vapari's picture
End of training
c77e838 verified
|
raw
history blame
2.49 kB
---
library_name: transformers
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: 0.7435897435897436
---
<!-- 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: 0.9861
- Accuracy: 0.7436
## 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: 10
- eval_batch_size: 10
- 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: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.1171 | 1.0 | 70 | 2.1232 | 0.2308 |
| 1.534 | 2.0 | 140 | 1.6014 | 0.5128 |
| 1.4328 | 3.0 | 210 | 1.2896 | 0.5641 |
| 0.8631 | 4.0 | 280 | 1.1275 | 0.5897 |
| 0.6448 | 5.0 | 350 | 1.0679 | 0.6667 |
| 0.482 | 6.0 | 420 | 0.8798 | 0.7051 |
| 0.2458 | 7.0 | 490 | 0.8290 | 0.7564 |
| 0.2264 | 8.0 | 560 | 0.8350 | 0.7564 |
| 0.1661 | 9.0 | 630 | 0.8284 | 0.7179 |
| 0.0286 | 10.0 | 700 | 0.9681 | 0.7179 |
| 0.0155 | 11.0 | 770 | 0.9861 | 0.7436 |
### Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0