betteib/xlm-tn-20epochs-lr

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

• Train Loss: 7.0724
• Train Accuracy: 0.0291
• Validation Loss: 6.9350
• Validation Accuracy: 0.0286
• Epoch: 5

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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0001, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 4464, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 496, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
9.6176	0.0035	9.2319	0.0048	0
8.9356	0.0059	8.5303	0.0071	1
8.1494	0.0100	7.7161	0.0137	2
7.5554	0.0180	7.2709	0.0281	3
7.2561	0.0273	7.0588	0.0289	4
7.0724	0.0291	6.9350	0.0286	5

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.19.1
• Tokenizers 0.13.3