metadata
license: apache-2.0
base_model: NemesisAlm/distilhubert-finetuned-gtzan
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan-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: 0.79
distilhubert-finetuned-gtzan-finetuned-gtzan
This model is a fine-tuned version of NemesisAlm/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.5928
- Accuracy: 0.79
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 |
|---|---|---|---|---|
| 0.1339 | 1.0 | 113 | 1.6467 | 0.79 |
| 0.0007 | 2.0 | 226 | 2.1081 | 0.75 |
| 0.1041 | 3.0 | 339 | 1.7809 | 0.77 |
| 0.0059 | 4.0 | 452 | 1.6295 | 0.8 |
| 0.0001 | 5.0 | 565 | 1.7973 | 0.8 |
| 0.0002 | 6.0 | 678 | 1.3648 | 0.82 |
| 0.0001 | 7.0 | 791 | 1.6571 | 0.77 |
| 0.0001 | 8.0 | 904 | 1.5916 | 0.77 |
| 0.0001 | 9.0 | 1017 | 1.5782 | 0.79 |
| 0.0001 | 10.0 | 1130 | 1.5928 | 0.79 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3