|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- marsyas/gtzan |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: hubert-large-ls960-ft-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. --> |
|
|
|
# hubert-large-ls960-ft-finetuned-gtzan |
|
|
|
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the GTZAN dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: nan |
|
- Accuracy: 0.86 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.2625 | 1.0 | 56 | 2.2399 | 0.23 | |
|
| 1.7887 | 1.99 | 112 | 1.7278 | 0.4 | |
|
| 1.4728 | 2.99 | 168 | 1.4387 | 0.48 | |
|
| 1.1536 | 4.0 | 225 | 1.3178 | 0.54 | |
|
| 1.0758 | 5.0 | 281 | 1.1903 | 0.6 | |
|
| 0.9742 | 5.99 | 337 | 0.8416 | 0.72 | |
|
| 0.8285 | 6.99 | 393 | 0.5875 | 0.78 | |
|
| 0.7953 | 8.0 | 450 | 0.7786 | 0.75 | |
|
| 0.6224 | 9.0 | 506 | 0.6753 | 0.8 | |
|
| 0.3806 | 9.99 | 562 | 0.5826 | 0.84 | |
|
| 0.3121 | 10.99 | 618 | 0.7312 | 0.78 | |
|
| 0.1729 | 12.0 | 675 | 0.6526 | 0.85 | |
|
| 0.2958 | 13.0 | 731 | 0.7831 | 0.83 | |
|
| 0.1496 | 13.99 | 787 | 0.8518 | 0.79 | |
|
| 0.0659 | 14.99 | 843 | 0.8194 | 0.82 | |
|
| 0.1208 | 16.0 | 900 | 0.8555 | 0.82 | |
|
| 0.147 | 17.0 | 956 | 0.6768 | 0.86 | |
|
| 0.0284 | 17.99 | 1012 | 0.7065 | 0.86 | |
|
| 0.0295 | 18.99 | 1068 | 0.6942 | 0.87 | |
|
| 0.0524 | 19.91 | 1120 | nan | 0.86 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
