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: 0.9452
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 14.6117 | 1.0 | 13 | 12.1354 |
| 4.7373 | 2.0 | 26 | 5.1054 |
| 1.7596 | 3.0 | 39 | 3.2154 |
| 1.3121 | 4.0 | 52 | 2.1497 |
| 1.1923 | 5.0 | 65 | 1.6547 |
| 0.3427 | 6.0 | 78 | 1.2120 |
| 0.3447 | 7.0 | 91 | 1.1350 |
| 1.8694 | 8.0 | 104 | 0.9754 |
| 0.7097 | 9.0 | 117 | 0.9623 |
| 1.4038 | 10.0 | 130 | 0.9452 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0
- Datasets 2.15.0
- Tokenizers 0.15.0