Question_Generation_ComQ_5
This model is a fine-tuned version of Gayathri142214002/Question_Generation_ComQ_4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2956
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0859 | 0.56 | 50 | 0.2674 |
| 0.2604 | 1.11 | 100 | 0.2472 |
| 0.2275 | 1.67 | 150 | 0.2586 |
| 0.2184 | 2.23 | 200 | 0.2670 |
| 0.2077 | 2.79 | 250 | 0.2683 |
| 0.1986 | 3.34 | 300 | 0.2726 |
| 0.1949 | 3.9 | 350 | 0.2805 |
| 0.1824 | 4.46 | 400 | 0.2839 |
| 0.1868 | 5.01 | 450 | 0.2849 |
| 0.1714 | 5.57 | 500 | 0.2928 |
| 0.1694 | 6.13 | 550 | 0.2934 |
| 0.1618 | 6.69 | 600 | 0.2956 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3