mmiteva/qa_model-customs_optimized

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: 0.2417
• Train End Logits Accuracy: 0.9192
• Train Start Logits Accuracy: 0.9158
• Validation Loss: 0.6317
• Validation End Logits Accuracy: 0.8375
• Validation Start Logits Accuracy: 0.8303
• Epoch: 3

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': 50860, '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	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
1.1671	0.6791	0.6668	0.6925	0.7903	0.7716	0
0.5541	0.8257	0.8179	0.5747	0.8230	0.8090	1
0.3527	0.8856	0.8786	0.5971	0.8352	0.8203	2
0.2417	0.9192	0.9158	0.6317	0.8375	0.8303	3

Framework versions

• Transformers 4.25.1
• TensorFlow 2.10.1
• Datasets 2.7.1
• Tokenizers 0.12.1