metadata
library_name: transformers
base_model: leamac51
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
- f1
model-index:
- name: bsclass-finetuned-gtzan-1st-aprox-less-LR
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: 0.915
- name: F1
type: f1
value: 0.9147312393158322
bsclass-finetuned-gtzan-1st-aprox-less-LR
This model is a fine-tuned version of leamac51 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.5240
- Accuracy: 0.915
- F1: 0.9147
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 | F1 |
|---|---|---|---|---|---|
| 2.0897 | 1.0 | 100 | 2.0161 | 0.685 | 0.6827 |
| 1.6456 | 2.0 | 200 | 1.7330 | 0.66 | 0.6290 |
| 1.4091 | 3.0 | 300 | 1.3255 | 0.78 | 0.7732 |
| 1.1217 | 4.0 | 400 | 1.1425 | 0.82 | 0.8186 |
| 1.0118 | 5.0 | 500 | 0.9657 | 0.85 | 0.8524 |
| 0.7186 | 6.0 | 600 | 0.7777 | 0.86 | 0.8609 |
| 0.4308 | 7.0 | 700 | 0.5975 | 0.905 | 0.9040 |
| 0.451 | 8.0 | 800 | 0.5240 | 0.915 | 0.9147 |
| 0.3558 | 9.0 | 900 | 0.5822 | 0.885 | 0.8853 |
| 0.2556 | 10.0 | 1000 | 0.5207 | 0.905 | 0.9052 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0