AlaaHussien/Arabic_pos

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0778
• Validation Loss: 0.1042
• Train Precision: 0.9603
• Train Recall: 0.9565
• Train F1: 0.9584
• Train Accuracy: 0.9708
• Epoch: 4

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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1515, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.3938	0.1375	0.9506	0.9430	0.9468	0.9625	0
0.1234	0.1165	0.9559	0.9507	0.9533	0.9670	1
0.1002	0.1112	0.9591	0.9531	0.9561	0.9690	2
0.0865	0.1051	0.9598	0.9555	0.9576	0.9702	3
0.0778	0.1042	0.9603	0.9565	0.9584	0.9708	4

Framework versions

• Transformers 4.51.1
• TensorFlow 2.18.0
• Datasets 3.5.0
• Tokenizers 0.21.0