learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 4
seed: 42
optimizer: Use 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: 20

Training Loss	Epoch	Step	Validation Loss
2.1171	1.0	868	2.1020
1.9553	2.0	1736	1.7631
1.8516	3.0	2604	1.5863
1.5528	4.0	3472	1.1517
1.0896	5.0	4340	0.8395
0.8676	6.0	5208	0.5463
0.813	7.0	6076	0.3515
0.9052	8.0	6944	0.2478
0.4102	9.0	7812	0.1674
0.4672	10.0	8680	0.1310
0.3296	11.0	9548	0.0990
0.364	12.0	10416	0.0778
0.1635	13.0	11284	0.0473
0.1695	14.0	12152	0.0223
0.0506	15.0	13020	0.0127
0.0004	16.0	13888	0.0088
0.0907	17.0	14756	0.0075
0.1488	18.0	15624	0.0001
0.0023	19.0	16492	0.0001
0.0004	20.0	17360	0.0001

jtatman/roberta-base-biomed-myers-briggs-classifier

roberta-base-biomed-myers-briggs-classifier