metadata
tags:
- generated_from_trainer
model-index:
- name: Pegasus_paraphraser_ComQG_2
results: []
Pegasus_paraphraser_ComQG_2
This model is a fine-tuned version of Gayathri142214002/Pegasus_paraphraser_1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2872
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 |
|---|---|---|---|
| 0.2379 | 0.49 | 1000 | 0.2476 |
| 0.2658 | 0.97 | 2000 | 0.2449 |
| 0.2192 | 1.46 | 3000 | 0.2616 |
| 0.2301 | 1.95 | 4000 | 0.2632 |
| 0.1943 | 2.44 | 5000 | 0.2761 |
| 0.2043 | 2.92 | 6000 | 0.2769 |
| 0.1752 | 3.41 | 7000 | 0.2871 |
| 0.1738 | 3.9 | 8000 | 0.2872 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3