metadata
license: apache-2.0
base_model: facebook/hubert-base-ls960
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: hubert-base-ls960-finetuned-gtzan-bs-8
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 1
hubert-base-ls960-finetuned-gtzan-bs-8
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: 0.0222
- Accuracy: 1.0
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.997 | 1.0 | 30 | 1.7902 | 0.8148 |
| 1.4902 | 2.0 | 60 | 1.3832 | 0.4074 |
| 1.2254 | 3.0 | 90 | 0.9829 | 1.0 |
| 0.8641 | 4.0 | 120 | 0.5986 | 1.0 |
| 0.4658 | 5.0 | 150 | 0.3381 | 0.9630 |
| 0.4094 | 6.0 | 180 | 0.5581 | 0.8519 |
| 0.2778 | 7.0 | 210 | 0.3275 | 0.9259 |
| 0.2474 | 8.0 | 240 | 0.0614 | 1.0 |
| 0.282 | 9.0 | 270 | 0.0402 | 1.0 |
| 0.0942 | 10.0 | 300 | 0.2155 | 0.9630 |
| 0.0704 | 11.0 | 330 | 0.1869 | 0.9630 |
| 0.0952 | 12.0 | 360 | 0.2176 | 0.9630 |
| 0.1569 | 13.0 | 390 | 0.1957 | 0.9630 |
| 0.1165 | 14.0 | 420 | 0.0165 | 1.0 |
| 0.0224 | 15.0 | 450 | 0.0222 | 1.0 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3