Padajno's picture
End of training
d98b596 verified
---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.82
---
<!-- 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: 1.0676
- Accuracy: 0.82
## 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: 4
- eval_batch_size: 4
- 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: 15
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.0002 | 1.0 | 225 | 2.0510 | 0.78 |
| 0.67 | 2.0 | 450 | 2.3754 | 0.77 |
| 0.0002 | 3.0 | 675 | 1.2463 | 0.83 |
| 0.0 | 4.0 | 900 | 1.4864 | 0.82 |
| 0.0001 | 5.0 | 1125 | 1.6275 | 0.8 |
| 0.0 | 6.0 | 1350 | 1.4957 | 0.84 |
| 0.0003 | 7.0 | 1575 | 1.4223 | 0.83 |
| 0.0001 | 8.0 | 1800 | 0.9586 | 0.89 |
| 0.0001 | 9.0 | 2025 | 1.4912 | 0.83 |
| 0.0001 | 10.0 | 2250 | 1.3005 | 0.83 |
| 0.0 | 11.0 | 2475 | 1.0646 | 0.83 |
| 0.0 | 12.0 | 2700 | 1.0408 | 0.84 |
| 0.0 | 13.0 | 2925 | 1.0233 | 0.84 |
| 0.0 | 14.0 | 3150 | 1.0709 | 0.83 |
| 0.0 | 15.0 | 3375 | 1.0676 | 0.82 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1