svenbl80/deberta-v3-Base-finetuned-Contradictory_Watson_All

This model is a fine-tuned version of microsoft/deberta-v3-Base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0544
• Validation Loss: 1.1823
• Train Accuracy: 0.7686
• 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': 6060, '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
0.7816	0.5801	0.7471	0
0.4851	0.5823	0.7583	1
0.3479	0.6302	0.7624	2
0.2592	0.7094	0.7624	3
0.1960	0.8222	0.7666	4
0.1528	0.9238	0.7657	5
0.1139	1.0170	0.7736	6
0.0900	1.0984	0.7695	7
0.0662	1.1683	0.7637	8
0.0544	1.1823	0.7686	9

Framework versions

• Transformers 4.28.0
• TensorFlow 2.9.1
• Datasets 2.15.0
• Tokenizers 0.13.3