videomae-base-finetuned-ucf101-subset

This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5926
• Accuracy: 0.7895

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: 8
• eval_batch_size: 8
• 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: 228

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6882	0.1272	29	0.6387	0.7067
0.6162	1.1272	58	0.6825	0.6667
0.6925	2.1272	87	0.6619	0.6667
0.598	3.1272	116	0.6190	0.6667
0.5897	4.1272	145	0.6271	0.6667
0.6333	5.1272	174	0.6206	0.6667
0.5614	6.1272	203	0.6193	0.6667
0.6856	7.1096	228	0.6110	0.6667

Framework versions

• Transformers 4.42.4
• Pytorch 2.2.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1