learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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: linear
lr_scheduler_warmup_steps: 500
num_epochs: 16

Training Loss	Epoch	Step	Validation Loss
1.4448	0.8	500	1.3321
1.2908	1.6	1000	1.2269
1.2095	2.4	1500	1.1415
1.1719	3.2	2000	1.1189
1.1117	4.0	2500	1.0708
1.0734	4.8	3000	1.0739
1.0157	5.6	3500	1.0240
0.9984	6.4	4000	0.9927
0.9614	7.2	4500	0.9533
0.9567	8.0	5000	0.9564
0.9296	8.8	5500	0.9449
0.9035	9.6	6000	0.9122
0.8902	10.4	6500	0.9244
0.8459	11.2	7000	0.8759
0.8616	12.0	7500	0.9022
0.8317	12.8	8000	0.8729
0.8307	13.6	8500	0.8655
0.8296	14.4	9000	0.8614
0.8063	15.2	9500	0.8714
0.8185	16.0	10000	0.8713

colaguo/legalBERTclass16

legalBERTclass16