arabert_baseline_organization_task6_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: 0.2898
• Qwk: 0.7030
• Mse: 0.2898

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	0.9213	0.0731	0.9213
No log	1.0	4	0.6822	0.1579	0.6822
No log	1.5	6	0.6736	0.5214	0.6736
No log	2.0	8	0.5063	0.5950	0.5063
No log	2.5	10	0.4323	0.7287	0.4323
No log	3.0	12	0.3923	0.6028	0.3923
No log	3.5	14	0.3540	0.5655	0.3540
No log	4.0	16	0.3227	0.6045	0.3227
No log	4.5	18	0.3808	0.5971	0.3808
No log	5.0	20	0.3736	0.5987	0.3736
No log	5.5	22	0.3093	0.6940	0.3093
No log	6.0	24	0.2786	0.6335	0.2786
No log	6.5	26	0.2805	0.6631	0.2805
No log	7.0	28	0.2913	0.6940	0.2913
No log	7.5	30	0.3159	0.7030	0.3159
No log	8.0	32	0.3198	0.76	0.3198
No log	8.5	34	0.3167	0.76	0.3167
No log	9.0	36	0.3027	0.7030	0.3027
No log	9.5	38	0.2926	0.7030	0.2926
No log	10.0	40	0.2898	0.7030	0.2898

Framework versions

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