metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: laryngitis-iau
results: []
laryngitis-iau
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5821
- Accuracy: 0.7727
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: 16
- eval_batch_size: 16
- 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6819 | 1.0 | 6 | 0.6926 | 0.5 |
| 0.6668 | 2.0 | 12 | 0.6997 | 0.3636 |
| 0.6168 | 3.0 | 18 | 0.6912 | 0.6364 |
| 0.5771 | 4.0 | 24 | 0.7330 | 0.6818 |
| 0.5231 | 5.0 | 30 | 0.6736 | 0.6818 |
| 0.474 | 6.0 | 36 | 0.6570 | 0.7273 |
| 0.4029 | 7.0 | 42 | 0.5917 | 0.7273 |
| 0.3747 | 8.0 | 48 | 0.5627 | 0.7273 |
| 0.3115 | 9.0 | 54 | 0.5429 | 0.7273 |
| 0.2836 | 10.0 | 60 | 0.6073 | 0.7727 |
| 0.214 | 11.0 | 66 | 0.4841 | 0.7273 |
| 0.1808 | 12.0 | 72 | 0.5193 | 0.8182 |
| 0.1979 | 13.0 | 78 | 0.5541 | 0.8182 |
| 0.1477 | 14.0 | 84 | 0.5782 | 0.7727 |
| 0.1348 | 15.0 | 90 | 0.5821 | 0.7727 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.12.0
- Tokenizers 0.15.1