arabert_baseline_development_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: 0.1605
• Qwk: 0.5882
• Mse: 0.1605

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	1.1160	-0.0107	1.1160
No log	1.0	4	0.4550	0.3396	0.4550
No log	1.5	6	0.3212	0.4916	0.3212
No log	2.0	8	0.5003	0.5103	0.5003
No log	2.5	10	0.1299	0.5882	0.1299
No log	3.0	12	0.1918	0.5739	0.1918
No log	3.5	14	0.2125	0.5942	0.2125
No log	4.0	16	0.2092	0.5698	0.2092
No log	4.5	18	0.2845	0.5698	0.2845
No log	5.0	20	0.3180	0.5698	0.3180
No log	5.5	22	0.1927	0.5698	0.1927
No log	6.0	24	0.1205	0.5882	0.1205
No log	6.5	26	0.1184	0.5882	0.1184
No log	7.0	28	0.1447	0.5882	0.1447
No log	7.5	30	0.1943	0.5956	0.1943
No log	8.0	32	0.2046	0.5956	0.2046
No log	8.5	34	0.2027	0.5956	0.2027
No log	9.0	36	0.1838	0.5698	0.1838
No log	9.5	38	0.1659	0.5698	0.1659
No log	10.0	40	0.1605	0.5882	0.1605

Framework versions

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