Asmaamaghraby/egyhistoryqa_model

This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.3303
• Validation Loss: 0.4029
• 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 210, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
4.1730	2.7673	0
1.9187	1.0734	1
0.6854	0.5224	2
0.4455	0.4661	3
0.3962	0.4519	4
0.3743	0.4135	5
0.3563	0.4067	6
0.3455	0.4087	7
0.3404	0.4034	8
0.3303	0.4029	9

Framework versions

• Transformers 4.40.0
• TensorFlow 2.15.0
• Datasets 2.19.0
• Tokenizers 0.19.1