edyfjm07/distilbert-base-uncased-v6-finetuned-squad-es
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.6561
- Train End Logits Accuracy: 0.5956
- Train Start Logits Accuracy: 0.5459
- Validation Loss: 2.1364
- Validation End Logits Accuracy: 0.5173
- Validation Start Logits Accuracy: 0.4621
- Epoch: 3
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': 42350, '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 Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
---|---|---|---|---|---|---|
2.8723 | 0.3424 | 0.3004 | 2.4112 | 0.4428 | 0.3921 | 0 |
2.2292 | 0.4764 | 0.4263 | 2.1631 | 0.5 | 0.4470 | 1 |
1.9022 | 0.5448 | 0.4936 | 2.1014 | 0.5072 | 0.4572 | 2 |
1.6561 | 0.5956 | 0.5459 | 2.1364 | 0.5173 | 0.4621 | 3 |
Framework versions
- Transformers 4.41.0
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 24