<!-- 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. -->
hubert-tiny-random-finetuned-gtzan
This model is a fine-tuned version of ybelkada/hubert-tiny-random on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.5950
- Accuracy: 0.38
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| 2.2739 | 1.0 | 450 | 2.2419 | 0.2 |
| 1.9553 | 2.0 | 900 | 2.0032 | 0.34 |
| 1.9284 | 3.0 | 1350 | 1.8883 | 0.34 |
| 1.7679 | 4.0 | 1800 | 1.8021 | 0.35 |
| 1.7378 | 5.0 | 2250 | 1.7266 | 0.39 |
| 1.9188 | 6.0 | 2700 | 1.7055 | 0.39 |
| 2.0909 | 7.0 | 3150 | 1.6855 | 0.35 |
| 1.3592 | 8.0 | 3600 | 1.6795 | 0.38 |
| 1.5726 | 9.0 | 4050 | 1.5932 | 0.37 |
| 1.634 | 10.0 | 4500 | 1.5950 | 0.38 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
