metadata
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: 0.85
distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6540
- 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: 7
- eval_batch_size: 7
- 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: 13
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.036 | 1.0 | 129 | 1.8621 | 0.54 |
| 1.272 | 2.0 | 258 | 1.2237 | 0.67 |
| 1.1092 | 3.0 | 387 | 0.9957 | 0.67 |
| 0.5955 | 4.0 | 516 | 0.8160 | 0.72 |
| 0.3345 | 5.0 | 645 | 0.6607 | 0.79 |
| 0.3451 | 6.0 | 774 | 0.7320 | 0.75 |
| 0.2405 | 7.0 | 903 | 0.4956 | 0.85 |
| 0.2242 | 8.0 | 1032 | 0.6112 | 0.81 |
| 0.0447 | 9.0 | 1161 | 0.6542 | 0.82 |
| 0.0194 | 10.0 | 1290 | 0.7455 | 0.84 |
| 0.0122 | 11.0 | 1419 | 0.6341 | 0.85 |
| 0.0119 | 12.0 | 1548 | 0.6671 | 0.84 |
| 0.0107 | 13.0 | 1677 | 0.6540 | 0.85 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3