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 sha256:56686be8efb821e091bee3a51891b692d647aeeb81fbc7182b4e5dc0ebc40f69
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825bb8bb691c9a60ed4ae3a0367f658e8d8b1fabbda91948b90fc8690477db12
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d588dffcc7868e4a44fc97bbf822a45636fc4b2d00bb9165b8fc0359b1500a4
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aac2bc2657f513108a8b17d3cf2326fad145ac0be9effbe71e07d77fe889fb6
+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 +1,242 @@
+{"current_steps": 1, "total_steps": 1195, "loss": 1.0378, "lr": 3.3333333333333335e-07, "epoch": 0.004173187271778821, "percentage": 0.08, "elapsed_time": "0:00:45", "remaining_time": "15:05:32"}
+{"current_steps": 2, "total_steps": 1195, "loss": 1.0303, "lr": 6.666666666666667e-07, "epoch": 0.008346374543557642, "percentage": 0.17, "elapsed_time": "0:01:26", "remaining_time": "14:20:39"}
+{"current_steps": 3, "total_steps": 1195, "loss": 1.0577, "lr": 1.0000000000000002e-06, "epoch": 0.012519561815336464, "percentage": 0.25, "elapsed_time": "0:02:06", "remaining_time": "13:55:45"}
+{"current_steps": 4, "total_steps": 1195, "loss": 1.0509, "lr": 1.3333333333333334e-06, "epoch": 0.016692749087115284, "percentage": 0.33, "elapsed_time": "0:02:46", "remaining_time": "13:47:13"}
+{"current_steps": 5, "total_steps": 1195, "loss": 1.065, "lr": 1.6666666666666667e-06, "epoch": 0.020865936358894107, "percentage": 0.42, "elapsed_time": "0:03:29", "remaining_time": "13:50:47"}
+{"current_steps": 6, "total_steps": 1195, "loss": 1.0591, "lr": 2.0000000000000003e-06, "epoch": 0.025039123630672927, "percentage": 0.5, "elapsed_time": "0:04:08", "remaining_time": "13:41:58"}
+{"current_steps": 7, "total_steps": 1195, "loss": 0.9879, "lr": 2.3333333333333336e-06, "epoch": 0.029212310902451747, "percentage": 0.59, "elapsed_time": "0:04:46", "remaining_time": "13:31:38"}
+{"current_steps": 8, "total_steps": 1195, "loss": 0.9762, "lr": 2.666666666666667e-06, "epoch": 0.03338549817423057, "percentage": 0.67, "elapsed_time": "0:05:19", "remaining_time": "13:10:02"}
+{"current_steps": 9, "total_steps": 1195, "loss": 0.9808, "lr": 3e-06, "epoch": 0.03755868544600939, "percentage": 0.75, "elapsed_time": "0:05:56", "remaining_time": "13:03:46"}
+{"current_steps": 10, "total_steps": 1195, "loss": 0.943, "lr": 3.3333333333333333e-06, "epoch": 0.041731872717788214, "percentage": 0.84, "elapsed_time": "0:06:37", "remaining_time": "13:04:32"}
+{"current_steps": 11, "total_steps": 1195, "loss": 0.9603, "lr": 3.6666666666666666e-06, "epoch": 0.04590505998956703, "percentage": 0.92, "elapsed_time": "0:07:16", "remaining_time": "13:02:40"}
+{"current_steps": 12, "total_steps": 1195, "loss": 0.9285, "lr": 4.000000000000001e-06, "epoch": 0.050078247261345854, "percentage": 1.0, "elapsed_time": "0:07:54", "remaining_time": "13:00:23"}
+{"current_steps": 13, "total_steps": 1195, "loss": 0.9622, "lr": 4.333333333333334e-06, "epoch": 0.05425143453312467, "percentage": 1.09, "elapsed_time": "0:08:40", "remaining_time": "13:08:26"}
+{"current_steps": 14, "total_steps": 1195, "loss": 0.925, "lr": 4.666666666666667e-06, "epoch": 0.058424621804903494, "percentage": 1.17, "elapsed_time": "0:09:22", "remaining_time": "13:10:12"}
+{"current_steps": 15, "total_steps": 1195, "loss": 0.9016, "lr": 5e-06, "epoch": 0.06259780907668232, "percentage": 1.26, "elapsed_time": "0:10:01", "remaining_time": "13:09:11"}
+{"current_steps": 16, "total_steps": 1195, "loss": 0.902, "lr": 5.333333333333334e-06, "epoch": 0.06677099634846113, "percentage": 1.34, "elapsed_time": "0:10:40", "remaining_time": "13:06:51"}
+{"current_steps": 17, "total_steps": 1195, "loss": 0.8756, "lr": 5.666666666666667e-06, "epoch": 0.07094418362023996, "percentage": 1.42, "elapsed_time": "0:11:20", "remaining_time": "13:05:56"}
+{"current_steps": 18, "total_steps": 1195, "loss": 0.8831, "lr": 6e-06, "epoch": 0.07511737089201878, "percentage": 1.51, "elapsed_time": "0:12:01", "remaining_time": "13:06:38"}
+{"current_steps": 19, "total_steps": 1195, "loss": 0.8183, "lr": 6.333333333333333e-06, "epoch": 0.0792905581637976, "percentage": 1.59, "elapsed_time": "0:12:40", "remaining_time": "13:04:18"}
+{"current_steps": 20, "total_steps": 1195, "loss": 0.8162, "lr": 6.666666666666667e-06, "epoch": 0.08346374543557643, "percentage": 1.67, "elapsed_time": "0:13:21", "remaining_time": "13:04:28"}
+{"current_steps": 21, "total_steps": 1195, "loss": 0.8161, "lr": 7e-06, "epoch": 0.08763693270735524, "percentage": 1.76, "elapsed_time": "0:13:58", "remaining_time": "13:00:56"}
+{"current_steps": 22, "total_steps": 1195, "loss": 0.8312, "lr": 7.333333333333333e-06, "epoch": 0.09181011997913406, "percentage": 1.84, "elapsed_time": "0:14:32", "remaining_time": "12:55:10"}
+{"current_steps": 23, "total_steps": 1195, "loss": 0.8089, "lr": 7.666666666666667e-06, "epoch": 0.09598330725091289, "percentage": 1.92, "elapsed_time": "0:15:13", "remaining_time": "12:55:50"}
+{"current_steps": 24, "total_steps": 1195, "loss": 0.8161, "lr": 8.000000000000001e-06, "epoch": 0.10015649452269171, "percentage": 2.01, "elapsed_time": "0:15:54", "remaining_time": "12:56:02"}
+{"current_steps": 25, "total_steps": 1195, "loss": 0.7889, "lr": 8.333333333333334e-06, "epoch": 0.10432968179447052, "percentage": 2.09, "elapsed_time": "0:16:36", "remaining_time": "12:57:11"}
+{"current_steps": 26, "total_steps": 1195, "loss": 0.7878, "lr": 8.666666666666668e-06, "epoch": 0.10850286906624934, "percentage": 2.18, "elapsed_time": "0:17:15", "remaining_time": "12:56:14"}
+{"current_steps": 27, "total_steps": 1195, "loss": 0.7592, "lr": 9e-06, "epoch": 0.11267605633802817, "percentage": 2.26, "elapsed_time": "0:17:56", "remaining_time": "12:56:25"}
+{"current_steps": 28, "total_steps": 1195, "loss": 0.7758, "lr": 9.333333333333334e-06, "epoch": 0.11684924360980699, "percentage": 2.34, "elapsed_time": "0:18:37", "remaining_time": "12:56:31"}
+{"current_steps": 29, "total_steps": 1195, "loss": 0.8058, "lr": 9.666666666666667e-06, "epoch": 0.1210224308815858, "percentage": 2.43, "elapsed_time": "0:19:14", "remaining_time": "12:53:51"}
+{"current_steps": 30, "total_steps": 1195, "loss": 0.7606, "lr": 1e-05, "epoch": 0.12519561815336464, "percentage": 2.51, "elapsed_time": "0:19:51", "remaining_time": "12:51:05"}
+{"current_steps": 31, "total_steps": 1195, "loss": 0.7644, "lr": 1.0333333333333335e-05, "epoch": 0.12936880542514345, "percentage": 2.59, "elapsed_time": "0:20:31", "remaining_time": "12:50:37"}
+{"current_steps": 32, "total_steps": 1195, "loss": 0.7453, "lr": 1.0666666666666667e-05, "epoch": 0.13354199269692227, "percentage": 2.68, "elapsed_time": "0:21:08", "remaining_time": "12:48:06"}
+{"current_steps": 33, "total_steps": 1195, "loss": 0.7601, "lr": 1.1000000000000001e-05, "epoch": 0.13771517996870108, "percentage": 2.76, "elapsed_time": "0:21:50", "remaining_time": "12:49:06"}
+{"current_steps": 34, "total_steps": 1195, "loss": 0.7406, "lr": 1.1333333333333334e-05, "epoch": 0.14188836724047993, "percentage": 2.85, "elapsed_time": "0:22:28", "remaining_time": "12:47:32"}
+{"current_steps": 35, "total_steps": 1195, "loss": 0.7528, "lr": 1.1666666666666668e-05, "epoch": 0.14606155451225875, "percentage": 2.93, "elapsed_time": "0:23:08", "remaining_time": "12:47:03"}
+{"current_steps": 36, "total_steps": 1195, "loss": 0.753, "lr": 1.2e-05, "epoch": 0.15023474178403756, "percentage": 3.01, "elapsed_time": "0:23:45", "remaining_time": "12:44:52"}
+{"current_steps": 37, "total_steps": 1195, "loss": 0.7213, "lr": 1.2333333333333334e-05, "epoch": 0.15440792905581638, "percentage": 3.1, "elapsed_time": "0:24:24", "remaining_time": "12:44:02"}
+{"current_steps": 38, "total_steps": 1195, "loss": 0.7404, "lr": 1.2666666666666667e-05, "epoch": 0.1585811163275952, "percentage": 3.18, "elapsed_time": "0:25:04", "remaining_time": "12:43:38"}
+{"current_steps": 39, "total_steps": 1195, "loss": 0.7337, "lr": 1.3000000000000001e-05, "epoch": 0.162754303599374, "percentage": 3.26, "elapsed_time": "0:25:43", "remaining_time": "12:42:37"}
+{"current_steps": 40, "total_steps": 1195, "loss": 0.7276, "lr": 1.3333333333333333e-05, "epoch": 0.16692749087115286, "percentage": 3.35, "elapsed_time": "0:26:17", "remaining_time": "12:38:57"}
+{"current_steps": 41, "total_steps": 1195, "loss": 0.7155, "lr": 1.3666666666666667e-05, "epoch": 0.17110067814293167, "percentage": 3.43, "elapsed_time": "0:26:54", "remaining_time": "12:37:18"}
+{"current_steps": 42, "total_steps": 1195, "loss": 0.7185, "lr": 1.4e-05, "epoch": 0.1752738654147105, "percentage": 3.51, "elapsed_time": "0:27:33", "remaining_time": "12:36:42"}
+{"current_steps": 43, "total_steps": 1195, "loss": 0.7478, "lr": 1.4333333333333334e-05, "epoch": 0.1794470526864893, "percentage": 3.6, "elapsed_time": "0:28:13", "remaining_time": "12:36:14"}
+{"current_steps": 44, "total_steps": 1195, "loss": 0.7522, "lr": 1.4666666666666666e-05, "epoch": 0.18362023995826812, "percentage": 3.68, "elapsed_time": "0:28:57", "remaining_time": "12:37:29"}
+{"current_steps": 45, "total_steps": 1195, "loss": 0.7334, "lr": 1.5000000000000002e-05, "epoch": 0.18779342723004694, "percentage": 3.77, "elapsed_time": "0:29:39", "remaining_time": "12:38:06"}
+{"current_steps": 46, "total_steps": 1195, "loss": 0.7258, "lr": 1.5333333333333334e-05, "epoch": 0.19196661450182578, "percentage": 3.85, "elapsed_time": "0:30:15", "remaining_time": "12:35:57"}
+{"current_steps": 47, "total_steps": 1195, "loss": 0.7052, "lr": 1.5666666666666667e-05, "epoch": 0.1961398017736046, "percentage": 3.93, "elapsed_time": "0:30:53", "remaining_time": "12:34:31"}
+{"current_steps": 48, "total_steps": 1195, "loss": 0.7408, "lr": 1.6000000000000003e-05, "epoch": 0.20031298904538342, "percentage": 4.02, "elapsed_time": "0:31:35", "remaining_time": "12:34:42"}
+{"current_steps": 49, "total_steps": 1195, "loss": 0.7136, "lr": 1.6333333333333335e-05, "epoch": 0.20448617631716223, "percentage": 4.1, "elapsed_time": "0:32:17", "remaining_time": "12:35:13"}
+{"current_steps": 50, "total_steps": 1195, "loss": 0.7078, "lr": 1.6666666666666667e-05, "epoch": 0.20865936358894105, "percentage": 4.18, "elapsed_time": "0:32:58", "remaining_time": "12:35:08"}
+{"current_steps": 51, "total_steps": 1195, "loss": 0.6946, "lr": 1.7e-05, "epoch": 0.21283255086071987, "percentage": 4.27, "elapsed_time": "0:33:35", "remaining_time": "12:33:34"}
+{"current_steps": 52, "total_steps": 1195, "loss": 0.7415, "lr": 1.7333333333333336e-05, "epoch": 0.21700573813249868, "percentage": 4.35, "elapsed_time": "0:34:14", "remaining_time": "12:32:30"}
+{"current_steps": 53, "total_steps": 1195, "loss": 0.6825, "lr": 1.7666666666666668e-05, "epoch": 0.22117892540427753, "percentage": 4.44, "elapsed_time": "0:34:55", "remaining_time": "12:32:34"}
+{"current_steps": 54, "total_steps": 1195, "loss": 0.6814, "lr": 1.8e-05, "epoch": 0.22535211267605634, "percentage": 4.52, "elapsed_time": "0:35:35", "remaining_time": "12:31:57"}
+{"current_steps": 55, "total_steps": 1195, "loss": 0.6901, "lr": 1.8333333333333333e-05, "epoch": 0.22952529994783516, "percentage": 4.6, "elapsed_time": "0:36:08", "remaining_time": "12:29:11"}
+{"current_steps": 56, "total_steps": 1195, "loss": 0.7401, "lr": 1.866666666666667e-05, "epoch": 0.23369848721961398, "percentage": 4.69, "elapsed_time": "0:36:47", "remaining_time": "12:28:09"}
+{"current_steps": 57, "total_steps": 1195, "loss": 0.6995, "lr": 1.9e-05, "epoch": 0.2378716744913928, "percentage": 4.77, "elapsed_time": "0:37:24", "remaining_time": "12:26:46"}
+{"current_steps": 58, "total_steps": 1195, "loss": 0.7015, "lr": 1.9333333333333333e-05, "epoch": 0.2420448617631716, "percentage": 4.85, "elapsed_time": "0:38:01", "remaining_time": "12:25:28"}
+{"current_steps": 59, "total_steps": 1195, "loss": 0.6685, "lr": 1.9666666666666666e-05, "epoch": 0.24621804903495045, "percentage": 4.94, "elapsed_time": "0:38:43", "remaining_time": "12:25:34"}
+{"current_steps": 60, "total_steps": 1195, "loss": 0.7043, "lr": 2e-05, "epoch": 0.25039123630672927, "percentage": 5.02, "elapsed_time": "0:39:25", "remaining_time": "12:25:39"}
+{"current_steps": 61, "total_steps": 1195, "loss": 0.7051, "lr": 2.0333333333333334e-05, "epoch": 0.25456442357850806, "percentage": 5.1, "elapsed_time": "0:40:00", "remaining_time": "12:23:53"}
+{"current_steps": 62, "total_steps": 1195, "loss": 0.7042, "lr": 2.066666666666667e-05, "epoch": 0.2587376108502869, "percentage": 5.19, "elapsed_time": "0:40:40", "remaining_time": "12:23:16"}
+{"current_steps": 63, "total_steps": 1195, "loss": 0.6957, "lr": 2.1000000000000002e-05, "epoch": 0.26291079812206575, "percentage": 5.27, "elapsed_time": "0:41:14", "remaining_time": "12:20:59"}
+{"current_steps": 64, "total_steps": 1195, "loss": 0.6837, "lr": 2.1333333333333335e-05, "epoch": 0.26708398539384454, "percentage": 5.36, "elapsed_time": "0:41:55", "remaining_time": "12:20:44"}
+{"current_steps": 65, "total_steps": 1195, "loss": 0.6587, "lr": 2.1666666666666667e-05, "epoch": 0.2712571726656234, "percentage": 5.44, "elapsed_time": "0:42:29", "remaining_time": "12:18:38"}
+{"current_steps": 66, "total_steps": 1195, "loss": 0.6874, "lr": 2.2000000000000003e-05, "epoch": 0.27543035993740217, "percentage": 5.52, "elapsed_time": "0:43:08", "remaining_time": "12:18:06"}
+{"current_steps": 67, "total_steps": 1195, "loss": 0.6943, "lr": 2.2333333333333335e-05, "epoch": 0.279603547209181, "percentage": 5.61, "elapsed_time": "0:43:51", "remaining_time": "12:18:31"}
+{"current_steps": 68, "total_steps": 1195, "loss": 0.682, "lr": 2.2666666666666668e-05, "epoch": 0.28377673448095986, "percentage": 5.69, "elapsed_time": "0:44:30", "remaining_time": "12:17:43"}
+{"current_steps": 69, "total_steps": 1195, "loss": 0.6925, "lr": 2.3e-05, "epoch": 0.28794992175273865, "percentage": 5.77, "elapsed_time": "0:45:02", "remaining_time": "12:15:01"}
+{"current_steps": 70, "total_steps": 1195, "loss": 0.6796, "lr": 2.3333333333333336e-05, "epoch": 0.2921231090245175, "percentage": 5.86, "elapsed_time": "0:45:42", "remaining_time": "12:14:34"}
+{"current_steps": 71, "total_steps": 1195, "loss": 0.7037, "lr": 2.3666666666666668e-05, "epoch": 0.2962962962962963, "percentage": 5.94, "elapsed_time": "0:46:24", "remaining_time": "12:14:37"}
+{"current_steps": 72, "total_steps": 1195, "loss": 0.6834, "lr": 2.4e-05, "epoch": 0.3004694835680751, "percentage": 6.03, "elapsed_time": "0:47:00", "remaining_time": "12:13:18"}
+{"current_steps": 73, "total_steps": 1195, "loss": 0.6732, "lr": 2.4333333333333333e-05, "epoch": 0.3046426708398539, "percentage": 6.11, "elapsed_time": "0:47:35", "remaining_time": "12:11:33"}
+{"current_steps": 74, "total_steps": 1195, "loss": 0.6841, "lr": 2.466666666666667e-05, "epoch": 0.30881585811163276, "percentage": 6.19, "elapsed_time": "0:48:17", "remaining_time": "12:11:34"}
+{"current_steps": 75, "total_steps": 1195, "loss": 0.6778, "lr": 2.5e-05, "epoch": 0.3129890453834116, "percentage": 6.28, "elapsed_time": "0:48:53", "remaining_time": "12:10:12"}
+{"current_steps": 76, "total_steps": 1195, "loss": 0.6977, "lr": 2.5333333333333334e-05, "epoch": 0.3171622326551904, "percentage": 6.36, "elapsed_time": "0:49:27", "remaining_time": "12:08:17"}
+{"current_steps": 77, "total_steps": 1195, "loss": 0.685, "lr": 2.566666666666667e-05, "epoch": 0.32133541992696923, "percentage": 6.44, "elapsed_time": "0:50:05", "remaining_time": "12:07:21"}
+{"current_steps": 78, "total_steps": 1195, "loss": 0.6537, "lr": 2.6000000000000002e-05, "epoch": 0.325508607198748, "percentage": 6.53, "elapsed_time": "0:50:44", "remaining_time": "12:06:41"}
+{"current_steps": 79, "total_steps": 1195, "loss": 0.6794, "lr": 2.6333333333333334e-05, "epoch": 0.32968179447052687, "percentage": 6.61, "elapsed_time": "0:51:24", "remaining_time": "12:06:19"}
+{"current_steps": 80, "total_steps": 1195, "loss": 0.6868, "lr": 2.6666666666666667e-05, "epoch": 0.3338549817423057, "percentage": 6.69, "elapsed_time": "0:52:06", "remaining_time": "12:06:21"}
+{"current_steps": 81, "total_steps": 1195, "loss": 0.7043, "lr": 2.7000000000000002e-05, "epoch": 0.3380281690140845, "percentage": 6.78, "elapsed_time": "0:52:42", "remaining_time": "12:04:49"}
+{"current_steps": 82, "total_steps": 1195, "loss": 0.6607, "lr": 2.7333333333333335e-05, "epoch": 0.34220135628586335, "percentage": 6.86, "elapsed_time": "0:53:23", "remaining_time": "12:04:44"}
+{"current_steps": 83, "total_steps": 1195, "loss": 0.6963, "lr": 2.7666666666666667e-05, "epoch": 0.34637454355764213, "percentage": 6.95, "elapsed_time": "0:54:05", "remaining_time": "12:04:40"}
+{"current_steps": 84, "total_steps": 1195, "loss": 0.639, "lr": 2.8e-05, "epoch": 0.350547730829421, "percentage": 7.03, "elapsed_time": "0:54:48", "remaining_time": "12:04:50"}
+{"current_steps": 85, "total_steps": 1195, "loss": 0.6731, "lr": 2.833333333333334e-05, "epoch": 0.35472091810119977, "percentage": 7.11, "elapsed_time": "0:55:32", "remaining_time": "12:05:19"}
+{"current_steps": 86, "total_steps": 1195, "loss": 0.6491, "lr": 2.8666666666666668e-05, "epoch": 0.3588941053729786, "percentage": 7.2, "elapsed_time": "0:56:12", "remaining_time": "12:04:50"}
+{"current_steps": 87, "total_steps": 1195, "loss": 0.6467, "lr": 2.9e-05, "epoch": 0.36306729264475746, "percentage": 7.28, "elapsed_time": "0:56:56", "remaining_time": "12:05:05"}
+{"current_steps": 88, "total_steps": 1195, "loss": 0.6677, "lr": 2.9333333333333333e-05, "epoch": 0.36724047991653624, "percentage": 7.36, "elapsed_time": "0:57:41", "remaining_time": "12:05:38"}
+{"current_steps": 89, "total_steps": 1195, "loss": 0.6711, "lr": 2.9666666666666672e-05, "epoch": 0.3714136671883151, "percentage": 7.45, "elapsed_time": "0:58:16", "remaining_time": "12:04:04"}
+{"current_steps": 90, "total_steps": 1195, "loss": 0.6742, "lr": 3.0000000000000004e-05, "epoch": 0.3755868544600939, "percentage": 7.53, "elapsed_time": "0:58:52", "remaining_time": "12:02:52"}
+{"current_steps": 91, "total_steps": 1195, "loss": 0.667, "lr": 3.0333333333333333e-05, "epoch": 0.3797600417318727, "percentage": 7.62, "elapsed_time": "0:59:33", "remaining_time": "12:02:38"}
+{"current_steps": 92, "total_steps": 1195, "loss": 0.6694, "lr": 3.066666666666667e-05, "epoch": 0.38393322900365157, "percentage": 7.7, "elapsed_time": "1:00:17", "remaining_time": "12:02:52"}
+{"current_steps": 93, "total_steps": 1195, "loss": 0.6744, "lr": 3.1e-05, "epoch": 0.38810641627543035, "percentage": 7.78, "elapsed_time": "1:00:50", "remaining_time": "12:00:57"}
+{"current_steps": 94, "total_steps": 1195, "loss": 0.6451, "lr": 3.1333333333333334e-05, "epoch": 0.3922796035472092, "percentage": 7.87, "elapsed_time": "1:01:31", "remaining_time": "12:00:43"}
+{"current_steps": 95, "total_steps": 1195, "loss": 0.6565, "lr": 3.1666666666666666e-05, "epoch": 0.396452790818988, "percentage": 7.95, "elapsed_time": "1:02:10", "remaining_time": "11:59:59"}
+{"current_steps": 96, "total_steps": 1195, "loss": 0.6671, "lr": 3.2000000000000005e-05, "epoch": 0.40062597809076683, "percentage": 8.03, "elapsed_time": "1:02:47", "remaining_time": "11:58:51"}
+{"current_steps": 97, "total_steps": 1195, "loss": 0.645, "lr": 3.233333333333334e-05, "epoch": 0.4047991653625456, "percentage": 8.12, "elapsed_time": "1:03:30", "remaining_time": "11:58:58"}
+{"current_steps": 98, "total_steps": 1195, "loss": 0.6354, "lr": 3.266666666666667e-05, "epoch": 0.40897235263432447, "percentage": 8.2, "elapsed_time": "1:04:06", "remaining_time": "11:57:33"}
+{"current_steps": 99, "total_steps": 1195, "loss": 0.636, "lr": 3.3e-05, "epoch": 0.4131455399061033, "percentage": 8.28, "elapsed_time": "1:04:48", "remaining_time": "11:57:31"}
+{"current_steps": 100, "total_steps": 1195, "loss": 0.6896, "lr": 3.3333333333333335e-05, "epoch": 0.4173187271778821, "percentage": 8.37, "elapsed_time": "1:05:22", "remaining_time": "11:55:55"}
+{"current_steps": 101, "total_steps": 1195, "loss": 0.6916, "lr": 3.366666666666667e-05, "epoch": 0.42149191444966094, "percentage": 8.45, "elapsed_time": "1:05:59", "remaining_time": "11:54:51"}
+{"current_steps": 102, "total_steps": 1195, "loss": 0.6771, "lr": 3.4e-05, "epoch": 0.42566510172143973, "percentage": 8.54, "elapsed_time": "1:06:34", "remaining_time": "11:53:20"}
+{"current_steps": 103, "total_steps": 1195, "loss": 0.6365, "lr": 3.433333333333333e-05, "epoch": 0.4298382889932186, "percentage": 8.62, "elapsed_time": "1:07:10", "remaining_time": "11:52:12"}
+{"current_steps": 104, "total_steps": 1195, "loss": 0.6675, "lr": 3.466666666666667e-05, "epoch": 0.43401147626499736, "percentage": 8.7, "elapsed_time": "1:07:50", "remaining_time": "11:51:45"}
+{"current_steps": 105, "total_steps": 1195, "loss": 0.6767, "lr": 3.5000000000000004e-05, "epoch": 0.4381846635367762, "percentage": 8.79, "elapsed_time": "1:08:32", "remaining_time": "11:51:28"}
+{"current_steps": 106, "total_steps": 1195, "loss": 0.6631, "lr": 3.5333333333333336e-05, "epoch": 0.44235785080855505, "percentage": 8.87, "elapsed_time": "1:09:13", "remaining_time": "11:51:09"}
+{"current_steps": 107, "total_steps": 1195, "loss": 0.6783, "lr": 3.566666666666667e-05, "epoch": 0.44653103808033384, "percentage": 8.95, "elapsed_time": "1:09:57", "remaining_time": "11:51:18"}
+{"current_steps": 108, "total_steps": 1195, "loss": 0.6513, "lr": 3.6e-05, "epoch": 0.4507042253521127, "percentage": 9.04, "elapsed_time": "1:10:37", "remaining_time": "11:50:45"}
+{"current_steps": 109, "total_steps": 1195, "loss": 0.6848, "lr": 3.633333333333333e-05, "epoch": 0.4548774126238915, "percentage": 9.12, "elapsed_time": "1:11:15", "remaining_time": "11:49:56"}
+{"current_steps": 110, "total_steps": 1195, "loss": 0.6453, "lr": 3.6666666666666666e-05, "epoch": 0.4590505998956703, "percentage": 9.21, "elapsed_time": "1:11:58", "remaining_time": "11:49:52"}
+{"current_steps": 111, "total_steps": 1195, "loss": 0.6661, "lr": 3.7000000000000005e-05, "epoch": 0.46322378716744916, "percentage": 9.29, "elapsed_time": "1:12:42", "remaining_time": "11:50:05"}
+{"current_steps": 112, "total_steps": 1195, "loss": 0.6566, "lr": 3.733333333333334e-05, "epoch": 0.46739697443922795, "percentage": 9.37, "elapsed_time": "1:13:22", "remaining_time": "11:49:34"}
+{"current_steps": 113, "total_steps": 1195, "loss": 0.6491, "lr": 3.766666666666667e-05, "epoch": 0.4715701617110068, "percentage": 9.46, "elapsed_time": "1:14:01", "remaining_time": "11:48:46"}
+{"current_steps": 114, "total_steps": 1195, "loss": 0.6566, "lr": 3.8e-05, "epoch": 0.4757433489827856, "percentage": 9.54, "elapsed_time": "1:14:40", "remaining_time": "11:48:06"}
+{"current_steps": 115, "total_steps": 1195, "loss": 0.6681, "lr": 3.833333333333334e-05, "epoch": 0.47991653625456443, "percentage": 9.62, "elapsed_time": "1:15:13", "remaining_time": "11:46:30"}
+{"current_steps": 116, "total_steps": 1195, "loss": 0.6377, "lr": 3.866666666666667e-05, "epoch": 0.4840897235263432, "percentage": 9.71, "elapsed_time": "1:15:53", "remaining_time": "11:45:52"}
+{"current_steps": 117, "total_steps": 1195, "loss": 0.6487, "lr": 3.9e-05, "epoch": 0.48826291079812206, "percentage": 9.79, "elapsed_time": "1:16:30", "remaining_time": "11:44:53"}
+{"current_steps": 118, "total_steps": 1195, "loss": 0.6356, "lr": 3.933333333333333e-05, "epoch": 0.4924360980699009, "percentage": 9.87, "elapsed_time": "1:17:07", "remaining_time": "11:43:51"}
+{"current_steps": 119, "total_steps": 1195, "loss": 0.6767, "lr": 3.966666666666667e-05, "epoch": 0.4966092853416797, "percentage": 9.96, "elapsed_time": "1:17:48", "remaining_time": "11:43:33"}
+{"current_steps": 120, "total_steps": 1195, "loss": 0.6882, "lr": 4e-05, "epoch": 0.5007824726134585, "percentage": 10.04, "elapsed_time": "1:18:31", "remaining_time": "11:43:26"}
+{"current_steps": 121, "total_steps": 1195, "loss": 0.6607, "lr": 3.9999914595155206e-05, "epoch": 0.5049556598852374, "percentage": 10.13, "elapsed_time": "1:19:11", "remaining_time": "11:42:51"}
+{"current_steps": 122, "total_steps": 1195, "loss": 0.6375, "lr": 3.999965838135022e-05, "epoch": 0.5091288471570161, "percentage": 10.21, "elapsed_time": "1:19:53", "remaining_time": "11:42:36"}
+{"current_steps": 123, "total_steps": 1195, "loss": 0.6718, "lr": 3.999923136077322e-05, "epoch": 0.513302034428795, "percentage": 10.29, "elapsed_time": "1:20:35", "remaining_time": "11:42:19"}
+{"current_steps": 124, "total_steps": 1195, "loss": 0.6807, "lr": 3.999863353707118e-05, "epoch": 0.5174752217005738, "percentage": 10.38, "elapsed_time": "1:21:09", "remaining_time": "11:40:57"}
+{"current_steps": 125, "total_steps": 1195, "loss": 0.6479, "lr": 3.999786491534981e-05, "epoch": 0.5216484089723527, "percentage": 10.46, "elapsed_time": "1:21:54", "remaining_time": "11:41:04"}
+{"current_steps": 126, "total_steps": 1195, "loss": 0.6665, "lr": 3.9996925502173496e-05, "epoch": 0.5258215962441315, "percentage": 10.54, "elapsed_time": "1:22:34", "remaining_time": "11:40:32"}
+{"current_steps": 127, "total_steps": 1195, "loss": 0.6486, "lr": 3.999581530556529e-05, "epoch": 0.5299947835159102, "percentage": 10.63, "elapsed_time": "1:23:11", "remaining_time": "11:39:33"}
+{"current_steps": 128, "total_steps": 1195, "loss": 0.6976, "lr": 3.999453433500681e-05, "epoch": 0.5341679707876891, "percentage": 10.71, "elapsed_time": "1:23:54", "remaining_time": "11:39:26"}
+{"current_steps": 129, "total_steps": 1195, "loss": 0.6642, "lr": 3.999308260143816e-05, "epoch": 0.5383411580594679, "percentage": 10.79, "elapsed_time": "1:24:37", "remaining_time": "11:39:15"}
+{"current_steps": 130, "total_steps": 1195, "loss": 0.6559, "lr": 3.9991460117257856e-05, "epoch": 0.5425143453312468, "percentage": 10.88, "elapsed_time": "1:25:17", "remaining_time": "11:38:44"}
+{"current_steps": 131, "total_steps": 1195, "loss": 0.6556, "lr": 3.998966689632269e-05, "epoch": 0.5466875326030256, "percentage": 10.96, "elapsed_time": "1:26:03", "remaining_time": "11:38:58"}
+{"current_steps": 132, "total_steps": 1195, "loss": 0.6555, "lr": 3.998770295394765e-05, "epoch": 0.5508607198748043, "percentage": 11.05, "elapsed_time": "1:26:41", "remaining_time": "11:38:06"}
+{"current_steps": 133, "total_steps": 1195, "loss": 0.6673, "lr": 3.9985568306905744e-05, "epoch": 0.5550339071465832, "percentage": 11.13, "elapsed_time": "1:27:19", "remaining_time": "11:37:15"}
+{"current_steps": 134, "total_steps": 1195, "loss": 0.627, "lr": 3.998326297342789e-05, "epoch": 0.559207094418362, "percentage": 11.21, "elapsed_time": "1:27:59", "remaining_time": "11:36:46"}
+{"current_steps": 135, "total_steps": 1195, "loss": 0.655, "lr": 3.998078697320277e-05, "epoch": 0.5633802816901409, "percentage": 11.3, "elapsed_time": "1:28:42", "remaining_time": "11:36:27"}
+{"current_steps": 136, "total_steps": 1195, "loss": 0.6464, "lr": 3.9978140327376607e-05, "epoch": 0.5675534689619197, "percentage": 11.38, "elapsed_time": "1:29:18", "remaining_time": "11:35:28"}
+{"current_steps": 137, "total_steps": 1195, "loss": 0.6649, "lr": 3.997532305855305e-05, "epoch": 0.5717266562336984, "percentage": 11.46, "elapsed_time": "1:30:02", "remaining_time": "11:35:18"}
+{"current_steps": 138, "total_steps": 1195, "loss": 0.6492, "lr": 3.9972335190792924e-05, "epoch": 0.5758998435054773, "percentage": 11.55, "elapsed_time": "1:30:40", "remaining_time": "11:34:32"}
+{"current_steps": 139, "total_steps": 1195, "loss": 0.6564, "lr": 3.9969176749614087e-05, "epoch": 0.5800730307772561, "percentage": 11.63, "elapsed_time": "1:31:20", "remaining_time": "11:33:53"}
+{"current_steps": 140, "total_steps": 1195, "loss": 0.6444, "lr": 3.996584776199114e-05, "epoch": 0.584246218049035, "percentage": 11.72, "elapsed_time": "1:31:59", "remaining_time": "11:33:11"}
+{"current_steps": 141, "total_steps": 1195, "loss": 0.6357, "lr": 3.996234825635527e-05, "epoch": 0.5884194053208138, "percentage": 11.8, "elapsed_time": "1:32:36", "remaining_time": "11:32:15"}
+{"current_steps": 142, "total_steps": 1195, "loss": 0.6522, "lr": 3.9958678262593936e-05, "epoch": 0.5925925925925926, "percentage": 11.88, "elapsed_time": "1:33:11", "remaining_time": "11:31:05"}
+{"current_steps": 143, "total_steps": 1195, "loss": 0.6647, "lr": 3.9954837812050656e-05, "epoch": 0.5967657798643714, "percentage": 11.97, "elapsed_time": "1:33:48", "remaining_time": "11:30:08"}
+{"current_steps": 144, "total_steps": 1195, "loss": 0.6562, "lr": 3.995082693752475e-05, "epoch": 0.6009389671361502, "percentage": 12.05, "elapsed_time": "1:34:30", "remaining_time": "11:29:44"}
+{"current_steps": 145, "total_steps": 1195, "loss": 0.6408, "lr": 3.9946645673271034e-05, "epoch": 0.6051121544079291, "percentage": 12.13, "elapsed_time": "1:35:10", "remaining_time": "11:29:14"}
+{"current_steps": 146, "total_steps": 1195, "loss": 0.6393, "lr": 3.9942294054999525e-05, "epoch": 0.6092853416797078, "percentage": 12.22, "elapsed_time": "1:35:52", "remaining_time": "11:28:52"}
+{"current_steps": 147, "total_steps": 1195, "loss": 0.6227, "lr": 3.9937772119875144e-05, "epoch": 0.6134585289514867, "percentage": 12.3, "elapsed_time": "1:36:33", "remaining_time": "11:28:24"}
+{"current_steps": 148, "total_steps": 1195, "loss": 0.6406, "lr": 3.993307990651742e-05, "epoch": 0.6176317162232655, "percentage": 12.38, "elapsed_time": "1:37:14", "remaining_time": "11:27:55"}
+{"current_steps": 149, "total_steps": 1195, "loss": 0.656, "lr": 3.9928217455000114e-05, "epoch": 0.6218049034950444, "percentage": 12.47, "elapsed_time": "1:37:53", "remaining_time": "11:27:10"}
+{"current_steps": 150, "total_steps": 1195, "loss": 0.677, "lr": 3.992318480685094e-05, "epoch": 0.6259780907668232, "percentage": 12.55, "elapsed_time": "1:38:30", "remaining_time": "11:26:14"}
+{"current_steps": 151, "total_steps": 1195, "loss": 0.6298, "lr": 3.9917982005051126e-05, "epoch": 0.6301512780386019, "percentage": 12.64, "elapsed_time": "1:39:08", "remaining_time": "11:25:29"}
+{"current_steps": 152, "total_steps": 1195, "loss": 0.6377, "lr": 3.991260909403513e-05, "epoch": 0.6343244653103808, "percentage": 12.72, "elapsed_time": "1:39:50", "remaining_time": "11:25:02"}
+{"current_steps": 153, "total_steps": 1195, "loss": 0.6214, "lr": 3.9907066119690224e-05, "epoch": 0.6384976525821596, "percentage": 12.8, "elapsed_time": "1:40:30", "remaining_time": "11:24:32"}
+{"current_steps": 154, "total_steps": 1195, "loss": 0.6491, "lr": 3.990135312935608e-05, "epoch": 0.6426708398539385, "percentage": 12.89, "elapsed_time": "1:41:09", "remaining_time": "11:23:47"}
+{"current_steps": 155, "total_steps": 1195, "loss": 0.6512, "lr": 3.989547017182442e-05, "epoch": 0.6468440271257173, "percentage": 12.97, "elapsed_time": "1:41:51", "remaining_time": "11:23:23"}
+{"current_steps": 156, "total_steps": 1195, "loss": 0.6612, "lr": 3.9889417297338534e-05, "epoch": 0.651017214397496, "percentage": 13.05, "elapsed_time": "1:42:31", "remaining_time": "11:22:49"}
+{"current_steps": 157, "total_steps": 1195, "loss": 0.6163, "lr": 3.9883194557592914e-05, "epoch": 0.6551904016692749, "percentage": 13.14, "elapsed_time": "1:43:11", "remaining_time": "11:22:14"}
+{"current_steps": 158, "total_steps": 1195, "loss": 0.6254, "lr": 3.987680200573277e-05, "epoch": 0.6593635889410537, "percentage": 13.22, "elapsed_time": "1:43:51", "remaining_time": "11:21:38"}
+{"current_steps": 159, "total_steps": 1195, "loss": 0.6387, "lr": 3.987023969635358e-05, "epoch": 0.6635367762128326, "percentage": 13.31, "elapsed_time": "1:44:32", "remaining_time": "11:21:11"}
+{"current_steps": 160, "total_steps": 1195, "loss": 0.6498, "lr": 3.986350768550066e-05, "epoch": 0.6677099634846114, "percentage": 13.39, "elapsed_time": "1:45:15", "remaining_time": "11:20:51"}
+{"current_steps": 161, "total_steps": 1195, "loss": 0.6361, "lr": 3.985660603066865e-05, "epoch": 0.6718831507563902, "percentage": 13.47, "elapsed_time": "1:45:54", "remaining_time": "11:20:09"}
+{"current_steps": 162, "total_steps": 1195, "loss": 0.6428, "lr": 3.984953479080101e-05, "epoch": 0.676056338028169, "percentage": 13.56, "elapsed_time": "1:46:35", "remaining_time": "11:19:44"}
+{"current_steps": 163, "total_steps": 1195, "loss": 0.6358, "lr": 3.9842294026289565e-05, "epoch": 0.6802295252999478, "percentage": 13.64, "elapsed_time": "1:47:19", "remaining_time": "11:19:29"}
+{"current_steps": 164, "total_steps": 1195, "loss": 0.6467, "lr": 3.983488379897394e-05, "epoch": 0.6844027125717267, "percentage": 13.72, "elapsed_time": "1:47:56", "remaining_time": "11:18:32"}
+{"current_steps": 165, "total_steps": 1195, "loss": 0.6509, "lr": 3.982730417214107e-05, "epoch": 0.6885758998435054, "percentage": 13.81, "elapsed_time": "1:48:37", "remaining_time": "11:18:07"}
+{"current_steps": 166, "total_steps": 1195, "loss": 0.6495, "lr": 3.9819555210524656e-05, "epoch": 0.6927490871152843, "percentage": 13.89, "elapsed_time": "1:49:18", "remaining_time": "11:17:31"}
+{"current_steps": 167, "total_steps": 1195, "loss": 0.6364, "lr": 3.9811636980304564e-05, "epoch": 0.6969222743870631, "percentage": 13.97, "elapsed_time": "1:50:02", "remaining_time": "11:17:20"}
+{"current_steps": 168, "total_steps": 1195, "loss": 0.6298, "lr": 3.9803549549106327e-05, "epoch": 0.701095461658842, "percentage": 14.06, "elapsed_time": "1:50:44", "remaining_time": "11:17:01"}
+{"current_steps": 169, "total_steps": 1195, "loss": 0.6599, "lr": 3.9795292986000527e-05, "epoch": 0.7052686489306208, "percentage": 14.14, "elapsed_time": "1:51:24", "remaining_time": "11:16:23"}
+{"current_steps": 170, "total_steps": 1195, "loss": 0.6166, "lr": 3.978686736150221e-05, "epoch": 0.7094418362023995, "percentage": 14.23, "elapsed_time": "1:52:03", "remaining_time": "11:15:41"}
+{"current_steps": 171, "total_steps": 1195, "loss": 0.6367, "lr": 3.977827274757029e-05, "epoch": 0.7136150234741784, "percentage": 14.31, "elapsed_time": "1:52:46", "remaining_time": "11:15:17"}
+{"current_steps": 172, "total_steps": 1195, "loss": 0.648, "lr": 3.976950921760692e-05, "epoch": 0.7177882107459572, "percentage": 14.39, "elapsed_time": "1:53:27", "remaining_time": "11:14:46"}
+{"current_steps": 173, "total_steps": 1195, "loss": 0.6448, "lr": 3.9760576846456925e-05, "epoch": 0.7219613980177361, "percentage": 14.48, "elapsed_time": "1:54:03", "remaining_time": "11:13:49"}
+{"current_steps": 174, "total_steps": 1195, "loss": 0.6104, "lr": 3.975147571040706e-05, "epoch": 0.7261345852895149, "percentage": 14.56, "elapsed_time": "1:54:43", "remaining_time": "11:13:08"}
+{"current_steps": 175, "total_steps": 1195, "loss": 0.6435, "lr": 3.9742205887185434e-05, "epoch": 0.7303077725612936, "percentage": 14.64, "elapsed_time": "1:55:21", "remaining_time": "11:12:23"}
+{"current_steps": 176, "total_steps": 1195, "loss": 0.6426, "lr": 3.973276745596084e-05, "epoch": 0.7344809598330725, "percentage": 14.73, "elapsed_time": "1:56:01", "remaining_time": "11:11:44"}
+{"current_steps": 177, "total_steps": 1195, "loss": 0.6281, "lr": 3.9723160497342046e-05, "epoch": 0.7386541471048513, "percentage": 14.81, "elapsed_time": "1:56:42", "remaining_time": "11:11:16"}
+{"current_steps": 178, "total_steps": 1195, "loss": 0.6424, "lr": 3.971338509337713e-05, "epoch": 0.7428273343766302, "percentage": 14.9, "elapsed_time": "1:57:24", "remaining_time": "11:10:49"}
+{"current_steps": 179, "total_steps": 1195, "loss": 0.6076, "lr": 3.9703441327552786e-05, "epoch": 0.747000521648409, "percentage": 14.98, "elapsed_time": "1:57:59", "remaining_time": "11:09:41"}
+{"current_steps": 180, "total_steps": 1195, "loss": 0.6321, "lr": 3.9693329284793586e-05, "epoch": 0.7511737089201878, "percentage": 15.06, "elapsed_time": "1:58:45", "remaining_time": "11:09:40"}
+{"current_steps": 181, "total_steps": 1195, "loss": 0.6408, "lr": 3.968304905146128e-05, "epoch": 0.7553468961919666, "percentage": 15.15, "elapsed_time": "1:59:30", "remaining_time": "11:09:29"}
+{"current_steps": 182, "total_steps": 1195, "loss": 0.6404, "lr": 3.9672600715354036e-05, "epoch": 0.7595200834637454, "percentage": 15.23, "elapsed_time": "2:00:13", "remaining_time": "11:09:12"}
+{"current_steps": 183, "total_steps": 1195, "loss": 0.6103, "lr": 3.96619843657057e-05, "epoch": 0.7636932707355243, "percentage": 15.31, "elapsed_time": "2:00:55", "remaining_time": "11:08:45"}
+{"current_steps": 184, "total_steps": 1195, "loss": 0.6565, "lr": 3.965120009318505e-05, "epoch": 0.7678664580073031, "percentage": 15.4, "elapsed_time": "2:01:33", "remaining_time": "11:07:54"}
+{"current_steps": 185, "total_steps": 1195, "loss": 0.6222, "lr": 3.964024798989501e-05, "epoch": 0.7720396452790819, "percentage": 15.48, "elapsed_time": "2:02:07", "remaining_time": "11:06:43"}
+{"current_steps": 186, "total_steps": 1195, "loss": 0.613, "lr": 3.962912814937183e-05, "epoch": 0.7762128325508607, "percentage": 15.56, "elapsed_time": "2:02:45", "remaining_time": "11:05:58"}
+{"current_steps": 187, "total_steps": 1195, "loss": 0.6439, "lr": 3.9617840666584336e-05, "epoch": 0.7803860198226396, "percentage": 15.65, "elapsed_time": "2:03:22", "remaining_time": "11:05:04"}
+{"current_steps": 188, "total_steps": 1195, "loss": 0.638, "lr": 3.9606385637933106e-05, "epoch": 0.7845592070944184, "percentage": 15.73, "elapsed_time": "2:04:02", "remaining_time": "11:04:24"}
+{"current_steps": 189, "total_steps": 1195, "loss": 0.6422, "lr": 3.9594763161249636e-05, "epoch": 0.7887323943661971, "percentage": 15.82, "elapsed_time": "2:04:41", "remaining_time": "11:03:40"}
+{"current_steps": 190, "total_steps": 1195, "loss": 0.6511, "lr": 3.95829733357955e-05, "epoch": 0.792905581637976, "percentage": 15.9, "elapsed_time": "2:05:09", "remaining_time": "11:02:00"}
+{"current_steps": 191, "total_steps": 1195, "loss": 0.6244, "lr": 3.957101626226153e-05, "epoch": 0.7970787689097548, "percentage": 15.98, "elapsed_time": "2:05:52", "remaining_time": "11:01:38"}
+{"current_steps": 192, "total_steps": 1195, "loss": 0.6296, "lr": 3.955889204276692e-05, "epoch": 0.8012519561815337, "percentage": 16.07, "elapsed_time": "2:06:29", "remaining_time": "11:00:46"}
+{"current_steps": 193, "total_steps": 1195, "loss": 0.6317, "lr": 3.9546600780858375e-05, "epoch": 0.8054251434533125, "percentage": 16.15, "elapsed_time": "2:07:07", "remaining_time": "11:00:01"}
+{"current_steps": 194, "total_steps": 1195, "loss": 0.614, "lr": 3.9534142581509226e-05, "epoch": 0.8095983307250912, "percentage": 16.23, "elapsed_time": "2:07:51", "remaining_time": "10:59:44"}
+{"current_steps": 195, "total_steps": 1195, "loss": 0.6044, "lr": 3.952151755111855e-05, "epoch": 0.8137715179968701, "percentage": 16.32, "elapsed_time": "2:08:31", "remaining_time": "10:59:05"}
+{"current_steps": 196, "total_steps": 1195, "loss": 0.6052, "lr": 3.9508725797510195e-05, "epoch": 0.8179447052686489, "percentage": 16.4, "elapsed_time": "2:09:11", "remaining_time": "10:58:28"}
+{"current_steps": 197, "total_steps": 1195, "loss": 0.6428, "lr": 3.9495767429931954e-05, "epoch": 0.8221178925404278, "percentage": 16.49, "elapsed_time": "2:09:54", "remaining_time": "10:58:06"}
+{"current_steps": 198, "total_steps": 1195, "loss": 0.6079, "lr": 3.948264255905456e-05, "epoch": 0.8262910798122066, "percentage": 16.57, "elapsed_time": "2:10:41", "remaining_time": "10:58:03"}
+{"current_steps": 199, "total_steps": 1195, "loss": 0.6306, "lr": 3.9469351296970766e-05, "epoch": 0.8304642670839854, "percentage": 16.65, "elapsed_time": "2:11:21", "remaining_time": "10:57:28"}
+{"current_steps": 200, "total_steps": 1195, "loss": 0.632, "lr": 3.945589375719439e-05, "epoch": 0.8346374543557642, "percentage": 16.74, "elapsed_time": "2:11:57", "remaining_time": "10:56:28"}
+{"current_steps": 201, "total_steps": 1195, "loss": 0.6349, "lr": 3.9442270054659346e-05, "epoch": 0.838810641627543, "percentage": 16.82, "elapsed_time": "2:12:37", "remaining_time": "10:55:53"}
+{"current_steps": 202, "total_steps": 1195, "loss": 0.632, "lr": 3.942848030571865e-05, "epoch": 0.8429838288993219, "percentage": 16.9, "elapsed_time": "2:13:16", "remaining_time": "10:55:08"}
+{"current_steps": 203, "total_steps": 1195, "loss": 0.6264, "lr": 3.941452462814344e-05, "epoch": 0.8471570161711007, "percentage": 16.99, "elapsed_time": "2:13:53", "remaining_time": "10:54:17"}
+{"current_steps": 204, "total_steps": 1195, "loss": 0.6193, "lr": 3.940040314112196e-05, "epoch": 0.8513302034428795, "percentage": 17.07, "elapsed_time": "2:14:32", "remaining_time": "10:53:36"}
+{"current_steps": 205, "total_steps": 1195, "loss": 0.6383, "lr": 3.938611596525855e-05, "epoch": 0.8555033907146583, "percentage": 17.15, "elapsed_time": "2:15:11", "remaining_time": "10:52:53"}
+{"current_steps": 206, "total_steps": 1195, "loss": 0.6097, "lr": 3.9371663222572625e-05, "epoch": 0.8596765779864372, "percentage": 17.24, "elapsed_time": "2:15:51", "remaining_time": "10:52:13"}
+{"current_steps": 207, "total_steps": 1195, "loss": 0.5909, "lr": 3.93570450364976e-05, "epoch": 0.863849765258216, "percentage": 17.32, "elapsed_time": "2:16:34", "remaining_time": "10:51:53"}
+{"current_steps": 208, "total_steps": 1195, "loss": 0.6143, "lr": 3.934226153187987e-05, "epoch": 0.8680229525299947, "percentage": 17.41, "elapsed_time": "2:17:09", "remaining_time": "10:50:51"}
+{"current_steps": 209, "total_steps": 1195, "loss": 0.6242, "lr": 3.932731283497772e-05, "epoch": 0.8721961398017736, "percentage": 17.49, "elapsed_time": "2:17:50", "remaining_time": "10:50:16"}
+{"current_steps": 210, "total_steps": 1195, "loss": 0.6112, "lr": 3.931219907346028e-05, "epoch": 0.8763693270735524, "percentage": 17.57, "elapsed_time": "2:18:35", "remaining_time": "10:50:03"}
+{"current_steps": 211, "total_steps": 1195, "loss": 0.6136, "lr": 3.9296920376406366e-05, "epoch": 0.8805425143453313, "percentage": 17.66, "elapsed_time": "2:19:13", "remaining_time": "10:49:16"}
+{"current_steps": 212, "total_steps": 1195, "loss": 0.6358, "lr": 3.9281476874303486e-05, "epoch": 0.8847157016171101, "percentage": 17.74, "elapsed_time": "2:19:47", "remaining_time": "10:48:09"}
+{"current_steps": 213, "total_steps": 1195, "loss": 0.5902, "lr": 3.926586869904662e-05, "epoch": 0.8888888888888888, "percentage": 17.82, "elapsed_time": "2:20:27", "remaining_time": "10:47:33"}
+{"current_steps": 214, "total_steps": 1195, "loss": 0.609, "lr": 3.9250095983937126e-05, "epoch": 0.8930620761606677, "percentage": 17.91, "elapsed_time": "2:21:01", "remaining_time": "10:46:29"}
+{"current_steps": 215, "total_steps": 1195, "loss": 0.6248, "lr": 3.923415886368166e-05, "epoch": 0.8972352634324465, "percentage": 17.99, "elapsed_time": "2:21:36", "remaining_time": "10:45:28"}
+{"current_steps": 216, "total_steps": 1195, "loss": 0.5824, "lr": 3.921805747439094e-05, "epoch": 0.9014084507042254, "percentage": 18.08, "elapsed_time": "2:22:17", "remaining_time": "10:44:55"}
+{"current_steps": 217, "total_steps": 1195, "loss": 0.5863, "lr": 3.920179195357863e-05, "epoch": 0.9055816379760042, "percentage": 18.16, "elapsed_time": "2:22:56", "remaining_time": "10:44:14"}
+{"current_steps": 218, "total_steps": 1195, "loss": 0.6094, "lr": 3.918536244016016e-05, "epoch": 0.909754825247783, "percentage": 18.24, "elapsed_time": "2:23:34", "remaining_time": "10:43:26"}
+{"current_steps": 219, "total_steps": 1195, "loss": 0.5956, "lr": 3.9168769074451525e-05, "epoch": 0.9139280125195618, "percentage": 18.33, "elapsed_time": "2:24:17", "remaining_time": "10:43:03"}
+{"current_steps": 220, "total_steps": 1195, "loss": 0.6014, "lr": 3.915201199816812e-05, "epoch": 0.9181011997913406, "percentage": 18.41, "elapsed_time": "2:24:56", "remaining_time": "10:42:21"}
+{"current_steps": 221, "total_steps": 1195, "loss": 0.597, "lr": 3.9135091354423494e-05, "epoch": 0.9222743870631195, "percentage": 18.49, "elapsed_time": "2:25:34", "remaining_time": "10:41:32"}
+{"current_steps": 222, "total_steps": 1195, "loss": 0.6153, "lr": 3.9118007287728134e-05, "epoch": 0.9264475743348983, "percentage": 18.58, "elapsed_time": "2:26:10", "remaining_time": "10:40:41"}
+{"current_steps": 223, "total_steps": 1195, "loss": 0.6044, "lr": 3.9100759943988246e-05, "epoch": 0.9306207616066771, "percentage": 18.66, "elapsed_time": "2:26:51", "remaining_time": "10:40:07"}
+{"current_steps": 224, "total_steps": 1195, "loss": 0.5953, "lr": 3.9083349470504515e-05, "epoch": 0.9347939488784559, "percentage": 18.74, "elapsed_time": "2:27:35", "remaining_time": "10:39:45"}
+{"current_steps": 225, "total_steps": 1195, "loss": 0.6082, "lr": 3.9065776015970815e-05, "epoch": 0.9389671361502347, "percentage": 18.83, "elapsed_time": "2:28:10", "remaining_time": "10:38:49"}
+{"current_steps": 226, "total_steps": 1195, "loss": 0.6148, "lr": 3.904803973047295e-05, "epoch": 0.9431403234220136, "percentage": 18.91, "elapsed_time": "2:28:47", "remaining_time": "10:37:58"}
+{"current_steps": 227, "total_steps": 1195, "loss": 0.6253, "lr": 3.90301407654874e-05, "epoch": 0.9473135106937924, "percentage": 19.0, "elapsed_time": "2:29:24", "remaining_time": "10:37:09"}
+{"current_steps": 228, "total_steps": 1195, "loss": 0.6399, "lr": 3.9012079273879994e-05, "epoch": 0.9514866979655712, "percentage": 19.08, "elapsed_time": "2:29:59", "remaining_time": "10:36:08"}
+{"current_steps": 229, "total_steps": 1195, "loss": 0.6137, "lr": 3.899385540990462e-05, "epoch": 0.95565988523735, "percentage": 19.16, "elapsed_time": "2:30:37", "remaining_time": "10:35:23"}
+{"current_steps": 230, "total_steps": 1195, "loss": 0.6319, "lr": 3.897546932920191e-05, "epoch": 0.9598330725091289, "percentage": 19.25, "elapsed_time": "2:31:11", "remaining_time": "10:34:20"}
+{"current_steps": 231, "total_steps": 1195, "loss": 0.5848, "lr": 3.895692118879791e-05, "epoch": 0.9640062597809077, "percentage": 19.33, "elapsed_time": "2:31:52", "remaining_time": "10:33:47"}
+{"current_steps": 232, "total_steps": 1195, "loss": 0.6259, "lr": 3.893821114710271e-05, "epoch": 0.9681794470526864, "percentage": 19.41, "elapsed_time": "2:32:35", "remaining_time": "10:33:22"}
+{"current_steps": 233, "total_steps": 1195, "loss": 0.6243, "lr": 3.891933936390914e-05, "epoch": 0.9723526343244653, "percentage": 19.5, "elapsed_time": "2:33:15", "remaining_time": "10:32:45"}
+{"current_steps": 234, "total_steps": 1195, "loss": 0.6076, "lr": 3.890030600039136e-05, "epoch": 0.9765258215962441, "percentage": 19.58, "elapsed_time": "2:33:58", "remaining_time": "10:32:21"}
+{"current_steps": 235, "total_steps": 1195, "loss": 0.6155, "lr": 3.8881111219103516e-05, "epoch": 0.980699008868023, "percentage": 19.67, "elapsed_time": "2:34:38", "remaining_time": "10:31:43"}
+{"current_steps": 236, "total_steps": 1195, "loss": 0.5946, "lr": 3.8861755183978346e-05, "epoch": 0.9848721961398018, "percentage": 19.75, "elapsed_time": "2:35:17", "remaining_time": "10:31:03"}
+{"current_steps": 237, "total_steps": 1195, "loss": 0.6109, "lr": 3.8842238060325784e-05, "epoch": 0.9890453834115805, "percentage": 19.83, "elapsed_time": "2:35:59", "remaining_time": "10:30:31"}
+{"current_steps": 238, "total_steps": 1195, "loss": 0.6067, "lr": 3.882256001483149e-05, "epoch": 0.9932185706833594, "percentage": 19.92, "elapsed_time": "2:36:38", "remaining_time": "10:29:52"}
+{"current_steps": 239, "total_steps": 1195, "loss": 0.6073, "lr": 3.880272121555553e-05, "epoch": 0.9973917579551382, "percentage": 20.0, "elapsed_time": "2:37:18", "remaining_time": "10:29:15"}
+{"current_steps": 240, "total_steps": 1195, "loss": 0.5611, "lr": 3.878272183193085e-05, "epoch": 1.001564945226917, "percentage": 20.08, "elapsed_time": "2:39:10", "remaining_time": "10:33:22"}
+{"current_steps": 241, "total_steps": 1195, "loss": 0.4993, "lr": 3.876256203476188e-05, "epoch": 1.0057381324986958, "percentage": 20.17, "elapsed_time": "2:39:50", "remaining_time": "10:32:42"}
+{"current_steps": 242, "total_steps": 1195, "loss": 0.5213, "lr": 3.874224199622306e-05, "epoch": 1.0099113197704748, "percentage": 20.25, "elapsed_time": "2:40:25", "remaining_time": "10:31:45"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30e51dc7c6fba182c3634063546d5fab5af9a3612f982e954d073d314a2f5fe
+size 7761