<!-- 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. -->
EricPeter/distilbert-base-cased-270823
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1660
- Epoch: 39
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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'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': 2596, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 4, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.06}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Epoch |
|---|---|
| 4.3370 | 0 |
| 3.0157 | 1 |
| 2.5394 | 2 |
| 2.1440 | 3 |
| 1.6916 | 4 |
| 1.2670 | 5 |
| 0.9564 | 6 |
| 0.7104 | 7 |
| 0.5675 | 8 |
| 0.4794 | 9 |
| 0.4146 | 10 |
| 0.3559 | 11 |
| 0.3041 | 12 |
| 0.3285 | 13 |
| 0.2704 | 14 |
| 0.2513 | 15 |
| 0.2537 | 16 |
| 0.2422 | 17 |
| 0.2162 | 18 |
| 0.2217 | 19 |
| 0.2135 | 20 |
| 0.2084 | 21 |
| 0.2009 | 22 |
| 0.2010 | 23 |
| 0.2020 | 24 |
| 0.1951 | 25 |
| 0.1939 | 26 |
| 0.1914 | 27 |
| 0.1868 | 28 |
| 0.1805 | 29 |
| 0.1877 | 30 |
| 0.1747 | 31 |
| 0.1676 | 32 |
| 0.1793 | 33 |
| 0.1774 | 34 |
| 0.1742 | 35 |
| 0.1690 | 36 |
| 0.1735 | 37 |
| 0.1706 | 38 |
| 0.1660 | 39 |
Framework versions
- Transformers 4.33.0
- TensorFlow 2.12.0
- Datasets 2.14.4
- Tokenizers 0.13.3
