Arabizi_Checkpoints-large

This model is a fine-tuned version of Mohamedd123321/XLMR_Large_Arabizi_MLM on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5551
• Accuracy: 0.8976
• F1: 0.8979
• Precision: 0.8983
• Recall: 0.8976

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Accuracy	F1	Validation Loss	Precision	Recall
0.2588	1.9841	10000	0.8947	0.8948	0.2934	0.8949	0.8947
0.1349	3.9683	20000	0.3518	0.8983	0.8981	0.8980	0.8983
0.0702	5.9524	30000	0.5551	0.8976	0.8979	0.8983	0.8976

Framework versions

• Transformers 4.40.2
• Pytorch 2.8.0+cu129
• Datasets 5.0.0
• Tokenizers 0.19.1