Arabic_FineTuningAraBERT_noAug_task5_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: 0.6478
• Qwk: 0.7586
• Mse: 0.6478
• Rmse: 0.8049

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	2.0442	0.0	2.0442	1.4297
No log	0.3636	4	1.1869	0.1700	1.1869	1.0895
No log	0.5455	6	0.8428	0.2068	0.8428	0.9180
No log	0.7273	8	0.7690	0.6040	0.7690	0.8769
No log	0.9091	10	0.8874	0.4444	0.8874	0.9420
No log	1.0909	12	0.9601	0.4097	0.9601	0.9799
No log	1.2727	14	0.8736	0.4502	0.8736	0.9347
No log	1.4545	16	0.6935	0.6285	0.6935	0.8328
No log	1.6364	18	0.6061	0.6626	0.6061	0.7785
No log	1.8182	20	0.5390	0.6960	0.5390	0.7342
No log	2.0	22	0.5004	0.6285	0.5004	0.7074
No log	2.1818	24	0.4846	0.6285	0.4846	0.6961
No log	2.3636	26	0.4671	0.6243	0.4671	0.6835
No log	2.5455	28	0.4528	0.6734	0.4528	0.6729
No log	2.7273	30	0.4648	0.7108	0.4648	0.6818
No log	2.9091	32	0.4552	0.7108	0.4552	0.6747
No log	3.0909	34	0.4754	0.7917	0.4754	0.6895
No log	3.2727	36	0.4998	0.6388	0.4998	0.7070
No log	3.4545	38	0.4805	0.7454	0.4805	0.6932
No log	3.6364	40	0.4750	0.8218	0.4750	0.6892
No log	3.8182	42	0.4828	0.7840	0.4828	0.6948
No log	4.0	44	0.4966	0.7840	0.4966	0.7047
No log	4.1818	46	0.4787	0.7534	0.4787	0.6918
No log	4.3636	48	0.4884	0.7534	0.4884	0.6989
No log	4.5455	50	0.4588	0.7534	0.4588	0.6773
No log	4.7273	52	0.4583	0.7534	0.4583	0.6770
No log	4.9091	54	0.4887	0.7840	0.4887	0.6990
No log	5.0909	56	0.4846	0.7840	0.4846	0.6961
No log	5.2727	58	0.5068	0.7840	0.5068	0.7119
No log	5.4545	60	0.5388	0.7586	0.5388	0.7340
No log	5.6364	62	0.5131	0.7516	0.5131	0.7163
No log	5.8182	64	0.4889	0.7773	0.4889	0.6992
No log	6.0	66	0.4785	0.7773	0.4785	0.6917
No log	6.1818	68	0.4649	0.7773	0.4649	0.6819
No log	6.3636	70	0.4552	0.7773	0.4552	0.6747
No log	6.5455	72	0.4719	0.7887	0.4719	0.6869
No log	6.7273	74	0.5683	0.7955	0.5683	0.7539
No log	6.9091	76	0.6327	0.7679	0.6327	0.7955
No log	7.0909	78	0.6407	0.7679	0.6407	0.8005
No log	7.2727	80	0.6376	0.7679	0.6376	0.7985
No log	7.4545	82	0.6129	0.7374	0.6129	0.7829
No log	7.6364	84	0.5554	0.7955	0.5554	0.7453
No log	7.8182	86	0.5371	0.7955	0.5371	0.7328
No log	8.0	88	0.5544	0.7955	0.5544	0.7446
No log	8.1818	90	0.5896	0.7374	0.5896	0.7678
No log	8.3636	92	0.6170	0.7679	0.6170	0.7855
No log	8.5455	94	0.6267	0.7679	0.6267	0.7916
No log	8.7273	96	0.6398	0.7586	0.6398	0.7999
No log	8.9091	98	0.6484	0.7586	0.6484	0.8053
No log	9.0909	100	0.6476	0.7586	0.6476	0.8047
No log	9.2727	102	0.6573	0.7586	0.6573	0.8107
No log	9.4545	104	0.6585	0.7586	0.6585	0.8115
No log	9.6364	106	0.6530	0.7586	0.6530	0.8081
No log	9.8182	108	0.6491	0.7586	0.6491	0.8057
No log	10.0	110	0.6478	0.7586	0.6478	0.8049

Framework versions

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