ArabicNewSplits_FineTuningAraBERT_noAug_task1_organization_fold0

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: 0.9847
• Qwk: 0.3100
• Mse: 0.9847
• Rmse: 0.9923

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	4.8450	0.0331	4.8450	2.2011
No log	2.0	4	3.2035	0.0737	3.2035	1.7898
No log	3.0	6	2.1175	0.0780	2.1175	1.4551
No log	4.0	8	1.4668	0.2619	1.4668	1.2111
No log	5.0	10	1.0858	0.2141	1.0858	1.0420
No log	6.0	12	0.8782	0.4655	0.8782	0.9371
No log	7.0	14	0.8190	0.5455	0.8190	0.9050
No log	8.0	16	0.8691	0.3705	0.8691	0.9322
No log	9.0	18	0.9591	0.3517	0.9591	0.9793
No log	10.0	20	0.9847	0.3100	0.9847	0.9923

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1