Question_Generation_ComQ_6
This model is a fine-tuned version of Gayathri142214002/Question_Generation_ComQ_5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2626
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 |
|---|---|---|---|
| 0.2588 | 0.51 | 50 | 0.2122 |
| 0.2571 | 1.02 | 100 | 0.2027 |
| 0.2098 | 1.53 | 150 | 0.2231 |
| 0.2227 | 2.04 | 200 | 0.2304 |
| 0.1974 | 2.54 | 250 | 0.2380 |
| 0.2024 | 3.05 | 300 | 0.2423 |
| 0.1839 | 3.56 | 350 | 0.2495 |
| 0.1916 | 4.07 | 400 | 0.2490 |
| 0.1777 | 4.58 | 450 | 0.2573 |
| 0.1776 | 5.09 | 500 | 0.2561 |
| 0.1663 | 5.6 | 550 | 0.2612 |
| 0.1761 | 6.11 | 600 | 0.2611 |
| 0.1563 | 6.62 | 650 | 0.2626 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3