learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.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	F1
1.5617	1.0	276	1.5414	0.4337	0.1590
1.5189	2.0	552	1.4909	0.4697	0.1881
1.4759	3.0	828	1.4480	0.4838	0.1948
1.4407	4.0	1104	1.4167	0.4913	0.1995
1.4147	5.0	1380	1.3995	0.4965	0.2061
1.3956	6.0	1656	1.3767	0.5046	0.2123
1.3795	7.0	1932	1.3666	0.5058	0.2141
1.3735	8.0	2208	1.3560	0.5071	0.2187
1.3678	9.0	2484	1.3515	0.5101	0.2214
1.3629	10.0	2760	1.3518	0.5085	0.2198

ttqdunggg/cls_10_backbone_100k_freeze_backbone_task1

cls_10_backbone_100k_freeze_backbone_task1