wav2vec_finetuning_output
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3368
- Accuracy: 0.5338
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 1.3588 | 1.0 | 203 | 1.3368 | 0.5338 |
| 1.2412 | 2.0 | 406 | 1.3360 | 0.5338 |
| 1.3518 | 3.0 | 609 | 1.3296 | 0.5314 |
| 1.3174 | 4.0 | 813 | 1.3107 | 0.5338 |
| 1.3107 | 4.99 | 1015 | 1.3112 | 0.5338 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
