arabert_cross_vocabulary_task6_fold6

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:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse
No log	0.0308	2	2.1344	0.0845	2.1260
No log	0.0615	4	1.0808	0.2961	1.0693
No log	0.0923	6	1.3454	0.2890	1.3254
No log	0.1231	8	0.6739	0.5314	0.6662
No log	0.1538	10	0.5779	0.6649	0.5736
No log	0.1846	12	0.5912	0.7569	0.5902
No log	0.2154	14	0.5775	0.7630	0.5772
No log	0.2462	16	0.5694	0.6622	0.5684
No log	0.2769	18	0.7642	0.5844	0.7634
No log	0.3077	20	1.2490	0.4005	1.2461
No log	0.3385	22	1.2661	0.3780	1.2624
No log	0.3692	24	0.8020	0.5334	0.8002
No log	0.4	26	0.6377	0.6083	0.6361
No log	0.4308	28	0.5794	0.6047	0.5774
No log	0.4615	30	0.5299	0.6342	0.5280
No log	0.4923	32	0.4877	0.6511	0.4861
No log	0.5231	34	0.4827	0.6483	0.4810
No log	0.5538	36	0.4477	0.7136	0.4467
No log	0.5846	38	0.4513	0.6644	0.4498
No log	0.6154	40	0.4864	0.6268	0.4842
No log	0.6462	42	0.5576	0.5786	0.5544
No log	0.6769	44	0.6809	0.4995	0.6764
No log	0.7077	46	0.7399	0.4954	0.7349
No log	0.7385	48	0.6881	0.4918	0.6838
No log	0.7692	50	0.6232	0.5309	0.6197
No log	0.8	52	0.5631	0.5592	0.5605
No log	0.8308	54	0.5054	0.6188	0.5036
No log	0.8615	56	0.4969	0.6158	0.4954
No log	0.8923	58	0.4962	0.6158	0.4947
No log	0.9231	60	0.4915	0.6233	0.4901
No log	0.9538	62	0.4898	0.6318	0.4885
No log	0.9846	64	0.4868	0.6478	0.4856