metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- boooooook/benben_demo
metrics:
- accuracy
model-index:
- name: boooooook/finetuned-bb
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: benben_demo
type: boooooook/benben_demo
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.8
boooooook/finetuned-bb
This model is a fine-tuned version of ntu-spml/distilhubert on the benben_demo dataset. It achieves the following results on the evaluation set:
- Loss: 0.4991
- Accuracy: 0.8
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: Use OptimizerNames.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 |
|---|---|---|---|---|
| 1.8883 | 1.0 | 124 | 1.8304 | 0.5182 |
| 1.1287 | 2.0 | 248 | 1.1052 | 0.7 |
| 0.897 | 3.0 | 372 | 0.7974 | 0.8182 |
| 0.7703 | 4.0 | 496 | 0.6288 | 0.8 |
| 0.6084 | 5.0 | 620 | 0.5731 | 0.8364 |
| 0.2206 | 6.0 | 744 | 0.5133 | 0.8455 |
| 0.1527 | 7.0 | 868 | 0.5248 | 0.8182 |
| 0.128 | 8.0 | 992 | 0.4986 | 0.8364 |
| 0.1382 | 9.0 | 1116 | 0.4998 | 0.8273 |
| 0.0664 | 10.0 | 1240 | 0.4991 | 0.8 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1