disilbert-blm-tweets-binary

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: 0.1159
• Train Accuracy: 0.9556
• Validation Loss: 0.5772
• Validation Accuracy: 0.7965
• Epoch: 4

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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.5941	0.6905	0.5159	0.7168	0
0.4041	0.8212	0.4589	0.8142	1
0.2491	0.9026	0.6014	0.7876	2
0.1011	0.9692	0.7181	0.8053	3
0.1159	0.9556	0.5772	0.7965	4

Framework versions

• Transformers 4.25.1
• TensorFlow 2.9.2
• Tokenizers 0.13.2