<!-- 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/bert-finetuned-squad-v22
This model is a fine-tuned version of badokorach/bert-finetuned-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0121
- Epoch: 29
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': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1950, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
Train Loss | Epoch |
---|---|
2.6826 | 0 |
1.9953 | 1 |
1.5543 | 2 |
1.2287 | 3 |
0.8953 | 4 |
0.6043 | 5 |
0.3745 | 6 |
0.2298 | 7 |
0.1536 | 8 |
0.1098 | 9 |
0.0987 | 10 |
0.0683 | 11 |
0.0609 | 12 |
0.0473 | 13 |
0.0345 | 14 |
0.0353 | 15 |
0.0294 | 16 |
0.0232 | 17 |
0.0243 | 18 |
0.0170 | 19 |
0.0190 | 20 |
0.0111 | 21 |
0.0138 | 22 |
0.0078 | 23 |
0.0143 | 24 |
0.0095 | 25 |
0.0112 | 26 |
0.0092 | 27 |
0.0116 | 28 |
0.0121 | 29 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.14.0
- Tokenizers 0.13.3