<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Question_Generation_ComQ_3
This model is a fine-tuned version of Gayathri142214002/Question_Generation_ComQ_2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4586
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|---|---|---|---|
| 0.6781 | 0.21 | 50 | 0.4871 |
| 0.6214 | 0.42 | 100 | 0.4547 |
| 0.6255 | 0.63 | 150 | 0.4467 |
| 0.5831 | 0.84 | 200 | 0.4339 |
| 0.517 | 1.05 | 250 | 0.4279 |
| 0.4126 | 1.26 | 300 | 0.4346 |
| 0.4093 | 1.46 | 350 | 0.4205 |
| 0.4252 | 1.67 | 400 | 0.4182 |
| 0.4132 | 1.88 | 450 | 0.4240 |
| 0.3381 | 2.09 | 500 | 0.4327 |
| 0.312 | 2.3 | 550 | 0.4482 |
| 0.3268 | 2.51 | 600 | 0.4379 |
| 0.342 | 2.72 | 650 | 0.4368 |
| 0.3442 | 2.93 | 700 | 0.4182 |
| 0.2802 | 3.14 | 750 | 0.4506 |
| 0.2735 | 3.35 | 800 | 0.4433 |
| 0.2869 | 3.56 | 850 | 0.4473 |
| 0.2827 | 3.77 | 900 | 0.4353 |
| 0.2792 | 3.97 | 950 | 0.4489 |
| 0.2455 | 4.18 | 1000 | 0.4465 |
| 0.2445 | 4.39 | 1050 | 0.4505 |
| 0.2373 | 4.6 | 1100 | 0.4508 |
| 0.2485 | 4.81 | 1150 | 0.4396 |
| 0.2362 | 5.02 | 1200 | 0.4401 |
| 0.2166 | 5.23 | 1250 | 0.4490 |
| 0.2088 | 5.44 | 1300 | 0.4487 |
| 0.2183 | 5.65 | 1350 | 0.4567 |
| 0.2219 | 5.86 | 1400 | 0.4518 |
| 0.2099 | 6.07 | 1450 | 0.4581 |
| 0.1932 | 6.28 | 1500 | 0.4589 |
| 0.1766 | 6.49 | 1550 | 0.4563 |
| 0.204 | 6.69 | 1600 | 0.4580 |
| 0.2102 | 6.9 | 1650 | 0.4586 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
