<!-- 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 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.9313
- Accuracy: 0.8
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: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.8811 | 1.0 | 80 | 2.0238 | 0.28 |
1.6445 | 2.0 | 160 | 1.6893 | 0.4 |
1.0582 | 3.0 | 240 | 1.3643 | 0.56 |
1.0183 | 4.0 | 320 | 1.2927 | 0.68 |
0.6467 | 5.0 | 400 | 1.1429 | 0.68 |
0.7339 | 6.0 | 480 | 1.2844 | 0.58 |
0.3296 | 7.0 | 560 | 0.8439 | 0.76 |
0.3062 | 8.0 | 640 | 0.7416 | 0.78 |
0.2511 | 9.0 | 720 | 0.8426 | 0.8 |
0.1362 | 10.0 | 800 | 0.9313 | 0.8 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1