metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: audiofolder
type: audiofolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0
distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 5.7174
- Accuracy: 0.0
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.6861 | 1.0 | 61 | 5.7174 | 0.0 |
| 5.573 | 2.0 | 122 | 5.7429 | 0.0 |
| 5.4992 | 3.0 | 183 | 5.7735 | 0.0 |
| 5.3129 | 4.0 | 244 | 5.7965 | 0.0 |
| 5.3243 | 5.0 | 305 | 5.8150 | 0.0 |
| 5.2456 | 6.0 | 366 | 5.7999 | 0.0 |
| 4.8339 | 7.0 | 427 | 5.8090 | 0.0 |
| 5.0512 | 8.0 | 488 | 5.8288 | 0.0 |
| 4.7789 | 9.0 | 549 | 5.8143 | 0.0 |
| 5.1463 | 10.0 | 610 | 5.8238 | 0.0 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0