metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: pratik33/distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.7625
pratik33/distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.7774
- Accuracy: 0.7625
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0699 | 1.0 | 75 | 2.0157 | 0.375 |
| 1.5657 | 2.0 | 150 | 1.4965 | 0.5775 |
| 1.3258 | 3.0 | 225 | 1.2250 | 0.6325 |
| 0.9701 | 4.0 | 300 | 1.0614 | 0.7175 |
| 0.9475 | 5.0 | 375 | 0.9632 | 0.725 |
| 0.8134 | 6.0 | 450 | 0.8347 | 0.7725 |
| 0.8038 | 7.0 | 525 | 0.8290 | 0.7575 |
| 0.3698 | 8.0 | 600 | 0.7886 | 0.775 |
| 0.4005 | 9.0 | 675 | 0.8095 | 0.7625 |
| 0.3392 | 10.0 | 750 | 0.7774 | 0.7625 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3