metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: my_awesome_billsum_model
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: 0.1648
my_awesome_billsum_model
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.3855
- Rouge1: 0.1648
- Rouge2: 0.0823
- Rougel: 0.1406
- Rougelsum: 0.1402
- Gen Len: 16.4718
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: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 2.7268 | 0.1497 | 0.0638 | 0.1259 | 0.126 | 19.0 |
| No log | 2.0 | 248 | 2.5127 | 0.1502 | 0.0647 | 0.126 | 0.1261 | 18.9234 |
| No log | 3.0 | 372 | 2.4331 | 0.151 | 0.0682 | 0.1274 | 0.1272 | 17.0081 |
| No log | 4.0 | 496 | 2.3971 | 0.1628 | 0.0786 | 0.1388 | 0.1385 | 16.7782 |
| 2.9098 | 5.0 | 620 | 2.3855 | 0.1648 | 0.0823 | 0.1406 | 0.1402 | 16.4718 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.14.1
- Tokenizers 0.13.3