<!-- 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. -->
Regression_albert_NOaug_CustomLoss_3
This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1481
- Train Mae: 0.5450
- Train Mse: 0.3746
- Train R2-score: 0.7999
- Validation Loss: 0.1364
- Validation Mae: 0.6382
- Validation Mse: 0.4728
- Validation R2-score: 0.8856
- Epoch: 14
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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
|---|---|---|---|---|---|---|---|---|
| 0.2075 | 0.6054 | 0.4691 | 0.1331 | 0.1389 | 0.6396 | 0.4919 | 0.8859 | 0 |
| 0.1982 | 0.5741 | 0.4337 | 0.8066 | 0.1275 | 0.5890 | 0.3885 | 0.8851 | 1 |
| 0.1775 | 0.5592 | 0.3934 | 0.7398 | 0.1849 | 0.6878 | 0.5975 | 0.8749 | 2 |
| 0.1511 | 0.5350 | 0.3713 | 0.8239 | 0.1441 | 0.6497 | 0.4982 | 0.8841 | 3 |
| 0.1489 | 0.5429 | 0.3710 | 0.8262 | 0.1319 | 0.6294 | 0.4547 | 0.8862 | 4 |
| 0.1477 | 0.5429 | 0.3837 | 0.7268 | 0.1269 | 0.6120 | 0.4229 | 0.8865 | 5 |
| 0.1580 | 0.5603 | 0.3782 | 0.6256 | 0.1556 | 0.6630 | 0.5300 | 0.8817 | 6 |
| 0.1491 | 0.5482 | 0.3743 | 0.8104 | 0.1515 | 0.6586 | 0.5192 | 0.8826 | 7 |
| 0.1499 | 0.5354 | 0.3661 | 0.8207 | 0.2043 | 0.7009 | 0.6370 | 0.8702 | 8 |
| 0.1811 | 0.5516 | 0.4196 | 0.7534 | 0.1303 | 0.6252 | 0.4465 | 0.8865 | 9 |
| 0.1547 | 0.5531 | 0.3798 | 0.6862 | 0.1438 | 0.6493 | 0.4971 | 0.8842 | 10 |
| 0.1464 | 0.5429 | 0.3604 | 0.7679 | 0.1549 | 0.6622 | 0.5282 | 0.8818 | 11 |
| 0.1507 | 0.5507 | 0.3787 | 0.7918 | 0.1489 | 0.6556 | 0.5119 | 0.8831 | 12 |
| 0.1555 | 0.5530 | 0.3888 | 0.7355 | 0.1269 | 0.6126 | 0.4238 | 0.8866 | 13 |
| 0.1481 | 0.5450 | 0.3746 | 0.7999 | 0.1364 | 0.6382 | 0.4728 | 0.8856 | 14 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
