2levels_26260

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: 0.9906
• Macro F1: 0.8031
• Macro Precision: 0.8191
• Macro Recall: 0.8065
• Accuracy: 0.8047

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: 64
• eval_batch_size: 16
• 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	Validation Loss	Macro F1	Macro Precision	Macro Recall	Accuracy
No log	1.0	411	0.4004	0.8111	0.8211	0.8134	0.8120
0.4173	2.0	822	0.4100	0.8204	0.8321	0.8229	0.8214
0.2747	3.0	1233	0.5065	0.8178	0.8298	0.8204	0.8189
0.1498	4.0	1644	0.6896	0.8100	0.8197	0.8123	0.8109
0.0747	5.0	2055	0.9460	0.8000	0.8182	0.8038	0.8020
0.0747	6.0	2466	0.9906	0.8031	0.8191	0.8065	0.8047

Framework versions

• Transformers 4.43.4
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.19.1