metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: CTC-based-finetuned-gtzan
results: []
CTC-based-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.7416
- 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 2.0707 | 1.0 | 57 | 2.0284 | 0.44 |
| 1.6357 | 2.0 | 114 | 1.5908 | 0.59 |
| 1.2311 | 3.0 | 171 | 1.2047 | 0.72 |
| 1.0721 | 4.0 | 228 | 1.0979 | 0.72 |
| 0.7338 | 5.0 | 285 | 0.9138 | 0.8 |
| 0.7419 | 6.0 | 342 | 0.8302 | 0.82 |
| 0.595 | 7.0 | 399 | 0.7976 | 0.81 |
| 0.5258 | 8.0 | 456 | 0.7662 | 0.8 |
| 0.4874 | 9.0 | 513 | 0.7442 | 0.82 |
| 0.4915 | 10.0 | 570 | 0.7416 | 0.83 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3