article_classification_modelv12

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: 0.0733
• Accuracy: 0.9884

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.2914	1.0	5554	0.9158	0.2781
0.2064	2.0	11108	0.9223	0.2741
0.1649	3.0	16662	0.9248	0.2919
0.1396	4.0	22216	0.9296	0.3014
0.1008	5.0	27770	0.9291	0.3584
0.0806	6.0	33324	0.9290	0.4003
0.0872	7.0	38878	0.9239	0.4435
0.0399	8.0	44432	0.9262	0.4933
0.0302	9.0	49986	0.9269	0.5392
0.0678	10.0	55540	0.9889	0.0564
0.0332	11.0	61094	0.9886	0.0650
0.0315	12.0	66648	0.9886	0.0666
0.0174	13.0	72202	0.9885	0.0701
0.0158	14.0	77756	0.9881	0.0742
0.0054	15.0	83310	0.0733	0.9884

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1