<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilhubert-finetuned-AESDD
This model is a fine-tuned version of ntu-spml/distilhubert on the aesdd dataset. It achieves the following results on the evaluation set:
- Loss: 0.4389
- Accuracy: 0.9016
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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1249 | 1.0 | 68 | 1.1905 | 0.5082 |
| 0.7441 | 2.0 | 136 | 0.8850 | 0.6721 |
| 0.5941 | 3.0 | 204 | 0.6579 | 0.8361 |
| 0.4349 | 4.0 | 272 | 0.9638 | 0.6721 |
| 0.2612 | 5.0 | 340 | 0.5081 | 0.8689 |
| 0.1883 | 6.0 | 408 | 0.6223 | 0.8197 |
| 0.0978 | 7.0 | 476 | 0.4671 | 0.8689 |
| 0.0425 | 8.0 | 544 | 0.4338 | 0.8852 |
| 0.0264 | 9.0 | 612 | 0.4488 | 0.8525 |
| 0.0219 | 10.0 | 680 | 0.4389 | 0.9016 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.2
- Tokenizers 0.13.3
