learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3444	0.5734	250	1.8315	0.6005
1.6084	1.1468	500	1.3722	0.6912
1.3134	1.7202	750	1.2174	0.7279
1.2049	2.2936	1000	1.1384	0.7589
1.1106	2.8670	1250	1.1195	0.7612
1.0872	3.4404	1500	1.1067	0.7623
1.0584	4.0138	1750	1.0888	0.7732
1.0103	4.5872	2000	1.0923	0.7715
1.0291	5.1606	2250	1.0798	0.7664
0.9996	5.7339	2500	1.0695	0.7750
0.9968	6.3073	2750	1.0799	0.7664
0.9800	6.8807	3000	1.0611	0.7750
0.9489	7.4541	3250	1.0626	0.7750
0.9542	8.0275	3500	1.0615	0.7790
0.9469	8.6009	3750	1.0603	0.7744
0.9380	9.1743	4000	1.0683	0.7767
0.9338	9.7477	4250	1.0636	0.7790

chiabingxuan/v2-heladepdet-bert-finetuned-classification

v2-heladepdet-bert-finetuned-classification