videomae-base-zhe2

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2914
• Accuracy: 0.8899

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 3020

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2517	0.0503	152	0.6275	0.7346
0.1811	1.0503	304	0.5874	0.7504
0.1583	2.0503	456	0.4959	0.7973
0.1164	3.0503	608	0.4979	0.8073
0.1101	4.0503	760	0.7060	0.8189
0.0187	5.0503	912	1.3802	0.7525
0.0409	6.0503	1064	1.0102	0.8025
0.0059	7.0503	1216	0.4607	0.8673
0.0162	8.0503	1368	0.3995	0.8689
0.04	9.0503	1520	0.2914	0.8899
0.0087	10.0503	1672	0.5509	0.8589
0.0414	11.0503	1824	1.1488	0.7973
0.0309	12.0503	1976	0.6293	0.8520
0.0465	13.0503	2128	0.7299	0.8499
0.0237	14.0503	2280	0.8618	0.8410
0.0192	15.0503	2432	0.6935	0.8552
0.0007	16.0503	2584	0.9183	0.8378
0.0009	17.0503	2736	0.8596	0.8447
0.04	18.0503	2888	0.7197	0.8594
0.0006	19.0437	3020	0.6732	0.8662

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1