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: 0.9
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: 0.6062
- Accuracy: 0.9
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0776 | 1.0 | 113 | 1.9082 | 0.48 |
| 1.3768 | 2.0 | 226 | 1.3052 | 0.63 |
| 1.0741 | 3.0 | 339 | 0.9721 | 0.79 |
| 0.778 | 4.0 | 452 | 0.8452 | 0.76 |
| 0.6383 | 5.0 | 565 | 0.5935 | 0.85 |
| 0.3313 | 6.0 | 678 | 0.5947 | 0.81 |
| 0.3514 | 7.0 | 791 | 0.6064 | 0.8 |
| 0.0922 | 8.0 | 904 | 0.5759 | 0.81 |
| 0.1757 | 9.0 | 1017 | 0.4683 | 0.88 |
| 0.0496 | 10.0 | 1130 | 0.5958 | 0.86 |
| 0.0141 | 11.0 | 1243 | 0.5512 | 0.87 |
| 0.0345 | 12.0 | 1356 | 0.6297 | 0.86 |
| 0.0079 | 13.0 | 1469 | 0.6009 | 0.89 |
| 0.0072 | 14.0 | 1582 | 0.6069 | 0.9 |
| 0.007 | 15.0 | 1695 | 0.6062 | 0.9 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0