Upload initial model

.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

README.md

@@ -0,0 +1,11 @@
+datasets:
+  - GX-XinGao/GRA
+language:
+  - en
+base_model:
+  - Qwen/Qwen2.5-7B
+license: apache-2.0
+metrics:
+  - accuracy
+pipeline_tag: text-generation
+library_name: transformers

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.998849252013809,
+    "total_flos": 2.9080852357930025e+18,
+    "train_loss": 0.39522024055230454,
+    "train_runtime": 4203.0638,
+    "train_samples_per_second": 13.229,
+    "train_steps_per_second": 0.052
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/petrelfs/gaoxin/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e8eed87843142b67b45e2167e82a4dd435eb0187aa116049cf9e6fc24acd71
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a05541833d85cac64daa893a5bbf55192f097c83cef305e18064906e50acc0
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61202f078552aefc5a116e3b6d8b0ce4fa99106f4af5c41e0d0655faf2f15317
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946f064a9c141a6e411ce39307ad64757fb0d197b75609646bccdf661423b736
+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 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 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": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.998849252013809,
+    "total_flos": 2.9080852357930025e+18,
+    "train_loss": 0.39522024055230454,
+    "train_runtime": 4203.0638,
+    "train_samples_per_second": 13.229,
+    "train_steps_per_second": 0.052
+}

trainer_log.jsonl

@@ -0,0 +1,218 @@
+{"current_steps": 1, "total_steps": 217, "loss": 0.5319, "lr": 7.142857142857143e-07, "epoch": 0.004602991944764097, "percentage": 0.46, "elapsed_time": "0:00:20", "remaining_time": "1:12:38"}
+{"current_steps": 2, "total_steps": 217, "loss": 0.5107, "lr": 1.4285714285714286e-06, "epoch": 0.009205983889528193, "percentage": 0.92, "elapsed_time": "0:00:37", "remaining_time": "1:07:03"}
+{"current_steps": 3, "total_steps": 217, "loss": 0.5124, "lr": 2.1428571428571427e-06, "epoch": 0.01380897583429229, "percentage": 1.38, "elapsed_time": "0:00:54", "remaining_time": "1:04:23"}
+{"current_steps": 4, "total_steps": 217, "loss": 0.536, "lr": 2.8571428571428573e-06, "epoch": 0.018411967779056387, "percentage": 1.84, "elapsed_time": "0:01:14", "remaining_time": "1:06:09"}
+{"current_steps": 5, "total_steps": 217, "loss": 0.492, "lr": 3.5714285714285718e-06, "epoch": 0.023014959723820484, "percentage": 2.3, "elapsed_time": "0:01:31", "remaining_time": "1:04:46"}
+{"current_steps": 6, "total_steps": 217, "loss": 0.5108, "lr": 4.2857142857142855e-06, "epoch": 0.02761795166858458, "percentage": 2.76, "elapsed_time": "0:01:53", "remaining_time": "1:06:35"}
+{"current_steps": 7, "total_steps": 217, "loss": 0.4918, "lr": 5e-06, "epoch": 0.03222094361334868, "percentage": 3.23, "elapsed_time": "0:02:11", "remaining_time": "1:05:35"}
+{"current_steps": 8, "total_steps": 217, "loss": 0.4705, "lr": 4.999720254525684e-06, "epoch": 0.03682393555811277, "percentage": 3.69, "elapsed_time": "0:02:30", "remaining_time": "1:05:44"}
+{"current_steps": 9, "total_steps": 217, "loss": 0.4622, "lr": 4.998881080708759e-06, "epoch": 0.04142692750287687, "percentage": 4.15, "elapsed_time": "0:02:49", "remaining_time": "1:05:13"}
+{"current_steps": 10, "total_steps": 217, "loss": 0.4538, "lr": 4.997482666353287e-06, "epoch": 0.04602991944764097, "percentage": 4.61, "elapsed_time": "0:03:10", "remaining_time": "1:05:35"}
+{"current_steps": 11, "total_steps": 217, "loss": 0.4832, "lr": 4.995525324419338e-06, "epoch": 0.05063291139240506, "percentage": 5.07, "elapsed_time": "0:03:27", "remaining_time": "1:04:43"}
+{"current_steps": 12, "total_steps": 217, "loss": 0.443, "lr": 4.993009492952951e-06, "epoch": 0.05523590333716916, "percentage": 5.53, "elapsed_time": "0:03:50", "remaining_time": "1:05:30"}
+{"current_steps": 13, "total_steps": 217, "loss": 0.4184, "lr": 4.989935734988098e-06, "epoch": 0.05983889528193326, "percentage": 5.99, "elapsed_time": "0:04:08", "remaining_time": "1:05:03"}
+{"current_steps": 14, "total_steps": 217, "loss": 0.4166, "lr": 4.986304738420684e-06, "epoch": 0.06444188722669736, "percentage": 6.45, "elapsed_time": "0:04:28", "remaining_time": "1:04:56"}
+{"current_steps": 15, "total_steps": 217, "loss": 0.4344, "lr": 4.982117315854594e-06, "epoch": 0.06904487917146145, "percentage": 6.91, "elapsed_time": "0:04:48", "remaining_time": "1:04:42"}
+{"current_steps": 16, "total_steps": 217, "loss": 0.4281, "lr": 4.977374404419838e-06, "epoch": 0.07364787111622555, "percentage": 7.37, "elapsed_time": "0:05:08", "remaining_time": "1:04:34"}
+{"current_steps": 17, "total_steps": 217, "loss": 0.4428, "lr": 4.9720770655628216e-06, "epoch": 0.07825086306098965, "percentage": 7.83, "elapsed_time": "0:05:28", "remaining_time": "1:04:25"}
+{"current_steps": 18, "total_steps": 217, "loss": 0.4129, "lr": 4.966226484808804e-06, "epoch": 0.08285385500575373, "percentage": 8.29, "elapsed_time": "0:05:51", "remaining_time": "1:04:43"}
+{"current_steps": 19, "total_steps": 217, "loss": 0.4362, "lr": 4.959823971496575e-06, "epoch": 0.08745684695051784, "percentage": 8.76, "elapsed_time": "0:06:10", "remaining_time": "1:04:20"}
+{"current_steps": 20, "total_steps": 217, "loss": 0.3944, "lr": 4.9528709584854316e-06, "epoch": 0.09205983889528194, "percentage": 9.22, "elapsed_time": "0:06:28", "remaining_time": "1:03:49"}
+{"current_steps": 21, "total_steps": 217, "loss": 0.4247, "lr": 4.9453690018345144e-06, "epoch": 0.09666283084004602, "percentage": 9.68, "elapsed_time": "0:06:46", "remaining_time": "1:03:14"}
+{"current_steps": 22, "total_steps": 217, "loss": 0.452, "lr": 4.937319780454559e-06, "epoch": 0.10126582278481013, "percentage": 10.14, "elapsed_time": "0:07:03", "remaining_time": "1:02:36"}
+{"current_steps": 23, "total_steps": 217, "loss": 0.4176, "lr": 4.9287250957321685e-06, "epoch": 0.10586881472957423, "percentage": 10.6, "elapsed_time": "0:07:22", "remaining_time": "1:02:10"}
+{"current_steps": 24, "total_steps": 217, "loss": 0.4235, "lr": 4.919586871126667e-06, "epoch": 0.11047180667433831, "percentage": 11.06, "elapsed_time": "0:07:39", "remaining_time": "1:01:36"}
+{"current_steps": 25, "total_steps": 217, "loss": 0.4128, "lr": 4.909907151739634e-06, "epoch": 0.11507479861910241, "percentage": 11.52, "elapsed_time": "0:07:57", "remaining_time": "1:01:06"}
+{"current_steps": 26, "total_steps": 217, "loss": 0.3971, "lr": 4.899688103857223e-06, "epoch": 0.11967779056386652, "percentage": 11.98, "elapsed_time": "0:08:15", "remaining_time": "1:00:43"}
+{"current_steps": 27, "total_steps": 217, "loss": 0.3675, "lr": 4.8889320144653525e-06, "epoch": 0.12428078250863062, "percentage": 12.44, "elapsed_time": "0:08:37", "remaining_time": "1:00:38"}
+{"current_steps": 28, "total_steps": 217, "loss": 0.4189, "lr": 4.8776412907378845e-06, "epoch": 0.12888377445339472, "percentage": 12.9, "elapsed_time": "0:08:56", "remaining_time": "1:00:22"}
+{"current_steps": 29, "total_steps": 217, "loss": 0.4309, "lr": 4.865818459497911e-06, "epoch": 0.1334867663981588, "percentage": 13.36, "elapsed_time": "0:09:15", "remaining_time": "0:59:58"}
+{"current_steps": 30, "total_steps": 217, "loss": 0.4159, "lr": 4.853466166652259e-06, "epoch": 0.1380897583429229, "percentage": 13.82, "elapsed_time": "0:09:32", "remaining_time": "0:59:29"}
+{"current_steps": 31, "total_steps": 217, "loss": 0.4043, "lr": 4.8405871765993435e-06, "epoch": 0.142692750287687, "percentage": 14.29, "elapsed_time": "0:09:50", "remaining_time": "0:59:02"}
+{"current_steps": 32, "total_steps": 217, "loss": 0.4331, "lr": 4.827184371610511e-06, "epoch": 0.1472957422324511, "percentage": 14.75, "elapsed_time": "0:10:07", "remaining_time": "0:58:29"}
+{"current_steps": 33, "total_steps": 217, "loss": 0.4027, "lr": 4.813260751184992e-06, "epoch": 0.1518987341772152, "percentage": 15.21, "elapsed_time": "0:10:30", "remaining_time": "0:58:35"}
+{"current_steps": 34, "total_steps": 217, "loss": 0.4286, "lr": 4.7988194313786275e-06, "epoch": 0.1565017261219793, "percentage": 15.67, "elapsed_time": "0:10:47", "remaining_time": "0:58:07"}
+{"current_steps": 35, "total_steps": 217, "loss": 0.4334, "lr": 4.783863644106502e-06, "epoch": 0.1611047180667434, "percentage": 16.13, "elapsed_time": "0:11:05", "remaining_time": "0:57:40"}
+{"current_steps": 36, "total_steps": 217, "loss": 0.4004, "lr": 4.7683967364196624e-06, "epoch": 0.16570771001150747, "percentage": 16.59, "elapsed_time": "0:11:24", "remaining_time": "0:57:20"}
+{"current_steps": 37, "total_steps": 217, "loss": 0.4058, "lr": 4.752422169756048e-06, "epoch": 0.17031070195627157, "percentage": 17.05, "elapsed_time": "0:11:42", "remaining_time": "0:56:59"}
+{"current_steps": 38, "total_steps": 217, "loss": 0.4199, "lr": 4.735943519165843e-06, "epoch": 0.17491369390103567, "percentage": 17.51, "elapsed_time": "0:12:02", "remaining_time": "0:56:44"}
+{"current_steps": 39, "total_steps": 217, "loss": 0.3845, "lr": 4.718964472511386e-06, "epoch": 0.17951668584579977, "percentage": 17.97, "elapsed_time": "0:12:21", "remaining_time": "0:56:24"}
+{"current_steps": 40, "total_steps": 217, "loss": 0.385, "lr": 4.701488829641845e-06, "epoch": 0.18411967779056387, "percentage": 18.43, "elapsed_time": "0:12:40", "remaining_time": "0:56:05"}
+{"current_steps": 41, "total_steps": 217, "loss": 0.4199, "lr": 4.683520501542825e-06, "epoch": 0.18872266973532797, "percentage": 18.89, "elapsed_time": "0:12:58", "remaining_time": "0:55:43"}
+{"current_steps": 42, "total_steps": 217, "loss": 0.393, "lr": 4.665063509461098e-06, "epoch": 0.19332566168009205, "percentage": 19.35, "elapsed_time": "0:13:17", "remaining_time": "0:55:22"}
+{"current_steps": 43, "total_steps": 217, "loss": 0.4143, "lr": 4.646121984004666e-06, "epoch": 0.19792865362485615, "percentage": 19.82, "elapsed_time": "0:13:34", "remaining_time": "0:54:56"}
+{"current_steps": 44, "total_steps": 217, "loss": 0.419, "lr": 4.626700164218349e-06, "epoch": 0.20253164556962025, "percentage": 20.28, "elapsed_time": "0:13:53", "remaining_time": "0:54:38"}
+{"current_steps": 45, "total_steps": 217, "loss": 0.3802, "lr": 4.606802396635098e-06, "epoch": 0.20713463751438435, "percentage": 20.74, "elapsed_time": "0:14:13", "remaining_time": "0:54:23"}
+{"current_steps": 46, "total_steps": 217, "loss": 0.4001, "lr": 4.586433134303257e-06, "epoch": 0.21173762945914845, "percentage": 21.2, "elapsed_time": "0:14:32", "remaining_time": "0:54:03"}
+{"current_steps": 47, "total_steps": 217, "loss": 0.3838, "lr": 4.565596935789987e-06, "epoch": 0.21634062140391255, "percentage": 21.66, "elapsed_time": "0:14:50", "remaining_time": "0:53:42"}
+{"current_steps": 48, "total_steps": 217, "loss": 0.4193, "lr": 4.544298464161079e-06, "epoch": 0.22094361334867663, "percentage": 22.12, "elapsed_time": "0:15:12", "remaining_time": "0:53:32"}
+{"current_steps": 49, "total_steps": 217, "loss": 0.4008, "lr": 4.522542485937369e-06, "epoch": 0.22554660529344073, "percentage": 22.58, "elapsed_time": "0:15:30", "remaining_time": "0:53:10"}
+{"current_steps": 50, "total_steps": 217, "loss": 0.4135, "lr": 4.500333870028017e-06, "epoch": 0.23014959723820483, "percentage": 23.04, "elapsed_time": "0:15:46", "remaining_time": "0:52:40"}
+{"current_steps": 51, "total_steps": 217, "loss": 0.4008, "lr": 4.477677586640854e-06, "epoch": 0.23475258918296893, "percentage": 23.5, "elapsed_time": "0:16:04", "remaining_time": "0:52:18"}
+{"current_steps": 52, "total_steps": 217, "loss": 0.423, "lr": 4.454578706170075e-06, "epoch": 0.23935558112773303, "percentage": 23.96, "elapsed_time": "0:16:22", "remaining_time": "0:51:56"}
+{"current_steps": 53, "total_steps": 217, "loss": 0.3918, "lr": 4.431042398061499e-06, "epoch": 0.24395857307249713, "percentage": 24.42, "elapsed_time": "0:16:42", "remaining_time": "0:51:41"}
+{"current_steps": 54, "total_steps": 217, "loss": 0.4121, "lr": 4.4070739296556665e-06, "epoch": 0.24856156501726123, "percentage": 24.88, "elapsed_time": "0:16:58", "remaining_time": "0:51:13"}
+{"current_steps": 55, "total_steps": 217, "loss": 0.4127, "lr": 4.382678665009028e-06, "epoch": 0.25316455696202533, "percentage": 25.35, "elapsed_time": "0:17:15", "remaining_time": "0:50:51"}
+{"current_steps": 56, "total_steps": 217, "loss": 0.4041, "lr": 4.357862063693486e-06, "epoch": 0.25776754890678943, "percentage": 25.81, "elapsed_time": "0:17:34", "remaining_time": "0:50:32"}
+{"current_steps": 57, "total_steps": 217, "loss": 0.3856, "lr": 4.332629679574566e-06, "epoch": 0.26237054085155354, "percentage": 26.27, "elapsed_time": "0:17:51", "remaining_time": "0:50:08"}
+{"current_steps": 58, "total_steps": 217, "loss": 0.3868, "lr": 4.3069871595684795e-06, "epoch": 0.2669735327963176, "percentage": 26.73, "elapsed_time": "0:18:14", "remaining_time": "0:50:00"}
+{"current_steps": 59, "total_steps": 217, "loss": 0.3801, "lr": 4.280940242378363e-06, "epoch": 0.2715765247410817, "percentage": 27.19, "elapsed_time": "0:18:33", "remaining_time": "0:49:42"}
+{"current_steps": 60, "total_steps": 217, "loss": 0.3916, "lr": 4.2544947572099795e-06, "epoch": 0.2761795166858458, "percentage": 27.65, "elapsed_time": "0:18:51", "remaining_time": "0:49:20"}
+{"current_steps": 61, "total_steps": 217, "loss": 0.3729, "lr": 4.227656622467162e-06, "epoch": 0.2807825086306099, "percentage": 28.11, "elapsed_time": "0:19:11", "remaining_time": "0:49:04"}
+{"current_steps": 62, "total_steps": 217, "loss": 0.3743, "lr": 4.200431844427299e-06, "epoch": 0.285385500575374, "percentage": 28.57, "elapsed_time": "0:19:29", "remaining_time": "0:48:43"}
+{"current_steps": 63, "total_steps": 217, "loss": 0.3639, "lr": 4.172826515897146e-06, "epoch": 0.2899884925201381, "percentage": 29.03, "elapsed_time": "0:19:50", "remaining_time": "0:48:30"}
+{"current_steps": 64, "total_steps": 217, "loss": 0.3813, "lr": 4.144846814849282e-06, "epoch": 0.2945914844649022, "percentage": 29.49, "elapsed_time": "0:20:08", "remaining_time": "0:48:09"}
+{"current_steps": 65, "total_steps": 217, "loss": 0.3792, "lr": 4.116499003039499e-06, "epoch": 0.2991944764096663, "percentage": 29.95, "elapsed_time": "0:20:28", "remaining_time": "0:47:53"}
+{"current_steps": 66, "total_steps": 217, "loss": 0.4266, "lr": 4.087789424605447e-06, "epoch": 0.3037974683544304, "percentage": 30.41, "elapsed_time": "0:20:43", "remaining_time": "0:47:25"}
+{"current_steps": 67, "total_steps": 217, "loss": 0.3893, "lr": 4.058724504646834e-06, "epoch": 0.3084004602991945, "percentage": 30.88, "elapsed_time": "0:21:01", "remaining_time": "0:47:03"}
+{"current_steps": 68, "total_steps": 217, "loss": 0.3922, "lr": 4.029310747787516e-06, "epoch": 0.3130034522439586, "percentage": 31.34, "elapsed_time": "0:21:21", "remaining_time": "0:46:47"}
+{"current_steps": 69, "total_steps": 217, "loss": 0.3626, "lr": 3.999554736719785e-06, "epoch": 0.3176064441887227, "percentage": 31.8, "elapsed_time": "0:21:40", "remaining_time": "0:46:29"}
+{"current_steps": 70, "total_steps": 217, "loss": 0.3702, "lr": 3.969463130731183e-06, "epoch": 0.3222094361334868, "percentage": 32.26, "elapsed_time": "0:21:57", "remaining_time": "0:46:06"}
+{"current_steps": 71, "total_steps": 217, "loss": 0.3826, "lr": 3.939042664214185e-06, "epoch": 0.32681242807825084, "percentage": 32.72, "elapsed_time": "0:22:18", "remaining_time": "0:45:51"}
+{"current_steps": 72, "total_steps": 217, "loss": 0.4251, "lr": 3.908300145159055e-06, "epoch": 0.33141542002301494, "percentage": 33.18, "elapsed_time": "0:22:33", "remaining_time": "0:45:26"}
+{"current_steps": 73, "total_steps": 217, "loss": 0.391, "lr": 3.8772424536302565e-06, "epoch": 0.33601841196777904, "percentage": 33.64, "elapsed_time": "0:22:50", "remaining_time": "0:45:03"}
+{"current_steps": 74, "total_steps": 217, "loss": 0.4103, "lr": 3.845876540226707e-06, "epoch": 0.34062140391254314, "percentage": 34.1, "elapsed_time": "0:23:08", "remaining_time": "0:44:44"}
+{"current_steps": 75, "total_steps": 217, "loss": 0.3976, "lr": 3.8142094245262617e-06, "epoch": 0.34522439585730724, "percentage": 34.56, "elapsed_time": "0:23:30", "remaining_time": "0:44:30"}
+{"current_steps": 76, "total_steps": 217, "loss": 0.407, "lr": 3.782248193514766e-06, "epoch": 0.34982738780207134, "percentage": 35.02, "elapsed_time": "0:23:47", "remaining_time": "0:44:08"}
+{"current_steps": 77, "total_steps": 217, "loss": 0.3929, "lr": 3.7500000000000005e-06, "epoch": 0.35443037974683544, "percentage": 35.48, "elapsed_time": "0:24:07", "remaining_time": "0:43:51"}
+{"current_steps": 78, "total_steps": 217, "loss": 0.3859, "lr": 3.7174720610109184e-06, "epoch": 0.35903337169159955, "percentage": 35.94, "elapsed_time": "0:24:26", "remaining_time": "0:43:33"}
+{"current_steps": 79, "total_steps": 217, "loss": 0.3987, "lr": 3.684671656182497e-06, "epoch": 0.36363636363636365, "percentage": 36.41, "elapsed_time": "0:24:44", "remaining_time": "0:43:13"}
+{"current_steps": 80, "total_steps": 217, "loss": 0.3847, "lr": 3.6516061261265813e-06, "epoch": 0.36823935558112775, "percentage": 36.87, "elapsed_time": "0:25:02", "remaining_time": "0:42:53"}
+{"current_steps": 81, "total_steps": 217, "loss": 0.3771, "lr": 3.6182828707890816e-06, "epoch": 0.37284234752589185, "percentage": 37.33, "elapsed_time": "0:25:21", "remaining_time": "0:42:35"}
+{"current_steps": 82, "total_steps": 217, "loss": 0.382, "lr": 3.5847093477938955e-06, "epoch": 0.37744533947065595, "percentage": 37.79, "elapsed_time": "0:25:42", "remaining_time": "0:42:19"}
+{"current_steps": 83, "total_steps": 217, "loss": 0.3608, "lr": 3.5508930707739143e-06, "epoch": 0.38204833141542005, "percentage": 38.25, "elapsed_time": "0:26:02", "remaining_time": "0:42:02"}
+{"current_steps": 84, "total_steps": 217, "loss": 0.4171, "lr": 3.516841607689501e-06, "epoch": 0.3866513233601841, "percentage": 38.71, "elapsed_time": "0:26:20", "remaining_time": "0:41:43"}
+{"current_steps": 85, "total_steps": 217, "loss": 0.3906, "lr": 3.4825625791348093e-06, "epoch": 0.3912543153049482, "percentage": 39.17, "elapsed_time": "0:26:39", "remaining_time": "0:41:24"}
+{"current_steps": 86, "total_steps": 217, "loss": 0.3802, "lr": 3.4480636566323215e-06, "epoch": 0.3958573072497123, "percentage": 39.63, "elapsed_time": "0:26:59", "remaining_time": "0:41:06"}
+{"current_steps": 87, "total_steps": 217, "loss": 0.3996, "lr": 3.4133525609159883e-06, "epoch": 0.4004602991944764, "percentage": 40.09, "elapsed_time": "0:27:18", "remaining_time": "0:40:47"}
+{"current_steps": 88, "total_steps": 217, "loss": 0.3938, "lr": 3.3784370602033572e-06, "epoch": 0.4050632911392405, "percentage": 40.55, "elapsed_time": "0:27:39", "remaining_time": "0:40:32"}
+{"current_steps": 89, "total_steps": 217, "loss": 0.3798, "lr": 3.3433249684570757e-06, "epoch": 0.4096662830840046, "percentage": 41.01, "elapsed_time": "0:27:57", "remaining_time": "0:40:12"}
+{"current_steps": 90, "total_steps": 217, "loss": 0.3804, "lr": 3.3080241436361505e-06, "epoch": 0.4142692750287687, "percentage": 41.47, "elapsed_time": "0:28:17", "remaining_time": "0:39:56"}
+{"current_steps": 91, "total_steps": 217, "loss": 0.3529, "lr": 3.272542485937369e-06, "epoch": 0.4188722669735328, "percentage": 41.94, "elapsed_time": "0:28:37", "remaining_time": "0:39:37"}
+{"current_steps": 92, "total_steps": 217, "loss": 0.4038, "lr": 3.236887936027261e-06, "epoch": 0.4234752589182969, "percentage": 42.4, "elapsed_time": "0:28:56", "remaining_time": "0:39:19"}
+{"current_steps": 93, "total_steps": 217, "loss": 0.3755, "lr": 3.201068473265007e-06, "epoch": 0.428078250863061, "percentage": 42.86, "elapsed_time": "0:29:17", "remaining_time": "0:39:03"}
+{"current_steps": 94, "total_steps": 217, "loss": 0.386, "lr": 3.165092113916688e-06, "epoch": 0.4326812428078251, "percentage": 43.32, "elapsed_time": "0:29:36", "remaining_time": "0:38:44"}
+{"current_steps": 95, "total_steps": 217, "loss": 0.413, "lr": 3.128966909361272e-06, "epoch": 0.4372842347525892, "percentage": 43.78, "elapsed_time": "0:29:55", "remaining_time": "0:38:25"}
+{"current_steps": 96, "total_steps": 217, "loss": 0.3824, "lr": 3.092700944288744e-06, "epoch": 0.44188722669735325, "percentage": 44.24, "elapsed_time": "0:30:15", "remaining_time": "0:38:07"}
+{"current_steps": 97, "total_steps": 217, "loss": 0.3582, "lr": 3.056302334890786e-06, "epoch": 0.44649021864211735, "percentage": 44.7, "elapsed_time": "0:30:35", "remaining_time": "0:37:50"}
+{"current_steps": 98, "total_steps": 217, "loss": 0.389, "lr": 3.019779227044398e-06, "epoch": 0.45109321058688145, "percentage": 45.16, "elapsed_time": "0:30:54", "remaining_time": "0:37:31"}
+{"current_steps": 99, "total_steps": 217, "loss": 0.4077, "lr": 2.9831397944888833e-06, "epoch": 0.45569620253164556, "percentage": 45.62, "elapsed_time": "0:31:13", "remaining_time": "0:37:12"}
+{"current_steps": 100, "total_steps": 217, "loss": 0.4167, "lr": 2.946392236996592e-06, "epoch": 0.46029919447640966, "percentage": 46.08, "elapsed_time": "0:31:29", "remaining_time": "0:36:51"}
+{"current_steps": 101, "total_steps": 217, "loss": 0.3941, "lr": 2.9095447785378446e-06, "epoch": 0.46490218642117376, "percentage": 46.54, "elapsed_time": "0:31:47", "remaining_time": "0:36:30"}
+{"current_steps": 102, "total_steps": 217, "loss": 0.3957, "lr": 2.872605665440436e-06, "epoch": 0.46950517836593786, "percentage": 47.0, "elapsed_time": "0:32:05", "remaining_time": "0:36:10"}
+{"current_steps": 103, "total_steps": 217, "loss": 0.3898, "lr": 2.835583164544139e-06, "epoch": 0.47410817031070196, "percentage": 47.47, "elapsed_time": "0:32:22", "remaining_time": "0:35:49"}
+{"current_steps": 104, "total_steps": 217, "loss": 0.3785, "lr": 2.7984855613506107e-06, "epoch": 0.47871116225546606, "percentage": 47.93, "elapsed_time": "0:32:38", "remaining_time": "0:35:28"}
+{"current_steps": 105, "total_steps": 217, "loss": 0.3767, "lr": 2.761321158169134e-06, "epoch": 0.48331415420023016, "percentage": 48.39, "elapsed_time": "0:32:55", "remaining_time": "0:35:07"}
+{"current_steps": 106, "total_steps": 217, "loss": 0.3817, "lr": 2.724098272258584e-06, "epoch": 0.48791714614499426, "percentage": 48.85, "elapsed_time": "0:33:15", "remaining_time": "0:34:49"}
+{"current_steps": 107, "total_steps": 217, "loss": 0.4088, "lr": 2.686825233966061e-06, "epoch": 0.49252013808975836, "percentage": 49.31, "elapsed_time": "0:33:34", "remaining_time": "0:34:30"}
+{"current_steps": 108, "total_steps": 217, "loss": 0.4014, "lr": 2.649510384862586e-06, "epoch": 0.49712313003452246, "percentage": 49.77, "elapsed_time": "0:33:53", "remaining_time": "0:34:11"}
+{"current_steps": 109, "total_steps": 217, "loss": 0.3753, "lr": 2.6121620758762877e-06, "epoch": 0.5017261219792866, "percentage": 50.23, "elapsed_time": "0:34:12", "remaining_time": "0:33:53"}
+{"current_steps": 110, "total_steps": 217, "loss": 0.3788, "lr": 2.5747886654234967e-06, "epoch": 0.5063291139240507, "percentage": 50.69, "elapsed_time": "0:34:30", "remaining_time": "0:33:34"}
+{"current_steps": 111, "total_steps": 217, "loss": 0.3713, "lr": 2.5373985175381595e-06, "epoch": 0.5109321058688148, "percentage": 51.15, "elapsed_time": "0:34:49", "remaining_time": "0:33:14"}
+{"current_steps": 112, "total_steps": 217, "loss": 0.3991, "lr": 2.5e-06, "epoch": 0.5155350978135789, "percentage": 51.61, "elapsed_time": "0:35:06", "remaining_time": "0:32:55"}
+{"current_steps": 113, "total_steps": 217, "loss": 0.3934, "lr": 2.4626014824618418e-06, "epoch": 0.520138089758343, "percentage": 52.07, "elapsed_time": "0:35:25", "remaining_time": "0:32:36"}
+{"current_steps": 114, "total_steps": 217, "loss": 0.384, "lr": 2.4252113345765045e-06, "epoch": 0.5247410817031071, "percentage": 52.53, "elapsed_time": "0:35:43", "remaining_time": "0:32:16"}
+{"current_steps": 115, "total_steps": 217, "loss": 0.4068, "lr": 2.3878379241237136e-06, "epoch": 0.5293440736478712, "percentage": 53.0, "elapsed_time": "0:36:02", "remaining_time": "0:31:57"}
+{"current_steps": 116, "total_steps": 217, "loss": 0.3903, "lr": 2.3504896151374145e-06, "epoch": 0.5339470655926352, "percentage": 53.46, "elapsed_time": "0:36:26", "remaining_time": "0:31:43"}
+{"current_steps": 117, "total_steps": 217, "loss": 0.3914, "lr": 2.3131747660339396e-06, "epoch": 0.5385500575373993, "percentage": 53.92, "elapsed_time": "0:36:43", "remaining_time": "0:31:23"}
+{"current_steps": 118, "total_steps": 217, "loss": 0.3669, "lr": 2.2759017277414165e-06, "epoch": 0.5431530494821634, "percentage": 54.38, "elapsed_time": "0:37:04", "remaining_time": "0:31:06"}
+{"current_steps": 119, "total_steps": 217, "loss": 0.404, "lr": 2.238678841830867e-06, "epoch": 0.5477560414269275, "percentage": 54.84, "elapsed_time": "0:37:20", "remaining_time": "0:30:45"}
+{"current_steps": 120, "total_steps": 217, "loss": 0.3735, "lr": 2.2015144386493898e-06, "epoch": 0.5523590333716916, "percentage": 55.3, "elapsed_time": "0:37:36", "remaining_time": "0:30:24"}
+{"current_steps": 121, "total_steps": 217, "loss": 0.3711, "lr": 2.1644168354558623e-06, "epoch": 0.5569620253164557, "percentage": 55.76, "elapsed_time": "0:37:55", "remaining_time": "0:30:05"}
+{"current_steps": 122, "total_steps": 217, "loss": 0.4074, "lr": 2.1273943345595637e-06, "epoch": 0.5615650172612198, "percentage": 56.22, "elapsed_time": "0:38:15", "remaining_time": "0:29:47"}
+{"current_steps": 123, "total_steps": 217, "loss": 0.4354, "lr": 2.090455221462156e-06, "epoch": 0.5661680092059839, "percentage": 56.68, "elapsed_time": "0:38:32", "remaining_time": "0:29:26"}
+{"current_steps": 124, "total_steps": 217, "loss": 0.3841, "lr": 2.053607763003409e-06, "epoch": 0.570771001150748, "percentage": 57.14, "elapsed_time": "0:38:49", "remaining_time": "0:29:07"}
+{"current_steps": 125, "total_steps": 217, "loss": 0.3855, "lr": 2.0168602055111175e-06, "epoch": 0.5753739930955121, "percentage": 57.6, "elapsed_time": "0:39:06", "remaining_time": "0:28:46"}
+{"current_steps": 126, "total_steps": 217, "loss": 0.3629, "lr": 1.9802207729556023e-06, "epoch": 0.5799769850402762, "percentage": 58.06, "elapsed_time": "0:39:26", "remaining_time": "0:28:28"}
+{"current_steps": 127, "total_steps": 217, "loss": 0.3741, "lr": 1.9436976651092143e-06, "epoch": 0.5845799769850403, "percentage": 58.53, "elapsed_time": "0:39:43", "remaining_time": "0:28:09"}
+{"current_steps": 128, "total_steps": 217, "loss": 0.3913, "lr": 1.9072990557112567e-06, "epoch": 0.5891829689298044, "percentage": 58.99, "elapsed_time": "0:40:02", "remaining_time": "0:27:50"}
+{"current_steps": 129, "total_steps": 217, "loss": 0.3686, "lr": 1.8710330906387288e-06, "epoch": 0.5937859608745685, "percentage": 59.45, "elapsed_time": "0:40:21", "remaining_time": "0:27:31"}
+{"current_steps": 130, "total_steps": 217, "loss": 0.3757, "lr": 1.8349078860833125e-06, "epoch": 0.5983889528193326, "percentage": 59.91, "elapsed_time": "0:40:38", "remaining_time": "0:27:12"}
+{"current_steps": 131, "total_steps": 217, "loss": 0.3639, "lr": 1.7989315267349936e-06, "epoch": 0.6029919447640967, "percentage": 60.37, "elapsed_time": "0:40:57", "remaining_time": "0:26:53"}
+{"current_steps": 132, "total_steps": 217, "loss": 0.3849, "lr": 1.7631120639727396e-06, "epoch": 0.6075949367088608, "percentage": 60.83, "elapsed_time": "0:41:17", "remaining_time": "0:26:35"}
+{"current_steps": 133, "total_steps": 217, "loss": 0.3775, "lr": 1.7274575140626318e-06, "epoch": 0.6121979286536249, "percentage": 61.29, "elapsed_time": "0:41:34", "remaining_time": "0:26:15"}
+{"current_steps": 134, "total_steps": 217, "loss": 0.3715, "lr": 1.6919758563638506e-06, "epoch": 0.616800920598389, "percentage": 61.75, "elapsed_time": "0:41:53", "remaining_time": "0:25:57"}
+{"current_steps": 135, "total_steps": 217, "loss": 0.3685, "lr": 1.6566750315429254e-06, "epoch": 0.6214039125431531, "percentage": 62.21, "elapsed_time": "0:42:11", "remaining_time": "0:25:37"}
+{"current_steps": 136, "total_steps": 217, "loss": 0.3526, "lr": 1.6215629397966432e-06, "epoch": 0.6260069044879172, "percentage": 62.67, "elapsed_time": "0:42:30", "remaining_time": "0:25:19"}
+{"current_steps": 137, "total_steps": 217, "loss": 0.3862, "lr": 1.5866474390840126e-06, "epoch": 0.6306098964326813, "percentage": 63.13, "elapsed_time": "0:42:47", "remaining_time": "0:24:59"}
+{"current_steps": 138, "total_steps": 217, "loss": 0.3885, "lr": 1.5519363433676794e-06, "epoch": 0.6352128883774454, "percentage": 63.59, "elapsed_time": "0:43:07", "remaining_time": "0:24:41"}
+{"current_steps": 139, "total_steps": 217, "loss": 0.3759, "lr": 1.5174374208651913e-06, "epoch": 0.6398158803222095, "percentage": 64.06, "elapsed_time": "0:43:27", "remaining_time": "0:24:23"}
+{"current_steps": 140, "total_steps": 217, "loss": 0.4084, "lr": 1.4831583923105e-06, "epoch": 0.6444188722669736, "percentage": 64.52, "elapsed_time": "0:43:46", "remaining_time": "0:24:04"}
+{"current_steps": 141, "total_steps": 217, "loss": 0.3878, "lr": 1.4491069292260867e-06, "epoch": 0.6490218642117376, "percentage": 64.98, "elapsed_time": "0:44:06", "remaining_time": "0:23:46"}
+{"current_steps": 142, "total_steps": 217, "loss": 0.4166, "lr": 1.415290652206105e-06, "epoch": 0.6536248561565017, "percentage": 65.44, "elapsed_time": "0:44:24", "remaining_time": "0:23:27"}
+{"current_steps": 143, "total_steps": 217, "loss": 0.3803, "lr": 1.3817171292109182e-06, "epoch": 0.6582278481012658, "percentage": 65.9, "elapsed_time": "0:44:43", "remaining_time": "0:23:08"}
+{"current_steps": 144, "total_steps": 217, "loss": 0.3696, "lr": 1.3483938738734197e-06, "epoch": 0.6628308400460299, "percentage": 66.36, "elapsed_time": "0:45:01", "remaining_time": "0:22:49"}
+{"current_steps": 145, "total_steps": 217, "loss": 0.3721, "lr": 1.3153283438175036e-06, "epoch": 0.667433831990794, "percentage": 66.82, "elapsed_time": "0:45:19", "remaining_time": "0:22:30"}
+{"current_steps": 146, "total_steps": 217, "loss": 0.3657, "lr": 1.2825279389890818e-06, "epoch": 0.6720368239355581, "percentage": 67.28, "elapsed_time": "0:45:41", "remaining_time": "0:22:13"}
+{"current_steps": 147, "total_steps": 217, "loss": 0.3682, "lr": 1.2500000000000007e-06, "epoch": 0.6766398158803222, "percentage": 67.74, "elapsed_time": "0:46:00", "remaining_time": "0:21:54"}
+{"current_steps": 148, "total_steps": 217, "loss": 0.392, "lr": 1.2177518064852348e-06, "epoch": 0.6812428078250863, "percentage": 68.2, "elapsed_time": "0:46:18", "remaining_time": "0:21:35"}
+{"current_steps": 149, "total_steps": 217, "loss": 0.4002, "lr": 1.185790575473738e-06, "epoch": 0.6858457997698504, "percentage": 68.66, "elapsed_time": "0:46:38", "remaining_time": "0:21:17"}
+{"current_steps": 150, "total_steps": 217, "loss": 0.3925, "lr": 1.1541234597732947e-06, "epoch": 0.6904487917146145, "percentage": 69.12, "elapsed_time": "0:47:01", "remaining_time": "0:21:00"}
+{"current_steps": 151, "total_steps": 217, "loss": 0.3788, "lr": 1.122757546369744e-06, "epoch": 0.6950517836593786, "percentage": 69.59, "elapsed_time": "0:47:19", "remaining_time": "0:20:41"}
+{"current_steps": 152, "total_steps": 217, "loss": 0.3696, "lr": 1.0916998548409449e-06, "epoch": 0.6996547756041427, "percentage": 70.05, "elapsed_time": "0:47:39", "remaining_time": "0:20:22"}
+{"current_steps": 153, "total_steps": 217, "loss": 0.3842, "lr": 1.0609573357858166e-06, "epoch": 0.7042577675489068, "percentage": 70.51, "elapsed_time": "0:47:58", "remaining_time": "0:20:04"}
+{"current_steps": 154, "total_steps": 217, "loss": 0.3879, "lr": 1.0305368692688175e-06, "epoch": 0.7088607594936709, "percentage": 70.97, "elapsed_time": "0:48:15", "remaining_time": "0:19:44"}
+{"current_steps": 155, "total_steps": 217, "loss": 0.3795, "lr": 1.0004452632802158e-06, "epoch": 0.713463751438435, "percentage": 71.43, "elapsed_time": "0:48:33", "remaining_time": "0:19:25"}
+{"current_steps": 156, "total_steps": 217, "loss": 0.3702, "lr": 9.70689252212484e-07, "epoch": 0.7180667433831991, "percentage": 71.89, "elapsed_time": "0:48:57", "remaining_time": "0:19:08"}
+{"current_steps": 157, "total_steps": 217, "loss": 0.3726, "lr": 9.412754953531664e-07, "epoch": 0.7226697353279632, "percentage": 72.35, "elapsed_time": "0:49:13", "remaining_time": "0:18:48"}
+{"current_steps": 158, "total_steps": 217, "loss": 0.3764, "lr": 9.122105753945532e-07, "epoch": 0.7272727272727273, "percentage": 72.81, "elapsed_time": "0:49:31", "remaining_time": "0:18:29"}
+{"current_steps": 159, "total_steps": 217, "loss": 0.4064, "lr": 8.835009969605013e-07, "epoch": 0.7318757192174914, "percentage": 73.27, "elapsed_time": "0:49:50", "remaining_time": "0:18:10"}
+{"current_steps": 160, "total_steps": 217, "loss": 0.3943, "lr": 8.551531851507186e-07, "epoch": 0.7364787111622555, "percentage": 73.73, "elapsed_time": "0:50:07", "remaining_time": "0:17:51"}
+{"current_steps": 161, "total_steps": 217, "loss": 0.3727, "lr": 8.271734841028553e-07, "epoch": 0.7410817031070196, "percentage": 74.19, "elapsed_time": "0:50:29", "remaining_time": "0:17:33"}
+{"current_steps": 162, "total_steps": 217, "loss": 0.3721, "lr": 7.995681555727011e-07, "epoch": 0.7456846950517837, "percentage": 74.65, "elapsed_time": "0:50:46", "remaining_time": "0:17:14"}
+{"current_steps": 163, "total_steps": 217, "loss": 0.4127, "lr": 7.723433775328385e-07, "epoch": 0.7502876869965478, "percentage": 75.12, "elapsed_time": "0:51:04", "remaining_time": "0:16:55"}
+{"current_steps": 164, "total_steps": 217, "loss": 0.3832, "lr": 7.455052427900214e-07, "epoch": 0.7548906789413119, "percentage": 75.58, "elapsed_time": "0:51:24", "remaining_time": "0:16:36"}
+{"current_steps": 165, "total_steps": 217, "loss": 0.3804, "lr": 7.190597576216385e-07, "epoch": 0.759493670886076, "percentage": 76.04, "elapsed_time": "0:51:44", "remaining_time": "0:16:18"}
+{"current_steps": 166, "total_steps": 217, "loss": 0.3873, "lr": 6.930128404315214e-07, "epoch": 0.7640966628308401, "percentage": 76.5, "elapsed_time": "0:52:02", "remaining_time": "0:15:59"}
+{"current_steps": 167, "total_steps": 217, "loss": 0.367, "lr": 6.673703204254348e-07, "epoch": 0.7686996547756041, "percentage": 76.96, "elapsed_time": "0:52:17", "remaining_time": "0:15:39"}
+{"current_steps": 168, "total_steps": 217, "loss": 0.3738, "lr": 6.421379363065142e-07, "epoch": 0.7733026467203682, "percentage": 77.42, "elapsed_time": "0:52:36", "remaining_time": "0:15:20"}
+{"current_steps": 169, "total_steps": 217, "loss": 0.3857, "lr": 6.17321334990973e-07, "epoch": 0.7779056386651323, "percentage": 77.88, "elapsed_time": "0:52:56", "remaining_time": "0:15:02"}
+{"current_steps": 170, "total_steps": 217, "loss": 0.3903, "lr": 5.929260703443337e-07, "epoch": 0.7825086306098964, "percentage": 78.34, "elapsed_time": "0:53:13", "remaining_time": "0:14:42"}
+{"current_steps": 171, "total_steps": 217, "loss": 0.3747, "lr": 5.689576019385015e-07, "epoch": 0.7871116225546605, "percentage": 78.8, "elapsed_time": "0:53:32", "remaining_time": "0:14:24"}
+{"current_steps": 172, "total_steps": 217, "loss": 0.3778, "lr": 5.454212938299256e-07, "epoch": 0.7917146144994246, "percentage": 79.26, "elapsed_time": "0:53:49", "remaining_time": "0:14:04"}
+{"current_steps": 173, "total_steps": 217, "loss": 0.3962, "lr": 5.223224133591475e-07, "epoch": 0.7963176064441887, "percentage": 79.72, "elapsed_time": "0:54:08", "remaining_time": "0:13:46"}
+{"current_steps": 174, "total_steps": 217, "loss": 0.3891, "lr": 4.996661299719846e-07, "epoch": 0.8009205983889528, "percentage": 80.18, "elapsed_time": "0:54:26", "remaining_time": "0:13:27"}
+{"current_steps": 175, "total_steps": 217, "loss": 0.3573, "lr": 4.774575140626317e-07, "epoch": 0.8055235903337169, "percentage": 80.65, "elapsed_time": "0:54:46", "remaining_time": "0:13:08"}
+{"current_steps": 176, "total_steps": 217, "loss": 0.3924, "lr": 4.5570153583892165e-07, "epoch": 0.810126582278481, "percentage": 81.11, "elapsed_time": "0:55:03", "remaining_time": "0:12:49"}
+{"current_steps": 177, "total_steps": 217, "loss": 0.3797, "lr": 4.344030642100133e-07, "epoch": 0.8147295742232451, "percentage": 81.57, "elapsed_time": "0:55:21", "remaining_time": "0:12:30"}
+{"current_steps": 178, "total_steps": 217, "loss": 0.3688, "lr": 4.1356686569674344e-07, "epoch": 0.8193325661680092, "percentage": 82.03, "elapsed_time": "0:55:41", "remaining_time": "0:12:12"}
+{"current_steps": 179, "total_steps": 217, "loss": 0.3858, "lr": 3.931976033649021e-07, "epoch": 0.8239355581127733, "percentage": 82.49, "elapsed_time": "0:56:03", "remaining_time": "0:11:54"}
+{"current_steps": 180, "total_steps": 217, "loss": 0.3782, "lr": 3.732998357816514e-07, "epoch": 0.8285385500575374, "percentage": 82.95, "elapsed_time": "0:56:20", "remaining_time": "0:11:34"}
+{"current_steps": 181, "total_steps": 217, "loss": 0.3729, "lr": 3.538780159953348e-07, "epoch": 0.8331415420023015, "percentage": 83.41, "elapsed_time": "0:56:40", "remaining_time": "0:11:16"}
+{"current_steps": 182, "total_steps": 217, "loss": 0.3887, "lr": 3.3493649053890325e-07, "epoch": 0.8377445339470656, "percentage": 83.87, "elapsed_time": "0:56:57", "remaining_time": "0:10:57"}
+{"current_steps": 183, "total_steps": 217, "loss": 0.3734, "lr": 3.164794984571759e-07, "epoch": 0.8423475258918297, "percentage": 84.33, "elapsed_time": "0:57:14", "remaining_time": "0:10:38"}
+{"current_steps": 184, "total_steps": 217, "loss": 0.3757, "lr": 2.98511170358155e-07, "epoch": 0.8469505178365938, "percentage": 84.79, "elapsed_time": "0:57:32", "remaining_time": "0:10:19"}
+{"current_steps": 185, "total_steps": 217, "loss": 0.3692, "lr": 2.810355274886148e-07, "epoch": 0.8515535097813579, "percentage": 85.25, "elapsed_time": "0:57:52", "remaining_time": "0:10:00"}
+{"current_steps": 186, "total_steps": 217, "loss": 0.3469, "lr": 2.6405648083415835e-07, "epoch": 0.856156501726122, "percentage": 85.71, "elapsed_time": "0:58:12", "remaining_time": "0:09:42"}
+{"current_steps": 187, "total_steps": 217, "loss": 0.3714, "lr": 2.4757783024395244e-07, "epoch": 0.8607594936708861, "percentage": 86.18, "elapsed_time": "0:58:33", "remaining_time": "0:09:23"}
+{"current_steps": 188, "total_steps": 217, "loss": 0.3681, "lr": 2.316032635803378e-07, "epoch": 0.8653624856156502, "percentage": 86.64, "elapsed_time": "0:58:52", "remaining_time": "0:09:04"}
+{"current_steps": 189, "total_steps": 217, "loss": 0.3828, "lr": 2.1613635589349756e-07, "epoch": 0.8699654775604143, "percentage": 87.1, "elapsed_time": "0:59:09", "remaining_time": "0:08:45"}
+{"current_steps": 190, "total_steps": 217, "loss": 0.3827, "lr": 2.0118056862137358e-07, "epoch": 0.8745684695051784, "percentage": 87.56, "elapsed_time": "0:59:27", "remaining_time": "0:08:27"}
+{"current_steps": 191, "total_steps": 217, "loss": 0.3707, "lr": 1.8673924881500826e-07, "epoch": 0.8791714614499425, "percentage": 88.02, "elapsed_time": "0:59:45", "remaining_time": "0:08:08"}
+{"current_steps": 192, "total_steps": 217, "loss": 0.3698, "lr": 1.7281562838948968e-07, "epoch": 0.8837744533947065, "percentage": 88.48, "elapsed_time": "1:00:04", "remaining_time": "0:07:49"}
+{"current_steps": 193, "total_steps": 217, "loss": 0.3597, "lr": 1.59412823400657e-07, "epoch": 0.8883774453394706, "percentage": 88.94, "elapsed_time": "1:00:24", "remaining_time": "0:07:30"}
+{"current_steps": 194, "total_steps": 217, "loss": 0.3825, "lr": 1.465338333477423e-07, "epoch": 0.8929804372842347, "percentage": 89.4, "elapsed_time": "1:00:41", "remaining_time": "0:07:11"}
+{"current_steps": 195, "total_steps": 217, "loss": 0.3477, "lr": 1.3418154050208937e-07, "epoch": 0.8975834292289988, "percentage": 89.86, "elapsed_time": "1:01:00", "remaining_time": "0:06:52"}
+{"current_steps": 196, "total_steps": 217, "loss": 0.3609, "lr": 1.223587092621162e-07, "epoch": 0.9021864211737629, "percentage": 90.32, "elapsed_time": "1:01:19", "remaining_time": "0:06:34"}
+{"current_steps": 197, "total_steps": 217, "loss": 0.3804, "lr": 1.1106798553464804e-07, "epoch": 0.906789413118527, "percentage": 90.78, "elapsed_time": "1:01:39", "remaining_time": "0:06:15"}
+{"current_steps": 198, "total_steps": 217, "loss": 0.372, "lr": 1.0031189614277765e-07, "epoch": 0.9113924050632911, "percentage": 91.24, "elapsed_time": "1:01:58", "remaining_time": "0:05:56"}
+{"current_steps": 199, "total_steps": 217, "loss": 0.3798, "lr": 9.00928482603669e-08, "epoch": 0.9159953970080552, "percentage": 91.71, "elapsed_time": "1:02:15", "remaining_time": "0:05:37"}
+{"current_steps": 200, "total_steps": 217, "loss": 0.372, "lr": 8.041312887333396e-08, "epoch": 0.9205983889528193, "percentage": 92.17, "elapsed_time": "1:02:34", "remaining_time": "0:05:19"}
+{"current_steps": 201, "total_steps": 217, "loss": 0.3909, "lr": 7.127490426783124e-08, "epoch": 0.9252013808975834, "percentage": 92.63, "elapsed_time": "1:02:53", "remaining_time": "0:05:00"}
+{"current_steps": 202, "total_steps": 217, "loss": 0.3921, "lr": 6.268021954544095e-08, "epoch": 0.9298043728423475, "percentage": 93.09, "elapsed_time": "1:03:10", "remaining_time": "0:04:41"}
+{"current_steps": 203, "total_steps": 217, "loss": 0.4175, "lr": 5.463099816548578e-08, "epoch": 0.9344073647871116, "percentage": 93.55, "elapsed_time": "1:03:26", "remaining_time": "0:04:22"}
+{"current_steps": 204, "total_steps": 217, "loss": 0.3589, "lr": 4.712904151456865e-08, "epoch": 0.9390103567318757, "percentage": 94.01, "elapsed_time": "1:03:50", "remaining_time": "0:04:04"}
+{"current_steps": 205, "total_steps": 217, "loss": 0.3839, "lr": 4.017602850342584e-08, "epoch": 0.9436133486766398, "percentage": 94.47, "elapsed_time": "1:04:07", "remaining_time": "0:03:45"}
+{"current_steps": 206, "total_steps": 217, "loss": 0.3901, "lr": 3.377351519119665e-08, "epoch": 0.9482163406214039, "percentage": 94.93, "elapsed_time": "1:04:29", "remaining_time": "0:03:26"}
+{"current_steps": 207, "total_steps": 217, "loss": 0.3694, "lr": 2.7922934437178695e-08, "epoch": 0.952819332566168, "percentage": 95.39, "elapsed_time": "1:04:48", "remaining_time": "0:03:07"}
+{"current_steps": 208, "total_steps": 217, "loss": 0.3935, "lr": 2.262559558016325e-08, "epoch": 0.9574223245109321, "percentage": 95.85, "elapsed_time": "1:05:06", "remaining_time": "0:02:49"}
+{"current_steps": 209, "total_steps": 217, "loss": 0.3797, "lr": 1.7882684145406616e-08, "epoch": 0.9620253164556962, "percentage": 96.31, "elapsed_time": "1:05:22", "remaining_time": "0:02:30"}
+{"current_steps": 210, "total_steps": 217, "loss": 0.371, "lr": 1.3695261579316776e-08, "epoch": 0.9666283084004603, "percentage": 96.77, "elapsed_time": "1:05:38", "remaining_time": "0:02:11"}
+{"current_steps": 211, "total_steps": 217, "loss": 0.3671, "lr": 1.006426501190233e-08, "epoch": 0.9712313003452244, "percentage": 97.24, "elapsed_time": "1:05:56", "remaining_time": "0:01:52"}
+{"current_steps": 212, "total_steps": 217, "loss": 0.3847, "lr": 6.990507047049677e-09, "epoch": 0.9758342922899885, "percentage": 97.7, "elapsed_time": "1:06:15", "remaining_time": "0:01:33"}
+{"current_steps": 213, "total_steps": 217, "loss": 0.3857, "lr": 4.474675580662113e-09, "epoch": 0.9804372842347526, "percentage": 98.16, "elapsed_time": "1:06:31", "remaining_time": "0:01:14"}
+{"current_steps": 214, "total_steps": 217, "loss": 0.3734, "lr": 2.5173336467135266e-09, "epoch": 0.9850402761795167, "percentage": 98.62, "elapsed_time": "1:06:49", "remaining_time": "0:00:56"}
+{"current_steps": 215, "total_steps": 217, "loss": 0.3936, "lr": 1.1189192912416935e-09, "epoch": 0.9896432681242808, "percentage": 99.08, "elapsed_time": "1:07:06", "remaining_time": "0:00:37"}
+{"current_steps": 216, "total_steps": 217, "loss": 0.3813, "lr": 2.797454743164174e-10, "epoch": 0.9942462600690449, "percentage": 99.54, "elapsed_time": "1:07:24", "remaining_time": "0:00:18"}
+{"current_steps": 217, "total_steps": 217, "loss": 0.4095, "lr": 0.0, "epoch": 0.998849252013809, "percentage": 100.0, "elapsed_time": "1:07:41", "remaining_time": "0:00:00"}
+{"current_steps": 217, "total_steps": 217, "epoch": 0.998849252013809, "percentage": 100.0, "elapsed_time": "1:10:01", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1561 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.998849252013809,
+  "eval_steps": 500,
+  "global_step": 217,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004602991944764097,
+      "grad_norm": 1.9528553485870361,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.5319,
+      "step": 1
+    },
+    {
+      "epoch": 0.009205983889528193,
+      "grad_norm": 1.8612775802612305,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.5107,
+      "step": 2
+    },
+    {
+      "epoch": 0.01380897583429229,
+      "grad_norm": 1.9053367376327515,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.5124,
+      "step": 3
+    },
+    {
+      "epoch": 0.018411967779056387,
+      "grad_norm": 1.76083505153656,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.536,
+      "step": 4
+    },
+    {
+      "epoch": 0.023014959723820484,
+      "grad_norm": 1.5051020383834839,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.492,
+      "step": 5
+    },
+    {
+      "epoch": 0.02761795166858458,
+      "grad_norm": 1.4977186918258667,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.5108,
+      "step": 6
+    },
+    {
+      "epoch": 0.03222094361334868,
+      "grad_norm": 1.1002470254898071,
+      "learning_rate": 5e-06,
+      "loss": 0.4918,
+      "step": 7
+    },
+    {
+      "epoch": 0.03682393555811277,
+      "grad_norm": 1.1534695625305176,
+      "learning_rate": 4.999720254525684e-06,
+      "loss": 0.4705,
+      "step": 8
+    },
+    {
+      "epoch": 0.04142692750287687,
+      "grad_norm": 1.756179928779602,
+      "learning_rate": 4.998881080708759e-06,
+      "loss": 0.4622,
+      "step": 9
+    },
+    {
+      "epoch": 0.04602991944764097,
+      "grad_norm": 1.7668858766555786,
+      "learning_rate": 4.997482666353287e-06,
+      "loss": 0.4538,
+      "step": 10
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 1.736067295074463,
+      "learning_rate": 4.995525324419338e-06,
+      "loss": 0.4832,
+      "step": 11
+    },
+    {
+      "epoch": 0.05523590333716916,
+      "grad_norm": 1.1255316734313965,
+      "learning_rate": 4.993009492952951e-06,
+      "loss": 0.443,
+      "step": 12
+    },
+    {
+      "epoch": 0.05983889528193326,
+      "grad_norm": 0.9772641658782959,
+      "learning_rate": 4.989935734988098e-06,
+      "loss": 0.4184,
+      "step": 13
+    },
+    {
+      "epoch": 0.06444188722669736,
+      "grad_norm": 0.7824466228485107,
+      "learning_rate": 4.986304738420684e-06,
+      "loss": 0.4166,
+      "step": 14
+    },
+    {
+      "epoch": 0.06904487917146145,
+      "grad_norm": 0.7207390666007996,
+      "learning_rate": 4.982117315854594e-06,
+      "loss": 0.4344,
+      "step": 15
+    },
+    {
+      "epoch": 0.07364787111622555,
+      "grad_norm": 0.7086092829704285,
+      "learning_rate": 4.977374404419838e-06,
+      "loss": 0.4281,
+      "step": 16
+    },
+    {
+      "epoch": 0.07825086306098965,
+      "grad_norm": 0.791322648525238,
+      "learning_rate": 4.9720770655628216e-06,
+      "loss": 0.4428,
+      "step": 17
+    },
+    {
+      "epoch": 0.08285385500575373,
+      "grad_norm": 0.674933671951294,
+      "learning_rate": 4.966226484808804e-06,
+      "loss": 0.4129,
+      "step": 18
+    },
+    {
+      "epoch": 0.08745684695051784,
+      "grad_norm": 0.615633487701416,
+      "learning_rate": 4.959823971496575e-06,
+      "loss": 0.4362,
+      "step": 19
+    },
+    {
+      "epoch": 0.09205983889528194,
+      "grad_norm": 0.656779944896698,
+      "learning_rate": 4.9528709584854316e-06,
+      "loss": 0.3944,
+      "step": 20
+    },
+    {
+      "epoch": 0.09666283084004602,
+      "grad_norm": 0.6281305551528931,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.4247,
+      "step": 21
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.6116930842399597,
+      "learning_rate": 4.937319780454559e-06,
+      "loss": 0.452,
+      "step": 22
+    },
+    {
+      "epoch": 0.10586881472957423,
+      "grad_norm": 0.5711112022399902,
+      "learning_rate": 4.9287250957321685e-06,
+      "loss": 0.4176,
+      "step": 23
+    },
+    {
+      "epoch": 0.11047180667433831,
+      "grad_norm": 0.5996497273445129,
+      "learning_rate": 4.919586871126667e-06,
+      "loss": 0.4235,
+      "step": 24
+    },
+    {
+      "epoch": 0.11507479861910241,
+      "grad_norm": 0.6450675129890442,
+      "learning_rate": 4.909907151739634e-06,
+      "loss": 0.4128,
+      "step": 25
+    },
+    {
+      "epoch": 0.11967779056386652,
+      "grad_norm": 0.6167646050453186,
+      "learning_rate": 4.899688103857223e-06,
+      "loss": 0.3971,
+      "step": 26
+    },
+    {
+      "epoch": 0.12428078250863062,
+      "grad_norm": 0.5306232571601868,
+      "learning_rate": 4.8889320144653525e-06,
+      "loss": 0.3675,
+      "step": 27
+    },
+    {
+      "epoch": 0.12888377445339472,
+      "grad_norm": 0.5794817209243774,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 0.4189,
+      "step": 28
+    },
+    {
+      "epoch": 0.1334867663981588,
+      "grad_norm": 0.5581746697425842,
+      "learning_rate": 4.865818459497911e-06,
+      "loss": 0.4309,
+      "step": 29
+    },
+    {
+      "epoch": 0.1380897583429229,
+      "grad_norm": 0.5573146939277649,
+      "learning_rate": 4.853466166652259e-06,
+      "loss": 0.4159,
+      "step": 30
+    },
+    {
+      "epoch": 0.142692750287687,
+      "grad_norm": 0.5848842859268188,
+      "learning_rate": 4.8405871765993435e-06,
+      "loss": 0.4043,
+      "step": 31
+    },
+    {
+      "epoch": 0.1472957422324511,
+      "grad_norm": 0.5522124767303467,
+      "learning_rate": 4.827184371610511e-06,
+      "loss": 0.4331,
+      "step": 32
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.542629063129425,
+      "learning_rate": 4.813260751184992e-06,
+      "loss": 0.4027,
+      "step": 33
+    },
+    {
+      "epoch": 0.1565017261219793,
+      "grad_norm": 0.6027759313583374,
+      "learning_rate": 4.7988194313786275e-06,
+      "loss": 0.4286,
+      "step": 34
+    },
+    {
+      "epoch": 0.1611047180667434,
+      "grad_norm": 0.5948846936225891,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.4334,
+      "step": 35
+    },
+    {
+      "epoch": 0.16570771001150747,
+      "grad_norm": 0.5355780720710754,
+      "learning_rate": 4.7683967364196624e-06,
+      "loss": 0.4004,
+      "step": 36
+    },
+    {
+      "epoch": 0.17031070195627157,
+      "grad_norm": 0.5100039839744568,
+      "learning_rate": 4.752422169756048e-06,
+      "loss": 0.4058,
+      "step": 37
+    },
+    {
+      "epoch": 0.17491369390103567,
+      "grad_norm": 0.5452431440353394,
+      "learning_rate": 4.735943519165843e-06,
+      "loss": 0.4199,
+      "step": 38
+    },
+    {
+      "epoch": 0.17951668584579977,
+      "grad_norm": 0.5305486917495728,
+      "learning_rate": 4.718964472511386e-06,
+      "loss": 0.3845,
+      "step": 39
+    },
+    {
+      "epoch": 0.18411967779056387,
+      "grad_norm": 0.5316929817199707,
+      "learning_rate": 4.701488829641845e-06,
+      "loss": 0.385,
+      "step": 40
+    },
+    {
+      "epoch": 0.18872266973532797,
+      "grad_norm": 0.5721151232719421,
+      "learning_rate": 4.683520501542825e-06,
+      "loss": 0.4199,
+      "step": 41
+    },
+    {
+      "epoch": 0.19332566168009205,
+      "grad_norm": 0.5623852610588074,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.393,
+      "step": 42
+    },
+    {
+      "epoch": 0.19792865362485615,
+      "grad_norm": 0.5426440238952637,
+      "learning_rate": 4.646121984004666e-06,
+      "loss": 0.4143,
+      "step": 43
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.5393860936164856,
+      "learning_rate": 4.626700164218349e-06,
+      "loss": 0.419,
+      "step": 44
+    },
+    {
+      "epoch": 0.20713463751438435,
+      "grad_norm": 0.5237355828285217,
+      "learning_rate": 4.606802396635098e-06,
+      "loss": 0.3802,
+      "step": 45
+    },
+    {
+      "epoch": 0.21173762945914845,
+      "grad_norm": 0.5436042547225952,
+      "learning_rate": 4.586433134303257e-06,
+      "loss": 0.4001,
+      "step": 46
+    },
+    {
+      "epoch": 0.21634062140391255,
+      "grad_norm": 0.5216776132583618,
+      "learning_rate": 4.565596935789987e-06,
+      "loss": 0.3838,
+      "step": 47
+    },
+    {
+      "epoch": 0.22094361334867663,
+      "grad_norm": 0.5988544821739197,
+      "learning_rate": 4.544298464161079e-06,
+      "loss": 0.4193,
+      "step": 48
+    },
+    {
+      "epoch": 0.22554660529344073,
+      "grad_norm": 0.5307754278182983,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.4008,
+      "step": 49
+    },
+    {
+      "epoch": 0.23014959723820483,
+      "grad_norm": 0.532762885093689,
+      "learning_rate": 4.500333870028017e-06,
+      "loss": 0.4135,
+      "step": 50
+    },
+    {
+      "epoch": 0.23475258918296893,
+      "grad_norm": 0.5370959639549255,
+      "learning_rate": 4.477677586640854e-06,
+      "loss": 0.4008,
+      "step": 51
+    },
+    {
+      "epoch": 0.23935558112773303,
+      "grad_norm": 0.5499489307403564,
+      "learning_rate": 4.454578706170075e-06,
+      "loss": 0.423,
+      "step": 52
+    },
+    {
+      "epoch": 0.24395857307249713,
+      "grad_norm": 0.5250299572944641,
+      "learning_rate": 4.431042398061499e-06,
+      "loss": 0.3918,
+      "step": 53
+    },
+    {
+      "epoch": 0.24856156501726123,
+      "grad_norm": 0.5530039668083191,
+      "learning_rate": 4.4070739296556665e-06,
+      "loss": 0.4121,
+      "step": 54
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.5588434934616089,
+      "learning_rate": 4.382678665009028e-06,
+      "loss": 0.4127,
+      "step": 55
+    },
+    {
+      "epoch": 0.25776754890678943,
+      "grad_norm": 0.5205167531967163,
+      "learning_rate": 4.357862063693486e-06,
+      "loss": 0.4041,
+      "step": 56
+    },
+    {
+      "epoch": 0.26237054085155354,
+      "grad_norm": 0.5239887833595276,
+      "learning_rate": 4.332629679574566e-06,
+      "loss": 0.3856,
+      "step": 57
+    },
+    {
+      "epoch": 0.2669735327963176,
+      "grad_norm": 0.527583122253418,
+      "learning_rate": 4.3069871595684795e-06,
+      "loss": 0.3868,
+      "step": 58
+    },
+    {
+      "epoch": 0.2715765247410817,
+      "grad_norm": 0.5135255455970764,
+      "learning_rate": 4.280940242378363e-06,
+      "loss": 0.3801,
+      "step": 59
+    },
+    {
+      "epoch": 0.2761795166858458,
+      "grad_norm": 0.5258612036705017,
+      "learning_rate": 4.2544947572099795e-06,
+      "loss": 0.3916,
+      "step": 60
+    },
+    {
+      "epoch": 0.2807825086306099,
+      "grad_norm": 0.5070046186447144,
+      "learning_rate": 4.227656622467162e-06,
+      "loss": 0.3729,
+      "step": 61
+    },
+    {
+      "epoch": 0.285385500575374,
+      "grad_norm": 0.5091351866722107,
+      "learning_rate": 4.200431844427299e-06,
+      "loss": 0.3743,
+      "step": 62
+    },
+    {
+      "epoch": 0.2899884925201381,
+      "grad_norm": 0.534995436668396,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 0.3639,
+      "step": 63
+    },
+    {
+      "epoch": 0.2945914844649022,
+      "grad_norm": 0.5401779413223267,
+      "learning_rate": 4.144846814849282e-06,
+      "loss": 0.3813,
+      "step": 64
+    },
+    {
+      "epoch": 0.2991944764096663,
+      "grad_norm": 0.5409132242202759,
+      "learning_rate": 4.116499003039499e-06,
+      "loss": 0.3792,
+      "step": 65
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.595007061958313,
+      "learning_rate": 4.087789424605447e-06,
+      "loss": 0.4266,
+      "step": 66
+    },
+    {
+      "epoch": 0.3084004602991945,
+      "grad_norm": 0.5434048771858215,
+      "learning_rate": 4.058724504646834e-06,
+      "loss": 0.3893,
+      "step": 67
+    },
+    {
+      "epoch": 0.3130034522439586,
+      "grad_norm": 0.5291695594787598,
+      "learning_rate": 4.029310747787516e-06,
+      "loss": 0.3922,
+      "step": 68
+    },
+    {
+      "epoch": 0.3176064441887227,
+      "grad_norm": 0.4903387129306793,
+      "learning_rate": 3.999554736719785e-06,
+      "loss": 0.3626,
+      "step": 69
+    },
+    {
+      "epoch": 0.3222094361334868,
+      "grad_norm": 0.5239253044128418,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.3702,
+      "step": 70
+    },
+    {
+      "epoch": 0.32681242807825084,
+      "grad_norm": 0.534202516078949,
+      "learning_rate": 3.939042664214185e-06,
+      "loss": 0.3826,
+      "step": 71
+    },
+    {
+      "epoch": 0.33141542002301494,
+      "grad_norm": 0.5841035842895508,
+      "learning_rate": 3.908300145159055e-06,
+      "loss": 0.4251,
+      "step": 72
+    },
+    {
+      "epoch": 0.33601841196777904,
+      "grad_norm": 0.5424667000770569,
+      "learning_rate": 3.8772424536302565e-06,
+      "loss": 0.391,
+      "step": 73
+    },
+    {
+      "epoch": 0.34062140391254314,
+      "grad_norm": 0.5215575098991394,
+      "learning_rate": 3.845876540226707e-06,
+      "loss": 0.4103,
+      "step": 74
+    },
+    {
+      "epoch": 0.34522439585730724,
+      "grad_norm": 0.5513401031494141,
+      "learning_rate": 3.8142094245262617e-06,
+      "loss": 0.3976,
+      "step": 75
+    },
+    {
+      "epoch": 0.34982738780207134,
+      "grad_norm": 0.5887762308120728,
+      "learning_rate": 3.782248193514766e-06,
+      "loss": 0.407,
+      "step": 76
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.533482015132904,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.3929,
+      "step": 77
+    },
+    {
+      "epoch": 0.35903337169159955,
+      "grad_norm": 0.5082557201385498,
+      "learning_rate": 3.7174720610109184e-06,
+      "loss": 0.3859,
+      "step": 78
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.538962721824646,
+      "learning_rate": 3.684671656182497e-06,
+      "loss": 0.3987,
+      "step": 79
+    },
+    {
+      "epoch": 0.36823935558112775,
+      "grad_norm": 0.5121095180511475,
+      "learning_rate": 3.6516061261265813e-06,
+      "loss": 0.3847,
+      "step": 80
+    },
+    {
+      "epoch": 0.37284234752589185,
+      "grad_norm": 0.5776516199111938,
+      "learning_rate": 3.6182828707890816e-06,
+      "loss": 0.3771,
+      "step": 81
+    },
+    {
+      "epoch": 0.37744533947065595,
+      "grad_norm": 0.5664410591125488,
+      "learning_rate": 3.5847093477938955e-06,
+      "loss": 0.382,
+      "step": 82
+    },
+    {
+      "epoch": 0.38204833141542005,
+      "grad_norm": 0.5202717781066895,
+      "learning_rate": 3.5508930707739143e-06,
+      "loss": 0.3608,
+      "step": 83
+    },
+    {
+      "epoch": 0.3866513233601841,
+      "grad_norm": 0.5437837243080139,
+      "learning_rate": 3.516841607689501e-06,
+      "loss": 0.4171,
+      "step": 84
+    },
+    {
+      "epoch": 0.3912543153049482,
+      "grad_norm": 0.5397577881813049,
+      "learning_rate": 3.4825625791348093e-06,
+      "loss": 0.3906,
+      "step": 85
+    },
+    {
+      "epoch": 0.3958573072497123,
+      "grad_norm": 0.5708394646644592,
+      "learning_rate": 3.4480636566323215e-06,
+      "loss": 0.3802,
+      "step": 86
+    },
+    {
+      "epoch": 0.4004602991944764,
+      "grad_norm": 0.5787578821182251,
+      "learning_rate": 3.4133525609159883e-06,
+      "loss": 0.3996,
+      "step": 87
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.596613347530365,
+      "learning_rate": 3.3784370602033572e-06,
+      "loss": 0.3938,
+      "step": 88
+    },
+    {
+      "epoch": 0.4096662830840046,
+      "grad_norm": 0.5240587592124939,
+      "learning_rate": 3.3433249684570757e-06,
+      "loss": 0.3798,
+      "step": 89
+    },
+    {
+      "epoch": 0.4142692750287687,
+      "grad_norm": 0.5174093842506409,
+      "learning_rate": 3.3080241436361505e-06,
+      "loss": 0.3804,
+      "step": 90
+    },
+    {
+      "epoch": 0.4188722669735328,
+      "grad_norm": 0.5353110432624817,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.3529,
+      "step": 91
+    },
+    {
+      "epoch": 0.4234752589182969,
+      "grad_norm": 0.5501390695571899,
+      "learning_rate": 3.236887936027261e-06,
+      "loss": 0.4038,
+      "step": 92
+    },
+    {
+      "epoch": 0.428078250863061,
+      "grad_norm": 0.5099984407424927,
+      "learning_rate": 3.201068473265007e-06,
+      "loss": 0.3755,
+      "step": 93
+    },
+    {
+      "epoch": 0.4326812428078251,
+      "grad_norm": 0.5678063035011292,
+      "learning_rate": 3.165092113916688e-06,
+      "loss": 0.386,
+      "step": 94
+    },
+    {
+      "epoch": 0.4372842347525892,
+      "grad_norm": 0.5758556723594666,
+      "learning_rate": 3.128966909361272e-06,
+      "loss": 0.413,
+      "step": 95
+    },
+    {
+      "epoch": 0.44188722669735325,
+      "grad_norm": 0.5315706729888916,
+      "learning_rate": 3.092700944288744e-06,
+      "loss": 0.3824,
+      "step": 96
+    },
+    {
+      "epoch": 0.44649021864211735,
+      "grad_norm": 0.5057752728462219,
+      "learning_rate": 3.056302334890786e-06,
+      "loss": 0.3582,
+      "step": 97
+    },
+    {
+      "epoch": 0.45109321058688145,
+      "grad_norm": 0.5494191646575928,
+      "learning_rate": 3.019779227044398e-06,
+      "loss": 0.389,
+      "step": 98
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.5015504360198975,
+      "learning_rate": 2.9831397944888833e-06,
+      "loss": 0.4077,
+      "step": 99
+    },
+    {
+      "epoch": 0.46029919447640966,
+      "grad_norm": 0.5424397587776184,
+      "learning_rate": 2.946392236996592e-06,
+      "loss": 0.4167,
+      "step": 100
+    },
+    {
+      "epoch": 0.46490218642117376,
+      "grad_norm": 0.526132345199585,
+      "learning_rate": 2.9095447785378446e-06,
+      "loss": 0.3941,
+      "step": 101
+    },
+    {
+      "epoch": 0.46950517836593786,
+      "grad_norm": 0.5486814379692078,
+      "learning_rate": 2.872605665440436e-06,
+      "loss": 0.3957,
+      "step": 102
+    },
+    {
+      "epoch": 0.47410817031070196,
+      "grad_norm": 0.5627570152282715,
+      "learning_rate": 2.835583164544139e-06,
+      "loss": 0.3898,
+      "step": 103
+    },
+    {
+      "epoch": 0.47871116225546606,
+      "grad_norm": 0.5162888765335083,
+      "learning_rate": 2.7984855613506107e-06,
+      "loss": 0.3785,
+      "step": 104
+    },
+    {
+      "epoch": 0.48331415420023016,
+      "grad_norm": 0.5262818932533264,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 0.3767,
+      "step": 105
+    },
+    {
+      "epoch": 0.48791714614499426,
+      "grad_norm": 0.5049371123313904,
+      "learning_rate": 2.724098272258584e-06,
+      "loss": 0.3817,
+      "step": 106
+    },
+    {
+      "epoch": 0.49252013808975836,
+      "grad_norm": 0.5545706748962402,
+      "learning_rate": 2.686825233966061e-06,
+      "loss": 0.4088,
+      "step": 107
+    },
+    {
+      "epoch": 0.49712313003452246,
+      "grad_norm": 0.5535576939582825,
+      "learning_rate": 2.649510384862586e-06,
+      "loss": 0.4014,
+      "step": 108
+    },
+    {
+      "epoch": 0.5017261219792866,
+      "grad_norm": 0.500004231929779,
+      "learning_rate": 2.6121620758762877e-06,
+      "loss": 0.3753,
+      "step": 109
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.5142732858657837,
+      "learning_rate": 2.5747886654234967e-06,
+      "loss": 0.3788,
+      "step": 110
+    },
+    {
+      "epoch": 0.5109321058688148,
+      "grad_norm": 0.5009371042251587,
+      "learning_rate": 2.5373985175381595e-06,
+      "loss": 0.3713,
+      "step": 111
+    },
+    {
+      "epoch": 0.5155350978135789,
+      "grad_norm": 0.5388939380645752,
+      "learning_rate": 2.5e-06,
+      "loss": 0.3991,
+      "step": 112
+    },
+    {
+      "epoch": 0.520138089758343,
+      "grad_norm": 0.5310930609703064,
+      "learning_rate": 2.4626014824618418e-06,
+      "loss": 0.3934,
+      "step": 113
+    },
+    {
+      "epoch": 0.5247410817031071,
+      "grad_norm": 0.522955596446991,
+      "learning_rate": 2.4252113345765045e-06,
+      "loss": 0.384,
+      "step": 114
+    },
+    {
+      "epoch": 0.5293440736478712,
+      "grad_norm": 0.5394883751869202,
+      "learning_rate": 2.3878379241237136e-06,
+      "loss": 0.4068,
+      "step": 115
+    },
+    {
+      "epoch": 0.5339470655926352,
+      "grad_norm": 0.5207949876785278,
+      "learning_rate": 2.3504896151374145e-06,
+      "loss": 0.3903,
+      "step": 116
+    },
+    {
+      "epoch": 0.5385500575373993,
+      "grad_norm": 0.544926643371582,
+      "learning_rate": 2.3131747660339396e-06,
+      "loss": 0.3914,
+      "step": 117
+    },
+    {
+      "epoch": 0.5431530494821634,
+      "grad_norm": 0.5148684978485107,
+      "learning_rate": 2.2759017277414165e-06,
+      "loss": 0.3669,
+      "step": 118
+    },
+    {
+      "epoch": 0.5477560414269275,
+      "grad_norm": 0.54156893491745,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.404,
+      "step": 119
+    },
+    {
+      "epoch": 0.5523590333716916,
+      "grad_norm": 0.5111318230628967,
+      "learning_rate": 2.2015144386493898e-06,
+      "loss": 0.3735,
+      "step": 120
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.5289490818977356,
+      "learning_rate": 2.1644168354558623e-06,
+      "loss": 0.3711,
+      "step": 121
+    },
+    {
+      "epoch": 0.5615650172612198,
+      "grad_norm": 0.5365771055221558,
+      "learning_rate": 2.1273943345595637e-06,
+      "loss": 0.4074,
+      "step": 122
+    },
+    {
+      "epoch": 0.5661680092059839,
+      "grad_norm": 0.5566303730010986,
+      "learning_rate": 2.090455221462156e-06,
+      "loss": 0.4354,
+      "step": 123
+    },
+    {
+      "epoch": 0.570771001150748,
+      "grad_norm": 0.5099798440933228,
+      "learning_rate": 2.053607763003409e-06,
+      "loss": 0.3841,
+      "step": 124
+    },
+    {
+      "epoch": 0.5753739930955121,
+      "grad_norm": 0.5596857070922852,
+      "learning_rate": 2.0168602055111175e-06,
+      "loss": 0.3855,
+      "step": 125
+    },
+    {
+      "epoch": 0.5799769850402762,
+      "grad_norm": 0.5068130493164062,
+      "learning_rate": 1.9802207729556023e-06,
+      "loss": 0.3629,
+      "step": 126
+    },
+    {
+      "epoch": 0.5845799769850403,
+      "grad_norm": 0.5307357907295227,
+      "learning_rate": 1.9436976651092143e-06,
+      "loss": 0.3741,
+      "step": 127
+    },
+    {
+      "epoch": 0.5891829689298044,
+      "grad_norm": 0.5442883372306824,
+      "learning_rate": 1.9072990557112567e-06,
+      "loss": 0.3913,
+      "step": 128
+    },
+    {
+      "epoch": 0.5937859608745685,
+      "grad_norm": 0.5069390535354614,
+      "learning_rate": 1.8710330906387288e-06,
+      "loss": 0.3686,
+      "step": 129
+    },
+    {
+      "epoch": 0.5983889528193326,
+      "grad_norm": 0.5523373484611511,
+      "learning_rate": 1.8349078860833125e-06,
+      "loss": 0.3757,
+      "step": 130
+    },
+    {
+      "epoch": 0.6029919447640967,
+      "grad_norm": 0.5090730786323547,
+      "learning_rate": 1.7989315267349936e-06,
+      "loss": 0.3639,
+      "step": 131
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.5404998660087585,
+      "learning_rate": 1.7631120639727396e-06,
+      "loss": 0.3849,
+      "step": 132
+    },
+    {
+      "epoch": 0.6121979286536249,
+      "grad_norm": 0.5424637794494629,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.3775,
+      "step": 133
+    },
+    {
+      "epoch": 0.616800920598389,
+      "grad_norm": 0.5275416374206543,
+      "learning_rate": 1.6919758563638506e-06,
+      "loss": 0.3715,
+      "step": 134
+    },
+    {
+      "epoch": 0.6214039125431531,
+      "grad_norm": 0.5071358680725098,
+      "learning_rate": 1.6566750315429254e-06,
+      "loss": 0.3685,
+      "step": 135
+    },
+    {
+      "epoch": 0.6260069044879172,
+      "grad_norm": 0.4969387352466583,
+      "learning_rate": 1.6215629397966432e-06,
+      "loss": 0.3526,
+      "step": 136
+    },
+    {
+      "epoch": 0.6306098964326813,
+      "grad_norm": 0.5176503658294678,
+      "learning_rate": 1.5866474390840126e-06,
+      "loss": 0.3862,
+      "step": 137
+    },
+    {
+      "epoch": 0.6352128883774454,
+      "grad_norm": 0.5372660160064697,
+      "learning_rate": 1.5519363433676794e-06,
+      "loss": 0.3885,
+      "step": 138
+    },
+    {
+      "epoch": 0.6398158803222095,
+      "grad_norm": 0.5269474387168884,
+      "learning_rate": 1.5174374208651913e-06,
+      "loss": 0.3759,
+      "step": 139
+    },
+    {
+      "epoch": 0.6444188722669736,
+      "grad_norm": 0.5645244121551514,
+      "learning_rate": 1.4831583923105e-06,
+      "loss": 0.4084,
+      "step": 140
+    },
+    {
+      "epoch": 0.6490218642117376,
+      "grad_norm": 0.5266773104667664,
+      "learning_rate": 1.4491069292260867e-06,
+      "loss": 0.3878,
+      "step": 141
+    },
+    {
+      "epoch": 0.6536248561565017,
+      "grad_norm": 0.5369369983673096,
+      "learning_rate": 1.415290652206105e-06,
+      "loss": 0.4166,
+      "step": 142
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.5402231216430664,
+      "learning_rate": 1.3817171292109182e-06,
+      "loss": 0.3803,
+      "step": 143
+    },
+    {
+      "epoch": 0.6628308400460299,
+      "grad_norm": 0.5421996116638184,
+      "learning_rate": 1.3483938738734197e-06,
+      "loss": 0.3696,
+      "step": 144
+    },
+    {
+      "epoch": 0.667433831990794,
+      "grad_norm": 0.5073113441467285,
+      "learning_rate": 1.3153283438175036e-06,
+      "loss": 0.3721,
+      "step": 145
+    },
+    {
+      "epoch": 0.6720368239355581,
+      "grad_norm": 0.5329331755638123,
+      "learning_rate": 1.2825279389890818e-06,
+      "loss": 0.3657,
+      "step": 146
+    },
+    {
+      "epoch": 0.6766398158803222,
+      "grad_norm": 0.5001095533370972,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.3682,
+      "step": 147
+    },
+    {
+      "epoch": 0.6812428078250863,
+      "grad_norm": 0.5310607552528381,
+      "learning_rate": 1.2177518064852348e-06,
+      "loss": 0.392,
+      "step": 148
+    },
+    {
+      "epoch": 0.6858457997698504,
+      "grad_norm": 0.5475272536277771,
+      "learning_rate": 1.185790575473738e-06,
+      "loss": 0.4002,
+      "step": 149
+    },
+    {
+      "epoch": 0.6904487917146145,
+      "grad_norm": 0.5163525342941284,
+      "learning_rate": 1.1541234597732947e-06,
+      "loss": 0.3925,
+      "step": 150
+    },
+    {
+      "epoch": 0.6950517836593786,
+      "grad_norm": 0.4944920539855957,
+      "learning_rate": 1.122757546369744e-06,
+      "loss": 0.3788,
+      "step": 151
+    },
+    {
+      "epoch": 0.6996547756041427,
+      "grad_norm": 0.5034787058830261,
+      "learning_rate": 1.0916998548409449e-06,
+      "loss": 0.3696,
+      "step": 152
+    },
+    {
+      "epoch": 0.7042577675489068,
+      "grad_norm": 0.5238296985626221,
+      "learning_rate": 1.0609573357858166e-06,
+      "loss": 0.3842,
+      "step": 153
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.5249406099319458,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.3879,
+      "step": 154
+    },
+    {
+      "epoch": 0.713463751438435,
+      "grad_norm": 0.5139413475990295,
+      "learning_rate": 1.0004452632802158e-06,
+      "loss": 0.3795,
+      "step": 155
+    },
+    {
+      "epoch": 0.7180667433831991,
+      "grad_norm": 0.49963629245758057,
+      "learning_rate": 9.70689252212484e-07,
+      "loss": 0.3702,
+      "step": 156
+    },
+    {
+      "epoch": 0.7226697353279632,
+      "grad_norm": 0.5272103548049927,
+      "learning_rate": 9.412754953531664e-07,
+      "loss": 0.3726,
+      "step": 157
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.4988826513290405,
+      "learning_rate": 9.122105753945532e-07,
+      "loss": 0.3764,
+      "step": 158
+    },
+    {
+      "epoch": 0.7318757192174914,
+      "grad_norm": 0.542015552520752,
+      "learning_rate": 8.835009969605013e-07,
+      "loss": 0.4064,
+      "step": 159
+    },
+    {
+      "epoch": 0.7364787111622555,
+      "grad_norm": 0.5293359756469727,
+      "learning_rate": 8.551531851507186e-07,
+      "loss": 0.3943,
+      "step": 160
+    },
+    {
+      "epoch": 0.7410817031070196,
+      "grad_norm": 0.4968125820159912,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 0.3727,
+      "step": 161
+    },
+    {
+      "epoch": 0.7456846950517837,
+      "grad_norm": 0.5024369955062866,
+      "learning_rate": 7.995681555727011e-07,
+      "loss": 0.3721,
+      "step": 162
+    },
+    {
+      "epoch": 0.7502876869965478,
+      "grad_norm": 0.5272569060325623,
+      "learning_rate": 7.723433775328385e-07,
+      "loss": 0.4127,
+      "step": 163
+    },
+    {
+      "epoch": 0.7548906789413119,
+      "grad_norm": 0.5185663104057312,
+      "learning_rate": 7.455052427900214e-07,
+      "loss": 0.3832,
+      "step": 164
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.5261924266815186,
+      "learning_rate": 7.190597576216385e-07,
+      "loss": 0.3804,
+      "step": 165
+    },
+    {
+      "epoch": 0.7640966628308401,
+      "grad_norm": 0.5177868008613586,
+      "learning_rate": 6.930128404315214e-07,
+      "loss": 0.3873,
+      "step": 166
+    },
+    {
+      "epoch": 0.7686996547756041,
+      "grad_norm": 0.5173397660255432,
+      "learning_rate": 6.673703204254348e-07,
+      "loss": 0.367,
+      "step": 167
+    },
+    {
+      "epoch": 0.7733026467203682,
+      "grad_norm": 0.5059581995010376,
+      "learning_rate": 6.421379363065142e-07,
+      "loss": 0.3738,
+      "step": 168
+    },
+    {
+      "epoch": 0.7779056386651323,
+      "grad_norm": 0.6127777695655823,
+      "learning_rate": 6.17321334990973e-07,
+      "loss": 0.3857,
+      "step": 169
+    },
+    {
+      "epoch": 0.7825086306098964,
+      "grad_norm": 0.5311411023139954,
+      "learning_rate": 5.929260703443337e-07,
+      "loss": 0.3903,
+      "step": 170
+    },
+    {
+      "epoch": 0.7871116225546605,
+      "grad_norm": 0.5173105597496033,
+      "learning_rate": 5.689576019385015e-07,
+      "loss": 0.3747,
+      "step": 171
+    },
+    {
+      "epoch": 0.7917146144994246,
+      "grad_norm": 0.5185012817382812,
+      "learning_rate": 5.454212938299256e-07,
+      "loss": 0.3778,
+      "step": 172
+    },
+    {
+      "epoch": 0.7963176064441887,
+      "grad_norm": 0.5253241658210754,
+      "learning_rate": 5.223224133591475e-07,
+      "loss": 0.3962,
+      "step": 173
+    },
+    {
+      "epoch": 0.8009205983889528,
+      "grad_norm": 0.5264940857887268,
+      "learning_rate": 4.996661299719846e-07,
+      "loss": 0.3891,
+      "step": 174
+    },
+    {
+      "epoch": 0.8055235903337169,
+      "grad_norm": 0.5051758289337158,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.3573,
+      "step": 175
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.5200861096382141,
+      "learning_rate": 4.5570153583892165e-07,
+      "loss": 0.3924,
+      "step": 176
+    },
+    {
+      "epoch": 0.8147295742232451,
+      "grad_norm": 0.5002381205558777,
+      "learning_rate": 4.344030642100133e-07,
+      "loss": 0.3797,
+      "step": 177
+    },
+    {
+      "epoch": 0.8193325661680092,
+      "grad_norm": 0.5222682952880859,
+      "learning_rate": 4.1356686569674344e-07,
+      "loss": 0.3688,
+      "step": 178
+    },
+    {
+      "epoch": 0.8239355581127733,
+      "grad_norm": 0.5002561807632446,
+      "learning_rate": 3.931976033649021e-07,
+      "loss": 0.3858,
+      "step": 179
+    },
+    {
+      "epoch": 0.8285385500575374,
+      "grad_norm": 0.5189615488052368,
+      "learning_rate": 3.732998357816514e-07,
+      "loss": 0.3782,
+      "step": 180
+    },
+    {
+      "epoch": 0.8331415420023015,
+      "grad_norm": 0.5137009620666504,
+      "learning_rate": 3.538780159953348e-07,
+      "loss": 0.3729,
+      "step": 181
+    },
+    {
+      "epoch": 0.8377445339470656,
+      "grad_norm": 0.533768892288208,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.3887,
+      "step": 182
+    },
+    {
+      "epoch": 0.8423475258918297,
+      "grad_norm": 0.5303562879562378,
+      "learning_rate": 3.164794984571759e-07,
+      "loss": 0.3734,
+      "step": 183
+    },
+    {
+      "epoch": 0.8469505178365938,
+      "grad_norm": 0.5147203803062439,
+      "learning_rate": 2.98511170358155e-07,
+      "loss": 0.3757,
+      "step": 184
+    },
+    {
+      "epoch": 0.8515535097813579,
+      "grad_norm": 0.487350732088089,
+      "learning_rate": 2.810355274886148e-07,
+      "loss": 0.3692,
+      "step": 185
+    },
+    {
+      "epoch": 0.856156501726122,
+      "grad_norm": 0.4838736057281494,
+      "learning_rate": 2.6405648083415835e-07,
+      "loss": 0.3469,
+      "step": 186
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.5008881092071533,
+      "learning_rate": 2.4757783024395244e-07,
+      "loss": 0.3714,
+      "step": 187
+    },
+    {
+      "epoch": 0.8653624856156502,
+      "grad_norm": 0.4887051582336426,
+      "learning_rate": 2.316032635803378e-07,
+      "loss": 0.3681,
+      "step": 188
+    },
+    {
+      "epoch": 0.8699654775604143,
+      "grad_norm": 0.521045446395874,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 0.3828,
+      "step": 189
+    },
+    {
+      "epoch": 0.8745684695051784,
+      "grad_norm": 0.5309224724769592,
+      "learning_rate": 2.0118056862137358e-07,
+      "loss": 0.3827,
+      "step": 190
+    },
+    {
+      "epoch": 0.8791714614499425,
+      "grad_norm": 0.5095206499099731,
+      "learning_rate": 1.8673924881500826e-07,
+      "loss": 0.3707,
+      "step": 191
+    },
+    {
+      "epoch": 0.8837744533947065,
+      "grad_norm": 0.49568819999694824,
+      "learning_rate": 1.7281562838948968e-07,
+      "loss": 0.3698,
+      "step": 192
+    },
+    {
+      "epoch": 0.8883774453394706,
+      "grad_norm": 0.48604169487953186,
+      "learning_rate": 1.59412823400657e-07,
+      "loss": 0.3597,
+      "step": 193
+    },
+    {
+      "epoch": 0.8929804372842347,
+      "grad_norm": 0.4996773898601532,
+      "learning_rate": 1.465338333477423e-07,
+      "loss": 0.3825,
+      "step": 194
+    },
+    {
+      "epoch": 0.8975834292289988,
+      "grad_norm": 0.4933512508869171,
+      "learning_rate": 1.3418154050208937e-07,
+      "loss": 0.3477,
+      "step": 195
+    },
+    {
+      "epoch": 0.9021864211737629,
+      "grad_norm": 0.5096411108970642,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 0.3609,
+      "step": 196
+    },
+    {
+      "epoch": 0.906789413118527,
+      "grad_norm": 0.5132354497909546,
+      "learning_rate": 1.1106798553464804e-07,
+      "loss": 0.3804,
+      "step": 197
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.5068391561508179,
+      "learning_rate": 1.0031189614277765e-07,
+      "loss": 0.372,
+      "step": 198
+    },
+    {
+      "epoch": 0.9159953970080552,
+      "grad_norm": 0.4996238350868225,
+      "learning_rate": 9.00928482603669e-08,
+      "loss": 0.3798,
+      "step": 199
+    },
+    {
+      "epoch": 0.9205983889528193,
+      "grad_norm": 0.5047898888587952,
+      "learning_rate": 8.041312887333396e-08,
+      "loss": 0.372,
+      "step": 200
+    },
+    {
+      "epoch": 0.9252013808975834,
+      "grad_norm": 0.500909686088562,
+      "learning_rate": 7.127490426783124e-08,
+      "loss": 0.3909,
+      "step": 201
+    },
+    {
+      "epoch": 0.9298043728423475,
+      "grad_norm": 0.5062527060508728,
+      "learning_rate": 6.268021954544095e-08,
+      "loss": 0.3921,
+      "step": 202
+    },
+    {
+      "epoch": 0.9344073647871116,
+      "grad_norm": 0.5464354753494263,
+      "learning_rate": 5.463099816548578e-08,
+      "loss": 0.4175,
+      "step": 203
+    },
+    {
+      "epoch": 0.9390103567318757,
+      "grad_norm": 0.4842507839202881,
+      "learning_rate": 4.712904151456865e-08,
+      "loss": 0.3589,
+      "step": 204
+    },
+    {
+      "epoch": 0.9436133486766398,
+      "grad_norm": 0.5234150290489197,
+      "learning_rate": 4.017602850342584e-08,
+      "loss": 0.3839,
+      "step": 205
+    },
+    {
+      "epoch": 0.9482163406214039,
+      "grad_norm": 0.5067636370658875,
+      "learning_rate": 3.377351519119665e-08,
+      "loss": 0.3901,
+      "step": 206
+    },
+    {
+      "epoch": 0.952819332566168,
+      "grad_norm": 0.48845621943473816,
+      "learning_rate": 2.7922934437178695e-08,
+      "loss": 0.3694,
+      "step": 207
+    },
+    {
+      "epoch": 0.9574223245109321,
+      "grad_norm": 0.5254659652709961,
+      "learning_rate": 2.262559558016325e-08,
+      "loss": 0.3935,
+      "step": 208
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.5244017839431763,
+      "learning_rate": 1.7882684145406616e-08,
+      "loss": 0.3797,
+      "step": 209
+    },
+    {
+      "epoch": 0.9666283084004603,
+      "grad_norm": 0.5155873894691467,
+      "learning_rate": 1.3695261579316776e-08,
+      "loss": 0.371,
+      "step": 210
+    },
+    {
+      "epoch": 0.9712313003452244,
+      "grad_norm": 0.4954945147037506,
+      "learning_rate": 1.006426501190233e-08,
+      "loss": 0.3671,
+      "step": 211
+    },
+    {
+      "epoch": 0.9758342922899885,
+      "grad_norm": 0.5454512238502502,
+      "learning_rate": 6.990507047049677e-09,
+      "loss": 0.3847,
+      "step": 212
+    },
+    {
+      "epoch": 0.9804372842347526,
+      "grad_norm": 0.5421791076660156,
+      "learning_rate": 4.474675580662113e-09,
+      "loss": 0.3857,
+      "step": 213
+    },
+    {
+      "epoch": 0.9850402761795167,
+      "grad_norm": 0.5033833980560303,
+      "learning_rate": 2.5173336467135266e-09,
+      "loss": 0.3734,
+      "step": 214
+    },
+    {
+      "epoch": 0.9896432681242808,
+      "grad_norm": 0.5605362057685852,
+      "learning_rate": 1.1189192912416935e-09,
+      "loss": 0.3936,
+      "step": 215
+    },
+    {
+      "epoch": 0.9942462600690449,
+      "grad_norm": 0.5034700632095337,
+      "learning_rate": 2.797454743164174e-10,
+      "loss": 0.3813,
+      "step": 216
+    },
+    {
+      "epoch": 0.998849252013809,
+      "grad_norm": 0.5011968016624451,
+      "learning_rate": 0.0,
+      "loss": 0.4095,
+      "step": 217
+    },
+    {
+      "epoch": 0.998849252013809,
+      "step": 217,
+      "total_flos": 2.9080852357930025e+18,
+      "train_loss": 0.39522024055230454,
+      "train_runtime": 4203.0638,
+      "train_samples_per_second": 13.229,
+      "train_steps_per_second": 0.052
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 217,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9080852357930025e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c51f92fa33a1a1be61855d97c8784970cf041079a5db1338dbd7f66be347a0
+size 7160