metadata
license: apache-2.0
base_model: t5-large
tags:
- generated_from_trainer
model-index:
- name: occ_extractor
results: []
occ_extractor
This model is a fine-tuned version of t5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0221
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 |
|---|---|---|---|
| 5.0173 | 1.0 | 26 | 3.6634 |
| 1.3207 | 2.0 | 52 | 1.6421 |
| 1.5145 | 3.0 | 78 | 0.8648 |
| 0.569 | 4.0 | 104 | 0.4282 |
| 0.959 | 5.0 | 130 | 0.2613 |
| 0.3348 | 6.0 | 156 | 0.1609 |
| 0.279 | 7.0 | 182 | 0.1122 |
| 0.1566 | 8.0 | 208 | 0.0876 |
| 0.1332 | 9.0 | 234 | 0.0692 |
| 0.0173 | 10.0 | 260 | 0.0540 |
| 0.1275 | 11.0 | 286 | 0.0489 |
| 0.0454 | 12.0 | 312 | 0.0424 |
| 0.0197 | 13.0 | 338 | 0.0367 |
| 0.0166 | 14.0 | 364 | 0.0332 |
| 0.0718 | 15.0 | 390 | 0.0289 |
| 0.0243 | 16.0 | 416 | 0.0261 |
| 0.1413 | 17.0 | 442 | 0.0244 |
| 0.2464 | 18.0 | 468 | 0.0231 |
| 0.0033 | 19.0 | 494 | 0.0223 |
| 0.0122 | 20.0 | 520 | 0.0221 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2
- Datasets 2.19.2
- Tokenizers 0.19.1