metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: my_awesome_mind_model
results: []
my_awesome_mind_model
This model is a fine-tuned version of facebook/wav2vec2-base on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6753
- Accuracy: 0.5818
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.678 | 0.99 | 39 | 0.6803 | 0.5730 |
| 0.6698 | 1.99 | 78 | 0.6785 | 0.5810 |
| 0.6622 | 2.99 | 117 | 0.6848 | 0.5746 |
| 0.6636 | 3.99 | 156 | 0.6748 | 0.5866 |
| 0.6464 | 4.99 | 195 | 0.6844 | 0.5650 |
| 0.6508 | 5.99 | 234 | 0.6758 | 0.5738 |
| 0.6385 | 6.99 | 273 | 0.6728 | 0.5738 |
| 0.6317 | 7.99 | 312 | 0.6737 | 0.5690 |
| 0.6279 | 8.99 | 351 | 0.6784 | 0.5722 |
| 0.6273 | 9.99 | 390 | 0.6753 | 0.5818 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2