horger89/SlightlyFineTunedBertOnSquad
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 6.5399
- Train End Logits Loss: 3.1546
- Train Start Logits Loss: 3.3853
- Train End Logits Accuracy: 0.3726
- Train Start Logits Accuracy: 0.3301
- Validation Loss: 6.1757
- Validation End Logits Loss: 3.0226
- Validation Start Logits Loss: 3.1531
- Validation End Logits Accuracy: 0.4046
- Validation Start Logits Accuracy: 0.3661
- 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': '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5250, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train End Logits Loss | Train Start Logits Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Loss | Validation Start Logits Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
---|---|---|---|---|---|---|---|---|---|---|
8.3613 | 4.1160 | 4.2453 | 0.1252 | 0.1231 | 7.2387 | 3.6778 | 3.5609 | 0.2866 | 0.2680 | 0 |
7.4922 | 3.5571 | 3.9351 | 0.2865 | 0.2273 | 6.9356 | 3.5662 | 3.3694 | 0.3823 | 0.3239 | 1 |
6.5399 | 3.1546 | 3.3853 | 0.3726 | 0.3301 | 6.1757 | 3.0226 | 3.1531 | 0.4046 | 0.3661 | 2 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4