metadata
license: apache-2.0
base_model: arshsin/distilhubert-finetuned-gtzan
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: 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: 0.84
distilhubert-finetuned-gtzan
This model is a fine-tuned version of arshsin/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.6457
- Accuracy: 0.84
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0001 | 0.99 | 56 | 1.4113 | 0.84 |
| 0.0001 | 2.0 | 113 | 1.4248 | 0.84 |
| 0.0001 | 2.99 | 169 | 1.4818 | 0.83 |
| 0.0001 | 4.0 | 226 | 1.5228 | 0.83 |
| 0.0001 | 4.99 | 282 | 1.5067 | 0.84 |
| 0.0032 | 6.0 | 339 | 1.5205 | 0.84 |
| 0.0 | 6.99 | 395 | 1.5488 | 0.84 |
| 0.0 | 8.0 | 452 | 1.5890 | 0.84 |
| 0.0 | 8.99 | 508 | 1.6020 | 0.83 |
| 0.0117 | 10.0 | 565 | 1.5945 | 0.84 |
| 0.0 | 10.99 | 621 | 1.6145 | 0.84 |
| 0.0 | 12.0 | 678 | 1.6370 | 0.83 |
| 0.0 | 12.99 | 734 | 1.6396 | 0.84 |
| 0.0 | 14.0 | 791 | 1.6458 | 0.83 |
| 0.0 | 14.87 | 840 | 1.6457 | 0.84 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.1