|
--- |
|
license: apache-2.0 |
|
base_model: ntu-spml/distilhubert |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- acordes_completo |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distilhubert-finetuned-chorddetection2 |
|
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-chorddetection2 |
|
|
|
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the ChordStimation2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0000 |
|
- Accuracy: 1.0 |
|
|
|
## 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 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.4498 | 1.0 | 3025 | 0.4276 | 0.9367 | |
|
| 0.0007 | 2.0 | 6050 | 0.0389 | 0.9899 | |
|
| 0.119 | 3.0 | 9075 | 0.0704 | 0.9863 | |
|
| 0.0 | 4.0 | 12100 | 0.0000 | 1.0 | |
|
| 0.0 | 5.0 | 15125 | 0.0000 | 1.0 | |
|
| 0.0 | 6.0 | 18150 | 0.0004 | 1.0 | |
|
| 0.0 | 7.0 | 21175 | 0.0009 | 0.9998 | |
|
| 0.0 | 8.0 | 24200 | 0.0000 | 1.0 | |
|
| 0.0 | 9.0 | 27225 | 0.0000 | 1.0 | |
|
| 0.0 | 10.0 | 30250 | 0.0000 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
