metadata
license: apache-2.0
tags:
- summarization
- generated_from_trainer
datasets:
- snli
metrics:
- rouge
model-index:
- name: t5-small-finetuned-contradiction
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: snli
type: snli
args: plain_text
metrics:
- name: Rouge1
type: rouge
value: 34.3503
t5-small-finetuned-contradiction
This model is a fine-tuned version of domenicrosati/t5-small-finetuned-contradiction on the snli dataset. It achieves the following results on the evaluation set:
- Loss: 2.0662
- Rouge1: 34.3503
- Rouge2: 14.671
- Rougel: 32.5398
- Rougelsum: 32.5331
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 2.0071 | 1.0 | 2863 | 2.1018 | 34.4519 | 14.6277 | 32.6441 | 32.6415 |
| 2.0704 | 2.0 | 5726 | 2.0897 | 34.4688 | 14.7508 | 32.6253 | 32.6227 |
| 2.0738 | 3.0 | 8589 | 2.0808 | 34.4291 | 14.5548 | 32.6263 | 32.6384 |
| 2.0788 | 4.0 | 11452 | 2.0744 | 34.6759 | 14.842 | 32.8169 | 32.823 |
| 2.0781 | 5.0 | 14315 | 2.0714 | 34.4961 | 14.7307 | 32.6362 | 32.6378 |
| 2.0687 | 6.0 | 17178 | 2.0674 | 34.6406 | 14.8359 | 32.8403 | 32.8423 |
| 2.0627 | 7.0 | 20041 | 2.0671 | 34.526 | 14.6943 | 32.6919 | 32.694 |
| 2.0585 | 8.0 | 22904 | 2.0662 | 34.4196 | 14.7107 | 32.607 | 32.6035 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu102
- Datasets 2.1.0
- Tokenizers 0.12.1