hubert-base-ls960-digit-mask-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: 0.0078
- Accuracy: 0.9987
- F1: 0.9987
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: 3
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss |
|---|---|---|---|---|---|
| 0.0094 | 1.0 | 14264 | 0.9985 | 0.9985 | 0.0087 |
| 0.0007 | 2.0 | 28528 | 0.9987 | 0.9987 | 0.0078 |
| 0.0008 | 3.0 | 42792 | 0.9987 | 0.9987 | 0.0101 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.0
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 5