arabert_baseline_organization_task8_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: 0.4941
• Qwk: 0.6010
• Mse: 0.4941

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse
No log	0.5	2	1.4026	0.0558	1.4026
No log	1.0	4	1.1702	0.0	1.1702
No log	1.5	6	1.0793	-0.0294	1.0793
No log	2.0	8	1.0475	0.4031	1.0475
No log	2.5	10	0.9473	0.5191	0.9473
No log	3.0	12	0.8743	0.3158	0.8743
No log	3.5	14	0.7934	0.3158	0.7934
No log	4.0	16	0.6914	0.4324	0.6914
No log	4.5	18	0.6177	0.4940	0.6177
No log	5.0	20	0.5611	0.4940	0.5611
No log	5.5	22	0.5294	0.5714	0.5294
No log	6.0	24	0.5033	0.5670	0.5033
No log	6.5	26	0.4918	0.6010	0.4918
No log	7.0	28	0.4919	0.6010	0.4919
No log	7.5	30	0.4963	0.6010	0.4963
No log	8.0	32	0.4997	0.6010	0.4997
No log	8.5	34	0.4990	0.6010	0.4990
No log	9.0	36	0.4963	0.6010	0.4963
No log	9.5	38	0.4948	0.6010	0.4948
No log	10.0	40	0.4941	0.6010	0.4941

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1