|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-samsum |
|
results: [] |
|
pipeline_tag: summarization |
|
--- |
|
|
|
<!-- 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-samsum |
|
|
|
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: 1.7651 |
|
- Rouge1: 41.6124 |
|
- Rouge2: 18.7668 |
|
- Rougel: 35.0271 |
|
- Rougelsum: 38.5305 |
|
- Gen Len: 16.6381 |
|
|
|
## 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: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.044 | 1.0 | 921 | 1.8159 | 41.1358 | 18.1022 | 34.3309 | 38.1969 | 16.5232 | |
|
| 1.9796 | 2.0 | 1842 | 1.7915 | 41.4713 | 18.6313 | 34.7999 | 38.4147 | 16.566 | |
|
| 1.9487 | 3.0 | 2763 | 1.7724 | 41.6106 | 18.6119 | 34.7796 | 38.5737 | 16.7213 | |
|
| 1.9265 | 4.0 | 3684 | 1.7687 | 41.6027 | 18.8083 | 34.8846 | 38.566 | 16.676 | |
|
| 1.9176 | 5.0 | 4605 | 1.7651 | 41.6124 | 18.7668 | 35.0271 | 38.5305 | 16.6381 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |