metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: t5_billsum_finetune
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: billsum
type: billsum
config: default
split: ca_test
args: default
metrics:
- name: Rouge1
type: rouge
value: 0.1926
t5_billsum_finetune
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.0955
- Rouge1: 0.1926
- Rouge2: 0.0931
- Rougel: 0.163
- Rougelsum: 0.1635
- 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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 248 | 2.1016 | 0.1917 | 0.0928 | 0.1624 | 0.1628 | 19.0 |
| No log | 2.0 | 496 | 2.0985 | 0.1931 | 0.0936 | 0.1635 | 0.1639 | 19.0 |
| 1.9507 | 3.0 | 744 | 2.0981 | 0.1926 | 0.0938 | 0.1633 | 0.1637 | 19.0 |
| 1.9507 | 4.0 | 992 | 2.0955 | 0.1926 | 0.0931 | 0.163 | 0.1635 | 19.0 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1