arabert_baseline_organization_task8_fold1

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: 0.3060
• Qwk: 0.7308
• Mse: 0.3060

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	1.3363	0.1206	1.3363
No log	1.0	4	1.0314	0.4940	1.0314
No log	1.5	6	0.6916	0.5444	0.6916
No log	2.0	8	0.6153	0.4510	0.6153
No log	2.5	10	0.6686	0.5062	0.6686
No log	3.0	12	0.4719	0.6147	0.4719
No log	3.5	14	0.3635	0.7172	0.3635
No log	4.0	16	0.3213	0.7070	0.3213
No log	4.5	18	0.2998	0.6908	0.2998
No log	5.0	20	0.4019	0.6111	0.4019
No log	5.5	22	0.6037	0.5368	0.6037
No log	6.0	24	0.5509	0.5368	0.5509
No log	6.5	26	0.4100	0.6908	0.4100
No log	7.0	28	0.3021	0.7308	0.3021
No log	7.5	30	0.2592	0.8192	0.2592
No log	8.0	32	0.2596	0.8346	0.2596
No log	8.5	34	0.2632	0.8346	0.2632
No log	9.0	36	0.2747	0.8192	0.2747
No log	9.5	38	0.2933	0.7308	0.2933
No log	10.0	40	0.3060	0.7308	0.3060

Framework versions

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