metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- kim2024military
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-MAD
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: MAD
type: kim2024military
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8900675024108003
distilhubert-finetuned-MAD
This model is a fine-tuned version of ntu-spml/distilhubert on the MAD dataset. It achieves the following results on the evaluation set:
- Loss: 1.6123
- Accuracy: 0.8901
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 0.624 | 1.0 | 402 | 0.6450 | 0.8245 |
| 0.425 | 2.0 | 804 | 0.4776 | 0.8708 |
| 0.0852 | 3.0 | 1206 | 0.5281 | 0.8698 |
| 0.2255 | 4.0 | 1608 | 0.7678 | 0.8650 |
| 0.0522 | 5.0 | 2010 | 1.0425 | 0.8814 |
| 0.2029 | 6.0 | 2412 | 1.3518 | 0.8930 |
| 0.0206 | 7.0 | 2814 | 1.5771 | 0.8939 |
| 0.0 | 8.0 | 3216 | 1.5804 | 0.8872 |
| 0.2069 | 9.0 | 3618 | 1.6365 | 0.8891 |
| 0.1882 | 10.0 | 4020 | 1.6123 | 0.8901 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3