edyfjm07/distilbert-base-uncased-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: 0.4326
- Train End Logits Accuracy: 0.8250
- Train Start Logits Accuracy: 0.8238
- Validation Loss: 0.4552
- Validation End Logits Accuracy: 0.8284
- Validation Start Logits Accuracy: 0.7873
- Epoch: 9
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': 500, '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 |
---|---|---|---|---|---|---|
3.9668 | 0.2262 | 0.1450 | 2.3827 | 0.4627 | 0.3470 | 0 |
1.8862 | 0.5138 | 0.4613 | 1.3513 | 0.5746 | 0.6269 | 1 |
1.1987 | 0.6388 | 0.6313 | 0.9111 | 0.6716 | 0.6866 | 2 |
0.8452 | 0.7275 | 0.7212 | 0.7251 | 0.7052 | 0.7164 | 3 |
0.6875 | 0.7400 | 0.7713 | 0.5832 | 0.7649 | 0.7724 | 4 |
0.5933 | 0.7825 | 0.7825 | 0.5321 | 0.7761 | 0.7799 | 5 |
0.5259 | 0.7962 | 0.8025 | 0.4906 | 0.7948 | 0.7687 | 6 |
0.4668 | 0.8288 | 0.8138 | 0.4699 | 0.8209 | 0.7799 | 7 |
0.4552 | 0.8450 | 0.8163 | 0.4554 | 0.8172 | 0.7724 | 8 |
0.4326 | 0.8250 | 0.8238 | 0.4552 | 0.8284 | 0.7873 | 9 |
Framework versions
- Transformers 4.40.1
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 43