metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- accuracy
model-index:
- name: distilhubert2024-05-17
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: 0.9668892305748047
distilhubert2024-05-17
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: 0.1072
- Accuracy: 0.9669
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1976 | 1.0 | 371 | 0.1556 | 0.9544 |
| 0.1323 | 2.0 | 742 | 0.1298 | 0.9590 |
| 0.1066 | 3.0 | 1113 | 0.1125 | 0.9652 |
| 0.0843 | 4.0 | 1484 | 0.1164 | 0.9632 |
| 0.116 | 5.0 | 1855 | 0.1072 | 0.9669 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2