Training in progress, epoch 0

.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 sha256:0f696450ea9889eb7888bf9318eb8762e50618d562b0edacc394cf6ae4a8cc76
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f788c81eb730119e62b0975bb2d882008a7f5f5bc142fcc3d8b397ee2337a4e7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3c5b7eb80e3582eb5f1874fe421a3b2b515460f8b9c5db7423cac851348518
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf7ef8851ecb6ed5828bf6ae99f8ce53c6f055a4092f464848f7b93bb22cb80
+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 +1,254 @@
+{"current_steps": 1, "total_steps": 1245, "loss": 1.0629, "lr": 3.2e-07, "epoch": 0.004012036108324975, "percentage": 0.08, "elapsed_time": "0:00:40", "remaining_time": "13:57:09"}
+{"current_steps": 2, "total_steps": 1245, "loss": 1.0651, "lr": 6.4e-07, "epoch": 0.00802407221664995, "percentage": 0.16, "elapsed_time": "0:01:13", "remaining_time": "12:45:18"}
+{"current_steps": 3, "total_steps": 1245, "loss": 1.0823, "lr": 9.600000000000001e-07, "epoch": 0.012036108324974924, "percentage": 0.24, "elapsed_time": "0:01:42", "remaining_time": "11:48:41"}
+{"current_steps": 4, "total_steps": 1245, "loss": 1.0671, "lr": 1.28e-06, "epoch": 0.0160481444332999, "percentage": 0.32, "elapsed_time": "0:02:15", "remaining_time": "11:43:02"}
+{"current_steps": 5, "total_steps": 1245, "loss": 1.0516, "lr": 1.6000000000000001e-06, "epoch": 0.020060180541624874, "percentage": 0.4, "elapsed_time": "0:02:54", "remaining_time": "12:00:23"}
+{"current_steps": 6, "total_steps": 1245, "loss": 1.0184, "lr": 1.9200000000000003e-06, "epoch": 0.024072216649949848, "percentage": 0.48, "elapsed_time": "0:03:26", "remaining_time": "11:51:10"}
+{"current_steps": 7, "total_steps": 1245, "loss": 1.001, "lr": 2.24e-06, "epoch": 0.028084252758274825, "percentage": 0.56, "elapsed_time": "0:04:02", "remaining_time": "11:54:41"}
+{"current_steps": 8, "total_steps": 1245, "loss": 1.0014, "lr": 2.56e-06, "epoch": 0.0320962888665998, "percentage": 0.64, "elapsed_time": "0:04:35", "remaining_time": "11:49:13"}
+{"current_steps": 9, "total_steps": 1245, "loss": 0.9665, "lr": 2.88e-06, "epoch": 0.03610832497492478, "percentage": 0.72, "elapsed_time": "0:05:03", "remaining_time": "11:35:44"}
+{"current_steps": 10, "total_steps": 1245, "loss": 0.9249, "lr": 3.2000000000000003e-06, "epoch": 0.04012036108324975, "percentage": 0.8, "elapsed_time": "0:05:37", "remaining_time": "11:35:05"}
+{"current_steps": 11, "total_steps": 1245, "loss": 0.9005, "lr": 3.52e-06, "epoch": 0.044132397191574725, "percentage": 0.88, "elapsed_time": "0:06:10", "remaining_time": "11:32:27"}
+{"current_steps": 12, "total_steps": 1245, "loss": 0.9884, "lr": 3.8400000000000005e-06, "epoch": 0.048144433299899696, "percentage": 0.96, "elapsed_time": "0:06:37", "remaining_time": "11:21:23"}
+{"current_steps": 13, "total_steps": 1245, "loss": 0.9352, "lr": 4.16e-06, "epoch": 0.05215646940822467, "percentage": 1.04, "elapsed_time": "0:07:11", "remaining_time": "11:20:58"}
+{"current_steps": 14, "total_steps": 1245, "loss": 0.886, "lr": 4.48e-06, "epoch": 0.05616850551654965, "percentage": 1.12, "elapsed_time": "0:07:46", "remaining_time": "11:24:07"}
+{"current_steps": 15, "total_steps": 1245, "loss": 0.9289, "lr": 4.800000000000001e-06, "epoch": 0.06018054162487462, "percentage": 1.2, "elapsed_time": "0:08:15", "remaining_time": "11:16:30"}
+{"current_steps": 16, "total_steps": 1245, "loss": 0.894, "lr": 5.12e-06, "epoch": 0.0641925777331996, "percentage": 1.29, "elapsed_time": "0:08:46", "remaining_time": "11:14:37"}
+{"current_steps": 17, "total_steps": 1245, "loss": 0.8662, "lr": 5.4400000000000004e-06, "epoch": 0.06820461384152457, "percentage": 1.37, "elapsed_time": "0:09:23", "remaining_time": "11:18:03"}
+{"current_steps": 18, "total_steps": 1245, "loss": 0.8784, "lr": 5.76e-06, "epoch": 0.07221664994984955, "percentage": 1.45, "elapsed_time": "0:09:57", "remaining_time": "11:18:52"}
+{"current_steps": 19, "total_steps": 1245, "loss": 0.8658, "lr": 6.08e-06, "epoch": 0.07622868605817452, "percentage": 1.53, "elapsed_time": "0:10:32", "remaining_time": "11:20:37"}
+{"current_steps": 20, "total_steps": 1245, "loss": 0.837, "lr": 6.4000000000000006e-06, "epoch": 0.0802407221664995, "percentage": 1.61, "elapsed_time": "0:11:00", "remaining_time": "11:14:14"}
+{"current_steps": 21, "total_steps": 1245, "loss": 0.8117, "lr": 6.720000000000001e-06, "epoch": 0.08425275827482448, "percentage": 1.69, "elapsed_time": "0:11:35", "remaining_time": "11:15:39"}
+{"current_steps": 22, "total_steps": 1245, "loss": 0.8189, "lr": 7.04e-06, "epoch": 0.08826479438314945, "percentage": 1.77, "elapsed_time": "0:12:10", "remaining_time": "11:17:11"}
+{"current_steps": 23, "total_steps": 1245, "loss": 0.7982, "lr": 7.360000000000001e-06, "epoch": 0.09227683049147442, "percentage": 1.85, "elapsed_time": "0:12:38", "remaining_time": "11:12:02"}
+{"current_steps": 24, "total_steps": 1245, "loss": 0.7923, "lr": 7.680000000000001e-06, "epoch": 0.09628886659979939, "percentage": 1.93, "elapsed_time": "0:13:09", "remaining_time": "11:09:40"}
+{"current_steps": 25, "total_steps": 1245, "loss": 0.8331, "lr": 8.000000000000001e-06, "epoch": 0.10030090270812438, "percentage": 2.01, "elapsed_time": "0:13:42", "remaining_time": "11:09:14"}
+{"current_steps": 26, "total_steps": 1245, "loss": 0.7942, "lr": 8.32e-06, "epoch": 0.10431293881644935, "percentage": 2.09, "elapsed_time": "0:14:11", "remaining_time": "11:05:24"}
+{"current_steps": 27, "total_steps": 1245, "loss": 0.7794, "lr": 8.64e-06, "epoch": 0.10832497492477432, "percentage": 2.17, "elapsed_time": "0:14:43", "remaining_time": "11:04:24"}
+{"current_steps": 28, "total_steps": 1245, "loss": 0.77, "lr": 8.96e-06, "epoch": 0.1123370110330993, "percentage": 2.25, "elapsed_time": "0:15:17", "remaining_time": "11:04:37"}
+{"current_steps": 29, "total_steps": 1245, "loss": 0.7667, "lr": 9.280000000000001e-06, "epoch": 0.11634904714142427, "percentage": 2.33, "elapsed_time": "0:15:57", "remaining_time": "11:09:01"}
+{"current_steps": 30, "total_steps": 1245, "loss": 0.7497, "lr": 9.600000000000001e-06, "epoch": 0.12036108324974924, "percentage": 2.41, "elapsed_time": "0:16:31", "remaining_time": "11:09:05"}
+{"current_steps": 31, "total_steps": 1245, "loss": 0.7536, "lr": 9.920000000000002e-06, "epoch": 0.12437311935807423, "percentage": 2.49, "elapsed_time": "0:17:00", "remaining_time": "11:06:01"}
+{"current_steps": 32, "total_steps": 1245, "loss": 0.7612, "lr": 1.024e-05, "epoch": 0.1283851554663992, "percentage": 2.57, "elapsed_time": "0:17:34", "remaining_time": "11:06:07"}
+{"current_steps": 33, "total_steps": 1245, "loss": 0.7479, "lr": 1.056e-05, "epoch": 0.13239719157472418, "percentage": 2.65, "elapsed_time": "0:18:10", "remaining_time": "11:07:25"}
+{"current_steps": 34, "total_steps": 1245, "loss": 0.7779, "lr": 1.0880000000000001e-05, "epoch": 0.13640922768304914, "percentage": 2.73, "elapsed_time": "0:18:42", "remaining_time": "11:06:12"}
+{"current_steps": 35, "total_steps": 1245, "loss": 0.7669, "lr": 1.1200000000000001e-05, "epoch": 0.14042126379137412, "percentage": 2.81, "elapsed_time": "0:19:11", "remaining_time": "11:03:44"}
+{"current_steps": 36, "total_steps": 1245, "loss": 0.7551, "lr": 1.152e-05, "epoch": 0.1444332998996991, "percentage": 2.89, "elapsed_time": "0:19:40", "remaining_time": "11:01:01"}
+{"current_steps": 37, "total_steps": 1245, "loss": 0.7517, "lr": 1.184e-05, "epoch": 0.14844533600802406, "percentage": 2.97, "elapsed_time": "0:20:12", "remaining_time": "10:59:31"}
+{"current_steps": 38, "total_steps": 1245, "loss": 0.7477, "lr": 1.216e-05, "epoch": 0.15245737211634905, "percentage": 3.05, "elapsed_time": "0:20:44", "remaining_time": "10:58:45"}
+{"current_steps": 39, "total_steps": 1245, "loss": 0.7515, "lr": 1.248e-05, "epoch": 0.15646940822467403, "percentage": 3.13, "elapsed_time": "0:21:13", "remaining_time": "10:56:34"}
+{"current_steps": 40, "total_steps": 1245, "loss": 0.7393, "lr": 1.2800000000000001e-05, "epoch": 0.160481444332999, "percentage": 3.21, "elapsed_time": "0:21:45", "remaining_time": "10:55:36"}
+{"current_steps": 41, "total_steps": 1245, "loss": 0.7195, "lr": 1.3120000000000001e-05, "epoch": 0.16449348044132397, "percentage": 3.29, "elapsed_time": "0:22:17", "remaining_time": "10:54:27"}
+{"current_steps": 42, "total_steps": 1245, "loss": 0.7409, "lr": 1.3440000000000002e-05, "epoch": 0.16850551654964896, "percentage": 3.37, "elapsed_time": "0:22:46", "remaining_time": "10:52:23"}
+{"current_steps": 43, "total_steps": 1245, "loss": 0.729, "lr": 1.376e-05, "epoch": 0.17251755265797392, "percentage": 3.45, "elapsed_time": "0:23:16", "remaining_time": "10:50:38"}
+{"current_steps": 44, "total_steps": 1245, "loss": 0.7094, "lr": 1.408e-05, "epoch": 0.1765295887662989, "percentage": 3.53, "elapsed_time": "0:23:47", "remaining_time": "10:49:26"}
+{"current_steps": 45, "total_steps": 1245, "loss": 0.726, "lr": 1.4400000000000001e-05, "epoch": 0.18054162487462388, "percentage": 3.61, "elapsed_time": "0:24:22", "remaining_time": "10:49:53"}
+{"current_steps": 46, "total_steps": 1245, "loss": 0.7311, "lr": 1.4720000000000001e-05, "epoch": 0.18455366098294884, "percentage": 3.69, "elapsed_time": "0:24:54", "remaining_time": "10:49:13"}
+{"current_steps": 47, "total_steps": 1245, "loss": 0.7381, "lr": 1.5040000000000002e-05, "epoch": 0.18856569709127383, "percentage": 3.78, "elapsed_time": "0:25:19", "remaining_time": "10:45:19"}
+{"current_steps": 48, "total_steps": 1245, "loss": 0.7479, "lr": 1.5360000000000002e-05, "epoch": 0.19257773319959878, "percentage": 3.86, "elapsed_time": "0:25:54", "remaining_time": "10:45:56"}
+{"current_steps": 49, "total_steps": 1245, "loss": 0.726, "lr": 1.5680000000000002e-05, "epoch": 0.19658976930792377, "percentage": 3.94, "elapsed_time": "0:26:30", "remaining_time": "10:46:52"}
+{"current_steps": 50, "total_steps": 1245, "loss": 0.7232, "lr": 1.6000000000000003e-05, "epoch": 0.20060180541624875, "percentage": 4.02, "elapsed_time": "0:26:57", "remaining_time": "10:44:08"}
+{"current_steps": 51, "total_steps": 1245, "loss": 0.6954, "lr": 1.632e-05, "epoch": 0.2046138415245737, "percentage": 4.1, "elapsed_time": "0:27:29", "remaining_time": "10:43:48"}
+{"current_steps": 52, "total_steps": 1245, "loss": 0.6998, "lr": 1.664e-05, "epoch": 0.2086258776328987, "percentage": 4.18, "elapsed_time": "0:28:02", "remaining_time": "10:43:10"}
+{"current_steps": 53, "total_steps": 1245, "loss": 0.7304, "lr": 1.696e-05, "epoch": 0.21263791374122368, "percentage": 4.26, "elapsed_time": "0:28:37", "remaining_time": "10:43:53"}
+{"current_steps": 54, "total_steps": 1245, "loss": 0.7249, "lr": 1.728e-05, "epoch": 0.21664994984954863, "percentage": 4.34, "elapsed_time": "0:29:08", "remaining_time": "10:42:51"}
+{"current_steps": 55, "total_steps": 1245, "loss": 0.7208, "lr": 1.76e-05, "epoch": 0.22066198595787362, "percentage": 4.42, "elapsed_time": "0:29:39", "remaining_time": "10:41:43"}
+{"current_steps": 56, "total_steps": 1245, "loss": 0.7264, "lr": 1.792e-05, "epoch": 0.2246740220661986, "percentage": 4.5, "elapsed_time": "0:30:09", "remaining_time": "10:40:17"}
+{"current_steps": 57, "total_steps": 1245, "loss": 0.7036, "lr": 1.824e-05, "epoch": 0.22868605817452356, "percentage": 4.58, "elapsed_time": "0:30:42", "remaining_time": "10:40:00"}
+{"current_steps": 58, "total_steps": 1245, "loss": 0.7252, "lr": 1.8560000000000002e-05, "epoch": 0.23269809428284854, "percentage": 4.66, "elapsed_time": "0:31:14", "remaining_time": "10:39:30"}
+{"current_steps": 59, "total_steps": 1245, "loss": 0.7033, "lr": 1.8880000000000002e-05, "epoch": 0.23671013039117353, "percentage": 4.74, "elapsed_time": "0:31:39", "remaining_time": "10:36:25"}
+{"current_steps": 60, "total_steps": 1245, "loss": 0.7038, "lr": 1.9200000000000003e-05, "epoch": 0.24072216649949849, "percentage": 4.82, "elapsed_time": "0:32:09", "remaining_time": "10:34:59"}
+{"current_steps": 61, "total_steps": 1245, "loss": 0.7009, "lr": 1.9520000000000003e-05, "epoch": 0.24473420260782347, "percentage": 4.9, "elapsed_time": "0:32:37", "remaining_time": "10:33:22"}
+{"current_steps": 62, "total_steps": 1245, "loss": 0.6995, "lr": 1.9840000000000003e-05, "epoch": 0.24874623871614845, "percentage": 4.98, "elapsed_time": "0:33:12", "remaining_time": "10:33:34"}
+{"current_steps": 63, "total_steps": 1245, "loss": 0.6912, "lr": 2.016e-05, "epoch": 0.25275827482447344, "percentage": 5.06, "elapsed_time": "0:33:45", "remaining_time": "10:33:17"}
+{"current_steps": 64, "total_steps": 1245, "loss": 0.7159, "lr": 2.048e-05, "epoch": 0.2567703109327984, "percentage": 5.14, "elapsed_time": "0:34:16", "remaining_time": "10:32:28"}
+{"current_steps": 65, "total_steps": 1245, "loss": 0.6906, "lr": 2.08e-05, "epoch": 0.26078234704112335, "percentage": 5.22, "elapsed_time": "0:34:47", "remaining_time": "10:31:38"}
+{"current_steps": 66, "total_steps": 1245, "loss": 0.6703, "lr": 2.112e-05, "epoch": 0.26479438314944836, "percentage": 5.3, "elapsed_time": "0:35:15", "remaining_time": "10:29:47"}
+{"current_steps": 67, "total_steps": 1245, "loss": 0.713, "lr": 2.144e-05, "epoch": 0.2688064192577733, "percentage": 5.38, "elapsed_time": "0:35:39", "remaining_time": "10:26:51"}
+{"current_steps": 68, "total_steps": 1245, "loss": 0.6858, "lr": 2.1760000000000002e-05, "epoch": 0.2728184553660983, "percentage": 5.46, "elapsed_time": "0:36:08", "remaining_time": "10:25:33"}
+{"current_steps": 69, "total_steps": 1245, "loss": 0.6847, "lr": 2.2080000000000002e-05, "epoch": 0.2768304914744233, "percentage": 5.54, "elapsed_time": "0:36:38", "remaining_time": "10:24:27"}
+{"current_steps": 70, "total_steps": 1245, "loss": 0.6812, "lr": 2.2400000000000002e-05, "epoch": 0.28084252758274825, "percentage": 5.62, "elapsed_time": "0:37:08", "remaining_time": "10:23:21"}
+{"current_steps": 71, "total_steps": 1245, "loss": 0.7123, "lr": 2.272e-05, "epoch": 0.2848545636910732, "percentage": 5.7, "elapsed_time": "0:37:39", "remaining_time": "10:22:34"}
+{"current_steps": 72, "total_steps": 1245, "loss": 0.6809, "lr": 2.304e-05, "epoch": 0.2888665997993982, "percentage": 5.78, "elapsed_time": "0:38:12", "remaining_time": "10:22:22"}
+{"current_steps": 73, "total_steps": 1245, "loss": 0.693, "lr": 2.336e-05, "epoch": 0.2928786359077232, "percentage": 5.86, "elapsed_time": "0:38:41", "remaining_time": "10:21:03"}
+{"current_steps": 74, "total_steps": 1245, "loss": 0.6878, "lr": 2.368e-05, "epoch": 0.29689067201604813, "percentage": 5.94, "elapsed_time": "0:39:16", "remaining_time": "10:21:32"}
+{"current_steps": 75, "total_steps": 1245, "loss": 0.6485, "lr": 2.4e-05, "epoch": 0.30090270812437314, "percentage": 6.02, "elapsed_time": "0:39:50", "remaining_time": "10:21:37"}
+{"current_steps": 76, "total_steps": 1245, "loss": 0.6786, "lr": 2.432e-05, "epoch": 0.3049147442326981, "percentage": 6.1, "elapsed_time": "0:40:24", "remaining_time": "10:21:30"}
+{"current_steps": 77, "total_steps": 1245, "loss": 0.7066, "lr": 2.464e-05, "epoch": 0.30892678034102306, "percentage": 6.18, "elapsed_time": "0:41:00", "remaining_time": "10:22:07"}
+{"current_steps": 78, "total_steps": 1245, "loss": 0.6959, "lr": 2.496e-05, "epoch": 0.31293881644934807, "percentage": 6.27, "elapsed_time": "0:41:36", "remaining_time": "10:22:24"}
+{"current_steps": 79, "total_steps": 1245, "loss": 0.7013, "lr": 2.5280000000000002e-05, "epoch": 0.316950852557673, "percentage": 6.35, "elapsed_time": "0:42:11", "remaining_time": "10:22:44"}
+{"current_steps": 80, "total_steps": 1245, "loss": 0.6751, "lr": 2.5600000000000002e-05, "epoch": 0.320962888665998, "percentage": 6.43, "elapsed_time": "0:42:46", "remaining_time": "10:22:48"}
+{"current_steps": 81, "total_steps": 1245, "loss": 0.6508, "lr": 2.5920000000000003e-05, "epoch": 0.324974924774323, "percentage": 6.51, "elapsed_time": "0:43:13", "remaining_time": "10:21:12"}
+{"current_steps": 82, "total_steps": 1245, "loss": 0.699, "lr": 2.6240000000000003e-05, "epoch": 0.32898696088264795, "percentage": 6.59, "elapsed_time": "0:43:41", "remaining_time": "10:19:37"}
+{"current_steps": 83, "total_steps": 1245, "loss": 0.6991, "lr": 2.6560000000000003e-05, "epoch": 0.3329989969909729, "percentage": 6.67, "elapsed_time": "0:44:09", "remaining_time": "10:18:19"}
+{"current_steps": 84, "total_steps": 1245, "loss": 0.6758, "lr": 2.6880000000000004e-05, "epoch": 0.3370110330992979, "percentage": 6.75, "elapsed_time": "0:44:44", "remaining_time": "10:18:24"}
+{"current_steps": 85, "total_steps": 1245, "loss": 0.7108, "lr": 2.7200000000000004e-05, "epoch": 0.3410230692076229, "percentage": 6.83, "elapsed_time": "0:45:13", "remaining_time": "10:17:10"}
+{"current_steps": 86, "total_steps": 1245, "loss": 0.6832, "lr": 2.752e-05, "epoch": 0.34503510531594783, "percentage": 6.91, "elapsed_time": "0:45:46", "remaining_time": "10:16:48"}
+{"current_steps": 87, "total_steps": 1245, "loss": 0.6681, "lr": 2.784e-05, "epoch": 0.34904714142427284, "percentage": 6.99, "elapsed_time": "0:46:18", "remaining_time": "10:16:25"}
+{"current_steps": 88, "total_steps": 1245, "loss": 0.6683, "lr": 2.816e-05, "epoch": 0.3530591775325978, "percentage": 7.07, "elapsed_time": "0:46:50", "remaining_time": "10:15:52"}
+{"current_steps": 89, "total_steps": 1245, "loss": 0.6953, "lr": 2.8480000000000002e-05, "epoch": 0.35707121364092276, "percentage": 7.15, "elapsed_time": "0:47:25", "remaining_time": "10:16:03"}
+{"current_steps": 90, "total_steps": 1245, "loss": 0.6926, "lr": 2.8800000000000002e-05, "epoch": 0.36108324974924777, "percentage": 7.23, "elapsed_time": "0:47:55", "remaining_time": "10:14:56"}
+{"current_steps": 91, "total_steps": 1245, "loss": 0.6601, "lr": 2.9120000000000002e-05, "epoch": 0.3650952858575727, "percentage": 7.31, "elapsed_time": "0:48:25", "remaining_time": "10:14:10"}
+{"current_steps": 92, "total_steps": 1245, "loss": 0.6782, "lr": 2.9440000000000003e-05, "epoch": 0.3691073219658977, "percentage": 7.39, "elapsed_time": "0:48:57", "remaining_time": "10:13:35"}
+{"current_steps": 93, "total_steps": 1245, "loss": 0.6897, "lr": 2.9760000000000003e-05, "epoch": 0.3731193580742227, "percentage": 7.47, "elapsed_time": "0:49:30", "remaining_time": "10:13:11"}
+{"current_steps": 94, "total_steps": 1245, "loss": 0.6607, "lr": 3.0080000000000003e-05, "epoch": 0.37713139418254765, "percentage": 7.55, "elapsed_time": "0:50:03", "remaining_time": "10:13:00"}
+{"current_steps": 95, "total_steps": 1245, "loss": 0.6788, "lr": 3.0400000000000004e-05, "epoch": 0.3811434302908726, "percentage": 7.63, "elapsed_time": "0:50:32", "remaining_time": "10:11:47"}
+{"current_steps": 96, "total_steps": 1245, "loss": 0.6533, "lr": 3.0720000000000004e-05, "epoch": 0.38515546639919757, "percentage": 7.71, "elapsed_time": "0:51:01", "remaining_time": "10:10:42"}
+{"current_steps": 97, "total_steps": 1245, "loss": 0.6761, "lr": 3.104e-05, "epoch": 0.3891675025075226, "percentage": 7.79, "elapsed_time": "0:51:34", "remaining_time": "10:10:27"}
+{"current_steps": 98, "total_steps": 1245, "loss": 0.6499, "lr": 3.1360000000000005e-05, "epoch": 0.39317953861584753, "percentage": 7.87, "elapsed_time": "0:52:07", "remaining_time": "10:09:58"}
+{"current_steps": 99, "total_steps": 1245, "loss": 0.6757, "lr": 3.168e-05, "epoch": 0.3971915747241725, "percentage": 7.95, "elapsed_time": "0:52:37", "remaining_time": "10:09:14"}
+{"current_steps": 100, "total_steps": 1245, "loss": 0.6669, "lr": 3.2000000000000005e-05, "epoch": 0.4012036108324975, "percentage": 8.03, "elapsed_time": "0:53:06", "remaining_time": "10:08:04"}
+{"current_steps": 101, "total_steps": 1245, "loss": 0.6747, "lr": 3.232e-05, "epoch": 0.40521564694082246, "percentage": 8.11, "elapsed_time": "0:53:33", "remaining_time": "10:06:34"}
+{"current_steps": 102, "total_steps": 1245, "loss": 0.678, "lr": 3.264e-05, "epoch": 0.4092276830491474, "percentage": 8.19, "elapsed_time": "0:54:06", "remaining_time": "10:06:21"}
+{"current_steps": 103, "total_steps": 1245, "loss": 0.6733, "lr": 3.296e-05, "epoch": 0.41323971915747243, "percentage": 8.27, "elapsed_time": "0:54:40", "remaining_time": "10:06:10"}
+{"current_steps": 104, "total_steps": 1245, "loss": 0.6874, "lr": 3.328e-05, "epoch": 0.4172517552657974, "percentage": 8.35, "elapsed_time": "0:55:12", "remaining_time": "10:05:39"}
+{"current_steps": 105, "total_steps": 1245, "loss": 0.6722, "lr": 3.3600000000000004e-05, "epoch": 0.42126379137412234, "percentage": 8.43, "elapsed_time": "0:55:44", "remaining_time": "10:05:14"}
+{"current_steps": 106, "total_steps": 1245, "loss": 0.6738, "lr": 3.392e-05, "epoch": 0.42527582748244735, "percentage": 8.51, "elapsed_time": "0:56:12", "remaining_time": "10:04:03"}
+{"current_steps": 107, "total_steps": 1245, "loss": 0.6769, "lr": 3.4240000000000004e-05, "epoch": 0.4292878635907723, "percentage": 8.59, "elapsed_time": "0:56:50", "remaining_time": "10:04:32"}
+{"current_steps": 108, "total_steps": 1245, "loss": 0.6688, "lr": 3.456e-05, "epoch": 0.43329989969909727, "percentage": 8.67, "elapsed_time": "0:57:21", "remaining_time": "10:03:49"}
+{"current_steps": 109, "total_steps": 1245, "loss": 0.6754, "lr": 3.4880000000000005e-05, "epoch": 0.4373119358074223, "percentage": 8.76, "elapsed_time": "0:57:51", "remaining_time": "10:03:01"}
+{"current_steps": 110, "total_steps": 1245, "loss": 0.6732, "lr": 3.52e-05, "epoch": 0.44132397191574724, "percentage": 8.84, "elapsed_time": "0:58:24", "remaining_time": "10:02:36"}
+{"current_steps": 111, "total_steps": 1245, "loss": 0.6878, "lr": 3.5520000000000006e-05, "epoch": 0.4453360080240722, "percentage": 8.92, "elapsed_time": "0:58:59", "remaining_time": "10:02:39"}
+{"current_steps": 112, "total_steps": 1245, "loss": 0.6581, "lr": 3.584e-05, "epoch": 0.4493480441323972, "percentage": 9.0, "elapsed_time": "0:59:36", "remaining_time": "10:03:02"}
+{"current_steps": 113, "total_steps": 1245, "loss": 0.6674, "lr": 3.6160000000000006e-05, "epoch": 0.45336008024072216, "percentage": 9.08, "elapsed_time": "1:00:03", "remaining_time": "10:01:41"}
+{"current_steps": 114, "total_steps": 1245, "loss": 0.6605, "lr": 3.648e-05, "epoch": 0.4573721163490471, "percentage": 9.16, "elapsed_time": "1:00:34", "remaining_time": "10:00:54"}
+{"current_steps": 115, "total_steps": 1245, "loss": 0.6873, "lr": 3.680000000000001e-05, "epoch": 0.46138415245737213, "percentage": 9.24, "elapsed_time": "1:01:05", "remaining_time": "10:00:13"}
+{"current_steps": 116, "total_steps": 1245, "loss": 0.6765, "lr": 3.7120000000000004e-05, "epoch": 0.4653961885656971, "percentage": 9.32, "elapsed_time": "1:01:37", "remaining_time": "9:59:42"}
+{"current_steps": 117, "total_steps": 1245, "loss": 0.6567, "lr": 3.744000000000001e-05, "epoch": 0.46940822467402205, "percentage": 9.4, "elapsed_time": "1:02:10", "remaining_time": "9:59:25"}
+{"current_steps": 118, "total_steps": 1245, "loss": 0.6605, "lr": 3.7760000000000004e-05, "epoch": 0.47342026078234706, "percentage": 9.48, "elapsed_time": "1:02:43", "remaining_time": "9:59:06"}
+{"current_steps": 119, "total_steps": 1245, "loss": 0.6759, "lr": 3.808e-05, "epoch": 0.477432296890672, "percentage": 9.56, "elapsed_time": "1:03:17", "remaining_time": "9:58:53"}
+{"current_steps": 120, "total_steps": 1245, "loss": 0.6779, "lr": 3.8400000000000005e-05, "epoch": 0.48144433299899697, "percentage": 9.64, "elapsed_time": "1:03:47", "remaining_time": "9:57:58"}
+{"current_steps": 121, "total_steps": 1245, "loss": 0.6813, "lr": 3.872e-05, "epoch": 0.485456369107322, "percentage": 9.72, "elapsed_time": "1:04:13", "remaining_time": "9:56:31"}
+{"current_steps": 122, "total_steps": 1245, "loss": 0.6598, "lr": 3.9040000000000006e-05, "epoch": 0.48946840521564694, "percentage": 9.8, "elapsed_time": "1:04:49", "remaining_time": "9:56:38"}
+{"current_steps": 123, "total_steps": 1245, "loss": 0.6447, "lr": 3.936e-05, "epoch": 0.4934804413239719, "percentage": 9.88, "elapsed_time": "1:05:20", "remaining_time": "9:56:04"}
+{"current_steps": 124, "total_steps": 1245, "loss": 0.6604, "lr": 3.9680000000000006e-05, "epoch": 0.4974924774322969, "percentage": 9.96, "elapsed_time": "1:05:53", "remaining_time": "9:55:38"}
+{"current_steps": 125, "total_steps": 1245, "loss": 0.687, "lr": 4e-05, "epoch": 0.5015045135406219, "percentage": 10.04, "elapsed_time": "1:06:23", "remaining_time": "9:54:50"}
+{"current_steps": 126, "total_steps": 1245, "loss": 0.6736, "lr": 3.9999921320169564e-05, "epoch": 0.5055165496489469, "percentage": 10.12, "elapsed_time": "1:06:54", "remaining_time": "9:54:14"}
+{"current_steps": 127, "total_steps": 1245, "loss": 0.6772, "lr": 3.999968528129731e-05, "epoch": 0.5095285857572718, "percentage": 10.2, "elapsed_time": "1:07:26", "remaining_time": "9:53:44"}
+{"current_steps": 128, "total_steps": 1245, "loss": 0.6711, "lr": 3.9999291885240385e-05, "epoch": 0.5135406218655968, "percentage": 10.28, "elapsed_time": "1:08:00", "remaining_time": "9:53:31"}
+{"current_steps": 129, "total_steps": 1245, "loss": 0.6761, "lr": 3.9998741135094016e-05, "epoch": 0.5175526579739218, "percentage": 10.36, "elapsed_time": "1:08:30", "remaining_time": "9:52:39"}
+{"current_steps": 130, "total_steps": 1245, "loss": 0.6848, "lr": 3.9998033035191504e-05, "epoch": 0.5215646940822467, "percentage": 10.44, "elapsed_time": "1:09:00", "remaining_time": "9:51:56"}
+{"current_steps": 131, "total_steps": 1245, "loss": 0.6813, "lr": 3.999716759110417e-05, "epoch": 0.5255767301905717, "percentage": 10.52, "elapsed_time": "1:09:38", "remaining_time": "9:52:10"}
+{"current_steps": 132, "total_steps": 1245, "loss": 0.6836, "lr": 3.9996144809641296e-05, "epoch": 0.5295887662988967, "percentage": 10.6, "elapsed_time": "1:10:05", "remaining_time": "9:51:00"}
+{"current_steps": 133, "total_steps": 1245, "loss": 0.6821, "lr": 3.999496469885014e-05, "epoch": 0.5336008024072216, "percentage": 10.68, "elapsed_time": "1:10:38", "remaining_time": "9:50:41"}
+{"current_steps": 134, "total_steps": 1245, "loss": 0.6731, "lr": 3.999362726801576e-05, "epoch": 0.5376128385155466, "percentage": 10.76, "elapsed_time": "1:11:15", "remaining_time": "9:50:45"}
+{"current_steps": 135, "total_steps": 1245, "loss": 0.6993, "lr": 3.9992132527661065e-05, "epoch": 0.5416248746238717, "percentage": 10.84, "elapsed_time": "1:11:46", "remaining_time": "9:50:08"}
+{"current_steps": 136, "total_steps": 1245, "loss": 0.6848, "lr": 3.999048048954663e-05, "epoch": 0.5456369107321966, "percentage": 10.92, "elapsed_time": "1:12:19", "remaining_time": "9:49:42"}
+{"current_steps": 137, "total_steps": 1245, "loss": 0.6748, "lr": 3.998867116667067e-05, "epoch": 0.5496489468405216, "percentage": 11.0, "elapsed_time": "1:12:56", "remaining_time": "9:49:57"}
+{"current_steps": 138, "total_steps": 1245, "loss": 0.6781, "lr": 3.998670457326891e-05, "epoch": 0.5536609829488466, "percentage": 11.08, "elapsed_time": "1:13:23", "remaining_time": "9:48:40"}
+{"current_steps": 139, "total_steps": 1245, "loss": 0.6371, "lr": 3.9984580724814464e-05, "epoch": 0.5576730190571715, "percentage": 11.16, "elapsed_time": "1:13:55", "remaining_time": "9:48:08"}
+{"current_steps": 140, "total_steps": 1245, "loss": 0.64, "lr": 3.998229963801774e-05, "epoch": 0.5616850551654965, "percentage": 11.24, "elapsed_time": "1:14:28", "remaining_time": "9:47:49"}
+{"current_steps": 141, "total_steps": 1245, "loss": 0.6464, "lr": 3.9979861330826295e-05, "epoch": 0.5656970912738215, "percentage": 11.33, "elapsed_time": "1:15:00", "remaining_time": "9:47:20"}
+{"current_steps": 142, "total_steps": 1245, "loss": 0.673, "lr": 3.997726582242469e-05, "epoch": 0.5697091273821464, "percentage": 11.41, "elapsed_time": "1:15:35", "remaining_time": "9:47:10"}
+{"current_steps": 143, "total_steps": 1245, "loss": 0.6635, "lr": 3.997451313323433e-05, "epoch": 0.5737211634904714, "percentage": 11.49, "elapsed_time": "1:16:05", "remaining_time": "9:46:20"}
+{"current_steps": 144, "total_steps": 1245, "loss": 0.6691, "lr": 3.997160328491333e-05, "epoch": 0.5777331995987964, "percentage": 11.57, "elapsed_time": "1:16:38", "remaining_time": "9:46:00"}
+{"current_steps": 145, "total_steps": 1245, "loss": 0.6731, "lr": 3.996853630035634e-05, "epoch": 0.5817452357071213, "percentage": 11.65, "elapsed_time": "1:17:06", "remaining_time": "9:45:00"}
+{"current_steps": 146, "total_steps": 1245, "loss": 0.6614, "lr": 3.996531220369432e-05, "epoch": 0.5857572718154463, "percentage": 11.73, "elapsed_time": "1:17:38", "remaining_time": "9:44:29"}
+{"current_steps": 147, "total_steps": 1245, "loss": 0.6434, "lr": 3.996193102029443e-05, "epoch": 0.5897693079237714, "percentage": 11.81, "elapsed_time": "1:18:10", "remaining_time": "9:43:51"}
+{"current_steps": 148, "total_steps": 1245, "loss": 0.672, "lr": 3.995839277675975e-05, "epoch": 0.5937813440320963, "percentage": 11.89, "elapsed_time": "1:18:43", "remaining_time": "9:43:27"}
+{"current_steps": 149, "total_steps": 1245, "loss": 0.6565, "lr": 3.995469750092912e-05, "epoch": 0.5977933801404213, "percentage": 11.97, "elapsed_time": "1:19:14", "remaining_time": "9:42:49"}
+{"current_steps": 150, "total_steps": 1245, "loss": 0.6663, "lr": 3.9950845221876926e-05, "epoch": 0.6018054162487463, "percentage": 12.05, "elapsed_time": "1:19:44", "remaining_time": "9:42:06"}
+{"current_steps": 151, "total_steps": 1245, "loss": 0.6762, "lr": 3.994683596991281e-05, "epoch": 0.6058174523570712, "percentage": 12.13, "elapsed_time": "1:20:13", "remaining_time": "9:41:14"}
+{"current_steps": 152, "total_steps": 1245, "loss": 0.6737, "lr": 3.994266977658151e-05, "epoch": 0.6098294884653962, "percentage": 12.21, "elapsed_time": "1:20:45", "remaining_time": "9:40:43"}
+{"current_steps": 153, "total_steps": 1245, "loss": 0.6813, "lr": 3.9938346674662565e-05, "epoch": 0.6138415245737212, "percentage": 12.29, "elapsed_time": "1:21:17", "remaining_time": "9:40:10"}
+{"current_steps": 154, "total_steps": 1245, "loss": 0.6382, "lr": 3.9933866698170065e-05, "epoch": 0.6178535606820461, "percentage": 12.37, "elapsed_time": "1:21:52", "remaining_time": "9:40:05"}
+{"current_steps": 155, "total_steps": 1245, "loss": 0.6438, "lr": 3.992922988235239e-05, "epoch": 0.6218655967903711, "percentage": 12.45, "elapsed_time": "1:22:19", "remaining_time": "9:38:56"}
+{"current_steps": 156, "total_steps": 1245, "loss": 0.6669, "lr": 3.992443626369192e-05, "epoch": 0.6258776328986961, "percentage": 12.53, "elapsed_time": "1:22:50", "remaining_time": "9:38:15"}
+{"current_steps": 157, "total_steps": 1245, "loss": 0.655, "lr": 3.991948587990479e-05, "epoch": 0.629889669007021, "percentage": 12.61, "elapsed_time": "1:23:24", "remaining_time": "9:38:01"}
+{"current_steps": 158, "total_steps": 1245, "loss": 0.6531, "lr": 3.9914378769940506e-05, "epoch": 0.633901705115346, "percentage": 12.69, "elapsed_time": "1:23:58", "remaining_time": "9:37:41"}
+{"current_steps": 159, "total_steps": 1245, "loss": 0.6557, "lr": 3.990911497398174e-05, "epoch": 0.6379137412236711, "percentage": 12.77, "elapsed_time": "1:24:28", "remaining_time": "9:37:00"}
+{"current_steps": 160, "total_steps": 1245, "loss": 0.6551, "lr": 3.990369453344394e-05, "epoch": 0.641925777331996, "percentage": 12.85, "elapsed_time": "1:24:57", "remaining_time": "9:36:04"}
+{"current_steps": 161, "total_steps": 1245, "loss": 0.6605, "lr": 3.989811749097505e-05, "epoch": 0.645937813440321, "percentage": 12.93, "elapsed_time": "1:25:30", "remaining_time": "9:35:46"}
+{"current_steps": 162, "total_steps": 1245, "loss": 0.6547, "lr": 3.989238389045514e-05, "epoch": 0.649949849548646, "percentage": 13.01, "elapsed_time": "1:26:03", "remaining_time": "9:35:17"}
+{"current_steps": 163, "total_steps": 1245, "loss": 0.6226, "lr": 3.988649377699608e-05, "epoch": 0.6539618856569709, "percentage": 13.09, "elapsed_time": "1:26:39", "remaining_time": "9:35:15"}
+{"current_steps": 164, "total_steps": 1245, "loss": 0.6332, "lr": 3.988044719694119e-05, "epoch": 0.6579739217652959, "percentage": 13.17, "elapsed_time": "1:27:08", "remaining_time": "9:34:23"}
+{"current_steps": 165, "total_steps": 1245, "loss": 0.6665, "lr": 3.9874244197864856e-05, "epoch": 0.6619859578736209, "percentage": 13.25, "elapsed_time": "1:27:44", "remaining_time": "9:34:18"}
+{"current_steps": 166, "total_steps": 1245, "loss": 0.6721, "lr": 3.9867884828572163e-05, "epoch": 0.6659979939819458, "percentage": 13.33, "elapsed_time": "1:28:15", "remaining_time": "9:33:43"}
+{"current_steps": 167, "total_steps": 1245, "loss": 0.6357, "lr": 3.986136913909853e-05, "epoch": 0.6700100300902708, "percentage": 13.41, "elapsed_time": "1:28:48", "remaining_time": "9:33:15"}
+{"current_steps": 168, "total_steps": 1245, "loss": 0.625, "lr": 3.9854697180709283e-05, "epoch": 0.6740220661985958, "percentage": 13.49, "elapsed_time": "1:29:22", "remaining_time": "9:32:55"}
+{"current_steps": 169, "total_steps": 1245, "loss": 0.6686, "lr": 3.984786900589929e-05, "epoch": 0.6780341023069207, "percentage": 13.57, "elapsed_time": "1:29:51", "remaining_time": "9:32:05"}
+{"current_steps": 170, "total_steps": 1245, "loss": 0.6442, "lr": 3.9840884668392495e-05, "epoch": 0.6820461384152458, "percentage": 13.65, "elapsed_time": "1:30:22", "remaining_time": "9:31:28"}
+{"current_steps": 171, "total_steps": 1245, "loss": 0.6595, "lr": 3.9833744223141565e-05, "epoch": 0.6860581745235708, "percentage": 13.73, "elapsed_time": "1:30:47", "remaining_time": "9:30:13"}
+{"current_steps": 172, "total_steps": 1245, "loss": 0.6528, "lr": 3.9826447726327395e-05, "epoch": 0.6900702106318957, "percentage": 13.82, "elapsed_time": "1:31:13", "remaining_time": "9:29:08"}
+{"current_steps": 173, "total_steps": 1245, "loss": 0.6588, "lr": 3.98189952353587e-05, "epoch": 0.6940822467402207, "percentage": 13.9, "elapsed_time": "1:31:47", "remaining_time": "9:28:49"}
+{"current_steps": 174, "total_steps": 1245, "loss": 0.6624, "lr": 3.981138680887154e-05, "epoch": 0.6980942828485457, "percentage": 13.98, "elapsed_time": "1:32:17", "remaining_time": "9:28:05"}
+{"current_steps": 175, "total_steps": 1245, "loss": 0.6452, "lr": 3.9803622506728916e-05, "epoch": 0.7021063189568706, "percentage": 14.06, "elapsed_time": "1:32:53", "remaining_time": "9:28:00"}
+{"current_steps": 176, "total_steps": 1245, "loss": 0.6612, "lr": 3.97957023900202e-05, "epoch": 0.7061183550651956, "percentage": 14.14, "elapsed_time": "1:33:28", "remaining_time": "9:27:47"}
+{"current_steps": 177, "total_steps": 1245, "loss": 0.6478, "lr": 3.9787626521060736e-05, "epoch": 0.7101303911735206, "percentage": 14.22, "elapsed_time": "1:34:01", "remaining_time": "9:27:20"}
+{"current_steps": 178, "total_steps": 1245, "loss": 0.647, "lr": 3.977939496339134e-05, "epoch": 0.7141424272818455, "percentage": 14.3, "elapsed_time": "1:34:35", "remaining_time": "9:27:03"}
+{"current_steps": 179, "total_steps": 1245, "loss": 0.6322, "lr": 3.977100778177775e-05, "epoch": 0.7181544633901705, "percentage": 14.38, "elapsed_time": "1:35:04", "remaining_time": "9:26:11"}
+{"current_steps": 180, "total_steps": 1245, "loss": 0.6284, "lr": 3.976246504221018e-05, "epoch": 0.7221664994984955, "percentage": 14.46, "elapsed_time": "1:35:39", "remaining_time": "9:25:58"}
+{"current_steps": 181, "total_steps": 1245, "loss": 0.6568, "lr": 3.9753766811902756e-05, "epoch": 0.7261785356068204, "percentage": 14.54, "elapsed_time": "1:36:04", "remaining_time": "9:24:46"}
+{"current_steps": 182, "total_steps": 1245, "loss": 0.6547, "lr": 3.974491315929301e-05, "epoch": 0.7301905717151455, "percentage": 14.62, "elapsed_time": "1:36:34", "remaining_time": "9:24:03"}
+{"current_steps": 183, "total_steps": 1245, "loss": 0.6633, "lr": 3.9735904154041335e-05, "epoch": 0.7342026078234705, "percentage": 14.7, "elapsed_time": "1:37:07", "remaining_time": "9:23:41"}
+{"current_steps": 184, "total_steps": 1245, "loss": 0.6546, "lr": 3.972673986703042e-05, "epoch": 0.7382146439317954, "percentage": 14.78, "elapsed_time": "1:37:41", "remaining_time": "9:23:19"}
+{"current_steps": 185, "total_steps": 1245, "loss": 0.6445, "lr": 3.971742037036472e-05, "epoch": 0.7422266800401204, "percentage": 14.86, "elapsed_time": "1:38:19", "remaining_time": "9:23:19"}
+{"current_steps": 186, "total_steps": 1245, "loss": 0.6582, "lr": 3.9707945737369885e-05, "epoch": 0.7462387161484454, "percentage": 14.94, "elapsed_time": "1:38:50", "remaining_time": "9:22:46"}
+{"current_steps": 187, "total_steps": 1245, "loss": 0.6335, "lr": 3.969831604259217e-05, "epoch": 0.7502507522567703, "percentage": 15.02, "elapsed_time": "1:39:19", "remaining_time": "9:21:56"}
+{"current_steps": 188, "total_steps": 1245, "loss": 0.6553, "lr": 3.9688531361797834e-05, "epoch": 0.7542627883650953, "percentage": 15.1, "elapsed_time": "1:39:47", "remaining_time": "9:21:06"}
+{"current_steps": 189, "total_steps": 1245, "loss": 0.6612, "lr": 3.96785917719726e-05, "epoch": 0.7582748244734202, "percentage": 15.18, "elapsed_time": "1:40:18", "remaining_time": "9:20:25"}
+{"current_steps": 190, "total_steps": 1245, "loss": 0.6446, "lr": 3.966849735132097e-05, "epoch": 0.7622868605817452, "percentage": 15.26, "elapsed_time": "1:40:49", "remaining_time": "9:19:53"}
+{"current_steps": 191, "total_steps": 1245, "loss": 0.6535, "lr": 3.96582481792657e-05, "epoch": 0.7662988966900702, "percentage": 15.34, "elapsed_time": "1:41:15", "remaining_time": "9:18:48"}
+{"current_steps": 192, "total_steps": 1245, "loss": 0.665, "lr": 3.9647844336447074e-05, "epoch": 0.7703109327983951, "percentage": 15.42, "elapsed_time": "1:41:49", "remaining_time": "9:18:26"}
+{"current_steps": 193, "total_steps": 1245, "loss": 0.6689, "lr": 3.9637285904722376e-05, "epoch": 0.7743229689067201, "percentage": 15.5, "elapsed_time": "1:42:21", "remaining_time": "9:17:54"}
+{"current_steps": 194, "total_steps": 1245, "loss": 0.6454, "lr": 3.962657296716515e-05, "epoch": 0.7783350050150452, "percentage": 15.58, "elapsed_time": "1:42:48", "remaining_time": "9:16:59"}
+{"current_steps": 195, "total_steps": 1245, "loss": 0.6565, "lr": 3.961570560806461e-05, "epoch": 0.7823470411233701, "percentage": 15.66, "elapsed_time": "1:43:18", "remaining_time": "9:16:15"}
+{"current_steps": 196, "total_steps": 1245, "loss": 0.6382, "lr": 3.960468391292496e-05, "epoch": 0.7863590772316951, "percentage": 15.74, "elapsed_time": "1:43:52", "remaining_time": "9:15:56"}
+{"current_steps": 197, "total_steps": 1245, "loss": 0.6614, "lr": 3.9593507968464714e-05, "epoch": 0.7903711133400201, "percentage": 15.82, "elapsed_time": "1:44:31", "remaining_time": "9:16:02"}
+{"current_steps": 198, "total_steps": 1245, "loss": 0.6484, "lr": 3.958217786261601e-05, "epoch": 0.794383149448345, "percentage": 15.9, "elapsed_time": "1:45:03", "remaining_time": "9:15:34"}
+{"current_steps": 199, "total_steps": 1245, "loss": 0.6315, "lr": 3.9570693684523914e-05, "epoch": 0.79839518555667, "percentage": 15.98, "elapsed_time": "1:45:33", "remaining_time": "9:14:50"}
+{"current_steps": 200, "total_steps": 1245, "loss": 0.6357, "lr": 3.9559055524545755e-05, "epoch": 0.802407221664995, "percentage": 16.06, "elapsed_time": "1:46:08", "remaining_time": "9:14:34"}
+{"current_steps": 201, "total_steps": 1245, "loss": 0.6409, "lr": 3.9547263474250385e-05, "epoch": 0.8064192577733199, "percentage": 16.14, "elapsed_time": "1:46:41", "remaining_time": "9:14:11"}
+{"current_steps": 202, "total_steps": 1245, "loss": 0.6481, "lr": 3.953531762641745e-05, "epoch": 0.8104312938816449, "percentage": 16.22, "elapsed_time": "1:47:14", "remaining_time": "9:13:43"}
+{"current_steps": 203, "total_steps": 1245, "loss": 0.6607, "lr": 3.952321807503668e-05, "epoch": 0.8144433299899699, "percentage": 16.31, "elapsed_time": "1:47:45", "remaining_time": "9:13:05"}
+{"current_steps": 204, "total_steps": 1245, "loss": 0.6522, "lr": 3.951096491530714e-05, "epoch": 0.8184553660982948, "percentage": 16.39, "elapsed_time": "1:48:16", "remaining_time": "9:12:29"}
+{"current_steps": 205, "total_steps": 1245, "loss": 0.6422, "lr": 3.949855824363647e-05, "epoch": 0.8224674022066198, "percentage": 16.47, "elapsed_time": "1:48:45", "remaining_time": "9:11:47"}
+{"current_steps": 206, "total_steps": 1245, "loss": 0.6635, "lr": 3.948599815764018e-05, "epoch": 0.8264794383149449, "percentage": 16.55, "elapsed_time": "1:49:13", "remaining_time": "9:10:54"}
+{"current_steps": 207, "total_steps": 1245, "loss": 0.6295, "lr": 3.9473284756140786e-05, "epoch": 0.8304914744232698, "percentage": 16.63, "elapsed_time": "1:49:43", "remaining_time": "9:10:12"}
+{"current_steps": 208, "total_steps": 1245, "loss": 0.6328, "lr": 3.946041813916713e-05, "epoch": 0.8345035105315948, "percentage": 16.71, "elapsed_time": "1:50:13", "remaining_time": "9:09:33"}
+{"current_steps": 209, "total_steps": 1245, "loss": 0.6433, "lr": 3.9447398407953536e-05, "epoch": 0.8385155466399198, "percentage": 16.79, "elapsed_time": "1:50:45", "remaining_time": "9:09:01"}
+{"current_steps": 210, "total_steps": 1245, "loss": 0.6832, "lr": 3.943422566493902e-05, "epoch": 0.8425275827482447, "percentage": 16.87, "elapsed_time": "1:51:17", "remaining_time": "9:08:32"}
+{"current_steps": 211, "total_steps": 1245, "loss": 0.6315, "lr": 3.9420900013766515e-05, "epoch": 0.8465396188565697, "percentage": 16.95, "elapsed_time": "1:51:49", "remaining_time": "9:07:59"}
+{"current_steps": 212, "total_steps": 1245, "loss": 0.6445, "lr": 3.9407421559282e-05, "epoch": 0.8505516549648947, "percentage": 17.03, "elapsed_time": "1:52:20", "remaining_time": "9:07:23"}
+{"current_steps": 213, "total_steps": 1245, "loss": 0.6357, "lr": 3.939379040753374e-05, "epoch": 0.8545636910732196, "percentage": 17.11, "elapsed_time": "1:52:52", "remaining_time": "9:06:55"}
+{"current_steps": 214, "total_steps": 1245, "loss": 0.6536, "lr": 3.93800066657714e-05, "epoch": 0.8585757271815446, "percentage": 17.19, "elapsed_time": "1:53:27", "remaining_time": "9:06:35"}
+{"current_steps": 215, "total_steps": 1245, "loss": 0.6759, "lr": 3.9366070442445234e-05, "epoch": 0.8625877632898696, "percentage": 17.27, "elapsed_time": "1:54:00", "remaining_time": "9:06:11"}
+{"current_steps": 216, "total_steps": 1245, "loss": 0.6356, "lr": 3.93519818472052e-05, "epoch": 0.8665997993981945, "percentage": 17.35, "elapsed_time": "1:54:28", "remaining_time": "9:05:20"}
+{"current_steps": 217, "total_steps": 1245, "loss": 0.6603, "lr": 3.933774099090013e-05, "epoch": 0.8706118355065195, "percentage": 17.43, "elapsed_time": "1:55:00", "remaining_time": "9:04:48"}
+{"current_steps": 218, "total_steps": 1245, "loss": 0.6529, "lr": 3.9323347985576846e-05, "epoch": 0.8746238716148446, "percentage": 17.51, "elapsed_time": "1:55:34", "remaining_time": "9:04:28"}
+{"current_steps": 219, "total_steps": 1245, "loss": 0.636, "lr": 3.930880294447926e-05, "epoch": 0.8786359077231695, "percentage": 17.59, "elapsed_time": "1:56:10", "remaining_time": "9:04:14"}
+{"current_steps": 220, "total_steps": 1245, "loss": 0.6072, "lr": 3.929410598204752e-05, "epoch": 0.8826479438314945, "percentage": 17.67, "elapsed_time": "1:56:41", "remaining_time": "9:03:42"}
+{"current_steps": 221, "total_steps": 1245, "loss": 0.6071, "lr": 3.927925721391707e-05, "epoch": 0.8866599799398195, "percentage": 17.75, "elapsed_time": "1:57:13", "remaining_time": "9:03:08"}
+{"current_steps": 222, "total_steps": 1245, "loss": 0.6386, "lr": 3.9264256756917765e-05, "epoch": 0.8906720160481444, "percentage": 17.83, "elapsed_time": "1:57:44", "remaining_time": "9:02:34"}
+{"current_steps": 223, "total_steps": 1245, "loss": 0.6363, "lr": 3.9249104729072944e-05, "epoch": 0.8946840521564694, "percentage": 17.91, "elapsed_time": "1:58:20", "remaining_time": "9:02:23"}
+{"current_steps": 224, "total_steps": 1245, "loss": 0.6422, "lr": 3.923380124959852e-05, "epoch": 0.8986960882647944, "percentage": 17.99, "elapsed_time": "1:58:54", "remaining_time": "9:02:01"}
+{"current_steps": 225, "total_steps": 1245, "loss": 0.644, "lr": 3.9218346438901996e-05, "epoch": 0.9027081243731193, "percentage": 18.07, "elapsed_time": "1:59:22", "remaining_time": "9:01:09"}
+{"current_steps": 226, "total_steps": 1245, "loss": 0.6252, "lr": 3.920274041858156e-05, "epoch": 0.9067201604814443, "percentage": 18.15, "elapsed_time": "1:59:58", "remaining_time": "9:00:56"}
+{"current_steps": 227, "total_steps": 1245, "loss": 0.646, "lr": 3.918698331142512e-05, "epoch": 0.9107321965897693, "percentage": 18.23, "elapsed_time": "2:00:28", "remaining_time": "9:00:17"}
+{"current_steps": 228, "total_steps": 1245, "loss": 0.6557, "lr": 3.917107524140933e-05, "epoch": 0.9147442326980942, "percentage": 18.31, "elapsed_time": "2:01:04", "remaining_time": "9:00:03"}
+{"current_steps": 229, "total_steps": 1245, "loss": 0.6233, "lr": 3.9155016333698615e-05, "epoch": 0.9187562688064193, "percentage": 18.39, "elapsed_time": "2:01:36", "remaining_time": "8:59:30"}
+{"current_steps": 230, "total_steps": 1245, "loss": 0.614, "lr": 3.913880671464418e-05, "epoch": 0.9227683049147443, "percentage": 18.47, "elapsed_time": "2:02:07", "remaining_time": "8:58:57"}
+{"current_steps": 231, "total_steps": 1245, "loss": 0.6363, "lr": 3.912244651178304e-05, "epoch": 0.9267803410230692, "percentage": 18.55, "elapsed_time": "2:02:34", "remaining_time": "8:58:01"}
+{"current_steps": 232, "total_steps": 1245, "loss": 0.6404, "lr": 3.9105935853837e-05, "epoch": 0.9307923771313942, "percentage": 18.63, "elapsed_time": "2:03:09", "remaining_time": "8:57:45"}
+{"current_steps": 233, "total_steps": 1245, "loss": 0.6395, "lr": 3.908927487071162e-05, "epoch": 0.9348044132397192, "percentage": 18.71, "elapsed_time": "2:03:38", "remaining_time": "8:57:01"}
+{"current_steps": 234, "total_steps": 1245, "loss": 0.637, "lr": 3.9072463693495243e-05, "epoch": 0.9388164493480441, "percentage": 18.8, "elapsed_time": "2:04:05", "remaining_time": "8:56:09"}
+{"current_steps": 235, "total_steps": 1245, "loss": 0.6224, "lr": 3.905550245445793e-05, "epoch": 0.9428284854563691, "percentage": 18.88, "elapsed_time": "2:04:38", "remaining_time": "8:55:40"}
+{"current_steps": 236, "total_steps": 1245, "loss": 0.6511, "lr": 3.903839128705041e-05, "epoch": 0.9468405215646941, "percentage": 18.96, "elapsed_time": "2:05:11", "remaining_time": "8:55:12"}
+{"current_steps": 237, "total_steps": 1245, "loss": 0.639, "lr": 3.9021130325903076e-05, "epoch": 0.950852557673019, "percentage": 19.04, "elapsed_time": "2:05:45", "remaining_time": "8:54:50"}
+{"current_steps": 238, "total_steps": 1245, "loss": 0.6158, "lr": 3.9003719706824863e-05, "epoch": 0.954864593781344, "percentage": 19.12, "elapsed_time": "2:06:20", "remaining_time": "8:54:33"}
+{"current_steps": 239, "total_steps": 1245, "loss": 0.6577, "lr": 3.898615956680223e-05, "epoch": 0.958876629889669, "percentage": 19.2, "elapsed_time": "2:06:45", "remaining_time": "8:53:33"}
+{"current_steps": 240, "total_steps": 1245, "loss": 0.6416, "lr": 3.8968450043998064e-05, "epoch": 0.9628886659979939, "percentage": 19.28, "elapsed_time": "2:07:16", "remaining_time": "8:52:57"}
+{"current_steps": 241, "total_steps": 1245, "loss": 0.6399, "lr": 3.895059127775058e-05, "epoch": 0.966900702106319, "percentage": 19.36, "elapsed_time": "2:07:47", "remaining_time": "8:52:23"}
+{"current_steps": 242, "total_steps": 1245, "loss": 0.6502, "lr": 3.893258340857226e-05, "epoch": 0.970912738214644, "percentage": 19.44, "elapsed_time": "2:08:17", "remaining_time": "8:51:41"}
+{"current_steps": 243, "total_steps": 1245, "loss": 0.6472, "lr": 3.891442657814871e-05, "epoch": 0.9749247743229689, "percentage": 19.52, "elapsed_time": "2:08:48", "remaining_time": "8:51:09"}
+{"current_steps": 244, "total_steps": 1245, "loss": 0.6337, "lr": 3.889612092933756e-05, "epoch": 0.9789368104312939, "percentage": 19.6, "elapsed_time": "2:09:22", "remaining_time": "8:50:45"}
+{"current_steps": 245, "total_steps": 1245, "loss": 0.6025, "lr": 3.8877666606167354e-05, "epoch": 0.9829488465396189, "percentage": 19.68, "elapsed_time": "2:10:01", "remaining_time": "8:50:43"}
+{"current_steps": 246, "total_steps": 1245, "loss": 0.6444, "lr": 3.8859063753836386e-05, "epoch": 0.9869608826479438, "percentage": 19.76, "elapsed_time": "2:10:36", "remaining_time": "8:50:25"}
+{"current_steps": 247, "total_steps": 1245, "loss": 0.6399, "lr": 3.884031251871158e-05, "epoch": 0.9909729187562688, "percentage": 19.84, "elapsed_time": "2:11:11", "remaining_time": "8:50:05"}
+{"current_steps": 248, "total_steps": 1245, "loss": 0.6321, "lr": 3.8821413048327346e-05, "epoch": 0.9949849548645938, "percentage": 19.92, "elapsed_time": "2:11:50", "remaining_time": "8:50:00"}
+{"current_steps": 249, "total_steps": 1245, "loss": 0.6277, "lr": 3.880236549138438e-05, "epoch": 0.9989969909729187, "percentage": 20.0, "elapsed_time": "2:12:24", "remaining_time": "8:49:36"}
+{"current_steps": 250, "total_steps": 1245, "loss": 0.5593, "lr": 3.878316999774856e-05, "epoch": 1.0030090270812437, "percentage": 20.08, "elapsed_time": "2:14:55", "remaining_time": "8:56:59"}
+{"current_steps": 251, "total_steps": 1245, "loss": 0.5183, "lr": 3.876382671844969e-05, "epoch": 1.0070210631895686, "percentage": 20.16, "elapsed_time": "2:15:28", "remaining_time": "8:56:29"}
+{"current_steps": 252, "total_steps": 1245, "loss": 0.533, "lr": 3.8744335805680355e-05, "epoch": 1.0110330992978938, "percentage": 20.24, "elapsed_time": "2:15:58", "remaining_time": "8:55:49"}
+{"current_steps": 253, "total_steps": 1245, "loss": 0.5436, "lr": 3.872469741279475e-05, "epoch": 1.0150451354062187, "percentage": 20.32, "elapsed_time": "2:16:30", "remaining_time": "8:55:15"}
+{"current_steps": 254, "total_steps": 1245, "loss": 0.5331, "lr": 3.87049116943074e-05, "epoch": 1.0190571715145436, "percentage": 20.4, "elapsed_time": "2:17:00", "remaining_time": "8:54:31"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f326e54cb3a3fb2e579c058e1894522dfbfe2e9a324e63f1ba99adbb93c24a13
+size 7224