metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-RHD_Dataset
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: 0.8048780487804879
distilhubert-finetuned-RHD_Dataset
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: 0.9447
- Accuracy: 0.8049
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: 0.0001
- 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 |
|---|---|---|---|---|
| 1.0412 | 1.0 | 46 | 1.0084 | 0.6829 |
| 0.8547 | 2.0 | 92 | 0.8433 | 0.6585 |
| 0.7936 | 3.0 | 138 | 0.7128 | 0.7073 |
| 0.5984 | 4.0 | 184 | 0.7778 | 0.7317 |
| 0.3888 | 5.0 | 230 | 0.6361 | 0.7317 |
| 0.4947 | 6.0 | 276 | 0.7471 | 0.7805 |
| 0.1663 | 7.0 | 322 | 0.8244 | 0.7561 |
| 0.1379 | 8.0 | 368 | 0.7986 | 0.8049 |
| 0.0405 | 9.0 | 414 | 0.8892 | 0.8049 |
| 0.0229 | 10.0 | 460 | 0.9447 | 0.8049 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0