<!-- 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. -->
Pegasus_paraphraser_ComQG_3
This model is a fine-tuned version of Gayathri142214002/Pegasus_paraphraser_ComQG_2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2753
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2237 | 0.47 | 1000 | 0.2237 |
| 0.244 | 0.93 | 2000 | 0.2321 |
| 0.2073 | 1.4 | 3000 | 0.2543 |
| 0.213 | 1.86 | 4000 | 0.2511 |
| 0.1863 | 2.33 | 5000 | 0.2712 |
| 0.1844 | 2.79 | 6000 | 0.2621 |
| 0.1707 | 3.26 | 7000 | 0.2778 |
| 0.1585 | 3.72 | 8000 | 0.2753 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
