learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
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
lr_scheduler_warmup_ratio: 0.05
training_steps: 3825

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1202	0.0403	154	0.7870	0.5094
0.3578	1.0403	308	0.8519	0.6348
0.018	2.0403	462	1.1708	0.5423
0.0203	3.0403	616	0.8862	0.6144
0.0009	4.0403	770	0.7493	0.5972
0.0039	5.0403	924	1.5555	0.6176
0.001	6.0403	1078	1.5310	0.6050
0.0071	7.0403	1232	1.5412	0.6473
0.0175	8.0403	1386	0.6643	0.7132
3.7788	9.0403	1540	1.3061	0.6223
0.0062	10.0403	1694	1.5036	0.6191
0.0003	11.0403	1848	1.7545	0.6364
0.0058	12.0403	2002	1.8030	0.6332
0.0029	13.0403	2156	1.4761	0.6552
0.0024	14.0403	2310	1.7483	0.6661
0.0007	15.0403	2464	1.8897	0.6379
0.0027	16.0403	2618	1.6131	0.6442
0.001	17.0403	2772	1.5463	0.6379
0.0001	18.0403	2926	1.8986	0.6301

d2o2ji/videomae-base-finetuned-kisa-crime

videomae-base-finetuned-kisa-crime