<!-- 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. -->
hsohn3/cchs-bert-visit-uncased-wordlevel-block512-batch4-ep60
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.8314
- Epoch: 59
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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Epoch |
|---|---|
| 3.8539 | 0 |
| 3.0645 | 1 |
| 3.0225 | 2 |
| 3.0128 | 3 |
| 3.0023 | 4 |
| 2.9834 | 5 |
| 2.9859 | 6 |
| 2.9814 | 7 |
| 2.9729 | 8 |
| 2.9736 | 9 |
| 2.9687 | 10 |
| 2.9665 | 11 |
| 2.9673 | 12 |
| 2.9612 | 13 |
| 2.9056 | 14 |
| 2.8781 | 15 |
| 2.8612 | 16 |
| 2.8259 | 17 |
| 2.8089 | 18 |
| 2.7865 | 19 |
| 2.7697 | 20 |
| 2.7307 | 21 |
| 2.6828 | 22 |
| 2.6168 | 23 |
| 2.5259 | 24 |
| 2.3860 | 25 |
| 2.2088 | 26 |
| 2.0192 | 27 |
| 1.8022 | 28 |
| 1.5856 | 29 |
| 1.4330 | 30 |
| 1.3441 | 31 |
| 1.2728 | 32 |
| 1.2154 | 33 |
| 1.1757 | 34 |
| 1.1411 | 35 |
| 1.1037 | 36 |
| 1.0883 | 37 |
| 1.0633 | 38 |
| 1.0368 | 39 |
| 1.0205 | 40 |
| 1.0047 | 41 |
| 0.9884 | 42 |
| 0.9754 | 43 |
| 0.9566 | 44 |
| 0.9427 | 45 |
| 0.9385 | 46 |
| 0.9246 | 47 |
| 0.9114 | 48 |
| 0.9029 | 49 |
| 0.8993 | 50 |
| 0.8850 | 51 |
| 0.8768 | 52 |
| 0.8701 | 53 |
| 0.8626 | 54 |
| 0.8580 | 55 |
| 0.8489 | 56 |
| 0.8407 | 57 |
| 0.8338 | 58 |
| 0.8314 | 59 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1
