vjsyong/xlm-roberta-dementia_detection

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0140
• Validation Loss: 0.4773
• Train Accuracy: 0.8958
• Epoch: 13

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': 378, '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
0.1762	0.3984	0.875	0
0.1873	0.3250	0.8542	1
0.1339	0.4448	0.875	2
0.0316	0.4015	0.8958	3
0.0226	0.4410	0.875	4
0.0166	0.4586	0.8958	5
0.0157	0.4710	0.8958	6
0.0113	0.4772	0.8958	7
0.0159	0.4773	0.8958	8
0.0105	0.4773	0.8958	9
0.0119	0.4773	0.8958	10
0.0120	0.4773	0.8958	11
0.0135	0.4773	0.8958	12
0.0140	0.4773	0.8958	13

Framework versions

• Transformers 4.28.1
• TensorFlow 2.10.1
• Datasets 2.11.0
• Tokenizers 0.13.3