metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-large
tags:
- video-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ucf101_42
results: []
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: 0.3255
- Accuracy: 0.9403
- Test Accuracy: 0.9403
- Df Accuracy: 1.0
- Unlearn Overall Accuracy: 0.4701
- Unlearn Time: 11529.0707
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: 1.5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 274 | 0.3193 | 0.9996 | 0.4691 | 0.4691 | -1 |
| No log | 1.49 | 408 | 0.3255 | 1.0 | 0.4701 | 0.4701 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2