open-ai-small-2
This model is a fine-tuned version of jadasdn/open-ai-small-1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3953
- Wer: 21.4497
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: 1e-05
- train_batch_size: 16
- 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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1941 | 2.0 | 1000 | 0.2854 | 21.5383 |
| 0.0212 | 4.0 | 2000 | 0.3384 | 18.9827 |
| 0.0032 | 6.0 | 3000 | 0.3801 | 20.4698 |
| 0.0015 | 8.0 | 4000 | 0.3953 | 21.4497 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0