bert-fa-zwnj-base
This model is a fine-tuned version of HooshvareLab/bert-fa-zwnj-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0005
- Accuracy: 1.0
- F1: 1.0
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6238 | 1.0 | 15 | 0.0168 | 1.0 | 1.0 |
| 0.0073 | 2.0 | 30 | 0.0017 | 1.0 | 1.0 |
| 0.0017 | 3.0 | 45 | 0.0009 | 1.0 | 1.0 |
| 0.0011 | 4.0 | 60 | 0.0007 | 1.0 | 1.0 |
| 0.0009 | 5.0 | 75 | 0.0007 | 1.0 | 1.0 |
| 0.0009 | 6.0 | 90 | 0.0006 | 1.0 | 1.0 |
| 0.0008 | 7.0 | 105 | 0.0006 | 1.0 | 1.0 |
| 0.0008 | 8.0 | 120 | 0.0005 | 1.0 | 1.0 |
| 0.0007 | 9.0 | 135 | 0.0005 | 1.0 | 1.0 |
| 0.0007 | 10.0 | 150 | 0.0005 | 1.0 | 1.0 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cpu
- Datasets 5.0.1
- Tokenizers 0.23.1