|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: t5-small-paraphrasing-mlm-med-mask-filling-cm0 |
|
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. --> |
|
|
|
# t5-small-paraphrasing-mlm-med-mask-filling-cm0 |
|
|
|
This model is a fine-tuned version of [gayanin/t5-small-paraphrase-pubmed](https://huggingface.co/gayanin/t5-small-paraphrase-pubmed) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6697 |
|
- Rouge2 Precision: 0.6929 |
|
- Rouge2 Recall: 0.4742 |
|
- Rouge2 Fmeasure: 0.5443 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:------:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.9213 | 1.0 | 13915 | 0.8075 | 0.6708 | 0.4603 | 0.5281 | |
|
| 0.8573 | 2.0 | 27830 | 0.7534 | 0.6802 | 0.4671 | 0.5356 | |
|
| 0.8127 | 3.0 | 41745 | 0.7254 | 0.684 | 0.468 | 0.5373 | |
|
| 0.7809 | 4.0 | 55660 | 0.7071 | 0.6867 | 0.4702 | 0.5397 | |
|
| 0.7651 | 5.0 | 69575 | 0.6939 | 0.6886 | 0.4711 | 0.5409 | |
|
| 0.7598 | 6.0 | 83490 | 0.6849 | 0.6904 | 0.4721 | 0.5422 | |
|
| 0.7429 | 7.0 | 97405 | 0.6778 | 0.6917 | 0.4725 | 0.5427 | |
|
| 0.7438 | 8.0 | 111320 | 0.6731 | 0.6917 | 0.4723 | 0.5426 | |
|
| 0.743 | 9.0 | 125235 | 0.6707 | 0.6935 | 0.4748 | 0.545 | |
|
| 0.7349 | 10.0 | 139150 | 0.6697 | 0.6929 | 0.4742 | 0.5443 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.1 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
