|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Pegasus_paraphraser_3 |
|
results: [] |
|
--- |
|
|
|
<!-- 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_3 |
|
|
|
This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser_2](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser_2) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2735 |
|
|
|
## 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 | 0.46 | 1000 | 0.2257 | |
|
| 0.2471 | 0.91 | 2000 | 0.2310 | |
|
| 0.2034 | 1.37 | 3000 | 0.2519 | |
|
| 0.2011 | 1.83 | 4000 | 0.2442 | |
|
| 0.1772 | 2.28 | 5000 | 0.2644 | |
|
| 0.1695 | 2.74 | 6000 | 0.2562 | |
|
| 0.1532 | 3.19 | 7000 | 0.2754 | |
|
| 0.1417 | 3.65 | 8000 | 0.2735 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
