<!-- 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. -->
HASAN55/bert-finetuned-for-three-didis
This model is a fine-tuned version of distilbert-base-cased-distilled-squad on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3386
- Train End Logits Accuracy: 0.8996
- Train Start Logits Accuracy: 0.8676
- Validation Loss: 1.3736
- Validation End Logits Accuracy: 0.7076
- Validation Start Logits Accuracy: 0.6787
- Epoch: 2
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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 16635, '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}
- training_precision: mixed_float16
Training results
Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
---|---|---|---|---|---|---|
0.6217 | 0.8207 | 0.7784 | 1.1429 | 0.7147 | 0.6855 | 0 |
0.4537 | 0.8660 | 0.8295 | 1.2282 | 0.7084 | 0.6765 | 1 |
0.3386 | 0.8996 | 0.8676 | 1.3736 | 0.7076 | 0.6787 | 2 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3