jialicheng/unlearn_ucf101_videomae-large_neggrad_10_42

ucf101_42

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

• Loss: -16.7255
• Accuracy: 0.0064
• Test Accuracy: 0.0064
• Df Accuracy: 0.0066
• Unlearn Overall Accuracy: 0.4999
• Unlearn Time: 5173.6167

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: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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	1.01	32	-16.7255	0.0066	0.4999	0.4999	-1
No log	2.01	64	-17.5466	0.0066	0.4999	0.4999	-1
No log	2.92	93	-17.7800	0.0066	0.4999	0.4999	-1

Framework versions

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