metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: gustavokpc/en_MODEL_bert-base-uncased_LRATE_1e-05_EPOCHS_7
results: []
gustavokpc/en_MODEL_bert-base-uncased_LRATE_1e-05_EPOCHS_7
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0150
- Train Accuracy: 0.9951
- Train F1 M: 0.5657
- Train Precision M: 0.4067
- Train Recall M: 0.9873
- Validation Loss: 0.1309
- Validation Accuracy: 0.9655
- Validation F1 M: 0.5737
- Validation Precision M: 0.4163
- Validation Recall M: 0.9980
- 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 3962, '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}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train F1 M | Train Precision M | Train Recall M | Validation Loss | Validation Accuracy | Validation F1 M | Validation Precision M | Validation Recall M | Epoch |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.1966 | 0.9215 | 0.4030 | 0.3067 | 0.6414 | 0.0842 | 0.9708 | 0.5427 | 0.4013 | 0.9115 | 0 |
| 0.0631 | 0.9799 | 0.5517 | 0.4014 | 0.9425 | 0.0667 | 0.9726 | 0.5583 | 0.4067 | 0.9621 | 1 |
| 0.0305 | 0.9912 | 0.5630 | 0.4059 | 0.9778 | 0.0696 | 0.9779 | 0.5517 | 0.4013 | 0.9580 | 2 |
| 0.0150 | 0.9951 | 0.5657 | 0.4067 | 0.9873 | 0.1309 | 0.9655 | 0.5737 | 0.4163 | 0.9980 | 3 |
Framework versions
- Transformers 4.34.1
- TensorFlow 2.10.0
- Datasets 2.14.5
- Tokenizers 0.14.1