metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: hubert-large-ll60k-finetuned-gtzan
results: []
hubert-large-ll60k-finetuned-gtzan
This model is a fine-tuned version of facebook/hubert-large-ll60k on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Accuracy: 0.1
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: 8e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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: 18
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2369 | 1.0 | 112 | 2.1698 | 0.32 |
| 1.9093 | 2.0 | 225 | 1.7851 | 0.34 |
| 1.5339 | 3.0 | 337 | 1.4068 | 0.46 |
| 1.4127 | 4.0 | 450 | 1.2916 | 0.53 |
| 0.991 | 5.0 | 562 | 1.0534 | 0.58 |
| 0.8365 | 6.0 | 675 | 0.9250 | 0.67 |
| 0.6994 | 7.0 | 787 | 1.0032 | 0.72 |
| 1.3372 | 8.0 | 900 | nan | 0.41 |
| 4.3377 | 9.0 | 1012 | nan | 0.29 |
| 0.0 | 10.0 | 1125 | nan | 0.1 |
| 0.0 | 11.0 | 1237 | nan | 0.1 |
| 0.0 | 12.0 | 1350 | nan | 0.1 |
| 0.0 | 13.0 | 1462 | nan | 0.1 |
| 0.0 | 14.0 | 1575 | nan | 0.1 |
| 0.0 | 15.0 | 1687 | nan | 0.1 |
| 0.0 | 16.0 | 1800 | nan | 0.1 |
| 0.0 | 17.0 | 1912 | nan | 0.1 |
| 0.0 | 17.92 | 2016 | nan | 0.1 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3