RavGau/rav_nlp_qa

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: 0.1488
• Train End Logits Accuracy: 0.9536
• Train Start Logits Accuracy: 0.9542
• Validation Loss: 1.8833
• Validation End Logits Accuracy: 0.6524
• Validation Start Logits Accuracy: 0.6465
• 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', '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': 5060, '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

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
2.7167	0.3467	0.3386	1.4679	0.6185	0.5949	0
1.3089	0.6476	0.6325	1.3092	0.6495	0.6264	1
0.8910	0.7514	0.7385	1.3037	0.6568	0.6357	2
0.6336	0.8166	0.8137	1.3668	0.6632	0.6352	3
0.4474	0.8582	0.8617	1.5254	0.6603	0.6465	4
0.3308	0.8907	0.9014	1.6029	0.6514	0.6386	5
0.2596	0.9144	0.9223	1.6924	0.6524	0.6426	6
0.2055	0.9358	0.9374	1.7831	0.6490	0.6480	7
0.1719	0.9436	0.9442	1.8572	0.6534	0.6445	8
0.1488	0.9536	0.9542	1.8833	0.6524	0.6465	9

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3