arabert_baseline_organization_task7_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: 0.4509
• Qwk: 0.6
• Mse: 0.4509

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	0.3333	2	1.2538	0.1333	1.2538
No log	0.6667	4	0.6732	0.5116	0.6732
No log	1.0	6	1.0128	0.3810	1.0128
No log	1.3333	8	0.6424	0.5455	0.6424
No log	1.6667	10	0.6331	0.5455	0.6331
No log	2.0	12	0.6841	0.5455	0.6841
No log	2.3333	14	0.6488	0.5306	0.6488
No log	2.6667	16	0.7438	0.5185	0.7438
No log	3.0	18	1.0106	0.3636	1.0106
No log	3.3333	20	1.0009	0.3810	1.0009
No log	3.6667	22	0.6870	0.5098	0.6870
No log	4.0	24	0.5375	0.5106	0.5375
No log	4.3333	26	0.5197	0.55	0.5197
No log	4.6667	28	0.5082	0.5366	0.5082
No log	5.0	30	0.5130	0.5652	0.5130
No log	5.3333	32	0.5730	0.56	0.5730
No log	5.6667	34	0.5916	0.56	0.5916
No log	6.0	36	0.5065	0.5306	0.5065
No log	6.3333	38	0.4667	0.6	0.4667
No log	6.6667	40	0.4403	0.6	0.4403
No log	7.0	42	0.4374	0.6	0.4374
No log	7.3333	44	0.4427	0.6	0.4427
No log	7.6667	46	0.4590	0.6	0.4590
No log	8.0	48	0.4783	0.6275	0.4783
No log	8.3333	50	0.4751	0.6275	0.4751
No log	8.6667	52	0.4701	0.6275	0.4701
No log	9.0	54	0.4678	0.6275	0.4678
No log	9.3333	56	0.4574	0.6275	0.4574
No log	9.6667	58	0.4535	0.6	0.4535
No log	10.0	60	0.4509	0.6	0.4509

Framework versions

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