|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilhubert-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. --> |
|
|
|
# distilhubert-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7463 |
|
- 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.9408 | 1.0 | 113 | 1.9838 | 0.43 | |
|
| 1.2842 | 2.0 | 226 | 1.2837 | 0.67 | |
|
| 1.0008 | 3.0 | 339 | 0.9786 | 0.74 | |
|
| 0.656 | 4.0 | 452 | 0.7425 | 0.83 | |
|
| 0.39 | 5.0 | 565 | 0.5993 | 0.82 | |
|
| 0.2612 | 6.0 | 678 | 0.6584 | 0.8 | |
|
| 0.1779 | 7.0 | 791 | 0.5676 | 0.81 | |
|
| 0.1512 | 8.0 | 904 | 0.9030 | 0.76 | |
|
| 0.093 | 9.0 | 1017 | 0.7049 | 0.85 | |
|
| 0.0355 | 10.0 | 1130 | 0.7865 | 0.82 | |
|
| 0.0111 | 11.0 | 1243 | 0.7816 | 0.83 | |
|
| 0.0088 | 12.0 | 1356 | 0.7861 | 0.82 | |
|
| 0.0073 | 13.0 | 1469 | 0.7535 | 0.84 | |
|
| 0.007 | 14.0 | 1582 | 0.7547 | 0.83 | |
|
| 0.0063 | 15.0 | 1695 | 0.7463 | 0.83 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|