jialicheng/unlearn_ucf101_videomae-large_random_label_6_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: 0.3300
• Accuracy: 0.9256
• Test Accuracy: 0.9256
• Df Accuracy: 0.9239
• Unlearn Overall Accuracy: 0.5009
• Unlearn Time: 12868.6803

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	1.0	298	0.5062	0.9423	0.4680	0.4680	-1
No log	2.0	596	0.3504	0.9423	0.4892	0.4892	-1
No log	3.0	894	0.3300	0.9239	0.5009	0.5009	-1

Framework versions

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