|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: t5_small_SA_SapBERT |
|
|
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_SA_SapBERT |
|
|
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.8542 |
|
|
- Rouge1: 0.1048 |
|
|
- Rouge2: 0.0468 |
|
|
- Rougel: 0.1053 |
|
|
- Rougelsum: 0.1053 |
|
|
- Gen Len: 4.354 |
|
|
|
|
|
## 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: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 12 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
|
| 2.9168 | 1.0 | 527 | 1.0769 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | |
|
|
| 1.0195 | 2.0 | 1054 | 0.9827 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.9535 | 3.0 | 1581 | 0.9101 | 0.0156 | 0.0053 | 0.0158 | 0.0155 | 3.2389 | |
|
|
| 0.8636 | 4.0 | 2108 | 0.8914 | 0.0275 | 0.0061 | 0.0272 | 0.0277 | 3.5398 | |
|
|
| 0.8634 | 5.0 | 2635 | 0.8782 | 0.0508 | 0.0184 | 0.0501 | 0.0511 | 3.885 | |
|
|
| 0.8494 | 6.0 | 3162 | 0.8714 | 0.0703 | 0.0288 | 0.0695 | 0.0701 | 4.5398 | |
|
|
| 0.7966 | 7.0 | 3689 | 0.8633 | 0.0715 | 0.0298 | 0.0712 | 0.0714 | 4.3628 | |
|
|
| 0.8073 | 8.0 | 4216 | 0.8601 | 0.0869 | 0.0398 | 0.0868 | 0.0874 | 4.4336 | |
|
|
| 0.8308 | 9.0 | 4743 | 0.8578 | 0.0936 | 0.0377 | 0.0933 | 0.0936 | 4.3628 | |
|
|
| 0.8068 | 10.0 | 5270 | 0.8553 | 0.1014 | 0.0449 | 0.1019 | 0.1014 | 4.2301 | |
|
|
| 0.8187 | 11.0 | 5797 | 0.8544 | 0.0951 | 0.0381 | 0.0949 | 0.0953 | 4.1681 | |
|
|
| 0.7627 | 12.0 | 6324 | 0.8542 | 0.1048 | 0.0468 | 0.1053 | 0.1053 | 4.354 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.1 |
|
|
- Pytorch 1.13.1+cu116 |
|
|
- Datasets 2.10.1 |
|
|
- Tokenizers 0.13.2 |
|
|
|
