yidi-huang's picture
Training in progress epoch 16
71793d6
metadata
license: mit
base_model: dbmdz/bert-base-french-europeana-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: yidi-huang/bert-finetuned-ner-lieu
    results: []

yidi-huang/bert-finetuned-ner-lieu

This model is a fine-tuned version of dbmdz/bert-base-french-europeana-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0023
  • Epoch: 16

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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 47400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
  • training_precision: float32

Training results

Train Loss Epoch
0.2157 0
0.0923 1
0.0492 2
0.0331 3
0.0224 4
0.0161 5
0.0137 6
0.0102 7
0.0082 8
0.0078 9
0.0064 10
0.0052 11
0.0046 12
0.0037 13
0.0041 14
0.0038 15
0.0023 16

Framework versions

  • Transformers 4.40.2
  • TensorFlow 2.15.0
  • Datasets 2.19.1
  • Tokenizers 0.19.1