jialicheng/unlearn_ucf101_videomae-base_bad_teaching_2_42

ucf101_42

This model is a fine-tuned version of MCG-NJU/videomae-base on the ucf101 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9081
• Accuracy: 0.7916
• Test Accuracy: 0.7916
• Df Accuracy: 0.9715
• Unlearn Overall Accuracy: 0.4101
• Unlearn Time: 1384.8440

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: 4
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.1	14	0.9686	0.9665	0.4066	0.4066	-1
No log	2.14	29	0.9081	0.9715	0.4101	0.4101	-1
No log	2.55	36	0.9118	0.9715	0.4098	0.4098	-1

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2