metadata
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
model-index:
- name: occ_extractor
results: []
occ_extractor
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1291
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.5491 | 1.0 | 26 | 3.2512 |
| 1.628 | 2.0 | 52 | 1.8521 |
| 1.7683 | 3.0 | 78 | 1.2445 |
| 0.7533 | 4.0 | 104 | 0.8269 |
| 1.5694 | 5.0 | 130 | 0.5890 |
| 0.7123 | 6.0 | 156 | 0.4530 |
| 0.6509 | 7.0 | 182 | 0.3668 |
| 0.5216 | 8.0 | 208 | 0.3004 |
| 0.3966 | 9.0 | 234 | 0.2569 |
| 0.2632 | 10.0 | 260 | 0.2259 |
| 0.4013 | 11.0 | 286 | 0.2019 |
| 0.669 | 12.0 | 312 | 0.1826 |
| 0.1427 | 13.0 | 338 | 0.1691 |
| 0.1859 | 14.0 | 364 | 0.1581 |
| 0.1458 | 15.0 | 390 | 0.1496 |
| 0.1999 | 16.0 | 416 | 0.1407 |
| 0.3686 | 17.0 | 442 | 0.1356 |
| 0.2666 | 18.0 | 468 | 0.1318 |
| 0.1874 | 19.0 | 494 | 0.1298 |
| 0.2286 | 20.0 | 520 | 0.1291 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2
- Datasets 2.19.2
- Tokenizers 0.19.1