metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: flan-t5-small-billsum
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: billsum
type: billsum
config: default
split: train[17000:]
args: default
metrics:
- name: Rouge1
type: rouge
value: 24.0011
flan-t5-small-billsum
This model is a fine-tuned version of google/flan-t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.5675
- Rouge1: 24.0011
- Rouge2: 18.8602
- Rougel: 22.9037
- Rougelsum: 23.1161
- 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | 195 | 1.6773 | 22.8625 | 17.311 | 21.829 | 22.0089 | 19.0 |
| No log | 2.0 | 390 | 1.6134 | 23.6942 | 18.553 | 22.561 | 22.8895 | 19.0 |
| 1.9532 | 3.0 | 585 | 1.5882 | 23.8253 | 18.7086 | 22.6519 | 22.9745 | 19.0 |
| 1.9532 | 4.0 | 780 | 1.5739 | 24.0178 | 18.8429 | 22.9119 | 23.1471 | 19.0 |
| 1.9532 | 5.0 | 975 | 1.5675 | 24.0011 | 18.8602 | 22.9037 | 23.1161 | 19.0 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3