|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mydata-iau |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mydata-iau |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6711 |
|
- Accuracy: 0.5385 |
|
|
|
## 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: 8 |
|
- 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: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.697 | 1.0 | 7 | 0.6964 | 0.3846 | |
|
| 0.667 | 2.0 | 14 | 0.6996 | 0.3846 | |
|
| 0.6334 | 3.0 | 21 | 0.7151 | 0.3846 | |
|
| 0.6045 | 4.0 | 28 | 0.7357 | 0.3846 | |
|
| 0.6263 | 5.0 | 35 | 0.7421 | 0.3846 | |
|
| 0.549 | 6.0 | 42 | 0.7133 | 0.3846 | |
|
| 0.5676 | 7.0 | 49 | 0.7031 | 0.3846 | |
|
| 0.5625 | 8.0 | 56 | 0.7056 | 0.3846 | |
|
| 0.5074 | 9.0 | 63 | 0.6912 | 0.4615 | |
|
| 0.5372 | 10.0 | 70 | 0.6904 | 0.4615 | |
|
| 0.5103 | 11.0 | 77 | 0.6856 | 0.4615 | |
|
| 0.47 | 12.0 | 84 | 0.6895 | 0.4615 | |
|
| 0.4951 | 13.0 | 91 | 0.6855 | 0.4615 | |
|
| 0.4505 | 14.0 | 98 | 0.6744 | 0.5385 | |
|
| 0.4395 | 15.0 | 105 | 0.6711 | 0.5385 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.15.1 |
|
|
