videomae-base-finetuned-sphar

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: 0.9060
• Accuracy: 0.7428

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: 2
• eval_batch_size: 2
• 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: 3752

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1838	0.2463	924	1.1104	0.7292
1.0275	1.2463	1848	0.9165	0.7214
0.6294	2.2463	2772	0.9556	0.7409
1.2754	3.2463	3696	0.9022	0.7444
0.6501	4.0149	3752	0.9060	0.7428

Framework versions

• Transformers 4.41.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1