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:cbef30c6f12faaa1c3927063f435b110723f57cff0fc3562729b0018040a4772
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bfb79633910552c664c3c814aa9b8746a9f6ee834093ccc7909bf049393466
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66fb34087ada8d3c0cbcbf8ea72283d766be443c44c5191ecfe9b21e10ab79e
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6109a64f81afc3e3c3ed3bc723b2682533bdbef413ee18d263a9ad9cd927c62e
+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 +1,227 @@
+{"current_steps": 1, "total_steps": 1105, "loss": 1.7441, "lr": 3.603603603603604e-07, "epoch": 0.004509582863585118, "percentage": 0.09, "elapsed_time": "0:00:32", "remaining_time": "10:01:08"}
+{"current_steps": 2, "total_steps": 1105, "loss": 1.7415, "lr": 7.207207207207208e-07, "epoch": 0.009019165727170236, "percentage": 0.18, "elapsed_time": "0:00:56", "remaining_time": "8:38:34"}
+{"current_steps": 3, "total_steps": 1105, "loss": 1.7401, "lr": 1.0810810810810812e-06, "epoch": 0.013528748590755355, "percentage": 0.27, "elapsed_time": "0:01:20", "remaining_time": "8:11:57"}
+{"current_steps": 4, "total_steps": 1105, "loss": 1.7447, "lr": 1.4414414414414416e-06, "epoch": 0.018038331454340473, "percentage": 0.36, "elapsed_time": "0:01:44", "remaining_time": "8:00:15"}
+{"current_steps": 5, "total_steps": 1105, "loss": 1.7088, "lr": 1.801801801801802e-06, "epoch": 0.02254791431792559, "percentage": 0.45, "elapsed_time": "0:02:08", "remaining_time": "7:52:03"}
+{"current_steps": 6, "total_steps": 1105, "loss": 1.707, "lr": 2.1621621621621623e-06, "epoch": 0.02705749718151071, "percentage": 0.54, "elapsed_time": "0:02:33", "remaining_time": "7:47:28"}
+{"current_steps": 7, "total_steps": 1105, "loss": 1.6749, "lr": 2.5225225225225225e-06, "epoch": 0.03156708004509583, "percentage": 0.63, "elapsed_time": "0:02:57", "remaining_time": "7:42:49"}
+{"current_steps": 8, "total_steps": 1105, "loss": 1.6601, "lr": 2.882882882882883e-06, "epoch": 0.036076662908680945, "percentage": 0.72, "elapsed_time": "0:03:21", "remaining_time": "7:39:54"}
+{"current_steps": 9, "total_steps": 1105, "loss": 1.6475, "lr": 3.2432432432432437e-06, "epoch": 0.040586245772266064, "percentage": 0.81, "elapsed_time": "0:03:45", "remaining_time": "7:37:33"}
+{"current_steps": 10, "total_steps": 1105, "loss": 1.6547, "lr": 3.603603603603604e-06, "epoch": 0.04509582863585118, "percentage": 0.9, "elapsed_time": "0:04:09", "remaining_time": "7:35:58"}
+{"current_steps": 11, "total_steps": 1105, "loss": 1.6212, "lr": 3.9639639639639645e-06, "epoch": 0.0496054114994363, "percentage": 1.0, "elapsed_time": "0:04:34", "remaining_time": "7:34:23"}
+{"current_steps": 12, "total_steps": 1105, "loss": 1.6128, "lr": 4.324324324324325e-06, "epoch": 0.05411499436302142, "percentage": 1.09, "elapsed_time": "0:04:57", "remaining_time": "7:32:09"}
+{"current_steps": 13, "total_steps": 1105, "loss": 1.6889, "lr": 4.684684684684685e-06, "epoch": 0.058624577226606536, "percentage": 1.18, "elapsed_time": "0:05:22", "remaining_time": "7:31:24"}
+{"current_steps": 14, "total_steps": 1105, "loss": 1.6794, "lr": 5.045045045045045e-06, "epoch": 0.06313416009019165, "percentage": 1.27, "elapsed_time": "0:05:47", "remaining_time": "7:31:04"}
+{"current_steps": 15, "total_steps": 1105, "loss": 1.5862, "lr": 5.405405405405406e-06, "epoch": 0.06764374295377677, "percentage": 1.36, "elapsed_time": "0:06:11", "remaining_time": "7:29:46"}
+{"current_steps": 16, "total_steps": 1105, "loss": 1.5159, "lr": 5.765765765765766e-06, "epoch": 0.07215332581736189, "percentage": 1.45, "elapsed_time": "0:06:35", "remaining_time": "7:28:50"}
+{"current_steps": 17, "total_steps": 1105, "loss": 1.5183, "lr": 6.126126126126126e-06, "epoch": 0.07666290868094701, "percentage": 1.54, "elapsed_time": "0:07:00", "remaining_time": "7:28:01"}
+{"current_steps": 18, "total_steps": 1105, "loss": 1.4766, "lr": 6.486486486486487e-06, "epoch": 0.08117249154453213, "percentage": 1.63, "elapsed_time": "0:07:24", "remaining_time": "7:27:05"}
+{"current_steps": 19, "total_steps": 1105, "loss": 1.5237, "lr": 6.846846846846848e-06, "epoch": 0.08568207440811725, "percentage": 1.72, "elapsed_time": "0:07:48", "remaining_time": "7:26:45"}
+{"current_steps": 20, "total_steps": 1105, "loss": 1.4729, "lr": 7.207207207207208e-06, "epoch": 0.09019165727170236, "percentage": 1.81, "elapsed_time": "0:08:13", "remaining_time": "7:26:02"}
+{"current_steps": 21, "total_steps": 1105, "loss": 1.4889, "lr": 7.567567567567569e-06, "epoch": 0.09470124013528748, "percentage": 1.9, "elapsed_time": "0:08:37", "remaining_time": "7:24:48"}
+{"current_steps": 22, "total_steps": 1105, "loss": 1.4694, "lr": 7.927927927927929e-06, "epoch": 0.0992108229988726, "percentage": 1.99, "elapsed_time": "0:09:00", "remaining_time": "7:23:50"}
+{"current_steps": 23, "total_steps": 1105, "loss": 1.44, "lr": 8.288288288288289e-06, "epoch": 0.10372040586245772, "percentage": 2.08, "elapsed_time": "0:09:25", "remaining_time": "7:23:18"}
+{"current_steps": 24, "total_steps": 1105, "loss": 1.4003, "lr": 8.64864864864865e-06, "epoch": 0.10822998872604284, "percentage": 2.17, "elapsed_time": "0:09:49", "remaining_time": "7:22:40"}
+{"current_steps": 25, "total_steps": 1105, "loss": 1.4392, "lr": 9.00900900900901e-06, "epoch": 0.11273957158962795, "percentage": 2.26, "elapsed_time": "0:10:13", "remaining_time": "7:22:01"}
+{"current_steps": 26, "total_steps": 1105, "loss": 1.4629, "lr": 9.36936936936937e-06, "epoch": 0.11724915445321307, "percentage": 2.35, "elapsed_time": "0:10:37", "remaining_time": "7:21:14"}
+{"current_steps": 27, "total_steps": 1105, "loss": 1.3983, "lr": 9.729729729729732e-06, "epoch": 0.12175873731679819, "percentage": 2.44, "elapsed_time": "0:11:02", "remaining_time": "7:20:53"}
+{"current_steps": 28, "total_steps": 1105, "loss": 1.401, "lr": 1.009009009009009e-05, "epoch": 0.1262683201803833, "percentage": 2.53, "elapsed_time": "0:11:26", "remaining_time": "7:19:57"}
+{"current_steps": 29, "total_steps": 1105, "loss": 1.4099, "lr": 1.0450450450450452e-05, "epoch": 0.13077790304396844, "percentage": 2.62, "elapsed_time": "0:11:50", "remaining_time": "7:19:04"}
+{"current_steps": 30, "total_steps": 1105, "loss": 1.4376, "lr": 1.0810810810810812e-05, "epoch": 0.13528748590755355, "percentage": 2.71, "elapsed_time": "0:12:14", "remaining_time": "7:18:37"}
+{"current_steps": 31, "total_steps": 1105, "loss": 1.3534, "lr": 1.117117117117117e-05, "epoch": 0.13979706877113868, "percentage": 2.81, "elapsed_time": "0:12:38", "remaining_time": "7:17:45"}
+{"current_steps": 32, "total_steps": 1105, "loss": 1.398, "lr": 1.1531531531531532e-05, "epoch": 0.14430665163472378, "percentage": 2.9, "elapsed_time": "0:13:02", "remaining_time": "7:17:08"}
+{"current_steps": 33, "total_steps": 1105, "loss": 1.3643, "lr": 1.1891891891891894e-05, "epoch": 0.1488162344983089, "percentage": 2.99, "elapsed_time": "0:13:26", "remaining_time": "7:16:25"}
+{"current_steps": 34, "total_steps": 1105, "loss": 1.378, "lr": 1.2252252252252253e-05, "epoch": 0.15332581736189402, "percentage": 3.08, "elapsed_time": "0:13:49", "remaining_time": "7:15:41"}
+{"current_steps": 35, "total_steps": 1105, "loss": 1.3648, "lr": 1.2612612612612613e-05, "epoch": 0.15783540022547915, "percentage": 3.17, "elapsed_time": "0:14:13", "remaining_time": "7:14:46"}
+{"current_steps": 36, "total_steps": 1105, "loss": 1.3828, "lr": 1.2972972972972975e-05, "epoch": 0.16234498308906425, "percentage": 3.26, "elapsed_time": "0:14:37", "remaining_time": "7:14:18"}
+{"current_steps": 37, "total_steps": 1105, "loss": 1.3835, "lr": 1.3333333333333333e-05, "epoch": 0.1668545659526494, "percentage": 3.35, "elapsed_time": "0:15:01", "remaining_time": "7:13:31"}
+{"current_steps": 38, "total_steps": 1105, "loss": 1.3674, "lr": 1.3693693693693695e-05, "epoch": 0.1713641488162345, "percentage": 3.44, "elapsed_time": "0:15:25", "remaining_time": "7:13:06"}
+{"current_steps": 39, "total_steps": 1105, "loss": 1.3367, "lr": 1.4054054054054055e-05, "epoch": 0.17587373167981962, "percentage": 3.53, "elapsed_time": "0:15:49", "remaining_time": "7:12:23"}
+{"current_steps": 40, "total_steps": 1105, "loss": 1.3835, "lr": 1.4414414414414416e-05, "epoch": 0.18038331454340473, "percentage": 3.62, "elapsed_time": "0:16:13", "remaining_time": "7:11:52"}
+{"current_steps": 41, "total_steps": 1105, "loss": 1.3285, "lr": 1.4774774774774776e-05, "epoch": 0.18489289740698986, "percentage": 3.71, "elapsed_time": "0:16:37", "remaining_time": "7:11:26"}
+{"current_steps": 42, "total_steps": 1105, "loss": 1.3517, "lr": 1.5135135135135138e-05, "epoch": 0.18940248027057496, "percentage": 3.8, "elapsed_time": "0:17:01", "remaining_time": "7:10:59"}
+{"current_steps": 43, "total_steps": 1105, "loss": 1.3261, "lr": 1.5495495495495498e-05, "epoch": 0.1939120631341601, "percentage": 3.89, "elapsed_time": "0:17:25", "remaining_time": "7:10:31"}
+{"current_steps": 44, "total_steps": 1105, "loss": 1.3631, "lr": 1.5855855855855858e-05, "epoch": 0.1984216459977452, "percentage": 3.98, "elapsed_time": "0:17:50", "remaining_time": "7:10:07"}
+{"current_steps": 45, "total_steps": 1105, "loss": 1.3608, "lr": 1.6216216216216218e-05, "epoch": 0.20293122886133033, "percentage": 4.07, "elapsed_time": "0:18:13", "remaining_time": "7:09:22"}
+{"current_steps": 46, "total_steps": 1105, "loss": 1.3874, "lr": 1.6576576576576578e-05, "epoch": 0.20744081172491544, "percentage": 4.16, "elapsed_time": "0:18:38", "remaining_time": "7:09:01"}
+{"current_steps": 47, "total_steps": 1105, "loss": 1.3246, "lr": 1.693693693693694e-05, "epoch": 0.21195039458850057, "percentage": 4.25, "elapsed_time": "0:19:02", "remaining_time": "7:08:33"}
+{"current_steps": 48, "total_steps": 1105, "loss": 1.3327, "lr": 1.72972972972973e-05, "epoch": 0.21645997745208567, "percentage": 4.34, "elapsed_time": "0:19:26", "remaining_time": "7:08:00"}
+{"current_steps": 49, "total_steps": 1105, "loss": 1.3192, "lr": 1.765765765765766e-05, "epoch": 0.2209695603156708, "percentage": 4.43, "elapsed_time": "0:19:50", "remaining_time": "7:07:29"}
+{"current_steps": 50, "total_steps": 1105, "loss": 1.3296, "lr": 1.801801801801802e-05, "epoch": 0.2254791431792559, "percentage": 4.52, "elapsed_time": "0:20:13", "remaining_time": "7:06:54"}
+{"current_steps": 51, "total_steps": 1105, "loss": 1.3848, "lr": 1.8378378378378383e-05, "epoch": 0.22998872604284104, "percentage": 4.62, "elapsed_time": "0:20:38", "remaining_time": "7:06:27"}
+{"current_steps": 52, "total_steps": 1105, "loss": 1.3551, "lr": 1.873873873873874e-05, "epoch": 0.23449830890642615, "percentage": 4.71, "elapsed_time": "0:21:02", "remaining_time": "7:06:07"}
+{"current_steps": 53, "total_steps": 1105, "loss": 1.3022, "lr": 1.90990990990991e-05, "epoch": 0.23900789177001128, "percentage": 4.8, "elapsed_time": "0:21:27", "remaining_time": "7:05:49"}
+{"current_steps": 54, "total_steps": 1105, "loss": 1.298, "lr": 1.9459459459459463e-05, "epoch": 0.24351747463359638, "percentage": 4.89, "elapsed_time": "0:21:50", "remaining_time": "7:05:07"}
+{"current_steps": 55, "total_steps": 1105, "loss": 1.3154, "lr": 1.981981981981982e-05, "epoch": 0.2480270574971815, "percentage": 4.98, "elapsed_time": "0:22:14", "remaining_time": "7:04:44"}
+{"current_steps": 56, "total_steps": 1105, "loss": 1.3255, "lr": 2.018018018018018e-05, "epoch": 0.2525366403607666, "percentage": 5.07, "elapsed_time": "0:22:38", "remaining_time": "7:04:12"}
+{"current_steps": 57, "total_steps": 1105, "loss": 1.3287, "lr": 2.054054054054054e-05, "epoch": 0.2570462232243517, "percentage": 5.16, "elapsed_time": "0:23:02", "remaining_time": "7:03:33"}
+{"current_steps": 58, "total_steps": 1105, "loss": 1.3213, "lr": 2.0900900900900904e-05, "epoch": 0.2615558060879369, "percentage": 5.25, "elapsed_time": "0:23:26", "remaining_time": "7:03:03"}
+{"current_steps": 59, "total_steps": 1105, "loss": 1.3245, "lr": 2.1261261261261264e-05, "epoch": 0.266065388951522, "percentage": 5.34, "elapsed_time": "0:23:50", "remaining_time": "7:02:39"}
+{"current_steps": 60, "total_steps": 1105, "loss": 1.3137, "lr": 2.1621621621621624e-05, "epoch": 0.2705749718151071, "percentage": 5.43, "elapsed_time": "0:24:14", "remaining_time": "7:02:14"}
+{"current_steps": 61, "total_steps": 1105, "loss": 1.3186, "lr": 2.1981981981981984e-05, "epoch": 0.2750845546786922, "percentage": 5.52, "elapsed_time": "0:24:38", "remaining_time": "7:01:45"}
+{"current_steps": 62, "total_steps": 1105, "loss": 1.3106, "lr": 2.234234234234234e-05, "epoch": 0.27959413754227735, "percentage": 5.61, "elapsed_time": "0:25:02", "remaining_time": "7:01:16"}
+{"current_steps": 63, "total_steps": 1105, "loss": 1.2758, "lr": 2.2702702702702705e-05, "epoch": 0.28410372040586246, "percentage": 5.7, "elapsed_time": "0:25:27", "remaining_time": "7:00:57"}
+{"current_steps": 64, "total_steps": 1105, "loss": 1.2853, "lr": 2.3063063063063065e-05, "epoch": 0.28861330326944756, "percentage": 5.79, "elapsed_time": "0:25:51", "remaining_time": "7:00:33"}
+{"current_steps": 65, "total_steps": 1105, "loss": 1.3305, "lr": 2.3423423423423425e-05, "epoch": 0.29312288613303267, "percentage": 5.88, "elapsed_time": "0:26:15", "remaining_time": "7:00:04"}
+{"current_steps": 66, "total_steps": 1105, "loss": 1.2856, "lr": 2.378378378378379e-05, "epoch": 0.2976324689966178, "percentage": 5.97, "elapsed_time": "0:26:39", "remaining_time": "6:59:37"}
+{"current_steps": 67, "total_steps": 1105, "loss": 1.3123, "lr": 2.414414414414415e-05, "epoch": 0.30214205186020293, "percentage": 6.06, "elapsed_time": "0:27:02", "remaining_time": "6:59:02"}
+{"current_steps": 68, "total_steps": 1105, "loss": 1.2925, "lr": 2.4504504504504506e-05, "epoch": 0.30665163472378804, "percentage": 6.15, "elapsed_time": "0:27:26", "remaining_time": "6:58:29"}
+{"current_steps": 69, "total_steps": 1105, "loss": 1.2768, "lr": 2.4864864864864866e-05, "epoch": 0.3111612175873732, "percentage": 6.24, "elapsed_time": "0:27:50", "remaining_time": "6:58:04"}
+{"current_steps": 70, "total_steps": 1105, "loss": 1.2691, "lr": 2.5225225225225226e-05, "epoch": 0.3156708004509583, "percentage": 6.33, "elapsed_time": "0:28:14", "remaining_time": "6:57:27"}
+{"current_steps": 71, "total_steps": 1105, "loss": 1.2954, "lr": 2.558558558558559e-05, "epoch": 0.3201803833145434, "percentage": 6.43, "elapsed_time": "0:28:37", "remaining_time": "6:56:57"}
+{"current_steps": 72, "total_steps": 1105, "loss": 1.2997, "lr": 2.594594594594595e-05, "epoch": 0.3246899661781285, "percentage": 6.52, "elapsed_time": "0:29:02", "remaining_time": "6:56:35"}
+{"current_steps": 73, "total_steps": 1105, "loss": 1.3245, "lr": 2.630630630630631e-05, "epoch": 0.32919954904171367, "percentage": 6.61, "elapsed_time": "0:29:27", "remaining_time": "6:56:24"}
+{"current_steps": 74, "total_steps": 1105, "loss": 1.2691, "lr": 2.6666666666666667e-05, "epoch": 0.3337091319052988, "percentage": 6.7, "elapsed_time": "0:29:51", "remaining_time": "6:55:54"}
+{"current_steps": 75, "total_steps": 1105, "loss": 1.3416, "lr": 2.702702702702703e-05, "epoch": 0.3382187147688839, "percentage": 6.79, "elapsed_time": "0:30:15", "remaining_time": "6:55:28"}
+{"current_steps": 76, "total_steps": 1105, "loss": 1.2804, "lr": 2.738738738738739e-05, "epoch": 0.342728297632469, "percentage": 6.88, "elapsed_time": "0:30:38", "remaining_time": "6:54:58"}
+{"current_steps": 77, "total_steps": 1105, "loss": 1.3074, "lr": 2.774774774774775e-05, "epoch": 0.34723788049605414, "percentage": 6.97, "elapsed_time": "0:31:03", "remaining_time": "6:54:33"}
+{"current_steps": 78, "total_steps": 1105, "loss": 1.2636, "lr": 2.810810810810811e-05, "epoch": 0.35174746335963925, "percentage": 7.06, "elapsed_time": "0:31:27", "remaining_time": "6:54:06"}
+{"current_steps": 79, "total_steps": 1105, "loss": 1.3441, "lr": 2.8468468468468467e-05, "epoch": 0.35625704622322435, "percentage": 7.15, "elapsed_time": "0:31:50", "remaining_time": "6:53:36"}
+{"current_steps": 80, "total_steps": 1105, "loss": 1.3031, "lr": 2.882882882882883e-05, "epoch": 0.36076662908680945, "percentage": 7.24, "elapsed_time": "0:32:15", "remaining_time": "6:53:12"}
+{"current_steps": 81, "total_steps": 1105, "loss": 1.2942, "lr": 2.918918918918919e-05, "epoch": 0.3652762119503946, "percentage": 7.33, "elapsed_time": "0:32:39", "remaining_time": "6:52:46"}
+{"current_steps": 82, "total_steps": 1105, "loss": 1.3034, "lr": 2.954954954954955e-05, "epoch": 0.3697857948139797, "percentage": 7.42, "elapsed_time": "0:33:03", "remaining_time": "6:52:28"}
+{"current_steps": 83, "total_steps": 1105, "loss": 1.3119, "lr": 2.9909909909909915e-05, "epoch": 0.3742953776775648, "percentage": 7.51, "elapsed_time": "0:33:27", "remaining_time": "6:51:55"}
+{"current_steps": 84, "total_steps": 1105, "loss": 1.2506, "lr": 3.0270270270270275e-05, "epoch": 0.3788049605411499, "percentage": 7.6, "elapsed_time": "0:33:51", "remaining_time": "6:51:27"}
+{"current_steps": 85, "total_steps": 1105, "loss": 1.2912, "lr": 3.063063063063063e-05, "epoch": 0.3833145434047351, "percentage": 7.69, "elapsed_time": "0:34:15", "remaining_time": "6:51:01"}
+{"current_steps": 86, "total_steps": 1105, "loss": 1.3004, "lr": 3.0990990990990995e-05, "epoch": 0.3878241262683202, "percentage": 7.78, "elapsed_time": "0:34:38", "remaining_time": "6:50:33"}
+{"current_steps": 87, "total_steps": 1105, "loss": 1.3083, "lr": 3.135135135135135e-05, "epoch": 0.3923337091319053, "percentage": 7.87, "elapsed_time": "0:35:02", "remaining_time": "6:50:04"}
+{"current_steps": 88, "total_steps": 1105, "loss": 1.2949, "lr": 3.1711711711711716e-05, "epoch": 0.3968432919954904, "percentage": 7.96, "elapsed_time": "0:35:26", "remaining_time": "6:49:34"}
+{"current_steps": 89, "total_steps": 1105, "loss": 1.2768, "lr": 3.207207207207207e-05, "epoch": 0.40135287485907556, "percentage": 8.05, "elapsed_time": "0:35:50", "remaining_time": "6:49:10"}
+{"current_steps": 90, "total_steps": 1105, "loss": 1.3206, "lr": 3.2432432432432436e-05, "epoch": 0.40586245772266066, "percentage": 8.14, "elapsed_time": "0:36:14", "remaining_time": "6:48:41"}
+{"current_steps": 91, "total_steps": 1105, "loss": 1.2331, "lr": 3.279279279279279e-05, "epoch": 0.41037204058624577, "percentage": 8.24, "elapsed_time": "0:36:38", "remaining_time": "6:48:14"}
+{"current_steps": 92, "total_steps": 1105, "loss": 1.2896, "lr": 3.3153153153153157e-05, "epoch": 0.41488162344983087, "percentage": 8.33, "elapsed_time": "0:37:02", "remaining_time": "6:47:52"}
+{"current_steps": 93, "total_steps": 1105, "loss": 1.2787, "lr": 3.351351351351351e-05, "epoch": 0.41939120631341603, "percentage": 8.42, "elapsed_time": "0:37:26", "remaining_time": "6:47:23"}
+{"current_steps": 94, "total_steps": 1105, "loss": 1.3208, "lr": 3.387387387387388e-05, "epoch": 0.42390078917700114, "percentage": 8.51, "elapsed_time": "0:37:50", "remaining_time": "6:46:58"}
+{"current_steps": 95, "total_steps": 1105, "loss": 1.2842, "lr": 3.423423423423424e-05, "epoch": 0.42841037204058624, "percentage": 8.6, "elapsed_time": "0:38:14", "remaining_time": "6:46:32"}
+{"current_steps": 96, "total_steps": 1105, "loss": 1.3278, "lr": 3.45945945945946e-05, "epoch": 0.43291995490417134, "percentage": 8.69, "elapsed_time": "0:38:37", "remaining_time": "6:45:59"}
+{"current_steps": 97, "total_steps": 1105, "loss": 1.2771, "lr": 3.4954954954954954e-05, "epoch": 0.4374295377677565, "percentage": 8.78, "elapsed_time": "0:39:02", "remaining_time": "6:45:37"}
+{"current_steps": 98, "total_steps": 1105, "loss": 1.2932, "lr": 3.531531531531532e-05, "epoch": 0.4419391206313416, "percentage": 8.87, "elapsed_time": "0:39:25", "remaining_time": "6:45:10"}
+{"current_steps": 99, "total_steps": 1105, "loss": 1.2368, "lr": 3.567567567567568e-05, "epoch": 0.4464487034949267, "percentage": 8.96, "elapsed_time": "0:39:50", "remaining_time": "6:44:46"}
+{"current_steps": 100, "total_steps": 1105, "loss": 1.2911, "lr": 3.603603603603604e-05, "epoch": 0.4509582863585118, "percentage": 9.05, "elapsed_time": "0:40:14", "remaining_time": "6:44:21"}
+{"current_steps": 101, "total_steps": 1105, "loss": 1.2854, "lr": 3.63963963963964e-05, "epoch": 0.455467869222097, "percentage": 9.14, "elapsed_time": "0:40:38", "remaining_time": "6:43:57"}
+{"current_steps": 102, "total_steps": 1105, "loss": 1.2355, "lr": 3.6756756756756765e-05, "epoch": 0.4599774520856821, "percentage": 9.23, "elapsed_time": "0:41:02", "remaining_time": "6:43:33"}
+{"current_steps": 103, "total_steps": 1105, "loss": 1.2437, "lr": 3.711711711711712e-05, "epoch": 0.4644870349492672, "percentage": 9.32, "elapsed_time": "0:41:26", "remaining_time": "6:43:10"}
+{"current_steps": 104, "total_steps": 1105, "loss": 1.2932, "lr": 3.747747747747748e-05, "epoch": 0.4689966178128523, "percentage": 9.41, "elapsed_time": "0:41:50", "remaining_time": "6:42:45"}
+{"current_steps": 105, "total_steps": 1105, "loss": 1.2646, "lr": 3.783783783783784e-05, "epoch": 0.47350620067643745, "percentage": 9.5, "elapsed_time": "0:42:14", "remaining_time": "6:42:18"}
+{"current_steps": 106, "total_steps": 1105, "loss": 1.241, "lr": 3.81981981981982e-05, "epoch": 0.47801578354002255, "percentage": 9.59, "elapsed_time": "0:42:38", "remaining_time": "6:41:52"}
+{"current_steps": 107, "total_steps": 1105, "loss": 1.2707, "lr": 3.855855855855856e-05, "epoch": 0.48252536640360766, "percentage": 9.68, "elapsed_time": "0:43:02", "remaining_time": "6:41:27"}
+{"current_steps": 108, "total_steps": 1105, "loss": 1.2969, "lr": 3.8918918918918926e-05, "epoch": 0.48703494926719276, "percentage": 9.77, "elapsed_time": "0:43:26", "remaining_time": "6:41:03"}
+{"current_steps": 109, "total_steps": 1105, "loss": 1.2438, "lr": 3.927927927927928e-05, "epoch": 0.4915445321307779, "percentage": 9.86, "elapsed_time": "0:43:50", "remaining_time": "6:40:35"}
+{"current_steps": 110, "total_steps": 1105, "loss": 1.3073, "lr": 3.963963963963964e-05, "epoch": 0.496054114994363, "percentage": 9.95, "elapsed_time": "0:44:14", "remaining_time": "6:40:13"}
+{"current_steps": 111, "total_steps": 1105, "loss": 1.2391, "lr": 4e-05, "epoch": 0.5005636978579482, "percentage": 10.05, "elapsed_time": "0:44:39", "remaining_time": "6:39:50"}
+{"current_steps": 112, "total_steps": 1105, "loss": 1.3037, "lr": 3.9999900108941525e-05, "epoch": 0.5050732807215332, "percentage": 10.14, "elapsed_time": "0:45:02", "remaining_time": "6:39:24"}
+{"current_steps": 113, "total_steps": 1105, "loss": 1.2827, "lr": 3.9999600436763915e-05, "epoch": 0.5095828635851184, "percentage": 10.23, "elapsed_time": "0:45:27", "remaining_time": "6:39:00"}
+{"current_steps": 114, "total_steps": 1105, "loss": 1.3188, "lr": 3.999910098646063e-05, "epoch": 0.5140924464487034, "percentage": 10.32, "elapsed_time": "0:45:51", "remaining_time": "6:38:35"}
+{"current_steps": 115, "total_steps": 1105, "loss": 1.2759, "lr": 3.999840176302073e-05, "epoch": 0.5186020293122886, "percentage": 10.41, "elapsed_time": "0:46:15", "remaining_time": "6:38:10"}
+{"current_steps": 116, "total_steps": 1105, "loss": 1.2997, "lr": 3.999750277342884e-05, "epoch": 0.5231116121758738, "percentage": 10.5, "elapsed_time": "0:46:39", "remaining_time": "6:37:45"}
+{"current_steps": 117, "total_steps": 1105, "loss": 1.2697, "lr": 3.999640402666505e-05, "epoch": 0.5276211950394588, "percentage": 10.59, "elapsed_time": "0:47:02", "remaining_time": "6:37:17"}
+{"current_steps": 118, "total_steps": 1105, "loss": 1.3007, "lr": 3.999510553370487e-05, "epoch": 0.532130777903044, "percentage": 10.68, "elapsed_time": "0:47:27", "remaining_time": "6:36:54"}
+{"current_steps": 119, "total_steps": 1105, "loss": 1.2615, "lr": 3.999360730751907e-05, "epoch": 0.5366403607666291, "percentage": 10.77, "elapsed_time": "0:47:51", "remaining_time": "6:36:29"}
+{"current_steps": 120, "total_steps": 1105, "loss": 1.2899, "lr": 3.9991909363073595e-05, "epoch": 0.5411499436302142, "percentage": 10.86, "elapsed_time": "0:48:15", "remaining_time": "6:36:04"}
+{"current_steps": 121, "total_steps": 1105, "loss": 1.3223, "lr": 3.999001171732939e-05, "epoch": 0.5456595264937993, "percentage": 10.95, "elapsed_time": "0:48:38", "remaining_time": "6:35:37"}
+{"current_steps": 122, "total_steps": 1105, "loss": 1.2553, "lr": 3.9987914389242257e-05, "epoch": 0.5501691093573844, "percentage": 11.04, "elapsed_time": "0:49:03", "remaining_time": "6:35:13"}
+{"current_steps": 123, "total_steps": 1105, "loss": 1.2661, "lr": 3.9985617399762606e-05, "epoch": 0.5546786922209695, "percentage": 11.13, "elapsed_time": "0:49:27", "remaining_time": "6:34:48"}
+{"current_steps": 124, "total_steps": 1105, "loss": 1.2899, "lr": 3.998312077183532e-05, "epoch": 0.5591882750845547, "percentage": 11.22, "elapsed_time": "0:49:51", "remaining_time": "6:34:24"}
+{"current_steps": 125, "total_steps": 1105, "loss": 1.3068, "lr": 3.9980424530399475e-05, "epoch": 0.5636978579481398, "percentage": 11.31, "elapsed_time": "0:50:15", "remaining_time": "6:34:03"}
+{"current_steps": 126, "total_steps": 1105, "loss": 1.2842, "lr": 3.997752870238811e-05, "epoch": 0.5682074408117249, "percentage": 11.4, "elapsed_time": "0:50:39", "remaining_time": "6:33:37"}
+{"current_steps": 127, "total_steps": 1105, "loss": 1.2668, "lr": 3.9974433316727965e-05, "epoch": 0.5727170236753101, "percentage": 11.49, "elapsed_time": "0:51:04", "remaining_time": "6:33:17"}
+{"current_steps": 128, "total_steps": 1105, "loss": 1.2785, "lr": 3.997113840433917e-05, "epoch": 0.5772266065388951, "percentage": 11.58, "elapsed_time": "0:51:28", "remaining_time": "6:32:55"}
+{"current_steps": 129, "total_steps": 1105, "loss": 1.2286, "lr": 3.9967643998134956e-05, "epoch": 0.5817361894024803, "percentage": 11.67, "elapsed_time": "0:51:52", "remaining_time": "6:32:30"}
+{"current_steps": 130, "total_steps": 1105, "loss": 1.3004, "lr": 3.996395013302131e-05, "epoch": 0.5862457722660653, "percentage": 11.76, "elapsed_time": "0:52:16", "remaining_time": "6:32:01"}
+{"current_steps": 131, "total_steps": 1105, "loss": 1.228, "lr": 3.9960056845896646e-05, "epoch": 0.5907553551296505, "percentage": 11.86, "elapsed_time": "0:52:40", "remaining_time": "6:31:41"}
+{"current_steps": 132, "total_steps": 1105, "loss": 1.2764, "lr": 3.995596417565143e-05, "epoch": 0.5952649379932357, "percentage": 11.95, "elapsed_time": "0:53:05", "remaining_time": "6:31:18"}
+{"current_steps": 133, "total_steps": 1105, "loss": 1.2919, "lr": 3.995167216316776e-05, "epoch": 0.5997745208568207, "percentage": 12.04, "elapsed_time": "0:53:29", "remaining_time": "6:30:56"}
+{"current_steps": 134, "total_steps": 1105, "loss": 1.2549, "lr": 3.9947180851319017e-05, "epoch": 0.6042841037204059, "percentage": 12.13, "elapsed_time": "0:53:54", "remaining_time": "6:30:35"}
+{"current_steps": 135, "total_steps": 1105, "loss": 1.2275, "lr": 3.994249028496939e-05, "epoch": 0.608793686583991, "percentage": 12.22, "elapsed_time": "0:54:18", "remaining_time": "6:30:10"}
+{"current_steps": 136, "total_steps": 1105, "loss": 1.2316, "lr": 3.993760051097343e-05, "epoch": 0.6133032694475761, "percentage": 12.31, "elapsed_time": "0:54:42", "remaining_time": "6:29:47"}
+{"current_steps": 137, "total_steps": 1105, "loss": 1.2576, "lr": 3.993251157817562e-05, "epoch": 0.6178128523111612, "percentage": 12.4, "elapsed_time": "0:55:06", "remaining_time": "6:29:22"}
+{"current_steps": 138, "total_steps": 1105, "loss": 1.2764, "lr": 3.992722353740984e-05, "epoch": 0.6223224351747464, "percentage": 12.49, "elapsed_time": "0:55:31", "remaining_time": "6:29:03"}
+{"current_steps": 139, "total_steps": 1105, "loss": 1.3034, "lr": 3.99217364414989e-05, "epoch": 0.6268320180383314, "percentage": 12.58, "elapsed_time": "0:55:55", "remaining_time": "6:28:38"}
+{"current_steps": 140, "total_steps": 1105, "loss": 1.2906, "lr": 3.9916050345253976e-05, "epoch": 0.6313416009019166, "percentage": 12.67, "elapsed_time": "0:56:19", "remaining_time": "6:28:17"}
+{"current_steps": 141, "total_steps": 1105, "loss": 1.2419, "lr": 3.991016530547408e-05, "epoch": 0.6358511837655016, "percentage": 12.76, "elapsed_time": "0:56:43", "remaining_time": "6:27:52"}
+{"current_steps": 142, "total_steps": 1105, "loss": 1.2755, "lr": 3.9904081380945497e-05, "epoch": 0.6403607666290868, "percentage": 12.85, "elapsed_time": "0:57:08", "remaining_time": "6:27:32"}
+{"current_steps": 143, "total_steps": 1105, "loss": 1.2565, "lr": 3.9897798632441206e-05, "epoch": 0.644870349492672, "percentage": 12.94, "elapsed_time": "0:57:32", "remaining_time": "6:27:09"}
+{"current_steps": 144, "total_steps": 1105, "loss": 1.2593, "lr": 3.9891317122720236e-05, "epoch": 0.649379932356257, "percentage": 13.03, "elapsed_time": "0:57:56", "remaining_time": "6:26:40"}
+{"current_steps": 145, "total_steps": 1105, "loss": 1.267, "lr": 3.988463691652708e-05, "epoch": 0.6538895152198422, "percentage": 13.12, "elapsed_time": "0:58:20", "remaining_time": "6:26:15"}
+{"current_steps": 146, "total_steps": 1105, "loss": 1.2809, "lr": 3.9877758080591016e-05, "epoch": 0.6583990980834273, "percentage": 13.21, "elapsed_time": "0:58:44", "remaining_time": "6:25:50"}
+{"current_steps": 147, "total_steps": 1105, "loss": 1.2832, "lr": 3.9870680683625475e-05, "epoch": 0.6629086809470124, "percentage": 13.3, "elapsed_time": "0:59:08", "remaining_time": "6:25:25"}
+{"current_steps": 148, "total_steps": 1105, "loss": 1.2747, "lr": 3.986340479632731e-05, "epoch": 0.6674182638105975, "percentage": 13.39, "elapsed_time": "0:59:32", "remaining_time": "6:24:59"}
+{"current_steps": 149, "total_steps": 1105, "loss": 1.2163, "lr": 3.9855930491376147e-05, "epoch": 0.6719278466741826, "percentage": 13.48, "elapsed_time": "0:59:56", "remaining_time": "6:24:35"}
+{"current_steps": 150, "total_steps": 1105, "loss": 1.251, "lr": 3.984825784343359e-05, "epoch": 0.6764374295377678, "percentage": 13.57, "elapsed_time": "1:00:20", "remaining_time": "6:24:11"}
+{"current_steps": 151, "total_steps": 1105, "loss": 1.2695, "lr": 3.984038692914255e-05, "epoch": 0.6809470124013529, "percentage": 13.67, "elapsed_time": "1:00:44", "remaining_time": "6:23:42"}
+{"current_steps": 152, "total_steps": 1105, "loss": 1.2682, "lr": 3.9832317827126414e-05, "epoch": 0.685456595264938, "percentage": 13.76, "elapsed_time": "1:01:08", "remaining_time": "6:23:19"}
+{"current_steps": 153, "total_steps": 1105, "loss": 1.2862, "lr": 3.982405061798829e-05, "epoch": 0.6899661781285231, "percentage": 13.85, "elapsed_time": "1:01:32", "remaining_time": "6:22:53"}
+{"current_steps": 154, "total_steps": 1105, "loss": 1.2438, "lr": 3.981558538431022e-05, "epoch": 0.6944757609921083, "percentage": 13.94, "elapsed_time": "1:01:56", "remaining_time": "6:22:28"}
+{"current_steps": 155, "total_steps": 1105, "loss": 1.2175, "lr": 3.980692221065231e-05, "epoch": 0.6989853438556933, "percentage": 14.03, "elapsed_time": "1:02:20", "remaining_time": "6:22:05"}
+{"current_steps": 156, "total_steps": 1105, "loss": 1.2634, "lr": 3.979806118355192e-05, "epoch": 0.7034949267192785, "percentage": 14.12, "elapsed_time": "1:02:44", "remaining_time": "6:21:41"}
+{"current_steps": 157, "total_steps": 1105, "loss": 1.2144, "lr": 3.9789002391522786e-05, "epoch": 0.7080045095828635, "percentage": 14.21, "elapsed_time": "1:03:08", "remaining_time": "6:21:17"}
+{"current_steps": 158, "total_steps": 1105, "loss": 1.3034, "lr": 3.9779745925054146e-05, "epoch": 0.7125140924464487, "percentage": 14.3, "elapsed_time": "1:03:32", "remaining_time": "6:20:51"}
+{"current_steps": 159, "total_steps": 1105, "loss": 1.2542, "lr": 3.977029187660981e-05, "epoch": 0.7170236753100339, "percentage": 14.39, "elapsed_time": "1:03:56", "remaining_time": "6:20:28"}
+{"current_steps": 160, "total_steps": 1105, "loss": 1.2464, "lr": 3.976064034062728e-05, "epoch": 0.7215332581736189, "percentage": 14.48, "elapsed_time": "1:04:20", "remaining_time": "6:20:03"}
+{"current_steps": 161, "total_steps": 1105, "loss": 1.2645, "lr": 3.9750791413516776e-05, "epoch": 0.7260428410372041, "percentage": 14.57, "elapsed_time": "1:04:45", "remaining_time": "6:19:39"}
+{"current_steps": 162, "total_steps": 1105, "loss": 1.282, "lr": 3.974074519366026e-05, "epoch": 0.7305524239007892, "percentage": 14.66, "elapsed_time": "1:05:09", "remaining_time": "6:19:15"}
+{"current_steps": 163, "total_steps": 1105, "loss": 1.2594, "lr": 3.97305017814105e-05, "epoch": 0.7350620067643743, "percentage": 14.75, "elapsed_time": "1:05:32", "remaining_time": "6:18:48"}
+{"current_steps": 164, "total_steps": 1105, "loss": 1.3169, "lr": 3.972006127909e-05, "epoch": 0.7395715896279594, "percentage": 14.84, "elapsed_time": "1:05:56", "remaining_time": "6:18:23"}
+{"current_steps": 165, "total_steps": 1105, "loss": 1.2925, "lr": 3.970942379099007e-05, "epoch": 0.7440811724915445, "percentage": 14.93, "elapsed_time": "1:06:21", "remaining_time": "6:18:00"}
+{"current_steps": 166, "total_steps": 1105, "loss": 1.2366, "lr": 3.969858942336969e-05, "epoch": 0.7485907553551296, "percentage": 15.02, "elapsed_time": "1:06:44", "remaining_time": "6:17:34"}
+{"current_steps": 167, "total_steps": 1105, "loss": 1.2515, "lr": 3.9687558284454515e-05, "epoch": 0.7531003382187148, "percentage": 15.11, "elapsed_time": "1:07:09", "remaining_time": "6:17:11"}
+{"current_steps": 168, "total_steps": 1105, "loss": 1.3143, "lr": 3.967633048443575e-05, "epoch": 0.7576099210822999, "percentage": 15.2, "elapsed_time": "1:07:33", "remaining_time": "6:16:47"}
+{"current_steps": 169, "total_steps": 1105, "loss": 1.2703, "lr": 3.966490613546908e-05, "epoch": 0.762119503945885, "percentage": 15.29, "elapsed_time": "1:07:57", "remaining_time": "6:16:23"}
+{"current_steps": 170, "total_steps": 1105, "loss": 1.3046, "lr": 3.965328535167354e-05, "epoch": 0.7666290868094702, "percentage": 15.38, "elapsed_time": "1:08:21", "remaining_time": "6:15:59"}
+{"current_steps": 171, "total_steps": 1105, "loss": 1.2736, "lr": 3.964146824913036e-05, "epoch": 0.7711386696730552, "percentage": 15.48, "elapsed_time": "1:08:45", "remaining_time": "6:15:35"}
+{"current_steps": 172, "total_steps": 1105, "loss": 1.2836, "lr": 3.962945494588183e-05, "epoch": 0.7756482525366404, "percentage": 15.57, "elapsed_time": "1:09:09", "remaining_time": "6:15:10"}
+{"current_steps": 173, "total_steps": 1105, "loss": 1.2876, "lr": 3.961724556193013e-05, "epoch": 0.7801578354002254, "percentage": 15.66, "elapsed_time": "1:09:33", "remaining_time": "6:14:45"}
+{"current_steps": 174, "total_steps": 1105, "loss": 1.2624, "lr": 3.960484021923606e-05, "epoch": 0.7846674182638106, "percentage": 15.75, "elapsed_time": "1:09:57", "remaining_time": "6:14:19"}
+{"current_steps": 175, "total_steps": 1105, "loss": 1.2461, "lr": 3.9592239041717914e-05, "epoch": 0.7891770011273957, "percentage": 15.84, "elapsed_time": "1:10:21", "remaining_time": "6:13:53"}
+{"current_steps": 176, "total_steps": 1105, "loss": 1.2296, "lr": 3.9579442155250186e-05, "epoch": 0.7936865839909808, "percentage": 15.93, "elapsed_time": "1:10:45", "remaining_time": "6:13:29"}
+{"current_steps": 177, "total_steps": 1105, "loss": 1.2857, "lr": 3.9566449687662325e-05, "epoch": 0.798196166854566, "percentage": 16.02, "elapsed_time": "1:11:09", "remaining_time": "6:13:06"}
+{"current_steps": 178, "total_steps": 1105, "loss": 1.2219, "lr": 3.955326176873748e-05, "epoch": 0.8027057497181511, "percentage": 16.11, "elapsed_time": "1:11:33", "remaining_time": "6:12:40"}
+{"current_steps": 179, "total_steps": 1105, "loss": 1.2857, "lr": 3.9539878530211146e-05, "epoch": 0.8072153325817362, "percentage": 16.2, "elapsed_time": "1:11:57", "remaining_time": "6:12:16"}
+{"current_steps": 180, "total_steps": 1105, "loss": 1.2383, "lr": 3.952630010576993e-05, "epoch": 0.8117249154453213, "percentage": 16.29, "elapsed_time": "1:12:22", "remaining_time": "6:11:53"}
+{"current_steps": 181, "total_steps": 1105, "loss": 1.2237, "lr": 3.951252663105014e-05, "epoch": 0.8162344983089064, "percentage": 16.38, "elapsed_time": "1:12:45", "remaining_time": "6:11:28"}
+{"current_steps": 182, "total_steps": 1105, "loss": 1.2374, "lr": 3.949855824363647e-05, "epoch": 0.8207440811724915, "percentage": 16.47, "elapsed_time": "1:13:10", "remaining_time": "6:11:03"}
+{"current_steps": 183, "total_steps": 1105, "loss": 1.2458, "lr": 3.948439508306064e-05, "epoch": 0.8252536640360767, "percentage": 16.56, "elapsed_time": "1:13:35", "remaining_time": "6:10:44"}
+{"current_steps": 184, "total_steps": 1105, "loss": 1.2303, "lr": 3.947003729079994e-05, "epoch": 0.8297632468996617, "percentage": 16.65, "elapsed_time": "1:13:59", "remaining_time": "6:10:19"}
+{"current_steps": 185, "total_steps": 1105, "loss": 1.2397, "lr": 3.945548501027587e-05, "epoch": 0.8342728297632469, "percentage": 16.74, "elapsed_time": "1:14:22", "remaining_time": "6:09:53"}
+{"current_steps": 186, "total_steps": 1105, "loss": 1.2565, "lr": 3.944073838685273e-05, "epoch": 0.8387824126268321, "percentage": 16.83, "elapsed_time": "1:14:46", "remaining_time": "6:09:28"}
+{"current_steps": 187, "total_steps": 1105, "loss": 1.259, "lr": 3.942579756783608e-05, "epoch": 0.8432919954904171, "percentage": 16.92, "elapsed_time": "1:15:10", "remaining_time": "6:09:04"}
+{"current_steps": 188, "total_steps": 1105, "loss": 1.2733, "lr": 3.941066270247135e-05, "epoch": 0.8478015783540023, "percentage": 17.01, "elapsed_time": "1:15:35", "remaining_time": "6:08:42"}
+{"current_steps": 189, "total_steps": 1105, "loss": 1.2141, "lr": 3.939533394194231e-05, "epoch": 0.8523111612175873, "percentage": 17.1, "elapsed_time": "1:15:59", "remaining_time": "6:08:19"}
+{"current_steps": 190, "total_steps": 1105, "loss": 1.2918, "lr": 3.9379811439369565e-05, "epoch": 0.8568207440811725, "percentage": 17.19, "elapsed_time": "1:16:23", "remaining_time": "6:07:54"}
+{"current_steps": 191, "total_steps": 1105, "loss": 1.2598, "lr": 3.9364095349809053e-05, "epoch": 0.8613303269447576, "percentage": 17.29, "elapsed_time": "1:16:47", "remaining_time": "6:07:29"}
+{"current_steps": 192, "total_steps": 1105, "loss": 1.2298, "lr": 3.9348185830250436e-05, "epoch": 0.8658399098083427, "percentage": 17.38, "elapsed_time": "1:17:11", "remaining_time": "6:07:03"}
+{"current_steps": 193, "total_steps": 1105, "loss": 1.247, "lr": 3.9332083039615605e-05, "epoch": 0.8703494926719278, "percentage": 17.47, "elapsed_time": "1:17:35", "remaining_time": "6:06:39"}
+{"current_steps": 194, "total_steps": 1105, "loss": 1.2838, "lr": 3.931578713875704e-05, "epoch": 0.874859075535513, "percentage": 17.56, "elapsed_time": "1:17:58", "remaining_time": "6:06:10"}
+{"current_steps": 195, "total_steps": 1105, "loss": 1.2656, "lr": 3.92992982904562e-05, "epoch": 0.8793686583990981, "percentage": 17.65, "elapsed_time": "1:18:22", "remaining_time": "6:05:46"}
+{"current_steps": 196, "total_steps": 1105, "loss": 1.2061, "lr": 3.928261665942196e-05, "epoch": 0.8838782412626832, "percentage": 17.74, "elapsed_time": "1:18:46", "remaining_time": "6:05:21"}
+{"current_steps": 197, "total_steps": 1105, "loss": 1.2502, "lr": 3.926574241228888e-05, "epoch": 0.8883878241262683, "percentage": 17.83, "elapsed_time": "1:19:10", "remaining_time": "6:04:56"}
+{"current_steps": 198, "total_steps": 1105, "loss": 1.2472, "lr": 3.924867571761562e-05, "epoch": 0.8928974069898534, "percentage": 17.92, "elapsed_time": "1:19:35", "remaining_time": "6:04:34"}
+{"current_steps": 199, "total_steps": 1105, "loss": 1.2616, "lr": 3.9231416745883175e-05, "epoch": 0.8974069898534386, "percentage": 18.01, "elapsed_time": "1:19:59", "remaining_time": "6:04:10"}
+{"current_steps": 200, "total_steps": 1105, "loss": 1.2327, "lr": 3.9213965669493254e-05, "epoch": 0.9019165727170236, "percentage": 18.1, "elapsed_time": "1:20:23", "remaining_time": "6:03:46"}
+{"current_steps": 201, "total_steps": 1105, "loss": 1.2759, "lr": 3.9196322662766516e-05, "epoch": 0.9064261555806088, "percentage": 18.19, "elapsed_time": "1:20:47", "remaining_time": "6:03:21"}
+{"current_steps": 202, "total_steps": 1105, "loss": 1.241, "lr": 3.91784879019408e-05, "epoch": 0.910935738444194, "percentage": 18.28, "elapsed_time": "1:21:11", "remaining_time": "6:02:57"}
+{"current_steps": 203, "total_steps": 1105, "loss": 1.2329, "lr": 3.9160461565169445e-05, "epoch": 0.915445321307779, "percentage": 18.37, "elapsed_time": "1:21:35", "remaining_time": "6:02:32"}
+{"current_steps": 204, "total_steps": 1105, "loss": 1.2638, "lr": 3.9142243832519414e-05, "epoch": 0.9199549041713642, "percentage": 18.46, "elapsed_time": "1:21:59", "remaining_time": "6:02:06"}
+{"current_steps": 205, "total_steps": 1105, "loss": 1.2625, "lr": 3.912383488596958e-05, "epoch": 0.9244644870349493, "percentage": 18.55, "elapsed_time": "1:22:23", "remaining_time": "6:01:41"}
+{"current_steps": 206, "total_steps": 1105, "loss": 1.2353, "lr": 3.910523490940886e-05, "epoch": 0.9289740698985344, "percentage": 18.64, "elapsed_time": "1:22:47", "remaining_time": "6:01:20"}
+{"current_steps": 207, "total_steps": 1105, "loss": 1.2796, "lr": 3.908644408863438e-05, "epoch": 0.9334836527621195, "percentage": 18.73, "elapsed_time": "1:23:11", "remaining_time": "6:00:55"}
+{"current_steps": 208, "total_steps": 1105, "loss": 1.247, "lr": 3.9067462611349636e-05, "epoch": 0.9379932356257046, "percentage": 18.82, "elapsed_time": "1:23:35", "remaining_time": "6:00:28"}
+{"current_steps": 209, "total_steps": 1105, "loss": 1.2775, "lr": 3.904829066716263e-05, "epoch": 0.9425028184892897, "percentage": 18.91, "elapsed_time": "1:23:59", "remaining_time": "6:00:03"}
+{"current_steps": 210, "total_steps": 1105, "loss": 1.2389, "lr": 3.902892844758393e-05, "epoch": 0.9470124013528749, "percentage": 19.0, "elapsed_time": "1:24:22", "remaining_time": "5:59:36"}
+{"current_steps": 211, "total_steps": 1105, "loss": 1.2765, "lr": 3.9009376146024794e-05, "epoch": 0.95152198421646, "percentage": 19.1, "elapsed_time": "1:24:46", "remaining_time": "5:59:09"}
+{"current_steps": 212, "total_steps": 1105, "loss": 1.2412, "lr": 3.898963395779523e-05, "epoch": 0.9560315670800451, "percentage": 19.19, "elapsed_time": "1:25:10", "remaining_time": "5:58:48"}
+{"current_steps": 213, "total_steps": 1105, "loss": 1.2558, "lr": 3.896970208010206e-05, "epoch": 0.9605411499436303, "percentage": 19.28, "elapsed_time": "1:25:35", "remaining_time": "5:58:25"}
+{"current_steps": 214, "total_steps": 1105, "loss": 1.2639, "lr": 3.894958071204691e-05, "epoch": 0.9650507328072153, "percentage": 19.37, "elapsed_time": "1:25:59", "remaining_time": "5:58:02"}
+{"current_steps": 215, "total_steps": 1105, "loss": 1.2962, "lr": 3.892927005462426e-05, "epoch": 0.9695603156708005, "percentage": 19.46, "elapsed_time": "1:26:23", "remaining_time": "5:57:37"}
+{"current_steps": 216, "total_steps": 1105, "loss": 1.2562, "lr": 3.890877031071941e-05, "epoch": 0.9740698985343855, "percentage": 19.55, "elapsed_time": "1:26:47", "remaining_time": "5:57:11"}
+{"current_steps": 217, "total_steps": 1105, "loss": 1.2426, "lr": 3.888808168510648e-05, "epoch": 0.9785794813979707, "percentage": 19.64, "elapsed_time": "1:27:11", "remaining_time": "5:56:46"}
+{"current_steps": 218, "total_steps": 1105, "loss": 1.2326, "lr": 3.886720438444633e-05, "epoch": 0.9830890642615558, "percentage": 19.73, "elapsed_time": "1:27:34", "remaining_time": "5:56:18"}
+{"current_steps": 219, "total_steps": 1105, "loss": 1.2733, "lr": 3.8846138617284535e-05, "epoch": 0.9875986471251409, "percentage": 19.82, "elapsed_time": "1:27:57", "remaining_time": "5:55:51"}
+{"current_steps": 220, "total_steps": 1105, "loss": 1.2407, "lr": 3.882488459404927e-05, "epoch": 0.992108229988726, "percentage": 19.91, "elapsed_time": "1:28:22", "remaining_time": "5:55:29"}
+{"current_steps": 221, "total_steps": 1105, "loss": 1.2365, "lr": 3.880344252704923e-05, "epoch": 0.9966178128523112, "percentage": 20.0, "elapsed_time": "1:28:47", "remaining_time": "5:55:08"}
+{"current_steps": 222, "total_steps": 1105, "loss": 1.2279, "lr": 3.878181263047148e-05, "epoch": 1.003382187147689, "percentage": 20.09, "elapsed_time": "1:31:44", "remaining_time": "6:04:55"}
+{"current_steps": 223, "total_steps": 1105, "loss": 1.2262, "lr": 3.8759995120379355e-05, "epoch": 1.007891770011274, "percentage": 20.18, "elapsed_time": "1:32:08", "remaining_time": "6:04:26"}
+{"current_steps": 224, "total_steps": 1105, "loss": 1.1842, "lr": 3.873799021471027e-05, "epoch": 1.012401352874859, "percentage": 20.27, "elapsed_time": "1:32:32", "remaining_time": "6:03:57"}
+{"current_steps": 225, "total_steps": 1105, "loss": 1.1999, "lr": 3.871579813327355e-05, "epoch": 1.0169109357384443, "percentage": 20.36, "elapsed_time": "1:32:56", "remaining_time": "6:03:28"}
+{"current_steps": 226, "total_steps": 1105, "loss": 1.2036, "lr": 3.8693419097748256e-05, "epoch": 1.0214205186020293, "percentage": 20.45, "elapsed_time": "1:33:20", "remaining_time": "6:03:01"}
+{"current_steps": 227, "total_steps": 1105, "loss": 1.2475, "lr": 3.867085333168094e-05, "epoch": 1.0259301014656144, "percentage": 20.54, "elapsed_time": "1:33:43", "remaining_time": "6:02:32"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929df364a31c44e2d94e00fbc4c1550b045bbf09501760210eaa3480608b4a46
+size 7352