videomae-base-finetuned-movienet-finetuned-movienet-more
This model is a fine-tuned version of dvs/videomae-base-finetuned-movienet on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6822
- Accuracy: 0.7917
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: 8
- eval_batch_size: 8
- 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: 1480
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4977 | 0.13 | 186 | 0.8210 | 0.7234 |
| 0.3974 | 1.13 | 372 | 0.6322 | 0.8085 |
| 0.1101 | 2.13 | 558 | 1.0522 | 0.75 |
| 0.1618 | 3.13 | 744 | 0.9185 | 0.7872 |
| 0.0052 | 4.13 | 930 | 0.8586 | 0.8085 |
| 0.0013 | 5.13 | 1116 | 1.0029 | 0.7926 |
| 0.0044 | 6.13 | 1302 | 1.0400 | 0.7872 |
| 0.0008 | 7.12 | 1480 | 1.0018 | 0.7979 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3