learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
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: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.3234	0.2867	250	1.1322	0.4828
1.0071	0.5734	500	0.8364	0.6016
0.8471	0.8601	750	0.7494	0.6251
0.7557	1.1468	1000	0.7120	0.6447
0.7137	1.4335	1250	0.6895	0.6567
0.6944	1.7202	1500	0.6622	0.6705
0.6728	2.0069	1750	0.6579	0.6573
0.6648	2.2936	2000	0.6464	0.6716
0.6472	2.5803	2250	0.6320	0.6716
0.6261	2.8670	2500	0.6269	0.6716
0.6482	3.1537	2750	0.6214	0.6780
0.6327	3.4404	3000	0.6196	0.6762
0.6220	3.7271	3250	0.6163	0.7009
0.5996	4.0138	3500	0.6171	0.6762
0.6033	4.3005	3750	0.6135	0.6774
0.6108	4.5872	4000	0.6121	0.6900
0.6350	4.8739	4250	0.6113	0.6866

chiabingxuan/heladepdet-bert-finetuned-classification

heladepdet-bert-finetuned-classification