learning_rate: 0.0001
train_batch_size: 128
eval_batch_size: 256
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
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	391	0.1738	0.9803	0.2135	0.2135	None
0.6028	2.0	782	0.1637	0.9763	0.2200	0.2200	None
0.5434	3.0	1173	0.1589	0.9777	0.2180	0.2180	None
0.5343	4.0	1564	0.1642	0.9767	0.2195	0.2195	None
0.5343	5.0	1955	0.1583	0.977	0.2190	0.2190	None
0.5066	6.0	2346	0.1572	0.9737	0.2243	0.2243	None
0.4904	7.0	2737	0.1539	0.9753	0.2217	0.2217	None
0.4804	8.0	3128	0.1606	0.974	0.2238	0.2238	None
0.4628	9.0	3519	0.1560	0.9747	0.2227	0.2227	None
0.4628	10.0	3910	0.1608	0.972	0.2269	0.2269	None

jialicheng/unlearn-so_cifar10_resnet-50_random_label_6_42

42