bert-base-arabertv02-finetuned-sandouq

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an ٍSandouq financial dataset. It achieves the following results on the evaluation set:

• Loss: 2.9575

Model description

This is AraBert model which fine-tuned on financial dataset for financial purpous

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: 15
• eval_batch_size: 15
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss
3.3856	1.0	334	3.2282
3.2555	2.0	668	3.1496
3.1479	3.0	1002	3.1036
3.0899	4.0	1336	3.0090
3.025	5.0	1670	3.0105
2.9823	6.0	2004	3.0245
2.9893	7.0	2338	2.9781
2.9614	8.0	2672	2.9572

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3