metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-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: 0.85
hubert-base-ls960-finetuned-gtzan
This model is a fine-tuned version of facebook/hubert-base-ls960 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5673
- Accuracy: 0.85
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 2.0215 | 1.0 | 112 | 1.9334 | 0.2 |
| 1.5799 | 2.0 | 225 | 1.3860 | 0.58 |
| 1.1392 | 3.0 | 337 | 1.2514 | 0.55 |
| 0.9529 | 4.0 | 450 | 0.9821 | 0.65 |
| 0.7872 | 5.0 | 562 | 0.8525 | 0.74 |
| 0.7504 | 6.0 | 675 | 0.9070 | 0.71 |
| 0.8104 | 7.0 | 787 | 0.5771 | 0.83 |
| 0.303 | 8.0 | 900 | 0.6943 | 0.81 |
| 0.3939 | 9.0 | 1012 | 0.6368 | 0.84 |
| 0.6499 | 9.96 | 1120 | 0.5673 | 0.85 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.3