|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-base-billsum |
|
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-base-billsum |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6188 |
|
- Rouge1: 24.2144 |
|
- Rouge2: 19.5091 |
|
- Rougel: 23.4392 |
|
- Rougelsum: 23.6056 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:| |
|
| 1.9236 | 1.0 | 1185 | 1.5895 | 24.1667 | 19.4242 | 23.3539 | 23.5422 | |
|
| 1.7231 | 2.0 | 2370 | 1.5380 | 24.4655 | 19.8009 | 23.6777 | 23.8703 | |
|
| 1.6708 | 3.0 | 3555 | 1.5187 | 24.4628 | 19.816 | 23.6919 | 23.887 | |
|
| 1.7884 | 4.0 | 4740 | 1.6197 | 24.2271 | 19.5246 | 23.4512 | 23.6138 | |
|
| 1.8212 | 5.0 | 5925 | 1.6188 | 24.2144 | 19.5091 | 23.4392 | 23.6056 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
