metadata
library_name: transformers
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- Hoonvolution/hoons_music_data
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-hoon_music
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: Hoons music data
type: Hoonvolution/hoons_music_data
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.84375
distilhubert-finetuned-hoon_music
This model is a fine-tuned version of ntu-spml/distilhubert on the Hoons music data dataset. It achieves the following results on the evaluation set:
- Loss: 0.7307
- Accuracy: 0.8438
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 |
|---|---|---|---|---|
| 1.6265 | 1.0 | 298 | 1.7652 | 0.3792 |
| 0.9028 | 2.0 | 596 | 1.0772 | 0.6479 |
| 0.3958 | 3.0 | 894 | 0.7857 | 0.7812 |
| 0.2335 | 4.0 | 1192 | 0.5601 | 0.8521 |
| 0.1384 | 5.0 | 1490 | 0.8042 | 0.8229 |
| 0.0517 | 6.0 | 1788 | 0.7031 | 0.85 |
| 0.0025 | 7.0 | 2086 | 0.7261 | 0.8479 |
| 0.0018 | 8.0 | 2384 | 0.7103 | 0.85 |
| 0.0015 | 9.0 | 2682 | 0.7329 | 0.8458 |
| 0.0015 | 10.0 | 2980 | 0.7307 | 0.8438 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1