metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
datasets:
- opus_books
metrics:
- bleu
model-index:
- name: t5_small_en-pt
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: opus_books
type: opus_books
config: en-pt
split: train
args: en-pt
metrics:
- name: Bleu
type: bleu
value: 6.3078
t5_small_en-pt
This model is a fine-tuned version of t5-small on the opus_books dataset. It achieves the following results on the evaluation set:
- Loss: 1.5396
- Bleu: 6.3078
- Gen Len: 17.9644
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 36 | 2.9730 | 1.4396 | 17.9786 |
| No log | 2.0 | 72 | 2.6798 | 1.7604 | 18.1495 |
| No log | 3.0 | 108 | 2.4812 | 1.8606 | 18.2954 |
| No log | 4.0 | 144 | 2.3366 | 2.1379 | 18.2028 |
| No log | 5.0 | 180 | 2.2165 | 2.3636 | 18.1922 |
| No log | 6.0 | 216 | 2.1192 | 2.7925 | 18.1815 |
| No log | 7.0 | 252 | 2.0400 | 3.2243 | 18.1957 |
| No log | 8.0 | 288 | 1.9703 | 3.6722 | 18.1886 |
| No log | 9.0 | 324 | 1.9227 | 3.6416 | 18.1851 |
| No log | 10.0 | 360 | 1.8762 | 3.9984 | 18.1851 |
| No log | 11.0 | 396 | 1.8303 | 4.0942 | 18.1103 |
| No log | 12.0 | 432 | 1.8044 | 4.4425 | 18.1388 |
| No log | 13.0 | 468 | 1.7719 | 4.3346 | 18.1423 |
| 2.281 | 14.0 | 504 | 1.7477 | 4.6716 | 18.1032 |
| 2.281 | 15.0 | 540 | 1.7256 | 4.7874 | 18.1139 |
| 2.281 | 16.0 | 576 | 1.7057 | 4.8878 | 18.0783 |
| 2.281 | 17.0 | 612 | 1.6871 | 4.8045 | 18.0819 |
| 2.281 | 18.0 | 648 | 1.6770 | 4.9783 | 18.0676 |
| 2.281 | 19.0 | 684 | 1.6542 | 5.1069 | 18.0107 |
| 2.281 | 20.0 | 720 | 1.6414 | 4.902 | 18.0569 |
| 2.281 | 21.0 | 756 | 1.6326 | 5.0385 | 18.0214 |
| 2.281 | 22.0 | 792 | 1.6228 | 5.1533 | 18.0534 |
| 2.281 | 23.0 | 828 | 1.6233 | 5.397 | 18.0285 |
| 2.281 | 24.0 | 864 | 1.6076 | 5.4458 | 18.0214 |
| 2.281 | 25.0 | 900 | 1.5995 | 5.5752 | 18.0712 |
| 2.281 | 26.0 | 936 | 1.5938 | 5.3835 | 18.0925 |
| 2.281 | 27.0 | 972 | 1.5863 | 5.6135 | 18.0107 |
| 1.3904 | 28.0 | 1008 | 1.5780 | 5.8076 | 18.0356 |
| 1.3904 | 29.0 | 1044 | 1.5757 | 5.8528 | 18.0641 |
| 1.3904 | 30.0 | 1080 | 1.5721 | 5.8875 | 18.0285 |
| 1.3904 | 31.0 | 1116 | 1.5648 | 6.1429 | 18.0498 |
| 1.3904 | 32.0 | 1152 | 1.5596 | 6.0269 | 18.0819 |
| 1.3904 | 33.0 | 1188 | 1.5592 | 6.2233 | 18.0427 |
| 1.3904 | 34.0 | 1224 | 1.5552 | 6.0874 | 18.0569 |
| 1.3904 | 35.0 | 1260 | 1.5542 | 6.2611 | 18.0463 |
| 1.3904 | 36.0 | 1296 | 1.5493 | 6.1328 | 18.0391 |
| 1.3904 | 37.0 | 1332 | 1.5509 | 6.2341 | 18.0356 |
| 1.3904 | 38.0 | 1368 | 1.5455 | 6.2754 | 18.0036 |
| 1.3904 | 39.0 | 1404 | 1.5468 | 6.2263 | 18.0071 |
| 1.3904 | 40.0 | 1440 | 1.5446 | 6.1178 | 17.9929 |
| 1.3904 | 41.0 | 1476 | 1.5436 | 6.3536 | 17.9964 |
| 1.1159 | 42.0 | 1512 | 1.5426 | 6.296 | 17.9715 |
| 1.1159 | 43.0 | 1548 | 1.5402 | 6.1919 | 18.0356 |
| 1.1159 | 44.0 | 1584 | 1.5386 | 6.2256 | 18.0356 |
| 1.1159 | 45.0 | 1620 | 1.5392 | 6.2119 | 18.0356 |
| 1.1159 | 46.0 | 1656 | 1.5404 | 6.3696 | 18.032 |
| 1.1159 | 47.0 | 1692 | 1.5390 | 6.3779 | 17.9964 |
| 1.1159 | 48.0 | 1728 | 1.5392 | 6.2079 | 18.0107 |
| 1.1159 | 49.0 | 1764 | 1.5396 | 6.3334 | 17.968 |
| 1.1159 | 50.0 | 1800 | 1.5396 | 6.3078 | 17.9644 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3