learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Auc	Precision	Recall	F1	F1-macro	F1-micro	F1-weighted
0.4572	0.3870	2000	1.1618	0.604	0.59	0.567	0.823	0.671	0.587	0.604	0.585
0.4046	0.7740	4000	1.3086	0.607	0.589	0.572	0.792	0.665	0.595	0.607	0.594
0.3688	1.1610	6000	1.4375	0.612	0.599	0.579	0.772	0.662	0.604	0.612	0.603
0.3366	1.5480	8000	1.4779	0.615	0.598	0.581	0.774	0.664	0.607	0.615	0.606
0.3262	1.9350	10000	1.4898	0.617	0.605	0.581	0.791	0.67	0.607	0.617	0.606

adity12345/Biobert_combo_1-6lakh-8-8-4

Biobert_combo_1-6lakh-8-8-4