labse-base-part1
This model is a fine-tuned version of sentence-transformers/LaBSE on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0147
- F1: 0.9778
- Precision: 0.9744
- Recall: 0.9813
- Fpr: 0.0275
- Fnr: 0.0187
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Fpr | Fnr |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 207 | 0.0121 | 0.9756 | 0.9699 | 0.9813 | 0.0325 | 0.0187 |
| No log | 2.0 | 414 | 0.0227 | 0.9713 | 0.9527 | 0.9906 | 0.0525 | 0.0094 |
| 0.0135 | 3.0 | 621 | 0.0153 | 0.9765 | 0.9788 | 0.9742 | 0.0225 | 0.0258 |
| 0.0135 | 4.0 | 828 | 0.0147 | 0.9778 | 0.9744 | 0.9813 | 0.0275 | 0.0187 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2