|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Pegasus_paraphraser_Com_2 |
|
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_Com_2 |
|
|
|
This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3374 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4477 | 0.29 | 500 | 0.3761 | |
|
| 0.4244 | 0.58 | 1000 | 0.3560 | |
|
| 0.3958 | 0.87 | 1500 | 0.3475 | |
|
| 0.3396 | 1.16 | 2000 | 0.3404 | |
|
| 0.3041 | 1.45 | 2500 | 0.3419 | |
|
| 0.3114 | 1.74 | 3000 | 0.3290 | |
|
| 0.3066 | 2.03 | 3500 | 0.3337 | |
|
| 0.2461 | 2.32 | 4000 | 0.3375 | |
|
| 0.258 | 2.61 | 4500 | 0.3307 | |
|
| 0.2567 | 2.9 | 5000 | 0.3301 | |
|
| 0.2264 | 3.2 | 5500 | 0.3421 | |
|
| 0.2188 | 3.49 | 6000 | 0.3393 | |
|
| 0.2132 | 3.78 | 6500 | 0.3374 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|