videomae-base-finetuned-inhard-finetuned-inhard2-finetuned-inhard3
This model is a fine-tuned version of shossain11/videomae-base-finetuned-inhard-finetuned-inhard2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1820
- Accuracy: 0.6987
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: 2
- eval_batch_size: 2
- 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: 9580
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3379 | 0.2 | 1916 | 1.3811 | 0.6337 |
| 0.8188 | 1.2 | 3832 | 1.8435 | 0.5272 |
| 0.5813 | 2.2 | 5748 | 1.1628 | 0.7203 |
| 0.5712 | 3.2 | 7664 | 1.1364 | 0.6970 |
| 0.723 | 4.2 | 9580 | 1.0294 | 0.7303 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0