nsanghi's picture
update model card README.md
358e566
|
raw
history blame
1.97 kB
---
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: 0.5885
- Accuracy: 0.85
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.7525 | 1.0 | 113 | 1.8449 | 0.45 |
| 1.1831 | 2.0 | 226 | 1.2524 | 0.68 |
| 1.0426 | 3.0 | 339 | 0.9258 | 0.74 |
| 0.7915 | 4.0 | 452 | 0.8108 | 0.78 |
| 0.3659 | 5.0 | 565 | 0.6440 | 0.84 |
| 0.3221 | 6.0 | 678 | 0.6358 | 0.8 |
| 0.2171 | 7.0 | 791 | 0.6422 | 0.82 |
| 0.2947 | 8.0 | 904 | 0.5890 | 0.85 |
| 0.1494 | 9.0 | 1017 | 0.5541 | 0.86 |
| 0.1633 | 10.0 | 1130 | 0.5885 | 0.85 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3