metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
datasets:
- billsum
metrics:
- rouge
model-index:
- name: yingchuanong_582_team_summarization
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: 0.2039
yingchuanong_582_team_summarization
This model is a fine-tuned version of t5-base on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.8978
- Rouge1: 0.2039
- Rouge2: 0.1189
- Rougel: 0.1798
- Rougelsum: 0.1798
- 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: 2e-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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 2.0176 | 0.2024 | 0.1102 | 0.175 | 0.1747 | 19.0 |
| No log | 2.0 | 248 | 1.9361 | 0.2033 | 0.1146 | 0.1773 | 0.1771 | 19.0 |
| No log | 3.0 | 372 | 1.9046 | 0.2038 | 0.1184 | 0.1792 | 0.1791 | 19.0 |
| No log | 4.0 | 496 | 1.8978 | 0.2039 | 0.1189 | 0.1798 | 0.1798 | 19.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0