metadata
license: apache-2.0
tags:
- Summarization
- generated_from_trainer
datasets:
- amazon_reviews_multi
metrics:
- rouge
model-index:
- name: t5-finetuned-amazon-english
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: amazon_reviews_multi
type: amazon_reviews_multi
config: en
split: train
args: en
metrics:
- name: Rouge1
type: rouge
value: 18.7098
t5-finetuned-amazon-english
This model is a fine-tuned version of t5-small on the amazon_reviews_multi dataset. It achieves the following results on the evaluation set:
- Loss: 3.1713
- Rouge1: 18.7098
- Rouge2: 9.9019
- Rougel: 18.2795
- Rougelsum: 18.2925
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: 5.6e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.3583 | 1.0 | 771 | 3.2513 | 16.5417 | 8.9698 | 15.7926 | 15.8127 |
| 3.1022 | 2.0 | 1542 | 3.2147 | 16.6827 | 9.3524 | 16.1397 | 16.2087 |
| 3.0067 | 3.0 | 2313 | 3.1718 | 16.6986 | 8.6935 | 16.2053 | 16.1888 |
| 2.9482 | 4.0 | 3084 | 3.1854 | 18.6103 | 9.4789 | 18.1749 | 18.1577 |
| 2.8934 | 5.0 | 3855 | 3.1669 | 18.445 | 9.9309 | 17.9841 | 18.0504 |
| 2.8389 | 6.0 | 4626 | 3.1782 | 18.278 | 9.2814 | 17.8083 | 17.7972 |
| 2.8174 | 7.0 | 5397 | 3.1709 | 18.0617 | 9.7083 | 17.6292 | 17.6091 |
| 2.8 | 8.0 | 6168 | 3.1713 | 18.7098 | 9.9019 | 18.2795 | 18.2925 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1