labse-hard-part2
This model is a fine-tuned version of sentence-transformers/LaBSE on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0127
- F1: 0.9894
- Precision: 0.9915
- Recall: 0.9873
- Fpr: 0.0084
- Fnr: 0.0127
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 | 238 | 0.0088 | 0.9894 | 0.9915 | 0.9873 | 0.0084 | 0.0127 |
| No log | 2.0 | 476 | 0.0112 | 0.9915 | 0.9957 | 0.9873 | 0.0042 | 0.0127 |
| 0.0124 | 3.0 | 714 | 0.0121 | 0.9894 | 0.9915 | 0.9873 | 0.0084 | 0.0127 |
| 0.0124 | 4.0 | 952 | 0.0127 | 0.9894 | 0.9915 | 0.9873 | 0.0084 | 0.0127 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2