|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-qmsum |
|
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-finetuned-qmsum |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4617 |
|
- Rouge1: 27.6423 |
|
- Rouge2: 8.5163 |
|
- Rougel: 23.1505 |
|
|
|
## 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: 5.6e-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: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:| |
|
| 3.3956 | 1.0 | 126 | 3.5354 | 27.6519 | 8.0746 | 23.1321 | |
|
| 3.407 | 2.0 | 252 | 3.5115 | 27.4959 | 8.1111 | 23.1004 | |
|
| 3.36 | 3.0 | 378 | 3.4898 | 27.7611 | 8.3366 | 23.1863 | |
|
| 3.3032 | 4.0 | 504 | 3.4804 | 27.5676 | 8.2376 | 23.1387 | |
|
| 3.2602 | 5.0 | 630 | 3.4727 | 28.1638 | 8.6819 | 23.4878 | |
|
| 3.258 | 6.0 | 756 | 3.4644 | 27.8802 | 8.5634 | 23.3815 | |
|
| 3.2167 | 7.0 | 882 | 3.4626 | 27.649 | 8.5533 | 23.2101 | |
|
| 3.203 | 8.0 | 1008 | 3.4617 | 27.6423 | 8.5163 | 23.1505 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
