Edit model card

HASAN55/distilbert-uncased-finetuned-for-small_dataset

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

  • Train Loss: 0.3166
  • Train End Logits Accuracy: 0.9034
  • Train Start Logits Accuracy: 0.8900
  • Validation Loss: 0.0
  • Validation End Logits Accuracy: 0.0
  • Validation Start Logits Accuracy: 0.0
  • 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 5673, '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, 'weight_decay_rate': 0.01}
  • training_precision: mixed_float16

Training results

Train Loss Train End Logits Accuracy Train Start Logits Accuracy Validation Loss Validation End Logits Accuracy Validation Start Logits Accuracy Epoch
0.3178 0.9047 0.8883 0.0 0.0 0.0 0
0.3164 0.9066 0.8879 0.0 0.0 0.0 1
0.3166 0.9034 0.8900 0.0 0.0 0.0 2

Framework versions

  • Transformers 4.28.1
  • TensorFlow 2.12.0
  • Datasets 2.11.0
  • Tokenizers 0.13.3
Downloads last month
20