learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
0.6744	0.1792	50	0.6652	0.599	0.807	0.599	1.0	0.749	0.375	0.599	0.448
0.5797	0.3584	100	0.5099	0.755	0.84	0.757	0.872	0.81	0.733	0.755	0.748
0.4858	0.5376	150	0.4505	0.803	0.869	0.868	0.791	0.827	0.798	0.803	0.804
0.5104	0.7168	200	0.4649	0.784	0.887	0.894	0.725	0.801	0.782	0.784	0.786
0.445	0.8961	250	0.4417	0.807	0.882	0.835	0.846	0.84	0.799	0.807	0.807
0.4286	1.0753	300	0.4460	0.809	0.891	0.889	0.777	0.83	0.806	0.809	0.811
0.4057	1.2545	350	0.4269	0.828	0.89	0.818	0.916	0.864	0.814	0.828	0.824
0.3708	1.4337	400	0.4229	0.828	0.901	0.816	0.919	0.865	0.814	0.828	0.824
0.3363	1.6129	450	0.4221	0.829	0.905	0.874	0.835	0.854	0.824	0.829	0.83
0.3793	1.7921	500	0.4110	0.835	0.906	0.879	0.84	0.859	0.83	0.835	0.836
0.3598	1.9713	550	0.4039	0.831	0.909	0.859	0.859	0.859	0.824	0.831	0.831

adity12345/Roberta_vaxculture

Roberta_vaxculture