|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base-finetuned-gtzan |
|
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. --> |
|
|
|
# wav2vec2-base-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8270 |
|
- Accuracy: 0.83 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.0547 | 0.99 | 56 | 2.0066 | 0.45 | |
|
| 1.7392 | 2.0 | 113 | 1.5974 | 0.57 | |
|
| 1.5689 | 2.99 | 169 | 1.4470 | 0.59 | |
|
| 1.2626 | 4.0 | 226 | 1.2541 | 0.66 | |
|
| 1.1188 | 4.99 | 282 | 1.2458 | 0.65 | |
|
| 0.9776 | 6.0 | 339 | 0.9830 | 0.75 | |
|
| 0.9396 | 6.99 | 395 | 0.8980 | 0.74 | |
|
| 0.8677 | 8.0 | 452 | 0.8398 | 0.8 | |
|
| 0.8194 | 8.99 | 508 | 0.7868 | 0.82 | |
|
| 0.7274 | 9.91 | 560 | 0.8270 | 0.83 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
