results

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2839
• Accuracy: 0.9091

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	7	0.6566	0.7273
No log	2.0	14	0.6210	0.6364
No log	3.0	21	0.5906	0.6364
No log	4.0	28	0.5502	0.7273
No log	5.0	35	0.5382	0.7273
No log	6.0	42	0.5167	0.7273
No log	7.0	49	0.4885	0.7273
No log	8.0	56	0.4157	0.8182
No log	9.0	63	0.5560	0.7273
No log	10.0	70	0.2520	0.9091
No log	11.0	77	0.2724	0.9091
No log	12.0	84	0.2758	0.9091
No log	13.0	91	0.2935	0.8182
No log	14.0	98	0.2786	0.9091
0.2969	15.0	105	0.2839	0.9091

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 2.19.0
• Tokenizers 0.19.1