learning_rate: 0.000159
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 128
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
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.3834	0.9739	14	1.1666	0.5714	0.5553
1.0717	1.9478	28	0.9962	0.5952	0.5891
0.6143	2.9913	43	0.8219	0.7143	0.7228
0.4801	3.9652	57	0.8748	0.7143	0.7138
0.2112	4.9391	71	1.1275	0.6905	0.6878
0.1627	5.9826	86	1.2672	0.6905	0.6839
0.118	6.9565	100	1.4471	0.6429	0.6357
0.088	8.0	115	1.4548	0.7143	0.7149
0.0674	8.9739	129	1.4981	0.6905	0.6858
0.0715	9.7391	140	1.4867	0.7143	0.7126

maxg73872/biobert-v1.1-finetuned-medmcqa-2024-11-25-T17-12-23

biobert-v1.1-finetuned-medmcqa-2024-11-25-T17-12-23