TamerAbdelaziz/distilbert-base-uncased-finetuned-IMDB_BERT_11

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: 0.0094
• Validation Loss: 0.3097
• Train Accuracy: 0.9364
• Epoch: 9

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': 6250, '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
0.2466	0.1804	0.9314	0
0.1417	0.1824	0.9324	1
0.0892	0.2208	0.9268	2
0.0532	0.2212	0.9348	3
0.0328	0.2518	0.936	4
0.0218	0.2750	0.9358	5
0.0185	0.2856	0.9338	6
0.0147	0.3055	0.935	7
0.0113	0.3060	0.9352	8
0.0094	0.3097	0.9364	9

Framework versions

• Transformers 4.33.2
• TensorFlow 2.8.1
• Datasets 2.14.5
• Tokenizers 0.13.3