<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
xmelus/invoices-roberta-large
This model is a fine-tuned version of xlm-roberta-large on dataset . It achieves the following results on the evaluation set:
- Train Loss: 2.2317
- Train Accuracy: 0.0883
- Validation Loss: 2.1699
- Validation Accuracy: 0.0899
- Finished epochs: 13
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 754, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 11.4516 | 0.0165 | 4.5115 | 0.0501 | 0 |
| 3.6182 | 0.0628 | 2.8398 | 0.0752 | 1 |
| 2.2317 | 0.0883 | 2.1699 | 0.0899 | 2 |
| 1.9700 | 0.0942 | 2.5529 | 0.0831 | 3 |
| 1.9714 | 0.0941 | 2.4961 | 0.0843 | 4 |
| 1.9682 | 0.0940 | 2.5089 | 0.0839 | 5 |
| 1.9546 | 0.0944 | 2.5029 | 0.0841 | 6 |
| 1.9808 | 0.0939 | 2.5140 | 0.0838 | 7 |
| 1.9728 | 0.0937 | 2.5212 | 0.0833 | 8 |
| 1.9655 | 0.0941 | 2.5575 | 0.0838 | 9 |
| 1.9708 | 0.0935 | 2.5419 | 0.0833 | 10 |
| 1.9693 | 0.0940 | 2.5304 | 0.0836 | 11 |
| 1.9614 | 0.0941 | 2.5176 | 0.0835 | 12 |
Framework versions
- Transformers 4.21.2
- TensorFlow 2.8.2
- Datasets 2.4.0
- Tokenizers 0.12.1
