videomae-base-finetuned-ucf101-subset

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

• Loss: 1.1801
• Accuracy: 0.5412

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: 4920

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3212	0.0502	247	0.5765	0.7898
0.3799	1.0502	494	0.4347	0.8042
0.1638	2.0502	741	0.6744	0.6560
0.1194	3.0502	988	0.3914	0.8500
0.2124	4.0502	1235	0.8541	0.7002
0.0289	5.0502	1482	2.8893	0.5087
0.0909	6.0502	1729	1.3700	0.6822
0.0729	7.0502	1976	1.4459	0.6671
0.0122	8.0502	2223	1.9108	0.6382
0.0269	9.0502	2470	2.4835	0.5734
0.0659	10.0502	2717	2.8008	0.6112
0.0371	11.0502	2964	2.7996	0.5996
0.1188	12.0502	3211	2.8353	0.6063
0.0203	13.0502	3458	2.1282	0.6544
0.053	14.0502	3705	2.5461	0.6431
0.0006	15.0502	3952	2.9020	0.6257
0.0365	16.0502	4199	3.0216	0.5914
0.0005	17.0502	4446	2.8913	0.6036
0.0003	18.0502	4693	2.9041	0.6098
0.0003	19.0461	4920	2.9829	0.6028

Framework versions

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