hubert-base-ls960-ft
This model is a fine-tuned version of facebook/hubert-base-ls960 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0123
- Accuracy: 0.9973
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 0.1205 | 1.0 | 8558 | 0.9955 | 0.0173 |
| 0.0638 | 2.0 | 17116 | 0.9973 | 0.0123 |
| 0.0747 | 3.0 | 25674 | 0.9964 | 0.0183 |
| 0.0636 | 4.0 | 34232 | 0.9958 | 0.0201 |
| 0.0531 | 5.0 | 42790 | 0.9967 | 0.0168 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cpu
- Datasets 2.10.1
- Tokenizers 0.12.1
- Downloads last month
- 4