arabert_baseline_organization_task6_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: 1.0773
• Qwk: 0.5845
• Mse: 1.0773

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	1.6373	0.1538	1.6373
No log	1.0	4	1.2460	0.2222	1.2460
No log	1.5	6	1.5431	0.3000	1.5431
No log	2.0	8	1.3210	0.2609	1.3210
No log	2.5	10	1.0985	0.2222	1.0985
No log	3.0	12	1.2241	0.3000	1.2241
No log	3.5	14	1.5282	0.4020	1.5282
No log	4.0	16	1.3965	0.5427	1.3965
No log	4.5	18	1.0605	0.3636	1.0605
No log	5.0	20	1.0157	0.3438	1.0157
No log	5.5	22	1.1775	0.6379	1.1775
No log	6.0	24	1.3717	0.6638	1.3717
No log	6.5	26	1.3937	0.6638	1.3937
No log	7.0	28	1.2725	0.6667	1.2725
No log	7.5	30	1.1808	0.6379	1.1808
No log	8.0	32	1.1076	0.4615	1.1076
No log	8.5	34	1.0719	0.4615	1.0719
No log	9.0	36	1.0706	0.5845	1.0706
No log	9.5	38	1.0719	0.5845	1.0719
No log	10.0	40	1.0773	0.5845	1.0773

Framework versions

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