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 sha256:42ecdf0adf6e26e32017edbf289745879cc5ae825379953d02d6915b430f2437
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a027eb1b742111fabb4a4e39ef01a84ccfa348d599585da999649cbb037f005
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08261ffa8f9d101637a880843eaa7b08f6cfff17506c97ad0efc136a4d672ab
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad382d159fae4a3b1d112553bf4abdc7d9f2be695bb5077acd44e132879e2090
+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 +1,219 @@
+{"current_steps": 1, "total_steps": 1095, "loss": 0.8692, "lr": 7.272727272727273e-07, "epoch": 0.00456490727532097, "percentage": 0.09, "elapsed_time": "0:04:27", "remaining_time": "3 days, 9:12:55"}
+{"current_steps": 2, "total_steps": 1095, "loss": 0.8764, "lr": 1.4545454545454546e-06, "epoch": 0.00912981455064194, "percentage": 0.18, "elapsed_time": "0:08:04", "remaining_time": "3 days, 1:35:35"}
+{"current_steps": 3, "total_steps": 1095, "loss": 0.8604, "lr": 2.181818181818182e-06, "epoch": 0.013694721825962911, "percentage": 0.27, "elapsed_time": "0:11:42", "remaining_time": "2 days, 23:00:25"}
+{"current_steps": 4, "total_steps": 1095, "loss": 0.8563, "lr": 2.9090909090909093e-06, "epoch": 0.01825962910128388, "percentage": 0.37, "elapsed_time": "0:15:20", "remaining_time": "2 days, 21:43:18"}
+{"current_steps": 5, "total_steps": 1095, "loss": 0.8116, "lr": 3.6363636363636366e-06, "epoch": 0.02282453637660485, "percentage": 0.46, "elapsed_time": "0:18:58", "remaining_time": "2 days, 20:55:52"}
+{"current_steps": 6, "total_steps": 1095, "loss": 0.8014, "lr": 4.363636363636364e-06, "epoch": 0.027389443651925822, "percentage": 0.55, "elapsed_time": "0:22:36", "remaining_time": "2 days, 20:23:04"}
+{"current_steps": 7, "total_steps": 1095, "loss": 0.7707, "lr": 5.090909090909091e-06, "epoch": 0.03195435092724679, "percentage": 0.64, "elapsed_time": "0:26:13", "remaining_time": "2 days, 19:56:17"}
+{"current_steps": 8, "total_steps": 1095, "loss": 0.7609, "lr": 5.8181818181818185e-06, "epoch": 0.03651925820256776, "percentage": 0.73, "elapsed_time": "0:29:51", "remaining_time": "2 days, 19:37:25"}
+{"current_steps": 9, "total_steps": 1095, "loss": 0.7714, "lr": 6.545454545454546e-06, "epoch": 0.04108416547788873, "percentage": 0.82, "elapsed_time": "0:33:29", "remaining_time": "2 days, 19:20:55"}
+{"current_steps": 10, "total_steps": 1095, "loss": 0.7639, "lr": 7.272727272727273e-06, "epoch": 0.0456490727532097, "percentage": 0.91, "elapsed_time": "0:37:07", "remaining_time": "2 days, 19:07:51"}
+{"current_steps": 11, "total_steps": 1095, "loss": 0.738, "lr": 8.000000000000001e-06, "epoch": 0.05021398002853067, "percentage": 1.0, "elapsed_time": "0:40:45", "remaining_time": "2 days, 18:56:22"}
+{"current_steps": 12, "total_steps": 1095, "loss": 0.7147, "lr": 8.727272727272728e-06, "epoch": 0.054778887303851644, "percentage": 1.1, "elapsed_time": "0:44:23", "remaining_time": "2 days, 18:46:02"}
+{"current_steps": 13, "total_steps": 1095, "loss": 0.6984, "lr": 9.454545454545456e-06, "epoch": 0.05934379457917261, "percentage": 1.19, "elapsed_time": "0:48:00", "remaining_time": "2 days, 18:36:08"}
+{"current_steps": 14, "total_steps": 1095, "loss": 0.6752, "lr": 1.0181818181818182e-05, "epoch": 0.06390870185449359, "percentage": 1.28, "elapsed_time": "0:51:38", "remaining_time": "2 days, 18:28:01"}
+{"current_steps": 15, "total_steps": 1095, "loss": 0.6564, "lr": 1.0909090909090909e-05, "epoch": 0.06847360912981455, "percentage": 1.37, "elapsed_time": "0:55:16", "remaining_time": "2 days, 18:20:06"}
+{"current_steps": 16, "total_steps": 1095, "loss": 0.6595, "lr": 1.1636363636363637e-05, "epoch": 0.07303851640513552, "percentage": 1.46, "elapsed_time": "0:58:54", "remaining_time": "2 days, 18:12:50"}
+{"current_steps": 17, "total_steps": 1095, "loss": 0.6332, "lr": 1.2363636363636364e-05, "epoch": 0.07760342368045649, "percentage": 1.55, "elapsed_time": "1:02:32", "remaining_time": "2 days, 18:06:08"}
+{"current_steps": 18, "total_steps": 1095, "loss": 0.6275, "lr": 1.3090909090909092e-05, "epoch": 0.08216833095577745, "percentage": 1.64, "elapsed_time": "1:06:10", "remaining_time": "2 days, 17:59:10"}
+{"current_steps": 19, "total_steps": 1095, "loss": 0.617, "lr": 1.381818181818182e-05, "epoch": 0.08673323823109844, "percentage": 1.74, "elapsed_time": "1:09:47", "remaining_time": "2 days, 17:52:48"}
+{"current_steps": 20, "total_steps": 1095, "loss": 0.6102, "lr": 1.4545454545454546e-05, "epoch": 0.0912981455064194, "percentage": 1.83, "elapsed_time": "1:13:25", "remaining_time": "2 days, 17:46:55"}
+{"current_steps": 21, "total_steps": 1095, "loss": 0.6001, "lr": 1.5272727272727276e-05, "epoch": 0.09586305278174037, "percentage": 1.92, "elapsed_time": "1:17:03", "remaining_time": "2 days, 17:41:08"}
+{"current_steps": 22, "total_steps": 1095, "loss": 0.5908, "lr": 1.6000000000000003e-05, "epoch": 0.10042796005706134, "percentage": 2.01, "elapsed_time": "1:20:41", "remaining_time": "2 days, 17:35:39"}
+{"current_steps": 23, "total_steps": 1095, "loss": 0.5857, "lr": 1.672727272727273e-05, "epoch": 0.1049928673323823, "percentage": 2.1, "elapsed_time": "1:24:19", "remaining_time": "2 days, 17:30:37"}
+{"current_steps": 24, "total_steps": 1095, "loss": 0.5813, "lr": 1.7454545454545456e-05, "epoch": 0.10955777460770329, "percentage": 2.19, "elapsed_time": "1:27:57", "remaining_time": "2 days, 17:25:15"}
+{"current_steps": 25, "total_steps": 1095, "loss": 0.5654, "lr": 1.8181818181818182e-05, "epoch": 0.11412268188302425, "percentage": 2.28, "elapsed_time": "1:31:35", "remaining_time": "2 days, 17:20:01"}
+{"current_steps": 26, "total_steps": 1095, "loss": 0.5681, "lr": 1.8909090909090912e-05, "epoch": 0.11868758915834522, "percentage": 2.37, "elapsed_time": "1:35:13", "remaining_time": "2 days, 17:15:13"}
+{"current_steps": 27, "total_steps": 1095, "loss": 0.5726, "lr": 1.963636363636364e-05, "epoch": 0.12325249643366619, "percentage": 2.47, "elapsed_time": "1:38:50", "remaining_time": "2 days, 17:10:00"}
+{"current_steps": 28, "total_steps": 1095, "loss": 0.5707, "lr": 2.0363636363636365e-05, "epoch": 0.12781740370898717, "percentage": 2.56, "elapsed_time": "1:42:28", "remaining_time": "2 days, 17:05:18"}
+{"current_steps": 29, "total_steps": 1095, "loss": 0.562, "lr": 2.109090909090909e-05, "epoch": 0.13238231098430814, "percentage": 2.65, "elapsed_time": "1:46:06", "remaining_time": "2 days, 17:00:24"}
+{"current_steps": 30, "total_steps": 1095, "loss": 0.5622, "lr": 2.1818181818181818e-05, "epoch": 0.1369472182596291, "percentage": 2.74, "elapsed_time": "1:49:43", "remaining_time": "2 days, 16:55:16"}
+{"current_steps": 31, "total_steps": 1095, "loss": 0.5556, "lr": 2.2545454545454544e-05, "epoch": 0.14151212553495007, "percentage": 2.83, "elapsed_time": "1:53:21", "remaining_time": "2 days, 16:50:41"}
+{"current_steps": 32, "total_steps": 1095, "loss": 0.5521, "lr": 2.3272727272727274e-05, "epoch": 0.14607703281027104, "percentage": 2.92, "elapsed_time": "1:56:59", "remaining_time": "2 days, 16:46:23"}
+{"current_steps": 33, "total_steps": 1095, "loss": 0.5521, "lr": 2.4e-05, "epoch": 0.150641940085592, "percentage": 3.01, "elapsed_time": "2:00:37", "remaining_time": "2 days, 16:41:41"}
+{"current_steps": 34, "total_steps": 1095, "loss": 0.5556, "lr": 2.4727272727272727e-05, "epoch": 0.15520684736091298, "percentage": 3.11, "elapsed_time": "2:04:15", "remaining_time": "2 days, 16:37:21"}
+{"current_steps": 35, "total_steps": 1095, "loss": 0.5439, "lr": 2.5454545454545457e-05, "epoch": 0.15977175463623394, "percentage": 3.2, "elapsed_time": "2:07:52", "remaining_time": "2 days, 16:32:50"}
+{"current_steps": 36, "total_steps": 1095, "loss": 0.5399, "lr": 2.6181818181818183e-05, "epoch": 0.1643366619115549, "percentage": 3.29, "elapsed_time": "2:11:30", "remaining_time": "2 days, 16:28:21"}
+{"current_steps": 37, "total_steps": 1095, "loss": 0.534, "lr": 2.690909090909091e-05, "epoch": 0.1689015691868759, "percentage": 3.38, "elapsed_time": "2:15:07", "remaining_time": "2 days, 16:23:39"}
+{"current_steps": 38, "total_steps": 1095, "loss": 0.5432, "lr": 2.763636363636364e-05, "epoch": 0.17346647646219687, "percentage": 3.47, "elapsed_time": "2:18:44", "remaining_time": "2 days, 16:19:19"}
+{"current_steps": 39, "total_steps": 1095, "loss": 0.538, "lr": 2.8363636363636366e-05, "epoch": 0.17803138373751784, "percentage": 3.56, "elapsed_time": "2:22:22", "remaining_time": "2 days, 16:15:10"}
+{"current_steps": 40, "total_steps": 1095, "loss": 0.5311, "lr": 2.9090909090909093e-05, "epoch": 0.1825962910128388, "percentage": 3.65, "elapsed_time": "2:26:00", "remaining_time": "2 days, 16:10:57"}
+{"current_steps": 41, "total_steps": 1095, "loss": 0.5302, "lr": 2.9818181818181823e-05, "epoch": 0.18716119828815977, "percentage": 3.74, "elapsed_time": "2:29:38", "remaining_time": "2 days, 16:06:42"}
+{"current_steps": 42, "total_steps": 1095, "loss": 0.5287, "lr": 3.054545454545455e-05, "epoch": 0.19172610556348074, "percentage": 3.84, "elapsed_time": "2:33:15", "remaining_time": "2 days, 16:02:31"}
+{"current_steps": 43, "total_steps": 1095, "loss": 0.529, "lr": 3.127272727272728e-05, "epoch": 0.1962910128388017, "percentage": 3.93, "elapsed_time": "2:36:53", "remaining_time": "2 days, 15:58:28"}
+{"current_steps": 44, "total_steps": 1095, "loss": 0.5211, "lr": 3.2000000000000005e-05, "epoch": 0.20085592011412268, "percentage": 4.02, "elapsed_time": "2:40:31", "remaining_time": "2 days, 15:54:17"}
+{"current_steps": 45, "total_steps": 1095, "loss": 0.5286, "lr": 3.272727272727273e-05, "epoch": 0.20542082738944364, "percentage": 4.11, "elapsed_time": "2:44:09", "remaining_time": "2 days, 15:50:11"}
+{"current_steps": 46, "total_steps": 1095, "loss": 0.5251, "lr": 3.345454545454546e-05, "epoch": 0.2099857346647646, "percentage": 4.2, "elapsed_time": "2:47:46", "remaining_time": "2 days, 15:46:05"}
+{"current_steps": 47, "total_steps": 1095, "loss": 0.5307, "lr": 3.4181818181818185e-05, "epoch": 0.21455064194008558, "percentage": 4.29, "elapsed_time": "2:51:24", "remaining_time": "2 days, 15:42:03"}
+{"current_steps": 48, "total_steps": 1095, "loss": 0.5119, "lr": 3.490909090909091e-05, "epoch": 0.21911554921540657, "percentage": 4.38, "elapsed_time": "2:55:02", "remaining_time": "2 days, 15:38:06"}
+{"current_steps": 49, "total_steps": 1095, "loss": 0.522, "lr": 3.563636363636364e-05, "epoch": 0.22368045649072754, "percentage": 4.47, "elapsed_time": "2:58:40", "remaining_time": "2 days, 15:34:06"}
+{"current_steps": 50, "total_steps": 1095, "loss": 0.5185, "lr": 3.6363636363636364e-05, "epoch": 0.2282453637660485, "percentage": 4.57, "elapsed_time": "3:02:18", "remaining_time": "2 days, 15:30:10"}
+{"current_steps": 51, "total_steps": 1095, "loss": 0.5178, "lr": 3.709090909090909e-05, "epoch": 0.23281027104136948, "percentage": 4.66, "elapsed_time": "3:05:56", "remaining_time": "2 days, 15:26:16"}
+{"current_steps": 52, "total_steps": 1095, "loss": 0.5164, "lr": 3.7818181818181824e-05, "epoch": 0.23737517831669044, "percentage": 4.75, "elapsed_time": "3:09:34", "remaining_time": "2 days, 15:22:20"}
+{"current_steps": 53, "total_steps": 1095, "loss": 0.5161, "lr": 3.854545454545455e-05, "epoch": 0.2419400855920114, "percentage": 4.84, "elapsed_time": "3:13:12", "remaining_time": "2 days, 15:18:27"}
+{"current_steps": 54, "total_steps": 1095, "loss": 0.5142, "lr": 3.927272727272728e-05, "epoch": 0.24650499286733238, "percentage": 4.93, "elapsed_time": "3:16:50", "remaining_time": "2 days, 15:14:34"}
+{"current_steps": 55, "total_steps": 1095, "loss": 0.5097, "lr": 4e-05, "epoch": 0.25106990014265335, "percentage": 5.02, "elapsed_time": "3:20:27", "remaining_time": "2 days, 15:10:34"}
+{"current_steps": 56, "total_steps": 1095, "loss": 0.52, "lr": 4.072727272727273e-05, "epoch": 0.25563480741797434, "percentage": 5.11, "elapsed_time": "3:24:05", "remaining_time": "2 days, 15:06:41"}
+{"current_steps": 57, "total_steps": 1095, "loss": 0.5214, "lr": 4.1454545454545456e-05, "epoch": 0.2601997146932953, "percentage": 5.21, "elapsed_time": "3:27:43", "remaining_time": "2 days, 15:02:38"}
+{"current_steps": 58, "total_steps": 1095, "loss": 0.5131, "lr": 4.218181818181818e-05, "epoch": 0.2647646219686163, "percentage": 5.3, "elapsed_time": "3:31:20", "remaining_time": "2 days, 14:58:41"}
+{"current_steps": 59, "total_steps": 1095, "loss": 0.5156, "lr": 4.2909090909090916e-05, "epoch": 0.2693295292439372, "percentage": 5.39, "elapsed_time": "3:34:58", "remaining_time": "2 days, 14:54:48"}
+{"current_steps": 60, "total_steps": 1095, "loss": 0.5063, "lr": 4.3636363636363636e-05, "epoch": 0.2738944365192582, "percentage": 5.48, "elapsed_time": "3:38:35", "remaining_time": "2 days, 14:50:48"}
+{"current_steps": 61, "total_steps": 1095, "loss": 0.5058, "lr": 4.436363636363637e-05, "epoch": 0.27845934379457915, "percentage": 5.57, "elapsed_time": "3:42:13", "remaining_time": "2 days, 14:46:58"}
+{"current_steps": 62, "total_steps": 1095, "loss": 0.5169, "lr": 4.509090909090909e-05, "epoch": 0.28302425106990015, "percentage": 5.66, "elapsed_time": "3:45:51", "remaining_time": "2 days, 14:42:57"}
+{"current_steps": 63, "total_steps": 1095, "loss": 0.5077, "lr": 4.581818181818182e-05, "epoch": 0.2875891583452211, "percentage": 5.75, "elapsed_time": "3:49:28", "remaining_time": "2 days, 14:39:08"}
+{"current_steps": 64, "total_steps": 1095, "loss": 0.5137, "lr": 4.654545454545455e-05, "epoch": 0.2921540656205421, "percentage": 5.84, "elapsed_time": "3:53:06", "remaining_time": "2 days, 14:35:19"}
+{"current_steps": 65, "total_steps": 1095, "loss": 0.5066, "lr": 4.727272727272728e-05, "epoch": 0.2967189728958631, "percentage": 5.94, "elapsed_time": "3:56:44", "remaining_time": "2 days, 14:31:29"}
+{"current_steps": 66, "total_steps": 1095, "loss": 0.5012, "lr": 4.8e-05, "epoch": 0.301283880171184, "percentage": 6.03, "elapsed_time": "4:00:22", "remaining_time": "2 days, 14:27:44"}
+{"current_steps": 67, "total_steps": 1095, "loss": 0.4996, "lr": 4.8727272727272734e-05, "epoch": 0.305848787446505, "percentage": 6.12, "elapsed_time": "4:04:00", "remaining_time": "2 days, 14:23:49"}
+{"current_steps": 68, "total_steps": 1095, "loss": 0.5048, "lr": 4.9454545454545454e-05, "epoch": 0.31041369472182595, "percentage": 6.21, "elapsed_time": "4:07:37", "remaining_time": "2 days, 14:19:52"}
+{"current_steps": 69, "total_steps": 1095, "loss": 0.5005, "lr": 5.018181818181819e-05, "epoch": 0.31497860199714695, "percentage": 6.3, "elapsed_time": "4:11:14", "remaining_time": "2 days, 14:15:58"}
+{"current_steps": 70, "total_steps": 1095, "loss": 0.5011, "lr": 5.0909090909090914e-05, "epoch": 0.3195435092724679, "percentage": 6.39, "elapsed_time": "4:14:53", "remaining_time": "2 days, 14:12:13"}
+{"current_steps": 71, "total_steps": 1095, "loss": 0.5094, "lr": 5.163636363636365e-05, "epoch": 0.3241084165477889, "percentage": 6.48, "elapsed_time": "4:18:31", "remaining_time": "2 days, 14:08:33"}
+{"current_steps": 72, "total_steps": 1095, "loss": 0.4963, "lr": 5.236363636363637e-05, "epoch": 0.3286733238231098, "percentage": 6.58, "elapsed_time": "4:22:09", "remaining_time": "2 days, 14:04:45"}
+{"current_steps": 73, "total_steps": 1095, "loss": 0.5079, "lr": 5.30909090909091e-05, "epoch": 0.3332382310984308, "percentage": 6.67, "elapsed_time": "4:25:46", "remaining_time": "2 days, 14:00:53"}
+{"current_steps": 74, "total_steps": 1095, "loss": 0.5094, "lr": 5.381818181818182e-05, "epoch": 0.3378031383737518, "percentage": 6.76, "elapsed_time": "4:29:24", "remaining_time": "2 days, 13:57:07"}
+{"current_steps": 75, "total_steps": 1095, "loss": 0.5101, "lr": 5.4545454545454546e-05, "epoch": 0.34236804564907275, "percentage": 6.85, "elapsed_time": "4:33:02", "remaining_time": "2 days, 13:53:21"}
+{"current_steps": 76, "total_steps": 1095, "loss": 0.5009, "lr": 5.527272727272728e-05, "epoch": 0.34693295292439374, "percentage": 6.94, "elapsed_time": "4:36:39", "remaining_time": "2 days, 13:49:24"}
+{"current_steps": 77, "total_steps": 1095, "loss": 0.5185, "lr": 5.6e-05, "epoch": 0.3514978601997147, "percentage": 7.03, "elapsed_time": "4:40:17", "remaining_time": "2 days, 13:45:36"}
+{"current_steps": 78, "total_steps": 1095, "loss": 0.5033, "lr": 5.672727272727273e-05, "epoch": 0.3560627674750357, "percentage": 7.12, "elapsed_time": "4:43:54", "remaining_time": "2 days, 13:41:43"}
+{"current_steps": 79, "total_steps": 1095, "loss": 0.5038, "lr": 5.745454545454546e-05, "epoch": 0.3606276747503566, "percentage": 7.21, "elapsed_time": "4:47:32", "remaining_time": "2 days, 13:38:00"}
+{"current_steps": 80, "total_steps": 1095, "loss": 0.4969, "lr": 5.8181818181818185e-05, "epoch": 0.3651925820256776, "percentage": 7.31, "elapsed_time": "4:51:10", "remaining_time": "2 days, 13:34:14"}
+{"current_steps": 81, "total_steps": 1095, "loss": 0.5045, "lr": 5.890909090909091e-05, "epoch": 0.36975748930099855, "percentage": 7.4, "elapsed_time": "4:54:48", "remaining_time": "2 days, 13:30:32"}
+{"current_steps": 82, "total_steps": 1095, "loss": 0.5058, "lr": 5.9636363636363645e-05, "epoch": 0.37432239657631955, "percentage": 7.49, "elapsed_time": "4:58:26", "remaining_time": "2 days, 13:26:49"}
+{"current_steps": 83, "total_steps": 1095, "loss": 0.5064, "lr": 6.0363636363636365e-05, "epoch": 0.3788873038516405, "percentage": 7.58, "elapsed_time": "5:02:03", "remaining_time": "2 days, 13:23:00"}
+{"current_steps": 84, "total_steps": 1095, "loss": 0.5018, "lr": 6.10909090909091e-05, "epoch": 0.3834522111269615, "percentage": 7.67, "elapsed_time": "5:05:41", "remaining_time": "2 days, 13:19:17"}
+{"current_steps": 85, "total_steps": 1095, "loss": 0.5017, "lr": 6.181818181818182e-05, "epoch": 0.3880171184022825, "percentage": 7.76, "elapsed_time": "5:09:19", "remaining_time": "2 days, 13:15:31"}
+{"current_steps": 86, "total_steps": 1095, "loss": 0.498, "lr": 6.254545454545456e-05, "epoch": 0.3925820256776034, "percentage": 7.85, "elapsed_time": "5:12:57", "remaining_time": "2 days, 13:11:46"}
+{"current_steps": 87, "total_steps": 1095, "loss": 0.5019, "lr": 6.327272727272727e-05, "epoch": 0.3971469329529244, "percentage": 7.95, "elapsed_time": "5:16:35", "remaining_time": "2 days, 13:08:02"}
+{"current_steps": 88, "total_steps": 1095, "loss": 0.4968, "lr": 6.400000000000001e-05, "epoch": 0.40171184022824535, "percentage": 8.04, "elapsed_time": "5:20:13", "remaining_time": "2 days, 13:04:24"}
+{"current_steps": 89, "total_steps": 1095, "loss": 0.4957, "lr": 6.472727272727274e-05, "epoch": 0.40627674750356635, "percentage": 8.13, "elapsed_time": "5:23:51", "remaining_time": "2 days, 13:00:43"}
+{"current_steps": 90, "total_steps": 1095, "loss": 0.4966, "lr": 6.545454545454546e-05, "epoch": 0.4108416547788873, "percentage": 8.22, "elapsed_time": "5:27:28", "remaining_time": "2 days, 12:56:53"}
+{"current_steps": 91, "total_steps": 1095, "loss": 0.4966, "lr": 6.618181818181819e-05, "epoch": 0.4154065620542083, "percentage": 8.31, "elapsed_time": "5:31:06", "remaining_time": "2 days, 12:53:07"}
+{"current_steps": 92, "total_steps": 1095, "loss": 0.4925, "lr": 6.690909090909092e-05, "epoch": 0.4199714693295292, "percentage": 8.4, "elapsed_time": "5:34:44", "remaining_time": "2 days, 12:49:19"}
+{"current_steps": 93, "total_steps": 1095, "loss": 0.4876, "lr": 6.763636363636364e-05, "epoch": 0.4245363766048502, "percentage": 8.49, "elapsed_time": "5:38:21", "remaining_time": "2 days, 12:45:33"}
+{"current_steps": 94, "total_steps": 1095, "loss": 0.4913, "lr": 6.836363636363637e-05, "epoch": 0.42910128388017116, "percentage": 8.58, "elapsed_time": "5:41:58", "remaining_time": "2 days, 12:41:44"}
+{"current_steps": 95, "total_steps": 1095, "loss": 0.4903, "lr": 6.90909090909091e-05, "epoch": 0.43366619115549215, "percentage": 8.68, "elapsed_time": "5:45:36", "remaining_time": "2 days, 12:38:00"}
+{"current_steps": 96, "total_steps": 1095, "loss": 0.4912, "lr": 6.981818181818182e-05, "epoch": 0.43823109843081315, "percentage": 8.77, "elapsed_time": "5:49:13", "remaining_time": "2 days, 12:34:12"}
+{"current_steps": 97, "total_steps": 1095, "loss": 0.4901, "lr": 7.054545454545455e-05, "epoch": 0.4427960057061341, "percentage": 8.86, "elapsed_time": "5:52:52", "remaining_time": "2 days, 12:30:31"}
+{"current_steps": 98, "total_steps": 1095, "loss": 0.4873, "lr": 7.127272727272728e-05, "epoch": 0.4473609129814551, "percentage": 8.95, "elapsed_time": "5:56:29", "remaining_time": "2 days, 12:26:49"}
+{"current_steps": 99, "total_steps": 1095, "loss": 0.4891, "lr": 7.2e-05, "epoch": 0.451925820256776, "percentage": 9.04, "elapsed_time": "6:00:06", "remaining_time": "2 days, 12:22:55"}
+{"current_steps": 100, "total_steps": 1095, "loss": 0.49, "lr": 7.272727272727273e-05, "epoch": 0.456490727532097, "percentage": 9.13, "elapsed_time": "6:03:44", "remaining_time": "2 days, 12:19:13"}
+{"current_steps": 101, "total_steps": 1095, "loss": 0.5055, "lr": 7.345454545454547e-05, "epoch": 0.46105563480741796, "percentage": 9.22, "elapsed_time": "6:07:22", "remaining_time": "2 days, 12:15:29"}
+{"current_steps": 102, "total_steps": 1095, "loss": 0.4852, "lr": 7.418181818181818e-05, "epoch": 0.46562054208273895, "percentage": 9.32, "elapsed_time": "6:10:59", "remaining_time": "2 days, 12:11:46"}
+{"current_steps": 103, "total_steps": 1095, "loss": 0.4919, "lr": 7.490909090909092e-05, "epoch": 0.4701854493580599, "percentage": 9.41, "elapsed_time": "6:14:37", "remaining_time": "2 days, 12:08:04"}
+{"current_steps": 104, "total_steps": 1095, "loss": 0.4968, "lr": 7.563636363636365e-05, "epoch": 0.4747503566333809, "percentage": 9.5, "elapsed_time": "6:18:15", "remaining_time": "2 days, 12:04:17"}
+{"current_steps": 105, "total_steps": 1095, "loss": 0.4874, "lr": 7.636363636363637e-05, "epoch": 0.4793152639087018, "percentage": 9.59, "elapsed_time": "6:21:52", "remaining_time": "2 days, 12:00:30"}
+{"current_steps": 106, "total_steps": 1095, "loss": 0.4953, "lr": 7.70909090909091e-05, "epoch": 0.4838801711840228, "percentage": 9.68, "elapsed_time": "6:25:29", "remaining_time": "2 days, 11:56:44"}
+{"current_steps": 107, "total_steps": 1095, "loss": 0.5006, "lr": 7.781818181818183e-05, "epoch": 0.4884450784593438, "percentage": 9.77, "elapsed_time": "6:29:07", "remaining_time": "2 days, 11:53:02"}
+{"current_steps": 108, "total_steps": 1095, "loss": 0.4871, "lr": 7.854545454545455e-05, "epoch": 0.49300998573466476, "percentage": 9.86, "elapsed_time": "6:32:45", "remaining_time": "2 days, 11:49:21"}
+{"current_steps": 109, "total_steps": 1095, "loss": 0.4975, "lr": 7.927272727272728e-05, "epoch": 0.49757489300998575, "percentage": 9.95, "elapsed_time": "6:36:23", "remaining_time": "2 days, 11:45:42"}
+{"current_steps": 110, "total_steps": 1095, "loss": 0.492, "lr": 8e-05, "epoch": 0.5021398002853067, "percentage": 10.05, "elapsed_time": "6:40:00", "remaining_time": "2 days, 11:41:58"}
+{"current_steps": 111, "total_steps": 1095, "loss": 0.5094, "lr": 7.999979655036647e-05, "epoch": 0.5067047075606277, "percentage": 10.14, "elapsed_time": "6:43:38", "remaining_time": "2 days, 11:38:15"}
+{"current_steps": 112, "total_steps": 1095, "loss": 0.4931, "lr": 7.999918620353548e-05, "epoch": 0.5112696148359487, "percentage": 10.23, "elapsed_time": "6:47:16", "remaining_time": "2 days, 11:34:35"}
+{"current_steps": 113, "total_steps": 1095, "loss": 0.5051, "lr": 7.999816896571574e-05, "epoch": 0.5158345221112696, "percentage": 10.32, "elapsed_time": "6:50:54", "remaining_time": "2 days, 11:30:54"}
+{"current_steps": 114, "total_steps": 1095, "loss": 0.4984, "lr": 7.999674484725512e-05, "epoch": 0.5203994293865906, "percentage": 10.41, "elapsed_time": "6:54:32", "remaining_time": "2 days, 11:27:13"}
+{"current_steps": 115, "total_steps": 1095, "loss": 0.492, "lr": 7.999491386264042e-05, "epoch": 0.5249643366619116, "percentage": 10.5, "elapsed_time": "6:58:10", "remaining_time": "2 days, 11:23:30"}
+{"current_steps": 116, "total_steps": 1095, "loss": 0.4902, "lr": 7.999267603049729e-05, "epoch": 0.5295292439372326, "percentage": 10.59, "elapsed_time": "7:01:47", "remaining_time": "2 days, 11:19:49"}
+{"current_steps": 117, "total_steps": 1095, "loss": 0.4927, "lr": 7.999003137359006e-05, "epoch": 0.5340941512125535, "percentage": 10.68, "elapsed_time": "7:05:25", "remaining_time": "2 days, 11:16:04"}
+{"current_steps": 118, "total_steps": 1095, "loss": 0.4876, "lr": 7.998697991882144e-05, "epoch": 0.5386590584878744, "percentage": 10.78, "elapsed_time": "7:09:02", "remaining_time": "2 days, 11:12:22"}
+{"current_steps": 119, "total_steps": 1095, "loss": 0.4865, "lr": 7.998352169723229e-05, "epoch": 0.5432239657631954, "percentage": 10.87, "elapsed_time": "7:12:40", "remaining_time": "2 days, 11:08:42"}
+{"current_steps": 120, "total_steps": 1095, "loss": 0.4898, "lr": 7.997965674400132e-05, "epoch": 0.5477888730385164, "percentage": 10.96, "elapsed_time": "7:16:18", "remaining_time": "2 days, 11:05:00"}
+{"current_steps": 121, "total_steps": 1095, "loss": 0.4884, "lr": 7.997538509844469e-05, "epoch": 0.5523537803138374, "percentage": 11.05, "elapsed_time": "7:19:56", "remaining_time": "2 days, 11:01:21"}
+{"current_steps": 122, "total_steps": 1095, "loss": 0.4814, "lr": 7.997070680401562e-05, "epoch": 0.5569186875891583, "percentage": 11.14, "elapsed_time": "7:23:34", "remaining_time": "2 days, 10:57:39"}
+{"current_steps": 123, "total_steps": 1095, "loss": 0.4862, "lr": 7.9965621908304e-05, "epoch": 0.5614835948644793, "percentage": 11.23, "elapsed_time": "7:27:14", "remaining_time": "2 days, 10:54:18"}
+{"current_steps": 124, "total_steps": 1095, "loss": 0.4907, "lr": 7.996013046303583e-05, "epoch": 0.5660485021398003, "percentage": 11.32, "elapsed_time": "7:30:55", "remaining_time": "2 days, 10:51:04"}
+{"current_steps": 125, "total_steps": 1095, "loss": 0.4849, "lr": 7.995423252407275e-05, "epoch": 0.5706134094151213, "percentage": 11.42, "elapsed_time": "7:34:33", "remaining_time": "2 days, 10:47:22"}
+{"current_steps": 126, "total_steps": 1095, "loss": 0.4829, "lr": 7.99479281514114e-05, "epoch": 0.5751783166904422, "percentage": 11.51, "elapsed_time": "7:38:11", "remaining_time": "2 days, 10:43:42"}
+{"current_steps": 127, "total_steps": 1095, "loss": 0.4888, "lr": 7.994121740918293e-05, "epoch": 0.5797432239657632, "percentage": 11.6, "elapsed_time": "7:41:49", "remaining_time": "2 days, 10:40:02"}
+{"current_steps": 128, "total_steps": 1095, "loss": 0.4776, "lr": 7.993410036565223e-05, "epoch": 0.5843081312410842, "percentage": 11.69, "elapsed_time": "7:45:26", "remaining_time": "2 days, 10:36:18"}
+{"current_steps": 129, "total_steps": 1095, "loss": 0.4856, "lr": 7.992657709321728e-05, "epoch": 0.5888730385164052, "percentage": 11.78, "elapsed_time": "7:49:04", "remaining_time": "2 days, 10:32:34"}
+{"current_steps": 130, "total_steps": 1095, "loss": 0.4832, "lr": 7.991864766840846e-05, "epoch": 0.5934379457917262, "percentage": 11.87, "elapsed_time": "7:52:41", "remaining_time": "2 days, 10:28:52"}
+{"current_steps": 131, "total_steps": 1095, "loss": 0.483, "lr": 7.991031217188769e-05, "epoch": 0.598002853067047, "percentage": 11.96, "elapsed_time": "7:56:19", "remaining_time": "2 days, 10:25:08"}
+{"current_steps": 132, "total_steps": 1095, "loss": 0.4762, "lr": 7.990157068844764e-05, "epoch": 0.602567760342368, "percentage": 12.05, "elapsed_time": "7:59:56", "remaining_time": "2 days, 10:21:26"}
+{"current_steps": 133, "total_steps": 1095, "loss": 0.4794, "lr": 7.989242330701089e-05, "epoch": 0.607132667617689, "percentage": 12.15, "elapsed_time": "8:03:34", "remaining_time": "2 days, 10:17:44"}
+{"current_steps": 134, "total_steps": 1095, "loss": 0.4772, "lr": 7.988287012062902e-05, "epoch": 0.61169757489301, "percentage": 12.24, "elapsed_time": "8:07:11", "remaining_time": "2 days, 10:14:00"}
+{"current_steps": 135, "total_steps": 1095, "loss": 0.4844, "lr": 7.987291122648165e-05, "epoch": 0.6162624821683309, "percentage": 12.33, "elapsed_time": "8:10:49", "remaining_time": "2 days, 10:10:21"}
+{"current_steps": 136, "total_steps": 1095, "loss": 0.4872, "lr": 7.986254672587544e-05, "epoch": 0.6208273894436519, "percentage": 12.42, "elapsed_time": "8:14:27", "remaining_time": "2 days, 10:06:39"}
+{"current_steps": 137, "total_steps": 1095, "loss": 0.4742, "lr": 7.985177672424309e-05, "epoch": 0.6253922967189729, "percentage": 12.51, "elapsed_time": "8:18:05", "remaining_time": "2 days, 10:03:00"}
+{"current_steps": 138, "total_steps": 1095, "loss": 0.4828, "lr": 7.984060133114222e-05, "epoch": 0.6299572039942939, "percentage": 12.6, "elapsed_time": "8:21:43", "remaining_time": "2 days, 9:59:18"}
+{"current_steps": 139, "total_steps": 1095, "loss": 0.4841, "lr": 7.982902066025433e-05, "epoch": 0.6345221112696149, "percentage": 12.69, "elapsed_time": "8:25:20", "remaining_time": "2 days, 9:55:36"}
+{"current_steps": 140, "total_steps": 1095, "loss": 0.4765, "lr": 7.981703482938361e-05, "epoch": 0.6390870185449358, "percentage": 12.79, "elapsed_time": "8:28:58", "remaining_time": "2 days, 9:51:56"}
+{"current_steps": 141, "total_steps": 1095, "loss": 0.48, "lr": 7.980464396045565e-05, "epoch": 0.6436519258202568, "percentage": 12.88, "elapsed_time": "8:32:36", "remaining_time": "2 days, 9:48:16"}
+{"current_steps": 142, "total_steps": 1095, "loss": 0.472, "lr": 7.979184817951638e-05, "epoch": 0.6482168330955778, "percentage": 12.97, "elapsed_time": "8:36:14", "remaining_time": "2 days, 9:44:37"}
+{"current_steps": 143, "total_steps": 1095, "loss": 0.4819, "lr": 7.977864761673062e-05, "epoch": 0.6527817403708988, "percentage": 13.06, "elapsed_time": "8:39:52", "remaining_time": "2 days, 9:40:56"}
+{"current_steps": 144, "total_steps": 1095, "loss": 0.4759, "lr": 7.976504240638088e-05, "epoch": 0.6573466476462196, "percentage": 13.15, "elapsed_time": "8:43:29", "remaining_time": "2 days, 9:37:16"}
+{"current_steps": 145, "total_steps": 1095, "loss": 0.4708, "lr": 7.975103268686587e-05, "epoch": 0.6619115549215406, "percentage": 13.24, "elapsed_time": "8:47:07", "remaining_time": "2 days, 9:33:33"}
+{"current_steps": 146, "total_steps": 1095, "loss": 0.481, "lr": 7.973661860069925e-05, "epoch": 0.6664764621968616, "percentage": 13.33, "elapsed_time": "8:50:45", "remaining_time": "2 days, 9:29:53"}
+{"current_steps": 147, "total_steps": 1095, "loss": 0.4771, "lr": 7.972180029450804e-05, "epoch": 0.6710413694721826, "percentage": 13.42, "elapsed_time": "8:54:22", "remaining_time": "2 days, 9:26:08"}
+{"current_steps": 148, "total_steps": 1095, "loss": 0.4766, "lr": 7.970657791903115e-05, "epoch": 0.6756062767475036, "percentage": 13.52, "elapsed_time": "8:57:59", "remaining_time": "2 days, 9:22:26"}
+{"current_steps": 149, "total_steps": 1095, "loss": 0.4765, "lr": 7.969095162911796e-05, "epoch": 0.6801711840228245, "percentage": 13.61, "elapsed_time": "9:01:37", "remaining_time": "2 days, 9:18:45"}
+{"current_steps": 150, "total_steps": 1095, "loss": 0.4708, "lr": 7.967492158372659e-05, "epoch": 0.6847360912981455, "percentage": 13.7, "elapsed_time": "9:05:15", "remaining_time": "2 days, 9:15:04"}
+{"current_steps": 151, "total_steps": 1095, "loss": 0.4702, "lr": 7.965848794592241e-05, "epoch": 0.6893009985734665, "percentage": 13.79, "elapsed_time": "9:08:52", "remaining_time": "2 days, 9:11:21"}
+{"current_steps": 152, "total_steps": 1095, "loss": 0.4756, "lr": 7.964165088287627e-05, "epoch": 0.6938659058487875, "percentage": 13.88, "elapsed_time": "9:12:30", "remaining_time": "2 days, 9:07:42"}
+{"current_steps": 153, "total_steps": 1095, "loss": 0.4684, "lr": 7.96244105658629e-05, "epoch": 0.6984308131241084, "percentage": 13.97, "elapsed_time": "9:16:07", "remaining_time": "2 days, 9:03:59"}
+{"current_steps": 154, "total_steps": 1095, "loss": 0.4674, "lr": 7.960676717025912e-05, "epoch": 0.7029957203994294, "percentage": 14.06, "elapsed_time": "9:19:45", "remaining_time": "2 days, 9:00:19"}
+{"current_steps": 155, "total_steps": 1095, "loss": 0.4759, "lr": 7.958872087554204e-05, "epoch": 0.7075606276747504, "percentage": 14.16, "elapsed_time": "9:23:23", "remaining_time": "2 days, 8:56:43"}
+{"current_steps": 156, "total_steps": 1095, "loss": 0.4792, "lr": 7.957027186528724e-05, "epoch": 0.7121255349500714, "percentage": 14.25, "elapsed_time": "9:27:01", "remaining_time": "2 days, 8:53:04"}
+{"current_steps": 157, "total_steps": 1095, "loss": 0.4711, "lr": 7.955142032716696e-05, "epoch": 0.7166904422253922, "percentage": 14.34, "elapsed_time": "9:30:38", "remaining_time": "2 days, 8:49:21"}
+{"current_steps": 158, "total_steps": 1095, "loss": 0.4785, "lr": 7.953216645294813e-05, "epoch": 0.7212553495007132, "percentage": 14.43, "elapsed_time": "9:34:16", "remaining_time": "2 days, 8:45:42"}
+{"current_steps": 159, "total_steps": 1095, "loss": 0.4703, "lr": 7.951251043849043e-05, "epoch": 0.7258202567760342, "percentage": 14.52, "elapsed_time": "9:37:54", "remaining_time": "2 days, 8:42:03"}
+{"current_steps": 160, "total_steps": 1095, "loss": 0.4691, "lr": 7.94924524837443e-05, "epoch": 0.7303851640513552, "percentage": 14.61, "elapsed_time": "9:41:32", "remaining_time": "2 days, 8:38:24"}
+{"current_steps": 161, "total_steps": 1095, "loss": 0.4719, "lr": 7.947199279274892e-05, "epoch": 0.7349500713266762, "percentage": 14.7, "elapsed_time": "9:45:10", "remaining_time": "2 days, 8:34:43"}
+{"current_steps": 162, "total_steps": 1095, "loss": 0.4705, "lr": 7.945113157363012e-05, "epoch": 0.7395149786019971, "percentage": 14.79, "elapsed_time": "9:48:48", "remaining_time": "2 days, 8:31:03"}
+{"current_steps": 163, "total_steps": 1095, "loss": 0.476, "lr": 7.942986903859826e-05, "epoch": 0.7440798858773181, "percentage": 14.89, "elapsed_time": "9:52:25", "remaining_time": "2 days, 8:27:22"}
+{"current_steps": 164, "total_steps": 1095, "loss": 0.4685, "lr": 7.940820540394611e-05, "epoch": 0.7486447931526391, "percentage": 14.98, "elapsed_time": "9:56:03", "remaining_time": "2 days, 8:23:42"}
+{"current_steps": 165, "total_steps": 1095, "loss": 0.4634, "lr": 7.938614089004659e-05, "epoch": 0.7532097004279601, "percentage": 15.07, "elapsed_time": "9:59:40", "remaining_time": "2 days, 8:20:01"}
+{"current_steps": 166, "total_steps": 1095, "loss": 0.4741, "lr": 7.936367572135056e-05, "epoch": 0.757774607703281, "percentage": 15.16, "elapsed_time": "10:03:18", "remaining_time": "2 days, 8:16:19"}
+{"current_steps": 167, "total_steps": 1095, "loss": 0.4801, "lr": 7.934081012638452e-05, "epoch": 0.762339514978602, "percentage": 15.25, "elapsed_time": "10:06:56", "remaining_time": "2 days, 8:12:39"}
+{"current_steps": 168, "total_steps": 1095, "loss": 0.4753, "lr": 7.931754433774835e-05, "epoch": 0.766904422253923, "percentage": 15.34, "elapsed_time": "10:10:33", "remaining_time": "2 days, 8:08:58"}
+{"current_steps": 169, "total_steps": 1095, "loss": 0.4864, "lr": 7.929387859211283e-05, "epoch": 0.771469329529244, "percentage": 15.43, "elapsed_time": "10:14:11", "remaining_time": "2 days, 8:05:19"}
+{"current_steps": 170, "total_steps": 1095, "loss": 0.4845, "lr": 7.926981313021734e-05, "epoch": 0.776034236804565, "percentage": 15.53, "elapsed_time": "10:17:49", "remaining_time": "2 days, 8:01:43"}
+{"current_steps": 171, "total_steps": 1095, "loss": 0.4807, "lr": 7.924534819686735e-05, "epoch": 0.7805991440798858, "percentage": 15.62, "elapsed_time": "10:21:27", "remaining_time": "2 days, 7:58:05"}
+{"current_steps": 172, "total_steps": 1095, "loss": 0.4875, "lr": 7.922048404093193e-05, "epoch": 0.7851640513552068, "percentage": 15.71, "elapsed_time": "10:25:05", "remaining_time": "2 days, 7:54:26"}
+{"current_steps": 173, "total_steps": 1095, "loss": 0.4751, "lr": 7.919522091534125e-05, "epoch": 0.7897289586305278, "percentage": 15.8, "elapsed_time": "10:28:43", "remaining_time": "2 days, 7:50:44"}
+{"current_steps": 174, "total_steps": 1095, "loss": 0.4751, "lr": 7.916955907708403e-05, "epoch": 0.7942938659058488, "percentage": 15.89, "elapsed_time": "10:32:21", "remaining_time": "2 days, 7:47:05"}
+{"current_steps": 175, "total_steps": 1095, "loss": 0.467, "lr": 7.91434987872048e-05, "epoch": 0.7988587731811697, "percentage": 15.98, "elapsed_time": "10:35:59", "remaining_time": "2 days, 7:43:29"}
+{"current_steps": 176, "total_steps": 1095, "loss": 0.4734, "lr": 7.911704031080142e-05, "epoch": 0.8034236804564907, "percentage": 16.07, "elapsed_time": "10:39:37", "remaining_time": "2 days, 7:39:49"}
+{"current_steps": 177, "total_steps": 1095, "loss": 0.47, "lr": 7.909018391702224e-05, "epoch": 0.8079885877318117, "percentage": 16.16, "elapsed_time": "10:43:15", "remaining_time": "2 days, 7:36:11"}
+{"current_steps": 178, "total_steps": 1095, "loss": 0.4683, "lr": 7.906292987906343e-05, "epoch": 0.8125534950071327, "percentage": 16.26, "elapsed_time": "10:46:53", "remaining_time": "2 days, 7:32:35"}
+{"current_steps": 179, "total_steps": 1095, "loss": 0.4683, "lr": 7.90352784741662e-05, "epoch": 0.8171184022824537, "percentage": 16.35, "elapsed_time": "10:50:31", "remaining_time": "2 days, 7:28:57"}
+{"current_steps": 180, "total_steps": 1095, "loss": 0.4667, "lr": 7.900722998361394e-05, "epoch": 0.8216833095577746, "percentage": 16.44, "elapsed_time": "10:54:09", "remaining_time": "2 days, 7:25:17"}
+{"current_steps": 181, "total_steps": 1095, "loss": 0.472, "lr": 7.897878469272943e-05, "epoch": 0.8262482168330956, "percentage": 16.53, "elapsed_time": "10:57:47", "remaining_time": "2 days, 7:21:38"}
+{"current_steps": 182, "total_steps": 1095, "loss": 0.4628, "lr": 7.894994289087187e-05, "epoch": 0.8308131241084166, "percentage": 16.62, "elapsed_time": "11:01:25", "remaining_time": "2 days, 7:17:59"}
+{"current_steps": 183, "total_steps": 1095, "loss": 0.4621, "lr": 7.892070487143395e-05, "epoch": 0.8353780313837376, "percentage": 16.71, "elapsed_time": "11:05:03", "remaining_time": "2 days, 7:14:21"}
+{"current_steps": 184, "total_steps": 1095, "loss": 0.4665, "lr": 7.88910709318389e-05, "epoch": 0.8399429386590584, "percentage": 16.8, "elapsed_time": "11:08:41", "remaining_time": "2 days, 7:10:45"}
+{"current_steps": 185, "total_steps": 1095, "loss": 0.4629, "lr": 7.88610413735374e-05, "epoch": 0.8445078459343794, "percentage": 16.89, "elapsed_time": "11:12:19", "remaining_time": "2 days, 7:07:05"}
+{"current_steps": 186, "total_steps": 1095, "loss": 0.4671, "lr": 7.883061650200459e-05, "epoch": 0.8490727532097004, "percentage": 16.99, "elapsed_time": "11:15:57", "remaining_time": "2 days, 7:03:27"}
+{"current_steps": 187, "total_steps": 1095, "loss": 0.4613, "lr": 7.879979662673695e-05, "epoch": 0.8536376604850214, "percentage": 17.08, "elapsed_time": "11:19:34", "remaining_time": "2 days, 6:59:47"}
+{"current_steps": 188, "total_steps": 1095, "loss": 0.4697, "lr": 7.876858206124907e-05, "epoch": 0.8582025677603423, "percentage": 17.17, "elapsed_time": "11:23:12", "remaining_time": "2 days, 6:56:08"}
+{"current_steps": 189, "total_steps": 1095, "loss": 0.4696, "lr": 7.873697312307054e-05, "epoch": 0.8627674750356633, "percentage": 17.26, "elapsed_time": "11:26:50", "remaining_time": "2 days, 6:52:30"}
+{"current_steps": 190, "total_steps": 1095, "loss": 0.4639, "lr": 7.870497013374272e-05, "epoch": 0.8673323823109843, "percentage": 17.35, "elapsed_time": "11:30:28", "remaining_time": "2 days, 6:48:51"}
+{"current_steps": 191, "total_steps": 1095, "loss": 0.4653, "lr": 7.867257341881542e-05, "epoch": 0.8718972895863053, "percentage": 17.44, "elapsed_time": "11:34:06", "remaining_time": "2 days, 6:45:11"}
+{"current_steps": 192, "total_steps": 1095, "loss": 0.4675, "lr": 7.863978330784364e-05, "epoch": 0.8764621968616263, "percentage": 17.53, "elapsed_time": "11:37:43", "remaining_time": "2 days, 6:41:31"}
+{"current_steps": 193, "total_steps": 1095, "loss": 0.4602, "lr": 7.860660013438418e-05, "epoch": 0.8810271041369472, "percentage": 17.63, "elapsed_time": "11:41:21", "remaining_time": "2 days, 6:37:51"}
+{"current_steps": 194, "total_steps": 1095, "loss": 0.4642, "lr": 7.857302423599225e-05, "epoch": 0.8855920114122682, "percentage": 17.72, "elapsed_time": "11:44:59", "remaining_time": "2 days, 6:34:13"}
+{"current_steps": 195, "total_steps": 1095, "loss": 0.4718, "lr": 7.853905595421808e-05, "epoch": 0.8901569186875892, "percentage": 17.81, "elapsed_time": "11:48:37", "remaining_time": "2 days, 6:30:33"}
+{"current_steps": 196, "total_steps": 1095, "loss": 0.4697, "lr": 7.850469563460339e-05, "epoch": 0.8947218259629102, "percentage": 17.9, "elapsed_time": "11:52:15", "remaining_time": "2 days, 6:26:54"}
+{"current_steps": 197, "total_steps": 1095, "loss": 0.4645, "lr": 7.84699436266779e-05, "epoch": 0.899286733238231, "percentage": 17.99, "elapsed_time": "11:55:52", "remaining_time": "2 days, 6:23:14"}
+{"current_steps": 198, "total_steps": 1095, "loss": 0.4598, "lr": 7.843480028395578e-05, "epoch": 0.903851640513552, "percentage": 18.08, "elapsed_time": "11:59:30", "remaining_time": "2 days, 6:19:34"}
+{"current_steps": 199, "total_steps": 1095, "loss": 0.4613, "lr": 7.839926596393202e-05, "epoch": 0.908416547788873, "percentage": 18.17, "elapsed_time": "12:03:08", "remaining_time": "2 days, 6:15:56"}
+{"current_steps": 200, "total_steps": 1095, "loss": 0.4552, "lr": 7.836334102807886e-05, "epoch": 0.912981455064194, "percentage": 18.26, "elapsed_time": "12:06:46", "remaining_time": "2 days, 6:12:18"}
+{"current_steps": 201, "total_steps": 1095, "loss": 0.4609, "lr": 7.832702584184204e-05, "epoch": 0.917546362339515, "percentage": 18.36, "elapsed_time": "12:10:24", "remaining_time": "2 days, 6:08:39"}
+{"current_steps": 202, "total_steps": 1095, "loss": 0.4614, "lr": 7.829032077463713e-05, "epoch": 0.9221112696148359, "percentage": 18.45, "elapsed_time": "12:14:02", "remaining_time": "2 days, 6:05:02"}
+{"current_steps": 203, "total_steps": 1095, "loss": 0.4583, "lr": 7.825322619984576e-05, "epoch": 0.9266761768901569, "percentage": 18.54, "elapsed_time": "12:17:40", "remaining_time": "2 days, 6:01:22"}
+{"current_steps": 204, "total_steps": 1095, "loss": 0.4568, "lr": 7.821574249481179e-05, "epoch": 0.9312410841654779, "percentage": 18.63, "elapsed_time": "12:21:18", "remaining_time": "2 days, 5:57:46"}
+{"current_steps": 205, "total_steps": 1095, "loss": 0.4586, "lr": 7.817787004083756e-05, "epoch": 0.9358059914407989, "percentage": 18.72, "elapsed_time": "12:24:56", "remaining_time": "2 days, 5:54:07"}
+{"current_steps": 206, "total_steps": 1095, "loss": 0.4604, "lr": 7.813960922317988e-05, "epoch": 0.9403708987161198, "percentage": 18.81, "elapsed_time": "12:28:34", "remaining_time": "2 days, 5:50:28"}
+{"current_steps": 207, "total_steps": 1095, "loss": 0.4622, "lr": 7.810096043104623e-05, "epoch": 0.9449358059914408, "percentage": 18.9, "elapsed_time": "12:32:12", "remaining_time": "2 days, 5:46:51"}
+{"current_steps": 208, "total_steps": 1095, "loss": 0.4649, "lr": 7.806192405759074e-05, "epoch": 0.9495007132667618, "percentage": 19.0, "elapsed_time": "12:35:50", "remaining_time": "2 days, 5:43:15"}
+{"current_steps": 209, "total_steps": 1095, "loss": 0.4664, "lr": 7.80225004999102e-05, "epoch": 0.9540656205420828, "percentage": 19.09, "elapsed_time": "12:39:28", "remaining_time": "2 days, 5:39:37"}
+{"current_steps": 210, "total_steps": 1095, "loss": 0.4617, "lr": 7.798269015904004e-05, "epoch": 0.9586305278174037, "percentage": 19.18, "elapsed_time": "12:43:06", "remaining_time": "2 days, 5:35:57"}
+{"current_steps": 211, "total_steps": 1095, "loss": 0.4614, "lr": 7.79424934399502e-05, "epoch": 0.9631954350927246, "percentage": 19.27, "elapsed_time": "12:46:44", "remaining_time": "2 days, 5:32:20"}
+{"current_steps": 212, "total_steps": 1095, "loss": 0.4607, "lr": 7.790191075154109e-05, "epoch": 0.9677603423680456, "percentage": 19.36, "elapsed_time": "12:50:22", "remaining_time": "2 days, 5:28:42"}
+{"current_steps": 213, "total_steps": 1095, "loss": 0.4652, "lr": 7.786094250663936e-05, "epoch": 0.9723252496433666, "percentage": 19.45, "elapsed_time": "12:54:00", "remaining_time": "2 days, 5:25:03"}
+{"current_steps": 214, "total_steps": 1095, "loss": 0.4618, "lr": 7.781958912199372e-05, "epoch": 0.9768901569186876, "percentage": 19.54, "elapsed_time": "12:57:39", "remaining_time": "2 days, 5:21:27"}
+{"current_steps": 215, "total_steps": 1095, "loss": 0.4662, "lr": 7.777785101827073e-05, "epoch": 0.9814550641940085, "percentage": 19.63, "elapsed_time": "13:01:17", "remaining_time": "2 days, 5:17:48"}
+{"current_steps": 216, "total_steps": 1095, "loss": 0.4573, "lr": 7.773572862005048e-05, "epoch": 0.9860199714693295, "percentage": 19.73, "elapsed_time": "13:04:54", "remaining_time": "2 days, 5:14:07"}
+{"current_steps": 217, "total_steps": 1095, "loss": 0.461, "lr": 7.76932223558223e-05, "epoch": 0.9905848787446505, "percentage": 19.82, "elapsed_time": "13:08:32", "remaining_time": "2 days, 5:10:31"}
+{"current_steps": 218, "total_steps": 1095, "loss": 0.455, "lr": 7.765033265798038e-05, "epoch": 0.9951497860199715, "percentage": 19.91, "elapsed_time": "13:12:10", "remaining_time": "2 days, 5:06:51"}
+{"current_steps": 219, "total_steps": 1095, "loss": 0.4591, "lr": 7.760705996281937e-05, "epoch": 0.9997146932952924, "percentage": 20.0, "elapsed_time": "13:15:47", "remaining_time": "2 days, 5:03:08"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7221c52ca1661a173e000ca890c4cb91ad33a7d8a1e60564a9aea50a95e64e37
+size 7160