metadata
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: silviacamplani/distilbert-uncase-direct-finetuning-ai-ner_3labels
results: []
silviacamplani/distilbert-uncase-direct-finetuning-ai-ner_3labels
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: 0.6593
- Validation Loss: 0.6130
- 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 60, '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 | Validation Loss | Epoch |
|---|---|---|
| 1.9721 | 1.8113 | 0 |
| 1.6564 | 1.5052 | 1 |
| 1.3640 | 1.2332 | 2 |
| 1.1078 | 0.9996 | 3 |
| 0.9158 | 0.8249 | 4 |
| 0.7850 | 0.7188 | 5 |
| 0.7135 | 0.6595 | 6 |
| 0.6822 | 0.6310 | 7 |
| 0.6394 | 0.6171 | 8 |
| 0.6593 | 0.6130 | 9 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1