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 sha256:559c2fb671d203cbccab110aaafcd4aaafd4d9486730cf20fb152c402f67fcdd
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b6ee2047d0e1b3d714ff6debb29023c5aa67c784c77251517421da8b81406a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a837e275265cdb1da3ef2bacf4e26021d6204535c6d8ce4b622efa11e0ca96ab
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ee9e7c4fcfa455d7a6ce632a89233ceea6ec1fcb278c0c31a378374a937277
+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 +1,238 @@
+{"current_steps": 1, "total_steps": 1638, "loss": 0.8544, "lr": 2.439024390243903e-07, "epoch": 0.0042643923240938165, "percentage": 0.06, "elapsed_time": "0:00:47", "remaining_time": "21:36:42"}
+{"current_steps": 2, "total_steps": 1638, "loss": 0.8386, "lr": 4.878048780487805e-07, "epoch": 0.008528784648187633, "percentage": 0.12, "elapsed_time": "0:01:24", "remaining_time": "19:16:52"}
+{"current_steps": 3, "total_steps": 1638, "loss": 0.8842, "lr": 7.317073170731707e-07, "epoch": 0.01279317697228145, "percentage": 0.18, "elapsed_time": "0:02:08", "remaining_time": "19:28:25"}
+{"current_steps": 4, "total_steps": 1638, "loss": 0.8585, "lr": 9.75609756097561e-07, "epoch": 0.017057569296375266, "percentage": 0.24, "elapsed_time": "0:02:50", "remaining_time": "19:20:52"}
+{"current_steps": 5, "total_steps": 1638, "loss": 0.8617, "lr": 1.2195121951219514e-06, "epoch": 0.021321961620469083, "percentage": 0.31, "elapsed_time": "0:03:30", "remaining_time": "19:05:36"}
+{"current_steps": 6, "total_steps": 1638, "loss": 0.8788, "lr": 1.4634146341463414e-06, "epoch": 0.0255863539445629, "percentage": 0.37, "elapsed_time": "0:04:14", "remaining_time": "19:12:03"}
+{"current_steps": 7, "total_steps": 1638, "loss": 0.8485, "lr": 1.707317073170732e-06, "epoch": 0.029850746268656716, "percentage": 0.43, "elapsed_time": "0:04:56", "remaining_time": "19:13:14"}
+{"current_steps": 8, "total_steps": 1638, "loss": 0.7961, "lr": 1.951219512195122e-06, "epoch": 0.03411513859275053, "percentage": 0.49, "elapsed_time": "0:05:38", "remaining_time": "19:09:55"}
+{"current_steps": 9, "total_steps": 1638, "loss": 0.8442, "lr": 2.1951219512195125e-06, "epoch": 0.03837953091684435, "percentage": 0.55, "elapsed_time": "0:06:21", "remaining_time": "19:11:17"}
+{"current_steps": 10, "total_steps": 1638, "loss": 0.7601, "lr": 2.4390243902439027e-06, "epoch": 0.042643923240938165, "percentage": 0.61, "elapsed_time": "0:07:05", "remaining_time": "19:14:29"}
+{"current_steps": 11, "total_steps": 1638, "loss": 0.7609, "lr": 2.682926829268293e-06, "epoch": 0.046908315565031986, "percentage": 0.67, "elapsed_time": "0:07:50", "remaining_time": "19:19:18"}
+{"current_steps": 12, "total_steps": 1638, "loss": 0.7664, "lr": 2.926829268292683e-06, "epoch": 0.0511727078891258, "percentage": 0.73, "elapsed_time": "0:08:34", "remaining_time": "19:22:41"}
+{"current_steps": 13, "total_steps": 1638, "loss": 0.7287, "lr": 3.1707317073170736e-06, "epoch": 0.05543710021321962, "percentage": 0.79, "elapsed_time": "0:09:14", "remaining_time": "19:15:11"}
+{"current_steps": 14, "total_steps": 1638, "loss": 0.7397, "lr": 3.414634146341464e-06, "epoch": 0.05970149253731343, "percentage": 0.85, "elapsed_time": "0:10:02", "remaining_time": "19:24:14"}
+{"current_steps": 15, "total_steps": 1638, "loss": 0.7363, "lr": 3.6585365853658537e-06, "epoch": 0.06396588486140725, "percentage": 0.92, "elapsed_time": "0:10:41", "remaining_time": "19:16:26"}
+{"current_steps": 16, "total_steps": 1638, "loss": 0.7279, "lr": 3.902439024390244e-06, "epoch": 0.06823027718550106, "percentage": 0.98, "elapsed_time": "0:11:29", "remaining_time": "19:24:31"}
+{"current_steps": 17, "total_steps": 1638, "loss": 0.7128, "lr": 4.146341463414634e-06, "epoch": 0.07249466950959488, "percentage": 1.04, "elapsed_time": "0:12:11", "remaining_time": "19:23:08"}
+{"current_steps": 18, "total_steps": 1638, "loss": 0.7136, "lr": 4.390243902439025e-06, "epoch": 0.0767590618336887, "percentage": 1.1, "elapsed_time": "0:12:53", "remaining_time": "19:19:32"}
+{"current_steps": 19, "total_steps": 1638, "loss": 0.686, "lr": 4.634146341463416e-06, "epoch": 0.08102345415778252, "percentage": 1.16, "elapsed_time": "0:13:35", "remaining_time": "19:17:44"}
+{"current_steps": 20, "total_steps": 1638, "loss": 0.6627, "lr": 4.8780487804878055e-06, "epoch": 0.08528784648187633, "percentage": 1.22, "elapsed_time": "0:14:17", "remaining_time": "19:15:44"}
+{"current_steps": 21, "total_steps": 1638, "loss": 0.6594, "lr": 5.121951219512195e-06, "epoch": 0.08955223880597014, "percentage": 1.28, "elapsed_time": "0:15:00", "remaining_time": "19:15:28"}
+{"current_steps": 22, "total_steps": 1638, "loss": 0.6359, "lr": 5.365853658536586e-06, "epoch": 0.09381663113006397, "percentage": 1.34, "elapsed_time": "0:15:48", "remaining_time": "19:20:59"}
+{"current_steps": 23, "total_steps": 1638, "loss": 0.64, "lr": 5.609756097560977e-06, "epoch": 0.09808102345415778, "percentage": 1.4, "elapsed_time": "0:16:32", "remaining_time": "19:21:45"}
+{"current_steps": 24, "total_steps": 1638, "loss": 0.6421, "lr": 5.853658536585366e-06, "epoch": 0.1023454157782516, "percentage": 1.47, "elapsed_time": "0:17:14", "remaining_time": "19:19:25"}
+{"current_steps": 25, "total_steps": 1638, "loss": 0.6501, "lr": 6.0975609756097564e-06, "epoch": 0.10660980810234541, "percentage": 1.53, "elapsed_time": "0:17:55", "remaining_time": "19:16:45"}
+{"current_steps": 26, "total_steps": 1638, "loss": 0.6219, "lr": 6.341463414634147e-06, "epoch": 0.11087420042643924, "percentage": 1.59, "elapsed_time": "0:18:40", "remaining_time": "19:17:34"}
+{"current_steps": 27, "total_steps": 1638, "loss": 0.6385, "lr": 6.585365853658538e-06, "epoch": 0.11513859275053305, "percentage": 1.65, "elapsed_time": "0:19:24", "remaining_time": "19:17:35"}
+{"current_steps": 28, "total_steps": 1638, "loss": 0.6163, "lr": 6.829268292682928e-06, "epoch": 0.11940298507462686, "percentage": 1.71, "elapsed_time": "0:20:05", "remaining_time": "19:14:57"}
+{"current_steps": 29, "total_steps": 1638, "loss": 0.6056, "lr": 7.0731707317073175e-06, "epoch": 0.12366737739872068, "percentage": 1.77, "elapsed_time": "0:20:46", "remaining_time": "19:12:33"}
+{"current_steps": 30, "total_steps": 1638, "loss": 0.6117, "lr": 7.317073170731707e-06, "epoch": 0.1279317697228145, "percentage": 1.83, "elapsed_time": "0:21:29", "remaining_time": "19:11:42"}
+{"current_steps": 31, "total_steps": 1638, "loss": 0.5764, "lr": 7.560975609756098e-06, "epoch": 0.13219616204690832, "percentage": 1.89, "elapsed_time": "0:22:15", "remaining_time": "19:14:06"}
+{"current_steps": 32, "total_steps": 1638, "loss": 0.6044, "lr": 7.804878048780489e-06, "epoch": 0.13646055437100213, "percentage": 1.95, "elapsed_time": "0:22:59", "remaining_time": "19:13:53"}
+{"current_steps": 33, "total_steps": 1638, "loss": 0.6199, "lr": 8.048780487804879e-06, "epoch": 0.14072494669509594, "percentage": 2.01, "elapsed_time": "0:23:42", "remaining_time": "19:12:49"}
+{"current_steps": 34, "total_steps": 1638, "loss": 0.5868, "lr": 8.292682926829268e-06, "epoch": 0.14498933901918976, "percentage": 2.08, "elapsed_time": "0:24:23", "remaining_time": "19:10:40"}
+{"current_steps": 35, "total_steps": 1638, "loss": 0.5619, "lr": 8.536585365853658e-06, "epoch": 0.14925373134328357, "percentage": 2.14, "elapsed_time": "0:25:06", "remaining_time": "19:10:17"}
+{"current_steps": 36, "total_steps": 1638, "loss": 0.5885, "lr": 8.78048780487805e-06, "epoch": 0.1535181236673774, "percentage": 2.2, "elapsed_time": "0:25:45", "remaining_time": "19:06:31"}
+{"current_steps": 37, "total_steps": 1638, "loss": 0.5704, "lr": 9.02439024390244e-06, "epoch": 0.15778251599147122, "percentage": 2.26, "elapsed_time": "0:26:30", "remaining_time": "19:06:51"}
+{"current_steps": 38, "total_steps": 1638, "loss": 0.5636, "lr": 9.268292682926831e-06, "epoch": 0.16204690831556504, "percentage": 2.32, "elapsed_time": "0:27:08", "remaining_time": "19:02:48"}
+{"current_steps": 39, "total_steps": 1638, "loss": 0.597, "lr": 9.51219512195122e-06, "epoch": 0.16631130063965885, "percentage": 2.38, "elapsed_time": "0:27:50", "remaining_time": "19:01:44"}
+{"current_steps": 40, "total_steps": 1638, "loss": 0.5547, "lr": 9.756097560975611e-06, "epoch": 0.17057569296375266, "percentage": 2.44, "elapsed_time": "0:28:21", "remaining_time": "18:53:02"}
+{"current_steps": 41, "total_steps": 1638, "loss": 0.5808, "lr": 1e-05, "epoch": 0.17484008528784648, "percentage": 2.5, "elapsed_time": "0:29:06", "remaining_time": "18:53:55"}
+{"current_steps": 42, "total_steps": 1638, "loss": 0.5807, "lr": 1.024390243902439e-05, "epoch": 0.1791044776119403, "percentage": 2.56, "elapsed_time": "0:29:48", "remaining_time": "18:52:41"}
+{"current_steps": 43, "total_steps": 1638, "loss": 0.5706, "lr": 1.0487804878048782e-05, "epoch": 0.18336886993603413, "percentage": 2.63, "elapsed_time": "0:30:24", "remaining_time": "18:47:54"}
+{"current_steps": 44, "total_steps": 1638, "loss": 0.6006, "lr": 1.0731707317073172e-05, "epoch": 0.18763326226012794, "percentage": 2.69, "elapsed_time": "0:31:07", "remaining_time": "18:47:45"}
+{"current_steps": 45, "total_steps": 1638, "loss": 0.5661, "lr": 1.0975609756097562e-05, "epoch": 0.19189765458422176, "percentage": 2.75, "elapsed_time": "0:31:50", "remaining_time": "18:47:27"}
+{"current_steps": 46, "total_steps": 1638, "loss": 0.5526, "lr": 1.1219512195121953e-05, "epoch": 0.19616204690831557, "percentage": 2.81, "elapsed_time": "0:32:28", "remaining_time": "18:43:58"}
+{"current_steps": 47, "total_steps": 1638, "loss": 0.5647, "lr": 1.1463414634146342e-05, "epoch": 0.20042643923240938, "percentage": 2.87, "elapsed_time": "0:33:09", "remaining_time": "18:42:30"}
+{"current_steps": 48, "total_steps": 1638, "loss": 0.5301, "lr": 1.1707317073170731e-05, "epoch": 0.2046908315565032, "percentage": 2.93, "elapsed_time": "0:33:53", "remaining_time": "18:42:32"}
+{"current_steps": 49, "total_steps": 1638, "loss": 0.5398, "lr": 1.1951219512195123e-05, "epoch": 0.208955223880597, "percentage": 2.99, "elapsed_time": "0:34:34", "remaining_time": "18:41:12"}
+{"current_steps": 50, "total_steps": 1638, "loss": 0.5888, "lr": 1.2195121951219513e-05, "epoch": 0.21321961620469082, "percentage": 3.05, "elapsed_time": "0:35:16", "remaining_time": "18:40:32"}
+{"current_steps": 51, "total_steps": 1638, "loss": 0.5196, "lr": 1.2439024390243903e-05, "epoch": 0.21748400852878466, "percentage": 3.11, "elapsed_time": "0:35:59", "remaining_time": "18:39:57"}
+{"current_steps": 52, "total_steps": 1638, "loss": 0.5504, "lr": 1.2682926829268294e-05, "epoch": 0.22174840085287847, "percentage": 3.17, "elapsed_time": "0:36:37", "remaining_time": "18:37:16"}
+{"current_steps": 53, "total_steps": 1638, "loss": 0.5189, "lr": 1.2926829268292684e-05, "epoch": 0.2260127931769723, "percentage": 3.24, "elapsed_time": "0:37:16", "remaining_time": "18:34:54"}
+{"current_steps": 54, "total_steps": 1638, "loss": 0.56, "lr": 1.3170731707317076e-05, "epoch": 0.2302771855010661, "percentage": 3.3, "elapsed_time": "0:37:53", "remaining_time": "18:31:20"}
+{"current_steps": 55, "total_steps": 1638, "loss": 0.5365, "lr": 1.3414634146341466e-05, "epoch": 0.2345415778251599, "percentage": 3.36, "elapsed_time": "0:38:38", "remaining_time": "18:32:14"}
+{"current_steps": 56, "total_steps": 1638, "loss": 0.5431, "lr": 1.3658536585365855e-05, "epoch": 0.23880597014925373, "percentage": 3.42, "elapsed_time": "0:39:16", "remaining_time": "18:29:32"}
+{"current_steps": 57, "total_steps": 1638, "loss": 0.5226, "lr": 1.3902439024390244e-05, "epoch": 0.24307036247334754, "percentage": 3.48, "elapsed_time": "0:39:54", "remaining_time": "18:27:07"}
+{"current_steps": 58, "total_steps": 1638, "loss": 0.5645, "lr": 1.4146341463414635e-05, "epoch": 0.24733475479744135, "percentage": 3.54, "elapsed_time": "0:40:42", "remaining_time": "18:28:48"}
+{"current_steps": 59, "total_steps": 1638, "loss": 0.5291, "lr": 1.4390243902439025e-05, "epoch": 0.2515991471215352, "percentage": 3.6, "elapsed_time": "0:41:18", "remaining_time": "18:25:18"}
+{"current_steps": 60, "total_steps": 1638, "loss": 0.5303, "lr": 1.4634146341463415e-05, "epoch": 0.255863539445629, "percentage": 3.66, "elapsed_time": "0:42:02", "remaining_time": "18:25:52"}
+{"current_steps": 61, "total_steps": 1638, "loss": 0.5041, "lr": 1.4878048780487806e-05, "epoch": 0.2601279317697228, "percentage": 3.72, "elapsed_time": "0:42:44", "remaining_time": "18:25:02"}
+{"current_steps": 62, "total_steps": 1638, "loss": 0.542, "lr": 1.5121951219512196e-05, "epoch": 0.26439232409381663, "percentage": 3.79, "elapsed_time": "0:43:29", "remaining_time": "18:25:33"}
+{"current_steps": 63, "total_steps": 1638, "loss": 0.5337, "lr": 1.5365853658536586e-05, "epoch": 0.26865671641791045, "percentage": 3.85, "elapsed_time": "0:44:09", "remaining_time": "18:23:54"}
+{"current_steps": 64, "total_steps": 1638, "loss": 0.5606, "lr": 1.5609756097560978e-05, "epoch": 0.27292110874200426, "percentage": 3.91, "elapsed_time": "0:44:47", "remaining_time": "18:21:33"}
+{"current_steps": 65, "total_steps": 1638, "loss": 0.5401, "lr": 1.585365853658537e-05, "epoch": 0.2771855010660981, "percentage": 3.97, "elapsed_time": "0:45:24", "remaining_time": "18:18:51"}
+{"current_steps": 66, "total_steps": 1638, "loss": 0.499, "lr": 1.6097560975609757e-05, "epoch": 0.2814498933901919, "percentage": 4.03, "elapsed_time": "0:46:08", "remaining_time": "18:18:54"}
+{"current_steps": 67, "total_steps": 1638, "loss": 0.5135, "lr": 1.6341463414634145e-05, "epoch": 0.2857142857142857, "percentage": 4.09, "elapsed_time": "0:46:53", "remaining_time": "18:19:36"}
+{"current_steps": 68, "total_steps": 1638, "loss": 0.5455, "lr": 1.6585365853658537e-05, "epoch": 0.2899786780383795, "percentage": 4.15, "elapsed_time": "0:47:37", "remaining_time": "18:19:23"}
+{"current_steps": 69, "total_steps": 1638, "loss": 0.5155, "lr": 1.682926829268293e-05, "epoch": 0.2942430703624733, "percentage": 4.21, "elapsed_time": "0:48:20", "remaining_time": "18:19:23"}
+{"current_steps": 70, "total_steps": 1638, "loss": 0.5116, "lr": 1.7073170731707317e-05, "epoch": 0.29850746268656714, "percentage": 4.27, "elapsed_time": "0:48:59", "remaining_time": "18:17:18"}
+{"current_steps": 71, "total_steps": 1638, "loss": 0.5067, "lr": 1.7317073170731708e-05, "epoch": 0.302771855010661, "percentage": 4.33, "elapsed_time": "0:49:29", "remaining_time": "18:12:17"}
+{"current_steps": 72, "total_steps": 1638, "loss": 0.5185, "lr": 1.75609756097561e-05, "epoch": 0.3070362473347548, "percentage": 4.4, "elapsed_time": "0:50:11", "remaining_time": "18:11:43"}
+{"current_steps": 73, "total_steps": 1638, "loss": 0.5257, "lr": 1.7804878048780488e-05, "epoch": 0.31130063965884863, "percentage": 4.46, "elapsed_time": "0:50:54", "remaining_time": "18:11:20"}
+{"current_steps": 74, "total_steps": 1638, "loss": 0.5135, "lr": 1.804878048780488e-05, "epoch": 0.31556503198294245, "percentage": 4.52, "elapsed_time": "0:51:32", "remaining_time": "18:09:30"}
+{"current_steps": 75, "total_steps": 1638, "loss": 0.544, "lr": 1.829268292682927e-05, "epoch": 0.31982942430703626, "percentage": 4.58, "elapsed_time": "0:52:17", "remaining_time": "18:09:53"}
+{"current_steps": 76, "total_steps": 1638, "loss": 0.5738, "lr": 1.8536585365853663e-05, "epoch": 0.32409381663113007, "percentage": 4.64, "elapsed_time": "0:53:00", "remaining_time": "18:09:31"}
+{"current_steps": 77, "total_steps": 1638, "loss": 0.5245, "lr": 1.878048780487805e-05, "epoch": 0.3283582089552239, "percentage": 4.7, "elapsed_time": "0:53:46", "remaining_time": "18:10:07"}
+{"current_steps": 78, "total_steps": 1638, "loss": 0.5447, "lr": 1.902439024390244e-05, "epoch": 0.3326226012793177, "percentage": 4.76, "elapsed_time": "0:54:30", "remaining_time": "18:10:16"}
+{"current_steps": 79, "total_steps": 1638, "loss": 0.5263, "lr": 1.926829268292683e-05, "epoch": 0.3368869936034115, "percentage": 4.82, "elapsed_time": "0:55:10", "remaining_time": "18:08:49"}
+{"current_steps": 80, "total_steps": 1638, "loss": 0.5338, "lr": 1.9512195121951222e-05, "epoch": 0.3411513859275053, "percentage": 4.88, "elapsed_time": "0:55:54", "remaining_time": "18:08:42"}
+{"current_steps": 81, "total_steps": 1638, "loss": 0.5213, "lr": 1.975609756097561e-05, "epoch": 0.34541577825159914, "percentage": 4.95, "elapsed_time": "0:56:42", "remaining_time": "18:09:55"}
+{"current_steps": 82, "total_steps": 1638, "loss": 0.5356, "lr": 2e-05, "epoch": 0.34968017057569295, "percentage": 5.01, "elapsed_time": "0:57:23", "remaining_time": "18:08:57"}
+{"current_steps": 83, "total_steps": 1638, "loss": 0.5151, "lr": 2.0243902439024393e-05, "epoch": 0.35394456289978676, "percentage": 5.07, "elapsed_time": "0:58:07", "remaining_time": "18:08:57"}
+{"current_steps": 84, "total_steps": 1638, "loss": 0.5195, "lr": 2.048780487804878e-05, "epoch": 0.3582089552238806, "percentage": 5.13, "elapsed_time": "0:58:45", "remaining_time": "18:07:00"}
+{"current_steps": 85, "total_steps": 1638, "loss": 0.5414, "lr": 2.0731707317073173e-05, "epoch": 0.3624733475479744, "percentage": 5.19, "elapsed_time": "0:59:25", "remaining_time": "18:05:38"}
+{"current_steps": 86, "total_steps": 1638, "loss": 0.5204, "lr": 2.0975609756097564e-05, "epoch": 0.36673773987206826, "percentage": 5.25, "elapsed_time": "1:00:06", "remaining_time": "18:04:46"}
+{"current_steps": 87, "total_steps": 1638, "loss": 0.5104, "lr": 2.1219512195121953e-05, "epoch": 0.37100213219616207, "percentage": 5.31, "elapsed_time": "1:00:49", "remaining_time": "18:04:24"}
+{"current_steps": 88, "total_steps": 1638, "loss": 0.4985, "lr": 2.1463414634146344e-05, "epoch": 0.3752665245202559, "percentage": 5.37, "elapsed_time": "1:01:30", "remaining_time": "18:03:28"}
+{"current_steps": 89, "total_steps": 1638, "loss": 0.5435, "lr": 2.1707317073170736e-05, "epoch": 0.3795309168443497, "percentage": 5.43, "elapsed_time": "1:02:10", "remaining_time": "18:02:12"}
+{"current_steps": 90, "total_steps": 1638, "loss": 0.4954, "lr": 2.1951219512195124e-05, "epoch": 0.3837953091684435, "percentage": 5.49, "elapsed_time": "1:02:52", "remaining_time": "18:01:20"}
+{"current_steps": 91, "total_steps": 1638, "loss": 0.5056, "lr": 2.2195121951219515e-05, "epoch": 0.3880597014925373, "percentage": 5.56, "elapsed_time": "1:03:28", "remaining_time": "17:59:09"}
+{"current_steps": 92, "total_steps": 1638, "loss": 0.5207, "lr": 2.2439024390243907e-05, "epoch": 0.39232409381663114, "percentage": 5.62, "elapsed_time": "1:04:11", "remaining_time": "17:58:47"}
+{"current_steps": 93, "total_steps": 1638, "loss": 0.5287, "lr": 2.268292682926829e-05, "epoch": 0.39658848614072495, "percentage": 5.68, "elapsed_time": "1:04:45", "remaining_time": "17:55:55"}
+{"current_steps": 94, "total_steps": 1638, "loss": 0.505, "lr": 2.2926829268292683e-05, "epoch": 0.40085287846481876, "percentage": 5.74, "elapsed_time": "1:05:27", "remaining_time": "17:55:17"}
+{"current_steps": 95, "total_steps": 1638, "loss": 0.4994, "lr": 2.3170731707317075e-05, "epoch": 0.4051172707889126, "percentage": 5.8, "elapsed_time": "1:06:09", "remaining_time": "17:54:27"}
+{"current_steps": 96, "total_steps": 1638, "loss": 0.518, "lr": 2.3414634146341463e-05, "epoch": 0.4093816631130064, "percentage": 5.86, "elapsed_time": "1:06:49", "remaining_time": "17:53:17"}
+{"current_steps": 97, "total_steps": 1638, "loss": 0.5132, "lr": 2.3658536585365854e-05, "epoch": 0.4136460554371002, "percentage": 5.92, "elapsed_time": "1:07:29", "remaining_time": "17:52:18"}
+{"current_steps": 98, "total_steps": 1638, "loss": 0.5054, "lr": 2.3902439024390246e-05, "epoch": 0.417910447761194, "percentage": 5.98, "elapsed_time": "1:08:15", "remaining_time": "17:52:37"}
+{"current_steps": 99, "total_steps": 1638, "loss": 0.5234, "lr": 2.4146341463414634e-05, "epoch": 0.42217484008528783, "percentage": 6.04, "elapsed_time": "1:08:58", "remaining_time": "17:52:09"}
+{"current_steps": 100, "total_steps": 1638, "loss": 0.5117, "lr": 2.4390243902439026e-05, "epoch": 0.42643923240938164, "percentage": 6.11, "elapsed_time": "1:09:47", "remaining_time": "17:53:20"}
+{"current_steps": 101, "total_steps": 1638, "loss": 0.5112, "lr": 2.4634146341463417e-05, "epoch": 0.43070362473347545, "percentage": 6.17, "elapsed_time": "1:10:28", "remaining_time": "17:52:21"}
+{"current_steps": 102, "total_steps": 1638, "loss": 0.4905, "lr": 2.4878048780487805e-05, "epoch": 0.4349680170575693, "percentage": 6.23, "elapsed_time": "1:11:07", "remaining_time": "17:51:02"}
+{"current_steps": 103, "total_steps": 1638, "loss": 0.4982, "lr": 2.5121951219512197e-05, "epoch": 0.43923240938166314, "percentage": 6.29, "elapsed_time": "1:11:47", "remaining_time": "17:49:55"}
+{"current_steps": 104, "total_steps": 1638, "loss": 0.5069, "lr": 2.536585365853659e-05, "epoch": 0.44349680170575695, "percentage": 6.35, "elapsed_time": "1:12:32", "remaining_time": "17:50:00"}
+{"current_steps": 105, "total_steps": 1638, "loss": 0.5024, "lr": 2.5609756097560977e-05, "epoch": 0.44776119402985076, "percentage": 6.41, "elapsed_time": "1:13:11", "remaining_time": "17:48:43"}
+{"current_steps": 106, "total_steps": 1638, "loss": 0.5044, "lr": 2.5853658536585368e-05, "epoch": 0.4520255863539446, "percentage": 6.47, "elapsed_time": "1:13:55", "remaining_time": "17:48:28"}
+{"current_steps": 107, "total_steps": 1638, "loss": 0.5204, "lr": 2.609756097560976e-05, "epoch": 0.4562899786780384, "percentage": 6.53, "elapsed_time": "1:14:33", "remaining_time": "17:46:53"}
+{"current_steps": 108, "total_steps": 1638, "loss": 0.5279, "lr": 2.634146341463415e-05, "epoch": 0.4605543710021322, "percentage": 6.59, "elapsed_time": "1:15:14", "remaining_time": "17:45:55"}
+{"current_steps": 109, "total_steps": 1638, "loss": 0.5073, "lr": 2.658536585365854e-05, "epoch": 0.464818763326226, "percentage": 6.65, "elapsed_time": "1:15:55", "remaining_time": "17:44:57"}
+{"current_steps": 110, "total_steps": 1638, "loss": 0.5265, "lr": 2.682926829268293e-05, "epoch": 0.4690831556503198, "percentage": 6.72, "elapsed_time": "1:16:37", "remaining_time": "17:44:25"}
+{"current_steps": 111, "total_steps": 1638, "loss": 0.4978, "lr": 2.7073170731707323e-05, "epoch": 0.47334754797441364, "percentage": 6.78, "elapsed_time": "1:17:16", "remaining_time": "17:43:08"}
+{"current_steps": 112, "total_steps": 1638, "loss": 0.5127, "lr": 2.731707317073171e-05, "epoch": 0.47761194029850745, "percentage": 6.84, "elapsed_time": "1:17:59", "remaining_time": "17:42:33"}
+{"current_steps": 113, "total_steps": 1638, "loss": 0.4886, "lr": 2.75609756097561e-05, "epoch": 0.48187633262260127, "percentage": 6.9, "elapsed_time": "1:18:39", "remaining_time": "17:41:28"}
+{"current_steps": 114, "total_steps": 1638, "loss": 0.5304, "lr": 2.7804878048780487e-05, "epoch": 0.4861407249466951, "percentage": 6.96, "elapsed_time": "1:19:20", "remaining_time": "17:40:42"}
+{"current_steps": 115, "total_steps": 1638, "loss": 0.5179, "lr": 2.804878048780488e-05, "epoch": 0.4904051172707889, "percentage": 7.02, "elapsed_time": "1:20:07", "remaining_time": "17:41:08"}
+{"current_steps": 116, "total_steps": 1638, "loss": 0.5158, "lr": 2.829268292682927e-05, "epoch": 0.4946695095948827, "percentage": 7.08, "elapsed_time": "1:20:52", "remaining_time": "17:41:04"}
+{"current_steps": 117, "total_steps": 1638, "loss": 0.5044, "lr": 2.8536585365853658e-05, "epoch": 0.4989339019189765, "percentage": 7.14, "elapsed_time": "1:21:30", "remaining_time": "17:39:36"}
+{"current_steps": 118, "total_steps": 1638, "loss": 0.5297, "lr": 2.878048780487805e-05, "epoch": 0.5031982942430704, "percentage": 7.2, "elapsed_time": "1:22:12", "remaining_time": "17:39:01"}
+{"current_steps": 119, "total_steps": 1638, "loss": 0.5074, "lr": 2.902439024390244e-05, "epoch": 0.5074626865671642, "percentage": 7.26, "elapsed_time": "1:22:53", "remaining_time": "17:38:08"}
+{"current_steps": 120, "total_steps": 1638, "loss": 0.5295, "lr": 2.926829268292683e-05, "epoch": 0.511727078891258, "percentage": 7.33, "elapsed_time": "1:23:41", "remaining_time": "17:38:36"}
+{"current_steps": 121, "total_steps": 1638, "loss": 0.5216, "lr": 2.951219512195122e-05, "epoch": 0.5159914712153518, "percentage": 7.39, "elapsed_time": "1:24:23", "remaining_time": "17:37:56"}
+{"current_steps": 122, "total_steps": 1638, "loss": 0.5068, "lr": 2.9756097560975613e-05, "epoch": 0.5202558635394456, "percentage": 7.45, "elapsed_time": "1:25:09", "remaining_time": "17:38:12"}
+{"current_steps": 123, "total_steps": 1638, "loss": 0.5238, "lr": 3.0000000000000004e-05, "epoch": 0.5245202558635395, "percentage": 7.51, "elapsed_time": "1:25:53", "remaining_time": "17:37:53"}
+{"current_steps": 124, "total_steps": 1638, "loss": 0.5043, "lr": 3.0243902439024392e-05, "epoch": 0.5287846481876333, "percentage": 7.57, "elapsed_time": "1:26:33", "remaining_time": "17:36:53"}
+{"current_steps": 125, "total_steps": 1638, "loss": 0.4816, "lr": 3.0487804878048784e-05, "epoch": 0.5330490405117271, "percentage": 7.63, "elapsed_time": "1:27:11", "remaining_time": "17:35:23"}
+{"current_steps": 126, "total_steps": 1638, "loss": 0.5081, "lr": 3.073170731707317e-05, "epoch": 0.5373134328358209, "percentage": 7.69, "elapsed_time": "1:27:53", "remaining_time": "17:34:39"}
+{"current_steps": 127, "total_steps": 1638, "loss": 0.4986, "lr": 3.0975609756097564e-05, "epoch": 0.5415778251599147, "percentage": 7.75, "elapsed_time": "1:28:35", "remaining_time": "17:34:06"}
+{"current_steps": 128, "total_steps": 1638, "loss": 0.486, "lr": 3.1219512195121955e-05, "epoch": 0.5458422174840085, "percentage": 7.81, "elapsed_time": "1:29:18", "remaining_time": "17:33:30"}
+{"current_steps": 129, "total_steps": 1638, "loss": 0.4867, "lr": 3.146341463414635e-05, "epoch": 0.5501066098081023, "percentage": 7.88, "elapsed_time": "1:30:03", "remaining_time": "17:33:23"}
+{"current_steps": 130, "total_steps": 1638, "loss": 0.5119, "lr": 3.170731707317074e-05, "epoch": 0.5543710021321961, "percentage": 7.94, "elapsed_time": "1:30:45", "remaining_time": "17:32:51"}
+{"current_steps": 131, "total_steps": 1638, "loss": 0.4786, "lr": 3.195121951219512e-05, "epoch": 0.55863539445629, "percentage": 8.0, "elapsed_time": "1:31:27", "remaining_time": "17:32:05"}
+{"current_steps": 132, "total_steps": 1638, "loss": 0.4902, "lr": 3.2195121951219514e-05, "epoch": 0.5628997867803838, "percentage": 8.06, "elapsed_time": "1:32:09", "remaining_time": "17:31:30"}
+{"current_steps": 133, "total_steps": 1638, "loss": 0.5304, "lr": 3.2439024390243906e-05, "epoch": 0.5671641791044776, "percentage": 8.12, "elapsed_time": "1:32:54", "remaining_time": "17:31:22"}
+{"current_steps": 134, "total_steps": 1638, "loss": 0.4959, "lr": 3.268292682926829e-05, "epoch": 0.5714285714285714, "percentage": 8.18, "elapsed_time": "1:33:37", "remaining_time": "17:30:53"}
+{"current_steps": 135, "total_steps": 1638, "loss": 0.5074, "lr": 3.292682926829268e-05, "epoch": 0.5756929637526652, "percentage": 8.24, "elapsed_time": "1:34:24", "remaining_time": "17:31:06"}
+{"current_steps": 136, "total_steps": 1638, "loss": 0.524, "lr": 3.3170731707317074e-05, "epoch": 0.579957356076759, "percentage": 8.3, "elapsed_time": "1:35:12", "remaining_time": "17:31:32"}
+{"current_steps": 137, "total_steps": 1638, "loss": 0.5207, "lr": 3.3414634146341465e-05, "epoch": 0.5842217484008528, "percentage": 8.36, "elapsed_time": "1:35:48", "remaining_time": "17:29:39"}
+{"current_steps": 138, "total_steps": 1638, "loss": 0.506, "lr": 3.365853658536586e-05, "epoch": 0.5884861407249466, "percentage": 8.42, "elapsed_time": "1:36:32", "remaining_time": "17:29:24"}
+{"current_steps": 139, "total_steps": 1638, "loss": 0.4971, "lr": 3.390243902439025e-05, "epoch": 0.5927505330490405, "percentage": 8.49, "elapsed_time": "1:37:15", "remaining_time": "17:28:47"}
+{"current_steps": 140, "total_steps": 1638, "loss": 0.5151, "lr": 3.414634146341463e-05, "epoch": 0.5970149253731343, "percentage": 8.55, "elapsed_time": "1:37:54", "remaining_time": "17:27:40"}
+{"current_steps": 141, "total_steps": 1638, "loss": 0.4956, "lr": 3.4390243902439025e-05, "epoch": 0.6012793176972282, "percentage": 8.61, "elapsed_time": "1:38:37", "remaining_time": "17:27:08"}
+{"current_steps": 142, "total_steps": 1638, "loss": 0.5225, "lr": 3.4634146341463416e-05, "epoch": 0.605543710021322, "percentage": 8.67, "elapsed_time": "1:39:18", "remaining_time": "17:26:18"}
+{"current_steps": 143, "total_steps": 1638, "loss": 0.5232, "lr": 3.487804878048781e-05, "epoch": 0.6098081023454158, "percentage": 8.73, "elapsed_time": "1:39:58", "remaining_time": "17:25:10"}
+{"current_steps": 144, "total_steps": 1638, "loss": 0.4958, "lr": 3.51219512195122e-05, "epoch": 0.6140724946695096, "percentage": 8.79, "elapsed_time": "1:40:39", "remaining_time": "17:24:23"}
+{"current_steps": 145, "total_steps": 1638, "loss": 0.498, "lr": 3.536585365853659e-05, "epoch": 0.6183368869936035, "percentage": 8.85, "elapsed_time": "1:41:21", "remaining_time": "17:23:40"}
+{"current_steps": 146, "total_steps": 1638, "loss": 0.4964, "lr": 3.5609756097560976e-05, "epoch": 0.6226012793176973, "percentage": 8.91, "elapsed_time": "1:42:02", "remaining_time": "17:22:45"}
+{"current_steps": 147, "total_steps": 1638, "loss": 0.5256, "lr": 3.585365853658537e-05, "epoch": 0.6268656716417911, "percentage": 8.97, "elapsed_time": "1:42:44", "remaining_time": "17:22:02"}
+{"current_steps": 148, "total_steps": 1638, "loss": 0.4897, "lr": 3.609756097560976e-05, "epoch": 0.6311300639658849, "percentage": 9.04, "elapsed_time": "1:43:27", "remaining_time": "17:21:29"}
+{"current_steps": 149, "total_steps": 1638, "loss": 0.5262, "lr": 3.634146341463415e-05, "epoch": 0.6353944562899787, "percentage": 9.1, "elapsed_time": "1:44:04", "remaining_time": "17:20:03"}
+{"current_steps": 150, "total_steps": 1638, "loss": 0.4917, "lr": 3.658536585365854e-05, "epoch": 0.6396588486140725, "percentage": 9.16, "elapsed_time": "1:44:41", "remaining_time": "17:18:35"}
+{"current_steps": 151, "total_steps": 1638, "loss": 0.5011, "lr": 3.6829268292682934e-05, "epoch": 0.6439232409381663, "percentage": 9.22, "elapsed_time": "1:45:24", "remaining_time": "17:17:57"}
+{"current_steps": 152, "total_steps": 1638, "loss": 0.511, "lr": 3.7073170731707325e-05, "epoch": 0.6481876332622601, "percentage": 9.28, "elapsed_time": "1:46:08", "remaining_time": "17:17:38"}
+{"current_steps": 153, "total_steps": 1638, "loss": 0.5309, "lr": 3.731707317073171e-05, "epoch": 0.652452025586354, "percentage": 9.34, "elapsed_time": "1:46:52", "remaining_time": "17:17:15"}
+{"current_steps": 154, "total_steps": 1638, "loss": 0.4995, "lr": 3.75609756097561e-05, "epoch": 0.6567164179104478, "percentage": 9.4, "elapsed_time": "1:47:30", "remaining_time": "17:16:00"}
+{"current_steps": 155, "total_steps": 1638, "loss": 0.5112, "lr": 3.7804878048780486e-05, "epoch": 0.6609808102345416, "percentage": 9.46, "elapsed_time": "1:48:15", "remaining_time": "17:15:42"}
+{"current_steps": 156, "total_steps": 1638, "loss": 0.4969, "lr": 3.804878048780488e-05, "epoch": 0.6652452025586354, "percentage": 9.52, "elapsed_time": "1:48:58", "remaining_time": "17:15:15"}
+{"current_steps": 157, "total_steps": 1638, "loss": 0.5025, "lr": 3.829268292682927e-05, "epoch": 0.6695095948827292, "percentage": 9.58, "elapsed_time": "1:49:40", "remaining_time": "17:14:31"}
+{"current_steps": 158, "total_steps": 1638, "loss": 0.5005, "lr": 3.853658536585366e-05, "epoch": 0.673773987206823, "percentage": 9.65, "elapsed_time": "1:50:20", "remaining_time": "17:13:35"}
+{"current_steps": 159, "total_steps": 1638, "loss": 0.5445, "lr": 3.878048780487805e-05, "epoch": 0.6780383795309168, "percentage": 9.71, "elapsed_time": "1:51:03", "remaining_time": "17:13:06"}
+{"current_steps": 160, "total_steps": 1638, "loss": 0.5085, "lr": 3.9024390243902444e-05, "epoch": 0.6823027718550106, "percentage": 9.77, "elapsed_time": "1:51:45", "remaining_time": "17:12:21"}
+{"current_steps": 161, "total_steps": 1638, "loss": 0.4894, "lr": 3.926829268292683e-05, "epoch": 0.6865671641791045, "percentage": 9.83, "elapsed_time": "1:52:25", "remaining_time": "17:11:23"}
+{"current_steps": 162, "total_steps": 1638, "loss": 0.4918, "lr": 3.951219512195122e-05, "epoch": 0.6908315565031983, "percentage": 9.89, "elapsed_time": "1:53:11", "remaining_time": "17:11:13"}
+{"current_steps": 163, "total_steps": 1638, "loss": 0.5093, "lr": 3.975609756097561e-05, "epoch": 0.6950959488272921, "percentage": 9.95, "elapsed_time": "1:53:49", "remaining_time": "17:09:59"}
+{"current_steps": 164, "total_steps": 1638, "loss": 0.5107, "lr": 4e-05, "epoch": 0.6993603411513859, "percentage": 10.01, "elapsed_time": "1:54:29", "remaining_time": "17:09:05"}
+{"current_steps": 165, "total_steps": 1638, "loss": 0.5198, "lr": 3.999995457398773e-05, "epoch": 0.7036247334754797, "percentage": 10.07, "elapsed_time": "1:55:09", "remaining_time": "17:08:05"}
+{"current_steps": 166, "total_steps": 1638, "loss": 0.4923, "lr": 3.999981829615725e-05, "epoch": 0.7078891257995735, "percentage": 10.13, "elapsed_time": "1:55:52", "remaining_time": "17:07:28"}
+{"current_steps": 167, "total_steps": 1638, "loss": 0.5235, "lr": 3.999959116712763e-05, "epoch": 0.7121535181236673, "percentage": 10.2, "elapsed_time": "1:56:32", "remaining_time": "17:06:34"}
+{"current_steps": 168, "total_steps": 1638, "loss": 0.507, "lr": 3.999927318793061e-05, "epoch": 0.7164179104477612, "percentage": 10.26, "elapsed_time": "1:57:10", "remaining_time": "17:05:14"}
+{"current_steps": 169, "total_steps": 1638, "loss": 0.5073, "lr": 3.999886436001066e-05, "epoch": 0.720682302771855, "percentage": 10.32, "elapsed_time": "1:57:52", "remaining_time": "17:04:35"}
+{"current_steps": 170, "total_steps": 1638, "loss": 0.4896, "lr": 3.999836468522492e-05, "epoch": 0.7249466950959488, "percentage": 10.38, "elapsed_time": "1:58:35", "remaining_time": "17:04:00"}
+{"current_steps": 171, "total_steps": 1638, "loss": 0.4709, "lr": 3.999777416584321e-05, "epoch": 0.7292110874200426, "percentage": 10.44, "elapsed_time": "1:59:19", "remaining_time": "17:03:44"}
+{"current_steps": 172, "total_steps": 1638, "loss": 0.5043, "lr": 3.999709280454802e-05, "epoch": 0.7334754797441365, "percentage": 10.5, "elapsed_time": "2:00:02", "remaining_time": "17:03:09"}
+{"current_steps": 173, "total_steps": 1638, "loss": 0.4861, "lr": 3.999632060443451e-05, "epoch": 0.7377398720682303, "percentage": 10.56, "elapsed_time": "2:00:43", "remaining_time": "17:02:22"}
+{"current_steps": 174, "total_steps": 1638, "loss": 0.4757, "lr": 3.9995457569010465e-05, "epoch": 0.7420042643923241, "percentage": 10.62, "elapsed_time": "2:01:25", "remaining_time": "17:01:38"}
+{"current_steps": 175, "total_steps": 1638, "loss": 0.495, "lr": 3.999450370219632e-05, "epoch": 0.746268656716418, "percentage": 10.68, "elapsed_time": "2:02:05", "remaining_time": "17:00:40"}
+{"current_steps": 176, "total_steps": 1638, "loss": 0.4931, "lr": 3.999345900832512e-05, "epoch": 0.7505330490405118, "percentage": 10.74, "elapsed_time": "2:02:47", "remaining_time": "17:00:01"}
+{"current_steps": 177, "total_steps": 1638, "loss": 0.4882, "lr": 3.9992323492142476e-05, "epoch": 0.7547974413646056, "percentage": 10.81, "elapsed_time": "2:03:31", "remaining_time": "16:59:36"}
+{"current_steps": 178, "total_steps": 1638, "loss": 0.5201, "lr": 3.999109715880659e-05, "epoch": 0.7590618336886994, "percentage": 10.87, "elapsed_time": "2:04:11", "remaining_time": "16:58:35"}
+{"current_steps": 179, "total_steps": 1638, "loss": 0.5051, "lr": 3.998978001388821e-05, "epoch": 0.7633262260127932, "percentage": 10.93, "elapsed_time": "2:04:51", "remaining_time": "16:57:41"}
+{"current_steps": 180, "total_steps": 1638, "loss": 0.4956, "lr": 3.99883720633706e-05, "epoch": 0.767590618336887, "percentage": 10.99, "elapsed_time": "2:05:33", "remaining_time": "16:57:03"}
+{"current_steps": 181, "total_steps": 1638, "loss": 0.5113, "lr": 3.998687331364952e-05, "epoch": 0.7718550106609808, "percentage": 11.05, "elapsed_time": "2:06:13", "remaining_time": "16:56:05"}
+{"current_steps": 182, "total_steps": 1638, "loss": 0.5065, "lr": 3.998528377153318e-05, "epoch": 0.7761194029850746, "percentage": 11.11, "elapsed_time": "2:06:50", "remaining_time": "16:54:45"}
+{"current_steps": 183, "total_steps": 1638, "loss": 0.4919, "lr": 3.998360344424225e-05, "epoch": 0.7803837953091685, "percentage": 11.17, "elapsed_time": "2:07:33", "remaining_time": "16:54:15"}
+{"current_steps": 184, "total_steps": 1638, "loss": 0.493, "lr": 3.998183233940977e-05, "epoch": 0.7846481876332623, "percentage": 11.23, "elapsed_time": "2:08:17", "remaining_time": "16:53:48"}
+{"current_steps": 185, "total_steps": 1638, "loss": 0.5024, "lr": 3.9979970465081185e-05, "epoch": 0.7889125799573561, "percentage": 11.29, "elapsed_time": "2:09:02", "remaining_time": "16:53:26"}
+{"current_steps": 186, "total_steps": 1638, "loss": 0.5136, "lr": 3.997801782971423e-05, "epoch": 0.7931769722814499, "percentage": 11.36, "elapsed_time": "2:09:42", "remaining_time": "16:52:34"}
+{"current_steps": 187, "total_steps": 1638, "loss": 0.499, "lr": 3.997597444217896e-05, "epoch": 0.7974413646055437, "percentage": 11.42, "elapsed_time": "2:10:25", "remaining_time": "16:51:59"}
+{"current_steps": 188, "total_steps": 1638, "loss": 0.482, "lr": 3.997384031175766e-05, "epoch": 0.8017057569296375, "percentage": 11.48, "elapsed_time": "2:11:00", "remaining_time": "16:50:28"}
+{"current_steps": 189, "total_steps": 1638, "loss": 0.4907, "lr": 3.997161544814484e-05, "epoch": 0.8059701492537313, "percentage": 11.54, "elapsed_time": "2:11:43", "remaining_time": "16:49:50"}
+{"current_steps": 190, "total_steps": 1638, "loss": 0.5028, "lr": 3.996929986144717e-05, "epoch": 0.8102345415778252, "percentage": 11.6, "elapsed_time": "2:12:29", "remaining_time": "16:49:41"}
+{"current_steps": 191, "total_steps": 1638, "loss": 0.5033, "lr": 3.996689356218343e-05, "epoch": 0.814498933901919, "percentage": 11.66, "elapsed_time": "2:13:07", "remaining_time": "16:48:35"}
+{"current_steps": 192, "total_steps": 1638, "loss": 0.4686, "lr": 3.996439656128449e-05, "epoch": 0.8187633262260128, "percentage": 11.72, "elapsed_time": "2:13:51", "remaining_time": "16:48:08"}
+{"current_steps": 193, "total_steps": 1638, "loss": 0.4921, "lr": 3.9961808870093205e-05, "epoch": 0.8230277185501066, "percentage": 11.78, "elapsed_time": "2:14:35", "remaining_time": "16:47:39"}
+{"current_steps": 194, "total_steps": 1638, "loss": 0.4995, "lr": 3.9959130500364456e-05, "epoch": 0.8272921108742004, "percentage": 11.84, "elapsed_time": "2:15:17", "remaining_time": "16:47:03"}
+{"current_steps": 195, "total_steps": 1638, "loss": 0.5084, "lr": 3.995636146426498e-05, "epoch": 0.8315565031982942, "percentage": 11.9, "elapsed_time": "2:15:59", "remaining_time": "16:46:21"}
+{"current_steps": 196, "total_steps": 1638, "loss": 0.5, "lr": 3.9953501774373416e-05, "epoch": 0.835820895522388, "percentage": 11.97, "elapsed_time": "2:16:39", "remaining_time": "16:45:21"}
+{"current_steps": 197, "total_steps": 1638, "loss": 0.4816, "lr": 3.995055144368021e-05, "epoch": 0.8400852878464818, "percentage": 12.03, "elapsed_time": "2:17:11", "remaining_time": "16:43:33"}
+{"current_steps": 198, "total_steps": 1638, "loss": 0.5156, "lr": 3.994751048558751e-05, "epoch": 0.8443496801705757, "percentage": 12.09, "elapsed_time": "2:17:51", "remaining_time": "16:42:35"}
+{"current_steps": 199, "total_steps": 1638, "loss": 0.4851, "lr": 3.994437891390919e-05, "epoch": 0.8486140724946695, "percentage": 12.15, "elapsed_time": "2:18:32", "remaining_time": "16:41:52"}
+{"current_steps": 200, "total_steps": 1638, "loss": 0.5054, "lr": 3.9941156742870733e-05, "epoch": 0.8528784648187633, "percentage": 12.21, "elapsed_time": "2:19:11", "remaining_time": "16:40:49"}
+{"current_steps": 201, "total_steps": 1638, "loss": 0.4901, "lr": 3.993784398710918e-05, "epoch": 0.8571428571428571, "percentage": 12.27, "elapsed_time": "2:19:47", "remaining_time": "16:39:27"}
+{"current_steps": 202, "total_steps": 1638, "loss": 0.4962, "lr": 3.993444066167304e-05, "epoch": 0.8614072494669509, "percentage": 12.33, "elapsed_time": "2:20:28", "remaining_time": "16:38:34"}
+{"current_steps": 203, "total_steps": 1638, "loss": 0.5085, "lr": 3.993094678202229e-05, "epoch": 0.8656716417910447, "percentage": 12.39, "elapsed_time": "2:21:10", "remaining_time": "16:37:56"}
+{"current_steps": 204, "total_steps": 1638, "loss": 0.4973, "lr": 3.9927362364028214e-05, "epoch": 0.8699360341151386, "percentage": 12.45, "elapsed_time": "2:21:49", "remaining_time": "16:36:55"}
+{"current_steps": 205, "total_steps": 1638, "loss": 0.5159, "lr": 3.99236874239734e-05, "epoch": 0.8742004264392325, "percentage": 12.52, "elapsed_time": "2:22:32", "remaining_time": "16:36:25"}
+{"current_steps": 206, "total_steps": 1638, "loss": 0.5072, "lr": 3.991992197855163e-05, "epoch": 0.8784648187633263, "percentage": 12.58, "elapsed_time": "2:23:11", "remaining_time": "16:35:23"}
+{"current_steps": 207, "total_steps": 1638, "loss": 0.5262, "lr": 3.991606604486783e-05, "epoch": 0.8827292110874201, "percentage": 12.64, "elapsed_time": "2:23:50", "remaining_time": "16:34:24"}
+{"current_steps": 208, "total_steps": 1638, "loss": 0.5165, "lr": 3.9912119640437965e-05, "epoch": 0.8869936034115139, "percentage": 12.7, "elapsed_time": "2:24:26", "remaining_time": "16:33:05"}
+{"current_steps": 209, "total_steps": 1638, "loss": 0.507, "lr": 3.990808278318897e-05, "epoch": 0.8912579957356077, "percentage": 12.76, "elapsed_time": "2:25:09", "remaining_time": "16:32:29"}
+{"current_steps": 210, "total_steps": 1638, "loss": 0.469, "lr": 3.990395549145869e-05, "epoch": 0.8955223880597015, "percentage": 12.82, "elapsed_time": "2:25:56", "remaining_time": "16:32:22"}
+{"current_steps": 211, "total_steps": 1638, "loss": 0.4883, "lr": 3.9899737783995754e-05, "epoch": 0.8997867803837953, "percentage": 12.88, "elapsed_time": "2:26:35", "remaining_time": "16:31:22"}
+{"current_steps": 212, "total_steps": 1638, "loss": 0.5245, "lr": 3.989542967995953e-05, "epoch": 0.9040511727078892, "percentage": 12.94, "elapsed_time": "2:27:18", "remaining_time": "16:30:49"}
+{"current_steps": 213, "total_steps": 1638, "loss": 0.5069, "lr": 3.989103119892002e-05, "epoch": 0.908315565031983, "percentage": 13.0, "elapsed_time": "2:27:59", "remaining_time": "16:30:07"}
+{"current_steps": 214, "total_steps": 1638, "loss": 0.5098, "lr": 3.988654236085777e-05, "epoch": 0.9125799573560768, "percentage": 13.06, "elapsed_time": "2:28:42", "remaining_time": "16:29:30"}
+{"current_steps": 215, "total_steps": 1638, "loss": 0.4796, "lr": 3.988196318616377e-05, "epoch": 0.9168443496801706, "percentage": 13.13, "elapsed_time": "2:29:26", "remaining_time": "16:29:04"}
+{"current_steps": 216, "total_steps": 1638, "loss": 0.4843, "lr": 3.987729369563939e-05, "epoch": 0.9211087420042644, "percentage": 13.19, "elapsed_time": "2:30:09", "remaining_time": "16:28:34"}
+{"current_steps": 217, "total_steps": 1638, "loss": 0.4822, "lr": 3.9872533910496266e-05, "epoch": 0.9253731343283582, "percentage": 13.25, "elapsed_time": "2:30:49", "remaining_time": "16:27:42"}
+{"current_steps": 218, "total_steps": 1638, "loss": 0.51, "lr": 3.986768385235621e-05, "epoch": 0.929637526652452, "percentage": 13.31, "elapsed_time": "2:31:30", "remaining_time": "16:26:52"}
+{"current_steps": 219, "total_steps": 1638, "loss": 0.4882, "lr": 3.986274354325109e-05, "epoch": 0.9339019189765458, "percentage": 13.37, "elapsed_time": "2:32:04", "remaining_time": "16:25:24"}
+{"current_steps": 220, "total_steps": 1638, "loss": 0.4881, "lr": 3.9857713005622766e-05, "epoch": 0.9381663113006397, "percentage": 13.43, "elapsed_time": "2:32:46", "remaining_time": "16:24:44"}
+{"current_steps": 221, "total_steps": 1638, "loss": 0.4796, "lr": 3.985259226232296e-05, "epoch": 0.9424307036247335, "percentage": 13.49, "elapsed_time": "2:33:31", "remaining_time": "16:24:19"}
+{"current_steps": 222, "total_steps": 1638, "loss": 0.488, "lr": 3.984738133661318e-05, "epoch": 0.9466950959488273, "percentage": 13.55, "elapsed_time": "2:34:13", "remaining_time": "16:23:40"}
+{"current_steps": 223, "total_steps": 1638, "loss": 0.4806, "lr": 3.984208025216456e-05, "epoch": 0.9509594882729211, "percentage": 13.61, "elapsed_time": "2:34:53", "remaining_time": "16:22:49"}
+{"current_steps": 224, "total_steps": 1638, "loss": 0.4749, "lr": 3.983668903305784e-05, "epoch": 0.9552238805970149, "percentage": 13.68, "elapsed_time": "2:35:36", "remaining_time": "16:22:17"}
+{"current_steps": 225, "total_steps": 1638, "loss": 0.5029, "lr": 3.9831207703783154e-05, "epoch": 0.9594882729211087, "percentage": 13.74, "elapsed_time": "2:36:17", "remaining_time": "16:21:29"}
+{"current_steps": 226, "total_steps": 1638, "loss": 0.4896, "lr": 3.982563628924002e-05, "epoch": 0.9637526652452025, "percentage": 13.8, "elapsed_time": "2:36:52", "remaining_time": "16:20:07"}
+{"current_steps": 227, "total_steps": 1638, "loss": 0.4763, "lr": 3.981997481473713e-05, "epoch": 0.9680170575692963, "percentage": 13.86, "elapsed_time": "2:37:32", "remaining_time": "16:19:13"}
+{"current_steps": 228, "total_steps": 1638, "loss": 0.4847, "lr": 3.981422330599231e-05, "epoch": 0.9722814498933902, "percentage": 13.92, "elapsed_time": "2:38:09", "remaining_time": "16:18:05"}
+{"current_steps": 229, "total_steps": 1638, "loss": 0.4779, "lr": 3.980838178913239e-05, "epoch": 0.976545842217484, "percentage": 13.98, "elapsed_time": "2:38:45", "remaining_time": "16:16:47"}
+{"current_steps": 230, "total_steps": 1638, "loss": 0.4876, "lr": 3.980245029069302e-05, "epoch": 0.9808102345415778, "percentage": 14.04, "elapsed_time": "2:39:25", "remaining_time": "16:16:00"}
+{"current_steps": 231, "total_steps": 1638, "loss": 0.4964, "lr": 3.979642883761866e-05, "epoch": 0.9850746268656716, "percentage": 14.1, "elapsed_time": "2:40:08", "remaining_time": "16:15:24"}
+{"current_steps": 232, "total_steps": 1638, "loss": 0.489, "lr": 3.979031745726235e-05, "epoch": 0.9893390191897654, "percentage": 14.16, "elapsed_time": "2:40:56", "remaining_time": "16:15:19"}
+{"current_steps": 233, "total_steps": 1638, "loss": 0.4998, "lr": 3.978411617738567e-05, "epoch": 0.9936034115138592, "percentage": 14.22, "elapsed_time": "2:41:36", "remaining_time": "16:14:32"}
+{"current_steps": 234, "total_steps": 1638, "loss": 0.4953, "lr": 3.977782502615855e-05, "epoch": 0.997867803837953, "percentage": 14.29, "elapsed_time": "2:42:19", "remaining_time": "16:13:56"}
+{"current_steps": 235, "total_steps": 1638, "loss": 0.7992, "lr": 3.977144403215919e-05, "epoch": 1.0031982942430704, "percentage": 14.35, "elapsed_time": "2:43:41", "remaining_time": "16:17:18"}
+{"current_steps": 236, "total_steps": 1638, "loss": 0.4247, "lr": 3.976497322437389e-05, "epoch": 1.007462686567164, "percentage": 14.41, "elapsed_time": "2:44:19", "remaining_time": "16:16:11"}
+{"current_steps": 237, "total_steps": 1638, "loss": 0.4776, "lr": 3.9758412632196953e-05, "epoch": 1.011727078891258, "percentage": 14.47, "elapsed_time": "2:45:02", "remaining_time": "16:15:36"}
+{"current_steps": 238, "total_steps": 1638, "loss": 0.4273, "lr": 3.9751762285430544e-05, "epoch": 1.0159914712153517, "percentage": 14.53, "elapsed_time": "2:45:39", "remaining_time": "16:14:29"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028bd9997e831dee23d938f0470b59a51b0eccce2c8e463021a74d3cb4c45b5e
+size 7224