huynhdoo's picture
Update README.md
20b440e
metadata
license: mit
tags:
  - generated_from_keras_callback
model-index:
  - name: huynhdoo/flaubert_base_uncased-finetuned-CLS
    results: []

huynhdoo/flaubert_base_uncased-finetuned-CLS

This model is a fine-tuned version of flaubert/flaubert_base_uncased on FLUE/CLS dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.1491
  • Validation Loss: 0.2361
  • Train Accuracy: 0.9270
  • Epoch: 2

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': 2e-05, 'decay_steps': 669, '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 Validation Loss Train Accuracy Epoch
0.5561 0.3184 0.8589 0
0.2343 0.2487 0.9118 1
0.1491 0.2361 0.9270 2

Framework versions

  • Transformers 4.26.0
  • TensorFlow 2.9.2
  • Datasets 2.9.0
  • Tokenizers 0.13.2