hubert-base-ls960-fsc-v1
This model is a fine-tuned version of facebook/hubert-base-ls960 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0179
- Accuracy: 0.9966
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: 0.0005
- train_batch_size: 48
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 192
- optimizer: Use 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 121 | 0.1726 | 0.9623 |
| No log | 2.0 | 242 | 0.1376 | 0.9718 |
| No log | 3.0 | 363 | 0.0324 | 0.9931 |
| No log | 4.0 | 484 | 0.0257 | 0.9953 |
| No log | 4.9627 | 600 | 0.0179 | 0.9966 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1