superb_ks_42
This model is a fine-tuned version of openai/whisper-tiny on the superb dataset. It achieves the following results on the evaluation set:
- Loss: -15.9675
- Accuracy: 0.6209
- Test Accuracy: 0.6209
- Df Accuracy: 0.1405
- Unlearn Overall Accuracy: 0.7402
- Unlearn Time: 895.7547
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: 32
- 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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 160 | -15.9675 | 0.1405 | 0.7402 | 0.7402 | -1 |
| No log | 2.0 | 320 | -54.9508 | 0.1405 | 0.7402 | 0.7402 | -1 |
| No log | 3.0 | 480 | -102.3320 | 0.1405 | 0.7402 | 0.7402 | -1 |
| No log | 4.0 | 640 | -152.6219 | 0.1405 | 0.7402 | 0.7402 | -1 |
| No log | 5.0 | 800 | -201.8462 | 0.1405 | 0.7402 | 0.7402 | -1 |
| No log | 6.0 | 960 | -246.6915 | 0.1405 | 0.7402 | 0.7402 | -1 |
| -257.0104 | 7.0 | 1120 | -284.5345 | 0.1405 | 0.7402 | 0.7402 | -1 |
| -257.0104 | 8.0 | 1280 | -313.1969 | 0.1405 | 0.7402 | 0.7402 | -1 |
| -257.0104 | 9.0 | 1440 | -331.0823 | 0.1405 | 0.7402 | 0.7402 | -1 |
| -257.0104 | 10.0 | 1600 | -337.1996 | 0.1405 | 0.7402 | 0.7402 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2