learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	327	0.0271	0.8688	0.8590	0.8639	0.9916
0.0912	2.0	654	0.0196	0.8851	0.9370	0.9103	0.9942
0.0912	3.0	981	0.0177	0.9227	0.9283	0.9255	0.9953
0.012	4.0	1308	0.0178	0.9329	0.9387	0.9358	0.9957
0.0047	5.0	1635	0.0198	0.9340	0.9314	0.9327	0.9957
0.0047	6.0	1962	0.0191	0.9334	0.9435	0.9384	0.9960
0.0024	7.0	2289	0.0224	0.9426	0.9404	0.9415	0.9961
0.0014	8.0	2616	0.0223	0.9420	0.9466	0.9443	0.9963
0.0014	9.0	2943	0.0220	0.9344	0.9410	0.9377	0.9960
0.0009	10.0	3270	0.0221	0.9440	0.9449	0.9445	0.9963

luohuashijieyoufengjun/ner_based_ChineseModernBert

ner_based_ChineseModernBert