": 1.1213872832369943e-05, "epoch": 0.28034682080924855, "percentage": 5.61, "elapsed_time": "0:38:36", "remaining_time": "10:49:52"}
+{"current_steps": 98, "total_steps": 1730, "loss": 0.7057, "lr": 1.1329479768786129e-05, "epoch": 0.2832369942196532, "percentage": 5.66, "elapsed_time": "0:39:00", "remaining_time": "10:49:35"}
+{"current_steps": 99, "total_steps": 1730, "loss": 0.7249, "lr": 1.1445086705202313e-05, "epoch": 0.2861271676300578, "percentage": 5.72, "elapsed_time": "0:39:24", "remaining_time": "10:49:16"}
+{"current_steps": 100, "total_steps": 1730, "loss": 0.711, "lr": 1.15606936416185e-05, "epoch": 0.28901734104046245, "percentage": 5.78, "elapsed_time": "0:39:48", "remaining_time": "10:49:00"}
+{"current_steps": 101, "total_steps": 1730, "loss": 0.7094, "lr": 1.1676300578034682e-05, "epoch": 0.29190751445086704, "percentage": 5.84, "elapsed_time": "0:40:14", "remaining_time": "10:48:56"}
+{"current_steps": 102, "total_steps": 1730, "loss": 0.696, "lr": 1.1791907514450869e-05, "epoch": 0.2947976878612717, "percentage": 5.9, "elapsed_time": "0:40:37", "remaining_time": "10:48:26"}
+{"current_steps": 103, "total_steps": 1730, "loss": 0.7214, "lr": 1.1907514450867053e-05, "epoch": 0.2976878612716763, "percentage": 5.95, "elapsed_time": "0:41:01", "remaining_time": "10:48:05"}
+{"current_steps": 104, "total_steps": 1730, "loss": 0.712, "lr": 1.202312138728324e-05, "epoch": 0.30057803468208094, "percentage": 6.01, "elapsed_time": "0:41:24", "remaining_time": "10:47:28"}
+{"current_steps": 105, "total_steps": 1730, "loss": 0.7091, "lr": 1.2138728323699422e-05, "epoch": 0.30346820809248554, "percentage": 6.07, "elapsed_time": "0:41:49", "remaining_time": "10:47:14"}
+{"current_steps": 106, "total_steps": 1730, "loss": 0.6907, "lr": 1.2254335260115608e-05, "epoch": 0.3063583815028902, "percentage": 6.13, "elapsed_time": "0:42:12", "remaining_time": "10:46:40"}
+{"current_steps": 107, "total_steps": 1730, "loss": 0.7041, "lr": 1.2369942196531793e-05, "epoch": 0.3092485549132948, "percentage": 6.18, "elapsed_time": "0:42:35", "remaining_time": "10:46:04"}
+{"current_steps": 108, "total_steps": 1730, "loss": 0.7204, "lr": 1.2485549132947979e-05, "epoch": 0.31213872832369943, "percentage": 6.24, "elapsed_time": "0:43:00", "remaining_time": "10:45:51"}
+{"current_steps": 109, "total_steps": 1730, "loss": 0.7009, "lr": 1.2601156069364162e-05, "epoch": 0.315028901734104, "percentage": 6.3, "elapsed_time": "0:43:24", "remaining_time": "10:45:25"}
+{"current_steps": 110, "total_steps": 1730, "loss": 0.6945, "lr": 1.2716763005780348e-05, "epoch": 0.3179190751445087, "percentage": 6.36, "elapsed_time": "0:43:47", "remaining_time": "10:44:55"}
+{"current_steps": 111, "total_steps": 1730, "loss": 0.7291, "lr": 1.2832369942196533e-05, "epoch": 0.3208092485549133, "percentage": 6.42, "elapsed_time": "0:44:11", "remaining_time": "10:44:28"}
+{"current_steps": 112, "total_steps": 1730, "loss": 0.6884, "lr": 1.2947976878612719e-05, "epoch": 0.3236994219653179, "percentage": 6.47, "elapsed_time": "0:44:34", "remaining_time": "10:44:03"}
+{"current_steps": 113, "total_steps": 1730, "loss": 0.7021, "lr": 1.3063583815028902e-05, "epoch": 0.3265895953757225, "percentage": 6.53, "elapsed_time": "0:44:59", "remaining_time": "10:43:47"}
+{"current_steps": 114, "total_steps": 1730, "loss": 0.6719, "lr": 1.3179190751445088e-05, "epoch": 0.32947976878612717, "percentage": 6.59, "elapsed_time": "0:45:23", "remaining_time": "10:43:28"}
+{"current_steps": 115, "total_steps": 1730, "loss": 0.7254, "lr": 1.3294797687861272e-05, "epoch": 0.33236994219653176, "percentage": 6.65, "elapsed_time": "0:45:49", "remaining_time": "10:43:26"}
+{"current_steps": 116, "total_steps": 1730, "loss": 0.7031, "lr": 1.3410404624277457e-05, "epoch": 0.3352601156069364, "percentage": 6.71, "elapsed_time": "0:46:13", "remaining_time": "10:43:05"}
+{"current_steps": 117, "total_steps": 1730, "loss": 0.6987, "lr": 1.3526011560693643e-05, "epoch": 0.33815028901734107, "percentage": 6.76, "elapsed_time": "0:46:35", "remaining_time": "10:42:21"}
+{"current_steps": 118, "total_steps": 1730, "loss": 0.6682, "lr": 1.3641618497109828e-05, "epoch": 0.34104046242774566, "percentage": 6.82, "elapsed_time": "0:47:00", "remaining_time": "10:42:09"}
+{"current_steps": 119, "total_steps": 1730, "loss": 0.6923, "lr": 1.3757225433526014e-05, "epoch": 0.3439306358381503, "percentage": 6.88, "elapsed_time": "0:47:24", "remaining_time": "10:41:47"}
+{"current_steps": 120, "total_steps": 1730, "loss": 0.7202, "lr": 1.3872832369942197e-05, "epoch": 0.3468208092485549, "percentage": 6.94, "elapsed_time": "0:47:48", "remaining_time": "10:41:23"}
+{"current_steps": 121, "total_steps": 1730, "loss": 0.6936, "lr": 1.3988439306358383e-05, "epoch": 0.34971098265895956, "percentage": 6.99, "elapsed_time": "0:48:11", "remaining_time": "10:40:48"}
+{"current_steps": 122, "total_steps": 1730, "loss": 0.6995, "lr": 1.4104046242774567e-05, "epoch": 0.35260115606936415, "percentage": 7.05, "elapsed_time": "0:48:35", "remaining_time": "10:40:29"}
+{"current_steps": 123, "total_steps": 1730, "loss": 0.6927, "lr": 1.4219653179190754e-05, "epoch": 0.3554913294797688, "percentage": 7.11, "elapsed_time": "0:48:59", "remaining_time": "10:40:07"}
+{"current_steps": 124, "total_steps": 1730, "loss": 0.7048, "lr": 1.4335260115606936e-05, "epoch": 0.3583815028901734, "percentage": 7.17, "elapsed_time": "0:49:24", "remaining_time": "10:39:52"}
+{"current_steps": 125, "total_steps": 1730, "loss": 0.6681, "lr": 1.4450867052023123e-05, "epoch": 0.36127167630057805, "percentage": 7.23, "elapsed_time": "0:49:46", "remaining_time": "10:39:05"}
+{"current_steps": 126, "total_steps": 1730, "loss": 0.707, "lr": 1.4566473988439307e-05, "epoch": 0.36416184971098264, "percentage": 7.28, "elapsed_time": "0:50:10", "remaining_time": "10:38:45"}
+{"current_steps": 127, "total_steps": 1730, "loss": 0.6886, "lr": 1.4682080924855493e-05, "epoch": 0.3670520231213873, "percentage": 7.34, "elapsed_time": "0:50:33", "remaining_time": "10:38:15"}
+{"current_steps": 128, "total_steps": 1730, "loss": 0.7056, "lr": 1.4797687861271676e-05, "epoch": 0.3699421965317919, "percentage": 7.4, "elapsed_time": "0:50:56", "remaining_time": "10:37:35"}
+{"current_steps": 129, "total_steps": 1730, "loss": 0.691, "lr": 1.4913294797687862e-05, "epoch": 0.37283236994219654, "percentage": 7.46, "elapsed_time": "0:51:18", "remaining_time": "10:36:42"}
+{"current_steps": 130, "total_steps": 1730, "loss": 0.6827, "lr": 1.5028901734104047e-05, "epoch": 0.37572254335260113, "percentage": 7.51, "elapsed_time": "0:51:41", "remaining_time": "10:36:11"}
+{"current_steps": 131, "total_steps": 1730, "loss": 0.6998, "lr": 1.5144508670520233e-05, "epoch": 0.3786127167630058, "percentage": 7.57, "elapsed_time": "0:52:06", "remaining_time": "10:36:06"}
+{"current_steps": 132, "total_steps": 1730, "loss": 0.705, "lr": 1.5260115606936418e-05, "epoch": 0.3815028901734104, "percentage": 7.63, "elapsed_time": "0:52:30", "remaining_time": "10:35:36"}
+{"current_steps": 133, "total_steps": 1730, "loss": 0.7163, "lr": 1.5375722543352604e-05, "epoch": 0.38439306358381503, "percentage": 7.69, "elapsed_time": "0:52:54", "remaining_time": "10:35:13"}
+{"current_steps": 134, "total_steps": 1730, "loss": 0.6882, "lr": 1.5491329479768787e-05, "epoch": 0.3872832369942196, "percentage": 7.75, "elapsed_time": "0:53:18", "remaining_time": "10:34:56"}
+{"current_steps": 135, "total_steps": 1730, "loss": 0.7018, "lr": 1.5606936416184973e-05, "epoch": 0.3901734104046243, "percentage": 7.8, "elapsed_time": "0:53:41", "remaining_time": "10:34:22"}
+{"current_steps": 136, "total_steps": 1730, "loss": 0.697, "lr": 1.572254335260116e-05, "epoch": 0.3930635838150289, "percentage": 7.86, "elapsed_time": "0:54:06", "remaining_time": "10:34:08"}
+{"current_steps": 137, "total_steps": 1730, "loss": 0.6914, "lr": 1.5838150289017342e-05, "epoch": 0.3959537572254335, "percentage": 7.92, "elapsed_time": "0:54:28", "remaining_time": "10:33:25"}
+{"current_steps": 138, "total_steps": 1730, "loss": 0.706, "lr": 1.5953757225433528e-05, "epoch": 0.3988439306358382, "percentage": 7.98, "elapsed_time": "0:54:51", "remaining_time": "10:32:53"}
+{"current_steps": 139, "total_steps": 1730, "loss": 0.6902, "lr": 1.606936416184971e-05, "epoch": 0.40173410404624277, "percentage": 8.03, "elapsed_time": "0:55:14", "remaining_time": "10:32:22"}
+{"current_steps": 140, "total_steps": 1730, "loss": 0.6893, "lr": 1.6184971098265897e-05, "epoch": 0.4046242774566474, "percentage": 8.09, "elapsed_time": "0:55:38", "remaining_time": "10:31:54"}
+{"current_steps": 141, "total_steps": 1730, "loss": 0.6977, "lr": 1.6300578034682083e-05, "epoch": 0.407514450867052, "percentage": 8.15, "elapsed_time": "0:56:01", "remaining_time": "10:31:19"}
+{"current_steps": 142, "total_steps": 1730, "loss": 0.6668, "lr": 1.6416184971098266e-05, "epoch": 0.41040462427745666, "percentage": 8.21, "elapsed_time": "0:56:25", "remaining_time": "10:30:56"}
+{"current_steps": 143, "total_steps": 1730, "loss": 0.7113, "lr": 1.6531791907514452e-05, "epoch": 0.41329479768786126, "percentage": 8.27, "elapsed_time": "0:56:49", "remaining_time": "10:30:36"}
+{"current_steps": 144, "total_steps": 1730, "loss": 0.7026, "lr": 1.664739884393064e-05, "epoch": 0.4161849710982659, "percentage": 8.32, "elapsed_time": "0:57:14", "remaining_time": "10:30:28"}
+{"current_steps": 145, "total_steps": 1730, "loss": 0.6878, "lr": 1.676300578034682e-05, "epoch": 0.4190751445086705, "percentage": 8.38, "elapsed_time": "0:57:37", "remaining_time": "10:29:53"}
+{"current_steps": 146, "total_steps": 1730, "loss": 0.6796, "lr": 1.6878612716763008e-05, "epoch": 0.42196531791907516, "percentage": 8.44, "elapsed_time": "0:58:02", "remaining_time": "10:29:40"}
+{"current_steps": 147, "total_steps": 1730, "loss": 0.7025, "lr": 1.699421965317919e-05, "epoch": 0.42485549132947975, "percentage": 8.5, "elapsed_time": "0:58:25", "remaining_time": "10:29:07"}
+{"current_steps": 148, "total_steps": 1730, "loss": 0.6874, "lr": 1.7109826589595377e-05, "epoch": 0.4277456647398844, "percentage": 8.55, "elapsed_time": "0:58:48", "remaining_time": "10:28:40"}
+{"current_steps": 149, "total_steps": 1730, "loss": 0.6868, "lr": 1.722543352601156e-05, "epoch": 0.430635838150289, "percentage": 8.61, "elapsed_time": "0:59:11", "remaining_time": "10:28:08"}
+{"current_steps": 150, "total_steps": 1730, "loss": 0.6938, "lr": 1.7341040462427746e-05, "epoch": 0.43352601156069365, "percentage": 8.67, "elapsed_time": "0:59:36", "remaining_time": "10:27:52"}
+{"current_steps": 151, "total_steps": 1730, "loss": 0.6899, "lr": 1.7456647398843932e-05, "epoch": 0.43641618497109824, "percentage": 8.73, "elapsed_time": "0:59:59", "remaining_time": "10:27:20"}
+{"current_steps": 152, "total_steps": 1730, "loss": 0.7028, "lr": 1.7572254335260118e-05, "epoch": 0.4393063583815029, "percentage": 8.79, "elapsed_time": "1:00:23", "remaining_time": "10:26:55"}
+{"current_steps": 153, "total_steps": 1730, "loss": 0.7028, "lr": 1.76878612716763e-05, "epoch": 0.4421965317919075, "percentage": 8.84, "elapsed_time": "1:00:48", "remaining_time": "10:26:43"}
+{"current_steps": 154, "total_steps": 1730, "loss": 0.6727, "lr": 1.7803468208092487e-05, "epoch": 0.44508670520231214, "percentage": 8.9, "elapsed_time": "1:01:11", "remaining_time": "10:26:16"}
+{"current_steps": 155, "total_steps": 1730, "loss": 0.6922, "lr": 1.7919075144508673e-05, "epoch": 0.4479768786127168, "percentage": 8.96, "elapsed_time": "1:01:36", "remaining_time": "10:26:04"}
+{"current_steps": 156, "total_steps": 1730, "loss": 0.6903, "lr": 1.8034682080924856e-05, "epoch": 0.4508670520231214, "percentage": 9.02, "elapsed_time": "1:02:02", "remaining_time": "10:25:57"}
+{"current_steps": 157, "total_steps": 1730, "loss": 0.6819, "lr": 1.8150289017341043e-05, "epoch": 0.45375722543352603, "percentage": 9.08, "elapsed_time": "1:02:27", "remaining_time": "10:25:42"}
+{"current_steps": 158, "total_steps": 1730, "loss": 0.7148, "lr": 1.8265895953757225e-05, "epoch": 0.45664739884393063, "percentage": 9.13, "elapsed_time": "1:02:51", "remaining_time": "10:25:27"}
+{"current_steps": 159, "total_steps": 1730, "loss": 0.6929, "lr": 1.838150289017341e-05, "epoch": 0.4595375722543353, "percentage": 9.19, "elapsed_time": "1:03:15", "remaining_time": "10:24:56"}
+{"current_steps": 160, "total_steps": 1730, "loss": 0.6782, "lr": 1.8497109826589598e-05, "epoch": 0.4624277456647399, "percentage": 9.25, "elapsed_time": "1:03:39", "remaining_time": "10:24:41"}
+{"current_steps": 161, "total_steps": 1730, "loss": 0.6887, "lr": 1.8612716763005784e-05, "epoch": 0.4653179190751445, "percentage": 9.31, "elapsed_time": "1:04:04", "remaining_time": "10:24:27"}
+{"current_steps": 162, "total_steps": 1730, "loss": 0.6839, "lr": 1.8728323699421967e-05, "epoch": 0.4682080924855491, "percentage": 9.36, "elapsed_time": "1:04:28", "remaining_time": "10:24:04"}
+{"current_steps": 163, "total_steps": 1730, "loss": 0.6842, "lr": 1.8843930635838153e-05, "epoch": 0.47109826589595377, "percentage": 9.42, "elapsed_time": "1:04:51", "remaining_time": "10:23:35"}
+{"current_steps": 164, "total_steps": 1730, "loss": 0.6988, "lr": 1.8959537572254336e-05, "epoch": 0.47398843930635837, "percentage": 9.48, "elapsed_time": "1:05:14", "remaining_time": "10:22:55"}
+{"current_steps": 165, "total_steps": 1730, "loss": 0.6887, "lr": 1.9075144508670522e-05, "epoch": 0.476878612716763, "percentage": 9.54, "elapsed_time": "1:05:39", "remaining_time": "10:22:42"}
+{"current_steps": 166, "total_steps": 1730, "loss": 0.6952, "lr": 1.9190751445086705e-05, "epoch": 0.4797687861271676, "percentage": 9.6, "elapsed_time": "1:06:03", "remaining_time": "10:22:26"}
+{"current_steps": 167, "total_steps": 1730, "loss": 0.6602, "lr": 1.930635838150289e-05, "epoch": 0.48265895953757226, "percentage": 9.65, "elapsed_time": "1:06:26", "remaining_time": "10:21:53"}
+{"current_steps": 168, "total_steps": 1730, "loss": 0.696, "lr": 1.9421965317919077e-05, "epoch": 0.48554913294797686, "percentage": 9.71, "elapsed_time": "1:06:48", "remaining_time": "10:21:06"}
+{"current_steps": 169, "total_steps": 1730, "loss": 0.6959, "lr": 1.9537572254335264e-05, "epoch": 0.4884393063583815, "percentage": 9.77, "elapsed_time": "1:07:11", "remaining_time": "10:20:34"}
+{"current_steps": 170, "total_steps": 1730, "loss": 0.6751, "lr": 1.9653179190751446e-05, "epoch": 0.4913294797687861, "percentage": 9.83, "elapsed_time": "1:07:35", "remaining_time": "10:20:19"}
+{"current_steps": 171, "total_steps": 1730, "loss": 0.696, "lr": 1.9768786127167633e-05, "epoch": 0.49421965317919075, "percentage": 9.88, "elapsed_time": "1:07:58", "remaining_time": "10:19:44"}
+{"current_steps": 172, "total_steps": 1730, "loss": 0.7099, "lr": 1.9884393063583815e-05, "epoch": 0.49710982658959535, "percentage": 9.94, "elapsed_time": "1:08:22", "remaining_time": "10:19:18"}
+{"current_steps": 173, "total_steps": 1730, "loss": 0.6689, "lr": 2e-05, "epoch": 0.5, "percentage": 10.0, "elapsed_time": "1:08:47", "remaining_time": "10:19:03"}
+{"current_steps": 174, "total_steps": 1730, "loss": 0.666, "lr": 1.9999979644003047e-05, "epoch": 0.5028901734104047, "percentage": 10.06, "elapsed_time": "1:09:12", "remaining_time": "10:18:50"}
+{"current_steps": 175, "total_steps": 1730, "loss": 0.7095, "lr": 1.9999918576095053e-05, "epoch": 0.5057803468208093, "percentage": 10.12, "elapsed_time": "1:09:33", "remaining_time": "10:18:07"}
+{"current_steps": 176, "total_steps": 1730, "loss": 0.6636, "lr": 1.9999816796524642e-05, "epoch": 0.5086705202312138, "percentage": 10.17, "elapsed_time": "1:09:58", "remaining_time": "10:17:54"}
+{"current_steps": 177, "total_steps": 1730, "loss": 0.6844, "lr": 1.9999674305706178e-05, "epoch": 0.5115606936416185, "percentage": 10.23, "elapsed_time": "1:10:21", "remaining_time": "10:17:15"}
+{"current_steps": 178, "total_steps": 1730, "loss": 0.708, "lr": 1.999949110421977e-05, "epoch": 0.5144508670520231, "percentage": 10.29, "elapsed_time": "1:10:47", "remaining_time": "10:17:11"}
+{"current_steps": 179, "total_steps": 1730, "loss": 0.7004, "lr": 1.999926719281127e-05, "epoch": 0.5173410404624278, "percentage": 10.35, "elapsed_time": "1:11:11", "remaining_time": "10:16:48"}
+{"current_steps": 180, "total_steps": 1730, "loss": 0.6768, "lr": 1.9999002572392253e-05, "epoch": 0.5202312138728323, "percentage": 10.4, "elapsed_time": "1:11:33", "remaining_time": "10:16:15"}
+{"current_steps": 181, "total_steps": 1730, "loss": 0.6909, "lr": 1.9998697244040062e-05, "epoch": 0.523121387283237, "percentage": 10.46, "elapsed_time": "1:11:57", "remaining_time": "10:15:49"}
+{"current_steps": 182, "total_steps": 1730, "loss": 0.686, "lr": 1.9998351208997734e-05, "epoch": 0.5260115606936416, "percentage": 10.52, "elapsed_time": "1:12:21", "remaining_time": "10:15:25"}
+{"current_steps": 183, "total_steps": 1730, "loss": 0.6785, "lr": 1.9997964468674055e-05, "epoch": 0.5289017341040463, "percentage": 10.58, "elapsed_time": "1:12:44", "remaining_time": "10:14:52"}
+{"current_steps": 184, "total_steps": 1730, "loss": 0.6852, "lr": 1.999753702464352e-05, "epoch": 0.5317919075144508, "percentage": 10.64, "elapsed_time": "1:13:07", "remaining_time": "10:14:23"}
+{"current_steps": 185, "total_steps": 1730, "loss": 0.686, "lr": 1.9997068878646332e-05, "epoch": 0.5346820809248555, "percentage": 10.69, "elapsed_time": "1:13:33", "remaining_time": "10:14:14"}
+{"current_steps": 186, "total_steps": 1730, "loss": 0.6994, "lr": 1.999656003258842e-05, "epoch": 0.5375722543352601, "percentage": 10.75, "elapsed_time": "1:13:56", "remaining_time": "10:13:44"}
+{"current_steps": 187, "total_steps": 1730, "loss": 0.6895, "lr": 1.9996010488541384e-05, "epoch": 0.5404624277456648, "percentage": 10.81, "elapsed_time": "1:14:18", "remaining_time": "10:13:10"}
+{"current_steps": 188, "total_steps": 1730, "loss": 0.6929, "lr": 1.9995420248742534e-05, "epoch": 0.5433526011560693, "percentage": 10.87, "elapsed_time": "1:14:42", "remaining_time": "10:12:43"}
+{"current_steps": 189, "total_steps": 1730, "loss": 0.6971, "lr": 1.9994789315594854e-05, "epoch": 0.546242774566474, "percentage": 10.92, "elapsed_time": "1:15:05", "remaining_time": "10:12:18"}
+{"current_steps": 190, "total_steps": 1730, "loss": 0.6864, "lr": 1.9994117691667e-05, "epoch": 0.5491329479768786, "percentage": 10.98, "elapsed_time": "1:15:29", "remaining_time": "10:11:54"}
+{"current_steps": 191, "total_steps": 1730, "loss": 0.6997, "lr": 1.999340537969329e-05, "epoch": 0.5520231213872833, "percentage": 11.04, "elapsed_time": "1:15:53", "remaining_time": "10:11:28"}
+{"current_steps": 192, "total_steps": 1730, "loss": 0.6858, "lr": 1.9992652382573677e-05, "epoch": 0.5549132947976878, "percentage": 11.1, "elapsed_time": "1:16:19", "remaining_time": "10:11:21"}
+{"current_steps": 193, "total_steps": 1730, "loss": 0.7016, "lr": 1.999185870337377e-05, "epoch": 0.5578034682080925, "percentage": 11.16, "elapsed_time": "1:16:42", "remaining_time": "10:10:49"}
+{"current_steps": 194, "total_steps": 1730, "loss": 0.6755, "lr": 1.9991024345324793e-05, "epoch": 0.5606936416184971, "percentage": 11.21, "elapsed_time": "1:17:06", "remaining_time": "10:10:30"}
+{"current_steps": 195, "total_steps": 1730, "loss": 0.6709, "lr": 1.9990149311823586e-05, "epoch": 0.5635838150289018, "percentage": 11.27, "elapsed_time": "1:17:29", "remaining_time": "10:10:01"}
+{"current_steps": 196, "total_steps": 1730, "loss": 0.6916, "lr": 1.9989233606432587e-05, "epoch": 0.5664739884393064, "percentage": 11.33, "elapsed_time": "1:17:51", "remaining_time": "10:09:18"}
+{"current_steps": 197, "total_steps": 1730, "loss": 0.6607, "lr": 1.9988277232879806e-05, "epoch": 0.569364161849711, "percentage": 11.39, "elapsed_time": "1:18:14", "remaining_time": "10:08:54"}
+{"current_steps": 198, "total_steps": 1730, "loss": 0.6693, "lr": 1.998728019505884e-05, "epoch": 0.5722543352601156, "percentage": 11.45, "elapsed_time": "1:18:37", "remaining_time": "10:08:21"}
+{"current_steps": 199, "total_steps": 1730, "loss": 0.6801, "lr": 1.9986242497028823e-05, "epoch": 0.5751445086705202, "percentage": 11.5, "elapsed_time": "1:19:01", "remaining_time": "10:08:02"}
+{"current_steps": 200, "total_steps": 1730, "loss": 0.6726, "lr": 1.9985164143014433e-05, "epoch": 0.5780346820809249, "percentage": 11.56, "elapsed_time": "1:19:25", "remaining_time": "10:07:38"}
+{"current_steps": 201, "total_steps": 1730, "loss": 0.6865, "lr": 1.9984045137405864e-05, "epoch": 0.5809248554913294, "percentage": 11.62, "elapsed_time": "1:19:48", "remaining_time": "10:07:09"}
+{"current_steps": 202, "total_steps": 1730, "loss": 0.6453, "lr": 1.9982885484758813e-05, "epoch": 0.5838150289017341, "percentage": 11.68, "elapsed_time": "1:20:13", "remaining_time": "10:06:51"}
+{"current_steps": 203, "total_steps": 1730, "loss": 0.6843, "lr": 1.9981685189794457e-05, "epoch": 0.5867052023121387, "percentage": 11.73, "elapsed_time": "1:20:34", "remaining_time": "10:06:08"}
+{"current_steps": 204, "total_steps": 1730, "loss": 0.6981, "lr": 1.9980444257399428e-05, "epoch": 0.5895953757225434, "percentage": 11.79, "elapsed_time": "1:20:56", "remaining_time": "10:05:31"}
+{"current_steps": 205, "total_steps": 1730, "loss": 0.6855, "lr": 1.9979162692625817e-05, "epoch": 0.5924855491329479, "percentage": 11.85, "elapsed_time": "1:21:18", "remaining_time": "10:04:53"}
+{"current_steps": 206, "total_steps": 1730, "loss": 0.6869, "lr": 1.9977840500691133e-05, "epoch": 0.5953757225433526, "percentage": 11.91, "elapsed_time": "1:21:42", "remaining_time": "10:04:25"}
+{"current_steps": 207, "total_steps": 1730, "loss": 0.6627, "lr": 1.9976477686978274e-05, "epoch": 0.5982658959537572, "percentage": 11.97, "elapsed_time": "1:22:05", "remaining_time": "10:03:56"}
+{"current_steps": 208, "total_steps": 1730, "loss": 0.6831, "lr": 1.9975074257035533e-05, "epoch": 0.6011560693641619, "percentage": 12.02, "elapsed_time": "1:22:29", "remaining_time": "10:03:37"}
+{"current_steps": 209, "total_steps": 1730, "loss": 0.6689, "lr": 1.9973630216576547e-05, "epoch": 0.6040462427745664, "percentage": 12.08, "elapsed_time": "1:22:53", "remaining_time": "10:03:17"}
+{"current_steps": 210, "total_steps": 1730, "loss": 0.6975, "lr": 1.9972145571480296e-05, "epoch": 0.6069364161849711, "percentage": 12.14, "elapsed_time": "1:23:19", "remaining_time": "10:03:07"}
+{"current_steps": 211, "total_steps": 1730, "loss": 0.6528, "lr": 1.997062032779107e-05, "epoch": 0.6098265895953757, "percentage": 12.2, "elapsed_time": "1:23:43", "remaining_time": "10:02:45"}
+{"current_steps": 212, "total_steps": 1730, "loss": 0.6849, "lr": 1.9969054491718437e-05, "epoch": 0.6127167630057804, "percentage": 12.25, "elapsed_time": "1:24:04", "remaining_time": "10:02:03"}
+{"current_steps": 213, "total_steps": 1730, "loss": 0.6746, "lr": 1.9967448069637224e-05, "epoch": 0.615606936416185, "percentage": 12.31, "elapsed_time": "1:24:27", "remaining_time": "10:01:30"}
+{"current_steps": 214, "total_steps": 1730, "loss": 0.6556, "lr": 1.9965801068087504e-05, "epoch": 0.6184971098265896, "percentage": 12.37, "elapsed_time": "1:24:50", "remaining_time": "10:00:59"}
+{"current_steps": 215, "total_steps": 1730, "loss": 0.6805, "lr": 1.996411349377454e-05, "epoch": 0.6213872832369942, "percentage": 12.43, "elapsed_time": "1:25:12", "remaining_time": "10:00:28"}
+{"current_steps": 216, "total_steps": 1730, "loss": 0.6675, "lr": 1.9962385353568787e-05, "epoch": 0.6242774566473989, "percentage": 12.49, "elapsed_time": "1:25:35", "remaining_time": "9:59:54"}
+{"current_steps": 217, "total_steps": 1730, "loss": 0.6406, "lr": 1.9960616654505852e-05, "epoch": 0.6271676300578035, "percentage": 12.54, "elapsed_time": "1:25:58", "remaining_time": "9:59:29"}
+{"current_steps": 218, "total_steps": 1730, "loss": 0.6661, "lr": 1.9958807403786452e-05, "epoch": 0.630057803468208, "percentage": 12.6, "elapsed_time": "1:26:22", "remaining_time": "9:59:03"}
+{"current_steps": 219, "total_steps": 1730, "loss": 0.6556, "lr": 1.995695760877642e-05, "epoch": 0.6329479768786127, "percentage": 12.66, "elapsed_time": "1:26:46", "remaining_time": "9:58:40"}
+{"current_steps": 220, "total_steps": 1730, "loss": 0.6687, "lr": 1.9955067277006633e-05, "epoch": 0.6358381502890174, "percentage": 12.72, "elapsed_time": "1:27:10", "remaining_time": "9:58:22"}
+{"current_steps": 221, "total_steps": 1730, "loss": 0.6872, "lr": 1.9953136416173005e-05, "epoch": 0.638728323699422, "percentage": 12.77, "elapsed_time": "1:27:33", "remaining_time": "9:57:50"}
+{"current_steps": 222, "total_steps": 1730, "loss": 0.6606, "lr": 1.9951165034136465e-05, "epoch": 0.6416184971098265, "percentage": 12.83, "elapsed_time": "1:27:57", "remaining_time": "9:57:28"}
+{"current_steps": 223, "total_steps": 1730, "loss": 0.6727, "lr": 1.9949153138922897e-05, "epoch": 0.6445086705202312, "percentage": 12.89, "elapsed_time": "1:28:21", "remaining_time": "9:57:07"}
+{"current_steps": 224, "total_steps": 1730, "loss": 0.6903, "lr": 1.9947100738723126e-05, "epoch": 0.6473988439306358, "percentage": 12.95, "elapsed_time": "1:28:46", "remaining_time": "9:56:48"}
+{"current_steps": 225, "total_steps": 1730, "loss": 0.648, "lr": 1.9945007841892886e-05, "epoch": 0.6502890173410405, "percentage": 13.01, "elapsed_time": "1:29:08", "remaining_time": "9:56:17"}
+{"current_steps": 226, "total_steps": 1730, "loss": 0.6723, "lr": 1.994287445695277e-05, "epoch": 0.653179190751445, "percentage": 13.06, "elapsed_time": "1:29:34", "remaining_time": "9:56:04"}
+{"current_steps": 227, "total_steps": 1730, "loss": 0.6951, "lr": 1.9940700592588228e-05, "epoch": 0.6560693641618497, "percentage": 13.12, "elapsed_time": "1:29:57", "remaining_time": "9:55:37"}
+{"current_steps": 228, "total_steps": 1730, "loss": 0.6521, "lr": 1.9938486257649483e-05, "epoch": 0.6589595375722543, "percentage": 13.18, "elapsed_time": "1:30:22", "remaining_time": "9:55:19"}
+{"current_steps": 229, "total_steps": 1730, "loss": 0.6786, "lr": 1.9936231461151535e-05, "epoch": 0.661849710982659, "percentage": 13.24, "elapsed_time": "1:30:45", "remaining_time": "9:54:52"}
+{"current_steps": 230, "total_steps": 1730, "loss": 0.6619, "lr": 1.9933936212274115e-05, "epoch": 0.6647398843930635, "percentage": 13.29, "elapsed_time": "1:31:09", "remaining_time": "9:54:30"}
+{"current_steps": 231, "total_steps": 1730, "loss": 0.6549, "lr": 1.9931600520361637e-05, "epoch": 0.6676300578034682, "percentage": 13.35, "elapsed_time": "1:31:30", "remaining_time": "9:53:50"}
+{"current_steps": 232, "total_steps": 1730, "loss": 0.6781, "lr": 1.9929224394923167e-05, "epoch": 0.6705202312138728, "percentage": 13.41, "elapsed_time": "1:31:55", "remaining_time": "9:53:33"}
+{"current_steps": 233, "total_steps": 1730, "loss": 0.6814, "lr": 1.9926807845632385e-05, "epoch": 0.6734104046242775, "percentage": 13.47, "elapsed_time": "1:32:18", "remaining_time": "9:53:07"}
+{"current_steps": 234, "total_steps": 1730, "loss": 0.6834, "lr": 1.9924350882327545e-05, "epoch": 0.6763005780346821, "percentage": 13.53, "elapsed_time": "1:32:40", "remaining_time": "9:52:27"}
+{"current_steps": 235, "total_steps": 1730, "loss": 0.6735, "lr": 1.992185351501144e-05, "epoch": 0.6791907514450867, "percentage": 13.58, "elapsed_time": "1:33:01", "remaining_time": "9:51:45"}
+{"current_steps": 236, "total_steps": 1730, "loss": 0.6593, "lr": 1.9919315753851343e-05, "epoch": 0.6820809248554913, "percentage": 13.64, "elapsed_time": "1:33:24", "remaining_time": "9:51:19"}
+{"current_steps": 237, "total_steps": 1730, "loss": 0.67, "lr": 1.991673760917899e-05, "epoch": 0.684971098265896, "percentage": 13.7, "elapsed_time": "1:33:49", "remaining_time": "9:51:01"}
+{"current_steps": 238, "total_steps": 1730, "loss": 0.6785, "lr": 1.991411909149052e-05, "epoch": 0.6878612716763006, "percentage": 13.76, "elapsed_time": "1:34:13", "remaining_time": "9:50:41"}
+{"current_steps": 239, "total_steps": 1730, "loss": 0.6795, "lr": 1.9911460211446445e-05, "epoch": 0.6907514450867052, "percentage": 13.82, "elapsed_time": "1:34:37", "remaining_time": "9:50:17"}
+{"current_steps": 240, "total_steps": 1730, "loss": 0.6641, "lr": 1.990876097987159e-05, "epoch": 0.6936416184971098, "percentage": 13.87, "elapsed_time": "1:35:00", "remaining_time": "9:49:50"}
+{"current_steps": 241, "total_steps": 1730, "loss": 0.6738, "lr": 1.9906021407755064e-05, "epoch": 0.6965317919075145, "percentage": 13.93, "elapsed_time": "1:35:24", "remaining_time": "9:49:30"}
+{"current_steps": 242, "total_steps": 1730, "loss": 0.6688, "lr": 1.990324150625022e-05, "epoch": 0.6994219653179191, "percentage": 13.99, "elapsed_time": "1:35:47", "remaining_time": "9:49:02"}
+{"current_steps": 243, "total_steps": 1730, "loss": 0.6769, "lr": 1.9900421286674582e-05, "epoch": 0.7023121387283237, "percentage": 14.05, "elapsed_time": "1:36:13", "remaining_time": "9:48:47"}
+{"current_steps": 244, "total_steps": 1730, "loss": 0.667, "lr": 1.9897560760509834e-05, "epoch": 0.7052023121387283, "percentage": 14.1, "elapsed_time": "1:36:36", "remaining_time": "9:48:21"}
+{"current_steps": 245, "total_steps": 1730, "loss": 0.6734, "lr": 1.989465993940174e-05, "epoch": 0.708092485549133, "percentage": 14.16, "elapsed_time": "1:36:59", "remaining_time": "9:47:51"}
+{"current_steps": 246, "total_steps": 1730, "loss": 0.662, "lr": 1.9891718835160128e-05, "epoch": 0.7109826589595376, "percentage": 14.22, "elapsed_time": "1:37:20", "remaining_time": "9:47:14"}
+{"current_steps": 247, "total_steps": 1730, "loss": 0.6875, "lr": 1.9888737459758817e-05, "epoch": 0.7138728323699421, "percentage": 14.28, "elapsed_time": "1:37:44", "remaining_time": "9:46:52"}
+{"current_steps": 248, "total_steps": 1730, "loss": 0.6548, "lr": 1.9885715825335584e-05, "epoch": 0.7167630057803468, "percentage": 14.34, "elapsed_time": "1:38:08", "remaining_time": "9:46:29"}
+{"current_steps": 249, "total_steps": 1730, "loss": 0.6954, "lr": 1.9882653944192095e-05, "epoch": 0.7196531791907514, "percentage": 14.39, "elapsed_time": "1:38:32", "remaining_time": "9:46:07"}
+{"current_steps": 250, "total_steps": 1730, "loss": 0.6615, "lr": 1.9879551828793893e-05, "epoch": 0.7225433526011561, "percentage": 14.45, "elapsed_time": "1:38:56", "remaining_time": "9:45:45"}
+{"current_steps": 251, "total_steps": 1730, "loss": 0.6884, "lr": 1.98764094917703e-05, "epoch": 0.7254335260115607, "percentage": 14.51, "elapsed_time": "1:39:19", "remaining_time": "9:45:15"}
+{"current_steps": 252, "total_steps": 1730, "loss": 0.6705, "lr": 1.9873226945914394e-05, "epoch": 0.7283236994219653, "percentage": 14.57, "elapsed_time": "1:39:42", "remaining_time": "9:44:45"}
+{"current_steps": 253, "total_steps": 1730, "loss": 0.6749, "lr": 1.9870004204182962e-05, "epoch": 0.7312138728323699, "percentage": 14.62, "elapsed_time": "1:40:03", "remaining_time": "9:44:08"}
+{"current_steps": 254, "total_steps": 1730, "loss": 0.6542, "lr": 1.986674127969642e-05, "epoch": 0.7341040462427746, "percentage": 14.68, "elapsed_time": "1:40:27", "remaining_time": "9:43:44"}
+{"current_steps": 255, "total_steps": 1730, "loss": 0.6766, "lr": 1.986343818573879e-05, "epoch": 0.7369942196531792, "percentage": 14.74, "elapsed_time": "1:40:51", "remaining_time": "9:43:20"}
+{"current_steps": 256, "total_steps": 1730, "loss": 0.6674, "lr": 1.986009493575763e-05, "epoch": 0.7398843930635838, "percentage": 14.8, "elapsed_time": "1:41:15", "remaining_time": "9:43:01"}
+{"current_steps": 257, "total_steps": 1730, "loss": 0.6727, "lr": 1.985671154336396e-05, "epoch": 0.7427745664739884, "percentage": 14.86, "elapsed_time": "1:41:39", "remaining_time": "9:42:40"}
+{"current_steps": 258, "total_steps": 1730, "loss": 0.669, "lr": 1.9853288022332267e-05, "epoch": 0.7456647398843931, "percentage": 14.91, "elapsed_time": "1:42:03", "remaining_time": "9:42:18"}
+{"current_steps": 259, "total_steps": 1730, "loss": 0.6675, "lr": 1.9849824386600372e-05, "epoch": 0.7485549132947977, "percentage": 14.97, "elapsed_time": "1:42:27", "remaining_time": "9:41:53"}
+{"current_steps": 260, "total_steps": 1730, "loss": 0.675, "lr": 1.984632065026943e-05, "epoch": 0.7514450867052023, "percentage": 15.03, "elapsed_time": "1:42:51", "remaining_time": "9:41:30"}
+{"current_steps": 261, "total_steps": 1730, "loss": 0.6704, "lr": 1.9842776827603858e-05, "epoch": 0.7543352601156069, "percentage": 15.09, "elapsed_time": "1:43:14", "remaining_time": "9:41:03"}
+{"current_steps": 262, "total_steps": 1730, "loss": 0.6922, "lr": 1.9839192933031253e-05, "epoch": 0.7572254335260116, "percentage": 15.14, "elapsed_time": "1:43:37", "remaining_time": "9:40:36"}
+{"current_steps": 263, "total_steps": 1730, "loss": 0.6667, "lr": 1.9835568981142376e-05, "epoch": 0.7601156069364162, "percentage": 15.2, "elapsed_time": "1:44:00", "remaining_time": "9:40:06"}
+{"current_steps": 264, "total_steps": 1730, "loss": 0.6702, "lr": 1.9831904986691045e-05, "epoch": 0.7630057803468208, "percentage": 15.26, "elapsed_time": "1:44:22", "remaining_time": "9:39:37"}
+{"current_steps": 265, "total_steps": 1730, "loss": 0.6732, "lr": 1.9828200964594125e-05, "epoch": 0.7658959537572254, "percentage": 15.32, "elapsed_time": "1:44:46", "remaining_time": "9:39:14"}
+{"current_steps": 266, "total_steps": 1730, "loss": 0.6823, "lr": 1.9824456929931417e-05, "epoch": 0.7687861271676301, "percentage": 15.38, "elapsed_time": "1:45:10", "remaining_time": "9:38:52"}
+{"current_steps": 267, "total_steps": 1730, "loss": 0.6739, "lr": 1.982067289794564e-05, "epoch": 0.7716763005780347, "percentage": 15.43, "elapsed_time": "1:45:32", "remaining_time": "9:38:17"}
+{"current_steps": 268, "total_steps": 1730, "loss": 0.6619, "lr": 1.9816848884042342e-05, "epoch": 0.7745664739884393, "percentage": 15.49, "elapsed_time": "1:45:55", "remaining_time": "9:37:53"}
+{"current_steps": 269, "total_steps": 1730, "loss": 0.6618, "lr": 1.9812984903789845e-05, "epoch": 0.7774566473988439, "percentage": 15.55, "elapsed_time": "1:46:20", "remaining_time": "9:37:32"}
+{"current_steps": 270, "total_steps": 1730, "loss": 0.6831, "lr": 1.9809080972919182e-05, "epoch": 0.7803468208092486, "percentage": 15.61, "elapsed_time": "1:46:44", "remaining_time": "9:37:10"}
+{"current_steps": 271, "total_steps": 1730, "loss": 0.6717, "lr": 1.9805137107324034e-05, "epoch": 0.7832369942196532, "percentage": 15.66, "elapsed_time": "1:47:07", "remaining_time": "9:36:43"}
+{"current_steps": 272, "total_steps": 1730, "loss": 0.6666, "lr": 1.9801153323060667e-05, "epoch": 0.7861271676300579, "percentage": 15.72, "elapsed_time": "1:47:31", "remaining_time": "9:36:24"}
+{"current_steps": 273, "total_steps": 1730, "loss": 0.6756, "lr": 1.9797129636347857e-05, "epoch": 0.7890173410404624, "percentage": 15.78, "elapsed_time": "1:47:55", "remaining_time": "9:36:00"}
+{"current_steps": 274, "total_steps": 1730, "loss": 0.6678, "lr": 1.979306606356684e-05, "epoch": 0.791907514450867, "percentage": 15.84, "elapsed_time": "1:48:19", "remaining_time": "9:35:39"}
+{"current_steps": 275, "total_steps": 1730, "loss": 0.6746, "lr": 1.9788962621261224e-05, "epoch": 0.7947976878612717, "percentage": 15.9, "elapsed_time": "1:48:44", "remaining_time": "9:35:21"}
+{"current_steps": 276, "total_steps": 1730, "loss": 0.6663, "lr": 1.9784819326136947e-05, "epoch": 0.7976878612716763, "percentage": 15.95, "elapsed_time": "1:49:08", "remaining_time": "9:34:58"}
+{"current_steps": 277, "total_steps": 1730, "loss": 0.6849, "lr": 1.978063619506219e-05, "epoch": 0.8005780346820809, "percentage": 16.01, "elapsed_time": "1:49:32", "remaining_time": "9:34:33"}
+{"current_steps": 278, "total_steps": 1730, "loss": 0.6833, "lr": 1.9776413245067308e-05, "epoch": 0.8034682080924855, "percentage": 16.07, "elapsed_time": "1:49:55", "remaining_time": "9:34:10"}
+{"current_steps": 279, "total_steps": 1730, "loss": 0.6777, "lr": 1.9772150493344776e-05, "epoch": 0.8063583815028902, "percentage": 16.13, "elapsed_time": "1:50:18", "remaining_time": "9:33:38"}
+{"current_steps": 280, "total_steps": 1730, "loss": 0.6652, "lr": 1.9767847957249107e-05, "epoch": 0.8092485549132948, "percentage": 16.18, "elapsed_time": "1:50:42", "remaining_time": "9:33:16"}
+{"current_steps": 281, "total_steps": 1730, "loss": 0.6551, "lr": 1.9763505654296782e-05, "epoch": 0.8121387283236994, "percentage": 16.24, "elapsed_time": "1:51:03", "remaining_time": "9:32:41"}
+{"current_steps": 282, "total_steps": 1730, "loss": 0.6629, "lr": 1.9759123602166183e-05, "epoch": 0.815028901734104, "percentage": 16.3, "elapsed_time": "1:51:28", "remaining_time": "9:32:25"}
+{"current_steps": 283, "total_steps": 1730, "loss": 0.6754, "lr": 1.9754701818697515e-05, "epoch": 0.8179190751445087, "percentage": 16.36, "elapsed_time": "1:51:50", "remaining_time": "9:31:52"}
+{"current_steps": 284, "total_steps": 1730, "loss": 0.6653, "lr": 1.9750240321892743e-05, "epoch": 0.8208092485549133, "percentage": 16.42, "elapsed_time": "1:52:14", "remaining_time": "9:31:30"}
+{"current_steps": 285, "total_steps": 1730, "loss": 0.658, "lr": 1.9745739129915508e-05, "epoch": 0.8236994219653179, "percentage": 16.47, "elapsed_time": "1:52:36", "remaining_time": "9:30:57"}
+{"current_steps": 286, "total_steps": 1730, "loss": 0.6569, "lr": 1.9741198261091067e-05, "epoch": 0.8265895953757225, "percentage": 16.53, "elapsed_time": "1:53:00", "remaining_time": "9:30:35"}
+{"current_steps": 287, "total_steps": 1730, "loss": 0.6749, "lr": 1.973661773390619e-05, "epoch": 0.8294797687861272, "percentage": 16.59, "elapsed_time": "1:53:24", "remaining_time": "9:30:10"}
+{"current_steps": 288, "total_steps": 1730, "loss": 0.6593, "lr": 1.9731997567009125e-05, "epoch": 0.8323699421965318, "percentage": 16.65, "elapsed_time": "1:53:49", "remaining_time": "9:29:57"}
+{"current_steps": 289, "total_steps": 1730, "loss": 0.6544, "lr": 1.9727337779209496e-05, "epoch": 0.8352601156069365, "percentage": 16.71, "elapsed_time": "1:54:13", "remaining_time": "9:29:33"}
+{"current_steps": 290, "total_steps": 1730, "loss": 0.6785, "lr": 1.9722638389478218e-05, "epoch": 0.838150289017341, "percentage": 16.76, "elapsed_time": "1:54:38", "remaining_time": "9:29:14"}
+{"current_steps": 291, "total_steps": 1730, "loss": 0.6581, "lr": 1.9717899416947452e-05, "epoch": 0.8410404624277457, "percentage": 16.82, "elapsed_time": "1:55:02", "remaining_time": "9:28:50"}
+{"current_steps": 292, "total_steps": 1730, "loss": 0.6596, "lr": 1.9713120880910495e-05, "epoch": 0.8439306358381503, "percentage": 16.88, "elapsed_time": "1:55:26", "remaining_time": "9:28:28"}
+{"current_steps": 293, "total_steps": 1730, "loss": 0.6785, "lr": 1.9708302800821724e-05, "epoch": 0.846820809248555, "percentage": 16.94, "elapsed_time": "1:55:50", "remaining_time": "9:28:07"}
+{"current_steps": 294, "total_steps": 1730, "loss": 0.6578, "lr": 1.97034451962965e-05, "epoch": 0.8497109826589595, "percentage": 16.99, "elapsed_time": "1:56:12", "remaining_time": "9:27:36"}
+{"current_steps": 295, "total_steps": 1730, "loss": 0.6594, "lr": 1.9698548087111104e-05, "epoch": 0.8526011560693642, "percentage": 17.05, "elapsed_time": "1:56:35", "remaining_time": "9:27:07"}
+{"current_steps": 296, "total_steps": 1730, "loss": 0.6449, "lr": 1.9693611493202637e-05, "epoch": 0.8554913294797688, "percentage": 17.11, "elapsed_time": "1:56:58", "remaining_time": "9:26:40"}
+{"current_steps": 297, "total_steps": 1730, "loss": 0.6832, "lr": 1.9688635434668962e-05, "epoch": 0.8583815028901735, "percentage": 17.17, "elapsed_time": "1:57:22", "remaining_time": "9:26:20"}
+{"current_steps": 298, "total_steps": 1730, "loss": 0.657, "lr": 1.9683619931768606e-05, "epoch": 0.861271676300578, "percentage": 17.23, "elapsed_time": "1:57:46", "remaining_time": "9:25:57"}
+{"current_steps": 299, "total_steps": 1730, "loss": 0.6463, "lr": 1.967856500492068e-05, "epoch": 0.8641618497109826, "percentage": 17.28, "elapsed_time": "1:58:10", "remaining_time": "9:25:34"}
+{"current_steps": 300, "total_steps": 1730, "loss": 0.6678, "lr": 1.96734706747048e-05, "epoch": 0.8670520231213873, "percentage": 17.34, "elapsed_time": "1:58:33", "remaining_time": "9:25:07"}
+{"current_steps": 301, "total_steps": 1730, "loss": 0.6571, "lr": 1.9668336961861004e-05, "epoch": 0.869942196531792, "percentage": 17.4, "elapsed_time": "1:58:56", "remaining_time": "9:24:41"}
+{"current_steps": 302, "total_steps": 1730, "loss": 0.6841, "lr": 1.966316388728965e-05, "epoch": 0.8728323699421965, "percentage": 17.46, "elapsed_time": "1:59:19", "remaining_time": "9:24:11"}
+{"current_steps": 303, "total_steps": 1730, "loss": 0.6673, "lr": 1.9657951472051363e-05, "epoch": 0.8757225433526011, "percentage": 17.51, "elapsed_time": "1:59:42", "remaining_time": "9:23:46"}
+{"current_steps": 304, "total_steps": 1730, "loss": 0.6799, "lr": 1.9652699737366924e-05, "epoch": 0.8786127167630058, "percentage": 17.57, "elapsed_time": "2:00:05", "remaining_time": "9:23:20"}
+{"current_steps": 305, "total_steps": 1730, "loss": 0.656, "lr": 1.964740870461719e-05, "epoch": 0.8815028901734104, "percentage": 17.63, "elapsed_time": "2:00:29", "remaining_time": "9:22:58"}
+{"current_steps": 306, "total_steps": 1730, "loss": 0.6778, "lr": 1.9642078395343015e-05, "epoch": 0.884393063583815, "percentage": 17.69, "elapsed_time": "2:00:53", "remaining_time": "9:22:33"}
+{"current_steps": 307, "total_steps": 1730, "loss": 0.6687, "lr": 1.9636708831245147e-05, "epoch": 0.8872832369942196, "percentage": 17.75, "elapsed_time": "2:01:18", "remaining_time": "9:22:18"}
+{"current_steps": 308, "total_steps": 1730, "loss": 0.6614, "lr": 1.9631300034184155e-05, "epoch": 0.8901734104046243, "percentage": 17.8, "elapsed_time": "2:01:42", "remaining_time": "9:21:54"}
+{"current_steps": 309, "total_steps": 1730, "loss": 0.6511, "lr": 1.9625852026180325e-05, "epoch": 0.8930635838150289, "percentage": 17.86, "elapsed_time": "2:02:06", "remaining_time": "9:21:34"}
+{"current_steps": 310, "total_steps": 1730, "loss": 0.6278, "lr": 1.962036482941359e-05, "epoch": 0.8959537572254336, "percentage": 17.92, "elapsed_time": "2:02:30", "remaining_time": "9:21:09"}
+{"current_steps": 311, "total_steps": 1730, "loss": 0.6527, "lr": 1.9614838466223415e-05, "epoch": 0.8988439306358381, "percentage": 17.98, "elapsed_time": "2:02:54", "remaining_time": "9:20:46"}
+{"current_steps": 312, "total_steps": 1730, "loss": 0.6713, "lr": 1.9609272959108737e-05, "epoch": 0.9017341040462428, "percentage": 18.03, "elapsed_time": "2:03:15", "remaining_time": "9:20:13"}
+{"current_steps": 313, "total_steps": 1730, "loss": 0.6687, "lr": 1.9603668330727835e-05, "epoch": 0.9046242774566474, "percentage": 18.09, "elapsed_time": "2:03:40", "remaining_time": "9:19:52"}
+{"current_steps": 314, "total_steps": 1730, "loss": 0.6601, "lr": 1.9598024603898272e-05, "epoch": 0.9075144508670521, "percentage": 18.15, "elapsed_time": "2:04:04", "remaining_time": "9:19:33"}
+{"current_steps": 315, "total_steps": 1730, "loss": 0.6636, "lr": 1.959234180159679e-05, "epoch": 0.9104046242774566, "percentage": 18.21, "elapsed_time": "2:04:29", "remaining_time": "9:19:13"}
+{"current_steps": 316, "total_steps": 1730, "loss": 0.6662, "lr": 1.95866199469592e-05, "epoch": 0.9132947976878613, "percentage": 18.27, "elapsed_time": "2:04:51", "remaining_time": "9:18:42"}
+{"current_steps": 317, "total_steps": 1730, "loss": 0.6721, "lr": 1.9580859063280326e-05, "epoch": 0.9161849710982659, "percentage": 18.32, "elapsed_time": "2:05:15", "remaining_time": "9:18:17"}
+{"current_steps": 318, "total_steps": 1730, "loss": 0.6452, "lr": 1.9575059174013865e-05, "epoch": 0.9190751445086706, "percentage": 18.38, "elapsed_time": "2:05:37", "remaining_time": "9:17:48"}
+{"current_steps": 319, "total_steps": 1730, "loss": 0.68, "lr": 1.9569220302772324e-05, "epoch": 0.9219653179190751, "percentage": 18.44, "elapsed_time": "2:06:01", "remaining_time": "9:17:26"}
+{"current_steps": 320, "total_steps": 1730, "loss": 0.6669, "lr": 1.9563342473326915e-05, "epoch": 0.9248554913294798, "percentage": 18.5, "elapsed_time": "2:06:25", "remaining_time": "9:17:02"}
+{"current_steps": 321, "total_steps": 1730, "loss": 0.6569, "lr": 1.955742570960745e-05, "epoch": 0.9277456647398844, "percentage": 18.55, "elapsed_time": "2:06:48", "remaining_time": "9:16:36"}
+{"current_steps": 322, "total_steps": 1730, "loss": 0.6612, "lr": 1.9551470035702254e-05, "epoch": 0.930635838150289, "percentage": 18.61, "elapsed_time": "2:07:12", "remaining_time": "9:16:14"}
+{"current_steps": 323, "total_steps": 1730, "loss": 0.6542, "lr": 1.9545475475858068e-05, "epoch": 0.9335260115606936, "percentage": 18.67, "elapsed_time": "2:07:36", "remaining_time": "9:15:53"}
+{"current_steps": 324, "total_steps": 1730, "loss": 0.6642, "lr": 1.9539442054479932e-05, "epoch": 0.9364161849710982, "percentage": 18.73, "elapsed_time": "2:07:59", "remaining_time": "9:15:25"}
+{"current_steps": 325, "total_steps": 1730, "loss": 0.6582, "lr": 1.953336979613112e-05, "epoch": 0.9393063583815029, "percentage": 18.79, "elapsed_time": "2:08:23", "remaining_time": "9:15:01"}
+{"current_steps": 326, "total_steps": 1730, "loss": 0.6517, "lr": 1.952725872553299e-05, "epoch": 0.9421965317919075, "percentage": 18.84, "elapsed_time": "2:08:45", "remaining_time": "9:14:31"}
+{"current_steps": 327, "total_steps": 1730, "loss": 0.6567, "lr": 1.9521108867564945e-05, "epoch": 0.9450867052023122, "percentage": 18.9, "elapsed_time": "2:09:10", "remaining_time": "9:14:14"}
+{"current_steps": 328, "total_steps": 1730, "loss": 0.6778, "lr": 1.9514920247264272e-05, "epoch": 0.9479768786127167, "percentage": 18.96, "elapsed_time": "2:09:34", "remaining_time": "9:13:49"}
+{"current_steps": 329, "total_steps": 1730, "loss": 0.641, "lr": 1.9508692889826085e-05, "epoch": 0.9508670520231214, "percentage": 19.02, "elapsed_time": "2:09:56", "remaining_time": "9:13:21"}
+{"current_steps": 330, "total_steps": 1730, "loss": 0.6538, "lr": 1.9502426820603194e-05, "epoch": 0.953757225433526, "percentage": 19.08, "elapsed_time": "2:10:19", "remaining_time": "9:12:54"}
+{"current_steps": 331, "total_steps": 1730, "loss": 0.6689, "lr": 1.9496122065106017e-05, "epoch": 0.9566473988439307, "percentage": 19.13, "elapsed_time": "2:10:43", "remaining_time": "9:12:29"}
+{"current_steps": 332, "total_steps": 1730, "loss": 0.687, "lr": 1.948977864900247e-05, "epoch": 0.9595375722543352, "percentage": 19.19, "elapsed_time": "2:11:08", "remaining_time": "9:12:11"}
+{"current_steps": 333, "total_steps": 1730, "loss": 0.6688, "lr": 1.9483396598117865e-05, "epoch": 0.9624277456647399, "percentage": 19.25, "elapsed_time": "2:11:32", "remaining_time": "9:11:49"}
+{"current_steps": 334, "total_steps": 1730, "loss": 0.6519, "lr": 1.9476975938434807e-05, "epoch": 0.9653179190751445, "percentage": 19.31, "elapsed_time": "2:11:55", "remaining_time": "9:11:22"}
+{"current_steps": 335, "total_steps": 1730, "loss": 0.6804, "lr": 1.9470516696093075e-05, "epoch": 0.9682080924855492, "percentage": 19.36, "elapsed_time": "2:12:17", "remaining_time": "9:10:52"}
+{"current_steps": 336, "total_steps": 1730, "loss": 0.6735, "lr": 1.946401889738954e-05, "epoch": 0.9710982658959537, "percentage": 19.42, "elapsed_time": "2:12:40", "remaining_time": "9:10:28"}
+{"current_steps": 337, "total_steps": 1730, "loss": 0.6424, "lr": 1.945748256877803e-05, "epoch": 0.9739884393063584, "percentage": 19.48, "elapsed_time": "2:13:04", "remaining_time": "9:10:04"}
+{"current_steps": 338, "total_steps": 1730, "loss": 0.6616, "lr": 1.9450907736869244e-05, "epoch": 0.976878612716763, "percentage": 19.54, "elapsed_time": "2:13:27", "remaining_time": "9:09:37"}
+{"current_steps": 339, "total_steps": 1730, "loss": 0.6468, "lr": 1.9444294428430637e-05, "epoch": 0.9797687861271677, "percentage": 19.6, "elapsed_time": "2:13:51", "remaining_time": "9:09:14"}
+{"current_steps": 340, "total_steps": 1730, "loss": 0.6354, "lr": 1.9437642670386303e-05, "epoch": 0.9826589595375722, "percentage": 19.65, "elapsed_time": "2:14:13", "remaining_time": "9:08:46"}
+{"current_steps": 341, "total_steps": 1730, "loss": 0.667, "lr": 1.9430952489816876e-05, "epoch": 0.9855491329479769, "percentage": 19.71, "elapsed_time": "2:14:38", "remaining_time": "9:08:25"}
+{"current_steps": 342, "total_steps": 1730, "loss": 0.6473, "lr": 1.9424223913959415e-05, "epoch": 0.9884393063583815, "percentage": 19.77, "elapsed_time": "2:15:02", "remaining_time": "9:08:04"}
+{"current_steps": 343, "total_steps": 1730, "loss": 0.6506, "lr": 1.9417456970207294e-05, "epoch": 0.9913294797687862, "percentage": 19.83, "elapsed_time": "2:15:24", "remaining_time": "9:07:31"}
+{"current_steps": 344, "total_steps": 1730, "loss": 0.6588, "lr": 1.941065168611009e-05, "epoch": 0.9942196531791907, "percentage": 19.88, "elapsed_time": "2:15:44", "remaining_time": "9:06:56"}
+{"current_steps": 345, "total_steps": 1730, "loss": 0.6514, "lr": 1.9403808089373473e-05, "epoch": 0.9971098265895953, "percentage": 19.94, "elapsed_time": "2:16:08", "remaining_time": "9:06:33"}
+{"current_steps": 346, "total_steps": 1730, "loss": 0.6676, "lr": 1.9396926207859085e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "2:16:32", "remaining_time": "9:06:10"}
+{"current_steps": 347, "total_steps": 1730, "loss": 0.6119, "lr": 1.9390006069584443e-05, "epoch": 1.0028901734104045, "percentage": 20.06, "elapsed_time": "2:17:40", "remaining_time": "9:08:42"}
+{"current_steps": 348, "total_steps": 1730, "loss": 0.6021, "lr": 1.938304770272281e-05, "epoch": 1.0057803468208093, "percentage": 20.12, "elapsed_time": "2:18:04", "remaining_time": "9:08:18"}
+{"current_steps": 349, "total_steps": 1730, "loss": 0.6044, "lr": 1.9376051135603082e-05, "epoch": 1.0086705202312138, "percentage": 20.17, "elapsed_time": "2:18:26", "remaining_time": "9:07:48"}
+{"current_steps": 350, "total_steps": 1730, "loss": 0.579, "lr": 1.936901639670968e-05, "epoch": 1.0115606936416186, "percentage": 20.23, "elapsed_time": "2:18:48", "remaining_time": "9:07:19"}
+{"current_steps": 351, "total_steps": 1730, "loss": 0.6396, "lr": 1.9361943514682426e-05, "epoch": 1.0144508670520231, "percentage": 20.29, "elapsed_time": "2:19:12", "remaining_time": "9:06:56"}
+{"current_steps": 352, "total_steps": 1730, "loss": 0.5835, "lr": 1.935483251831644e-05, "epoch": 1.0173410404624277, "percentage": 20.35, "elapsed_time": "2:19:36", "remaining_time": "9:06:32"}
+{"current_steps": 353, "total_steps": 1730, "loss": 0.5972, "lr": 1.9347683436562e-05, "epoch": 1.0202312138728324, "percentage": 20.4, "elapsed_time": "2:19:58", "remaining_time": "9:06:01"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01d4e607944f89bffc37b510ea5aa03f3fb3c3dabedcf67e853dc77e1838e23
+size 7224