bert-base-arabertv2_with_categories

This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2450
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.5

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:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	5	1.2518	0.0	0.0	0.0	0.6277
No log	2.0	10	1.2573	0.0	0.0	0.0	0.6277
No log	3.0	15	1.1941	0.0	0.0	0.0	0.6277
No log	4.0	20	1.1636	0.0	0.0	0.0	0.6277
No log	5.0	25	1.1736	0.0	0.0	0.0	0.6277
No log	6.0	30	1.1222	0.0	0.0	0.0	0.6277
No log	7.0	35	1.0947	0.0	0.0	0.0	0.6383
No log	8.0	40	1.0881	0.0	0.0	0.0	0.6383
No log	9.0	45	1.0591	0.0	0.0	0.0	0.6489
No log	10.0	50	1.0475	0.0	0.0	0.0	0.6383

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0