Arabic_FineTuningAraBERT_noAug_task1_organization_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: 0.6299
• Qwk: 0.7439
• Mse: 0.6299
• Rmse: 0.7937

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	0.1818	2	5.1582	0.0	5.1582	2.2712
No log	0.3636	4	3.4397	0.1099	3.4397	1.8547
No log	0.5455	6	2.2989	0.1163	2.2989	1.5162
No log	0.7273	8	1.6783	0.3029	1.6783	1.2955
No log	0.9091	10	1.1464	0.3005	1.1464	1.0707
No log	1.0909	12	1.1684	0.1992	1.1684	1.0809
No log	1.2727	14	1.1472	0.2309	1.1472	1.0711
No log	1.4545	16	0.8973	0.5682	0.8973	0.9472
No log	1.6364	18	0.8612	0.5682	0.8612	0.9280
No log	1.8182	20	0.8342	0.5682	0.8342	0.9134
No log	2.0	22	0.8602	0.5674	0.8602	0.9275
No log	2.1818	24	0.9171	0.5078	0.9171	0.9577
No log	2.3636	26	0.8366	0.5455	0.8367	0.9147
No log	2.5455	28	0.9156	0.5237	0.9156	0.9569
No log	2.7273	30	1.0261	0.5224	1.0261	1.0129
No log	2.9091	32	0.8514	0.5645	0.8514	0.9227
No log	3.0909	34	0.9594	0.5674	0.9594	0.9795
No log	3.2727	36	1.1573	0.5249	1.1573	1.0758
No log	3.4545	38	1.0258	0.5252	1.0258	1.0128
No log	3.6364	40	0.8211	0.7073	0.8211	0.9061
No log	3.8182	42	0.7590	0.6207	0.7590	0.8712
No log	4.0	44	0.8733	0.5579	0.8733	0.9345
No log	4.1818	46	0.7719	0.5636	0.7719	0.8786
No log	4.3636	48	0.6061	0.6671	0.6061	0.7785
No log	4.5455	50	0.7785	0.7610	0.7785	0.8823
No log	4.7273	52	0.9622	0.6927	0.9622	0.9809
No log	4.9091	54	0.9068	0.7351	0.9068	0.9522
No log	5.0909	56	0.6798	0.7439	0.6798	0.8245
No log	5.2727	58	0.5728	0.7298	0.5728	0.7569
No log	5.4545	60	0.5883	0.7017	0.5883	0.7670
No log	5.6364	62	0.6125	0.7298	0.6125	0.7826
No log	5.8182	64	0.6933	0.7769	0.6933	0.8326
No log	6.0	66	0.7357	0.7769	0.7357	0.8577
No log	6.1818	68	0.7642	0.73	0.7642	0.8742
No log	6.3636	70	0.7194	0.7769	0.7194	0.8482
No log	6.5455	72	0.6427	0.7533	0.6427	0.8017
No log	6.7273	74	0.6055	0.6613	0.6055	0.7781
No log	6.9091	76	0.5907	0.7298	0.5907	0.7686
No log	7.0909	78	0.5844	0.7298	0.5844	0.7645
No log	7.2727	80	0.6063	0.7533	0.6063	0.7787
No log	7.4545	82	0.6572	0.7439	0.6572	0.8107
No log	7.6364	84	0.6463	0.7439	0.6463	0.8039
No log	7.8182	86	0.5916	0.7708	0.5916	0.7692
No log	8.0	88	0.5568	0.7449	0.5568	0.7462
No log	8.1818	90	0.5495	0.7449	0.5495	0.7413
No log	8.3636	92	0.5437	0.7371	0.5437	0.7373
No log	8.5455	94	0.5558	0.7449	0.5558	0.7455
No log	8.7273	96	0.5909	0.7708	0.5909	0.7687
No log	8.9091	98	0.6241	0.7439	0.6241	0.7900
No log	9.0909	100	0.6481	0.7439	0.6481	0.8051
No log	9.2727	102	0.6482	0.7439	0.6482	0.8051
No log	9.4545	104	0.6379	0.7439	0.6379	0.7987
No log	9.6364	106	0.6310	0.7439	0.6310	0.7944
No log	9.8182	108	0.6314	0.7439	0.6314	0.7946
No log	10.0	110	0.6299	0.7439	0.6299	0.7937

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1