|
--- |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-xsum |
|
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-xsum |
|
|
|
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: 2.4256 |
|
- Rouge1: 19.6262 |
|
- Rouge2: 3.6874 |
|
- Rougel: 17.4155 |
|
- Rougelsum: 17.5472 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
| 2.8869 | 1.0 | 584 | 2.6152 | 17.1618 | 2.621 | 15.8121 | 15.8907 | 19.0 | |
|
| 2.829 | 2.0 | 1168 | 2.5615 | 17.486 | 2.799 | 15.9032 | 15.9821 | 19.0 | |
|
| 2.7721 | 3.0 | 1752 | 2.5222 | 18.2742 | 3.0877 | 16.5789 | 16.6729 | 19.0 | |
|
| 2.7416 | 4.0 | 2336 | 2.4921 | 18.8283 | 3.362 | 16.858 | 16.9738 | 19.0 | |
|
| 2.7063 | 5.0 | 2920 | 2.4690 | 18.6113 | 3.2539 | 16.6872 | 16.7919 | 19.0 | |
|
| 2.6686 | 6.0 | 3504 | 2.4528 | 19.2086 | 3.5071 | 17.1746 | 17.2843 | 19.0 | |
|
| 2.652 | 7.0 | 4088 | 2.4403 | 19.3553 | 3.5814 | 17.1871 | 17.2981 | 19.0 | |
|
| 2.6338 | 8.0 | 4672 | 2.4319 | 19.6779 | 3.6693 | 17.4134 | 17.529 | 19.0 | |
|
| 2.6377 | 9.0 | 5256 | 2.4270 | 19.6024 | 3.6557 | 17.3604 | 17.4862 | 19.0 | |
|
| 2.6281 | 10.0 | 5840 | 2.4256 | 19.6262 | 3.6874 | 17.4155 | 17.5472 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.0+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
|
|
