|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-paraphrasing-mlm |
|
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. --> |
|
|
|
# bart-paraphrasing-mlm |
|
|
|
This model is a fine-tuned version of [gayanin/bart-paraphrase-pubmed-1.1](https://huggingface.co/gayanin/bart-paraphrase-pubmed-1.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5510 |
|
- Rouge2 Precision: 0.7148 |
|
- Rouge2 Recall: 0.5223 |
|
- Rouge2 Fmeasure: 0.5866 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:-----:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.6799 | 1.0 | 13833 | 0.5982 | 0.7016 | 0.5122 | 0.5756 | |
|
| 0.5894 | 2.0 | 27666 | 0.5663 | 0.7093 | 0.5193 | 0.583 | |
|
| 0.5329 | 3.0 | 41499 | 0.5540 | 0.7129 | 0.5212 | 0.5853 | |
|
| 0.4953 | 4.0 | 55332 | 0.5510 | 0.7148 | 0.5223 | 0.5866 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 1.18.4 |
|
- Tokenizers 0.11.6 |
|
|
