metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: ac-01-bert-finetuned
results: []
ac-01-bert-finetuned
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: 0.0955
- Validation Loss: 0.5721
- Train F1: 0.8418
- Epoch: 4
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': 4790, '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 | Validation Loss | Train F1 | Epoch |
---|---|---|---|
0.5128 | 0.3961 | 0.8342 | 0 |
0.3615 | 0.3747 | 0.8513 | 1 |
0.2357 | 0.5269 | 0.8243 | 2 |
0.1609 | 0.4436 | 0.8184 | 3 |
0.0955 | 0.5721 | 0.8418 | 4 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Datasets 2.14.4
- Tokenizers 0.13.3