arabert_baseline_relevance_task2_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: 0.1850
• Qwk: 0.0597
• Mse: 0.1935

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	0.9871	0.0205	0.9763
No log	0.6667	4	0.1822	0.1049	0.1846
No log	1.0	6	0.2694	-0.0176	0.2773
No log	1.3333	8	0.2612	-0.0791	0.2700
No log	1.6667	10	0.2291	0.0187	0.2405
No log	2.0	12	0.1605	0.0755	0.1675
No log	2.3333	14	0.1556	0.1049	0.1617
No log	2.6667	16	0.1455	0.1370	0.1500
No log	3.0	18	0.1386	0.0	0.1414
No log	3.3333	20	0.1423	0.0	0.1448
No log	3.6667	22	0.1393	0.0	0.1429
No log	4.0	24	0.1807	0.4815	0.1875
No log	4.3333	26	0.2622	0.0	0.2718
No log	4.6667	28	0.2372	0.0	0.2476
No log	5.0	30	0.1765	-0.1290	0.1845
No log	5.3333	32	0.1633	0.0483	0.1688
No log	5.6667	34	0.1551	0.0755	0.1613
No log	6.0	36	0.1689	0.1674	0.1757
No log	6.3333	38	0.1736	0.2687	0.1798
No log	6.6667	40	0.1678	0.2150	0.1732
No log	7.0	42	0.1581	0.1250	0.1631
No log	7.3333	44	0.1540	0.0526	0.1591
No log	7.6667	46	0.1536	0.0526	0.1590
No log	8.0	48	0.1603	0.1250	0.1666
No log	8.3333	50	0.1716	0.2150	0.1790
No log	8.6667	52	0.1797	0.0597	0.1878
No log	9.0	54	0.1828	0.0597	0.1911
No log	9.3333	56	0.1841	0.0597	0.1925
No log	9.6667	58	0.1849	0.0597	0.1933
No log	10.0	60	0.1850	0.0597	0.1935

Framework versions

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