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: 0.82
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: 1.0646
- 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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 18
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0114 | 1.0 | 225 | 1.8491 | 0.5 |
| 1.1983 | 2.0 | 450 | 1.1911 | 0.68 |
| 1.1408 | 3.0 | 675 | 0.9290 | 0.72 |
| 0.7166 | 4.0 | 900 | 0.7200 | 0.78 |
| 0.5334 | 5.0 | 1125 | 0.7233 | 0.79 |
| 0.3294 | 6.0 | 1350 | 0.4989 | 0.83 |
| 0.2949 | 7.0 | 1575 | 0.5294 | 0.85 |
| 0.0067 | 8.0 | 1800 | 0.7724 | 0.83 |
| 0.0041 | 9.0 | 2025 | 0.8986 | 0.8 |
| 0.0049 | 10.0 | 2250 | 0.9146 | 0.83 |
| 0.0016 | 11.0 | 2475 | 0.8999 | 0.85 |
| 0.0013 | 12.0 | 2700 | 0.8947 | 0.86 |
| 0.0015 | 13.0 | 2925 | 0.9257 | 0.85 |
| 0.0009 | 14.0 | 3150 | 1.0211 | 0.82 |
| 0.0009 | 15.0 | 3375 | 0.9288 | 0.84 |
| 0.0008 | 16.0 | 3600 | 0.9672 | 0.82 |
| 0.0009 | 17.0 | 3825 | 1.0717 | 0.82 |
| 0.0756 | 18.0 | 4050 | 1.0646 | 0.82 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3