learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
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
lr_scheduler_warmup_ratio: 0.06
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0715	1.0	1250	0.0952	0.8501	0.9106	0.8793	0.9759
0.0485	2.0	2500	0.0898	0.8887	0.9142	0.9013	0.9796
0.0562	3.0	3750	0.0815	0.8905	0.9197	0.9049	0.9805
0.0265	4.0	5000	0.0851	0.9034	0.9238	0.9135	0.9816
0.0253	5.0	6250	0.0872	0.9027	0.9261	0.9143	0.9816
0.0223	6.0	7500	0.0844	0.9089	0.9298	0.9192	0.9824
0.0208	7.0	8750	0.0880	0.9116	0.9280	0.9197	0.9821
0.0095	8.0	10000	0.0936	0.9064	0.9275	0.9168	0.9817
0.01	9.0	11250	0.0917	0.9089	0.9298	0.9192	0.9823
0.0113	10.0	12500	0.0922	0.9110	0.9285	0.9197	0.9825

AlexanderSid/dl2_hw2_task3

dl2_hw2_task3