parsbert_final2
This model is a fine-tuned version of pedramyazdipoor/parsbert_question_answering_PQuAD on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9585
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8784 | 0.3945 | 400 | 2.3892 |
| 2.5562 | 0.7890 | 800 | 2.0935 |
| 2.169 | 1.1834 | 1200 | 2.0202 |
| 2.0509 | 1.5779 | 1600 | 1.9735 |
| 2.0127 | 1.9724 | 2000 | 1.9585 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Downloads last month
- 3