learning_rate: 0.0005
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.9593	1.0	125	1.9856	0.3604	0.4074	0.3494	0.3418
1.7366	2.0	250	1.9730	0.4004	0.4294	0.3887	0.3687
1.6263	3.0	375	1.6785	0.4585	0.4611	0.4575	0.4397
1.3865	4.0	500	1.5892	0.5085	0.5101	0.4932	0.4907
1.4461	5.0	625	1.4895	0.5355	0.5539	0.5294	0.5244
1.1613	6.0	750	1.3479	0.5676	0.5793	0.5606	0.5578
1.0639	7.0	875	1.3396	0.5686	0.5657	0.5643	0.5563
1.0971	8.0	1000	1.1978	0.6096	0.6117	0.6021	0.5991
0.7975	9.0	1125	1.1968	0.6206	0.6143	0.6152	0.6091
0.7041	10.0	1250	1.1409	0.6466	0.6466	0.6439	0.6402

zkdeng/10-vit-mae-base-finetuned-spiderTraining20-500

10-vit-mae-base-finetuned-spiderTraining20-500