distilbert-clf-20newsgroups

This model is a fine-tuned version of distilbert-base-uncased on 20newsgroups. It achieves the following results on the evaluation set:

• loss: 0.5506
• accuracy: 0.8401

Model description

Intended uses & limitations

Training and evaluation data

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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1908, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

• loss: 0.2480
• accuracy: 0.9422
• val_loss: 0.3633
• val_accuracy: 0.8940

Framework versions

• Transformers 4.28.0
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3