learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
3.3831	1.0	782	3.1762
3.2331	2.0	1564	3.0950
3.1663	3.0	2346	3.0554
3.1182	4.0	3128	3.0244
3.0858	5.0	3910	3.0027
3.0602	6.0	4692	2.9821
3.0327	7.0	5474	2.9641
3.0029	8.0	6256	2.9434
2.9907	9.0	7038	2.9522
2.9734	10.0	7820	2.9366
2.9647	11.0	8602	2.9265
2.9446	12.0	9384	2.9066
2.933	13.0	10166	2.9123
2.9191	14.0	10948	2.9052
2.9073	15.0	11730	2.8842
2.9006	16.0	12512	2.8813
2.9015	17.0	13294	2.9061
2.8936	18.0	14076	2.8910
2.889	19.0	14858	2.8867
2.8898	20.0	15640	2.8702

pkcktkksh98/distilbert-base-uncased-finetuned-wwm-imdb-pkcktkksh

distilbert-base-uncased-finetuned-wwm-imdb-pkcktkksh