superb_ks_42
This model is a fine-tuned version of openai/whisper-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: -34.5401
- Accuracy: 0.0397
- Test Accuracy: 0.0397
- Df Accuracy: 0.0871
- Unlearn Overall Accuracy: 0.4763
- Unlearn Time: 1817.2761
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 | -34.5401 | 0.0871 | 0.4763 | 0.4763 | -1 |
| No log | 2.0 | 320 | -134.7059 | 0.0871 | 0.4763 | 0.4763 | -1 |
| No log | 3.0 | 480 | -261.1648 | 0.0871 | 0.4763 | 0.4763 | -1 |
| No log | 4.0 | 640 | -399.5732 | 0.0871 | 0.4763 | 0.4763 | -1 |
| No log | 5.0 | 800 | -537.6102 | 0.0871 | 0.4763 | 0.4763 | -1 |
| No log | 6.0 | 960 | -664.9000 | 0.0871 | 0.4763 | 0.4763 | -1 |
| -276.2742 | 7.0 | 1120 | -772.8525 | 0.0871 | 0.4763 | 0.4763 | -1 |
| -276.2742 | 8.0 | 1280 | -855.0079 | 0.0871 | 0.4763 | 0.4763 | -1 |
| -276.2742 | 9.0 | 1440 | -906.3054 | 0.0871 | 0.4763 | 0.4763 | -1 |
| -276.2742 | 10.0 | 1600 | -923.8580 | 0.0871 | 0.4763 | 0.4763 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2