metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ASBD_Augm
results: []
videomae-base-finetuned-ASBD_Augm
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: 1.0073
- Accuracy: 0.7647
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: 12
- eval_batch_size: 12
- 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: 1050
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0908 | 0.09 | 97 | 1.6048 | 0.2838 |
| 1.0824 | 1.09 | 194 | 1.0615 | 0.4459 |
| 0.4003 | 2.09 | 291 | 1.4701 | 0.6081 |
| 0.4568 | 3.09 | 388 | 2.2165 | 0.4595 |
| 0.133 | 4.09 | 485 | 2.0913 | 0.5135 |
| 0.07 | 5.09 | 582 | 1.7235 | 0.6081 |
| 0.018 | 6.09 | 679 | 1.8975 | 0.6622 |
| 0.0162 | 7.09 | 776 | 2.0286 | 0.6622 |
| 0.0019 | 8.09 | 873 | 2.0696 | 0.6486 |
| 0.0012 | 9.09 | 970 | 1.8754 | 0.6892 |
| 0.0042 | 10.08 | 1050 | 1.8898 | 0.6757 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3