arabert_cross_relevance_task1_fold3

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: 0.2800
Qwk: 0.4057
Mse: 0.2800

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: 64
eval_batch_size: 64
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	0.1333	2	0.4841	0.2229	0.4841
No log	0.2667	4	0.4548	0.1951	0.4548
No log	0.4	6	0.3736	0.2470	0.3736
No log	0.5333	8	0.3640	0.2129	0.3640
No log	0.6667	10	0.3899	0.1839	0.3899
No log	0.8	12	0.3649	0.1986	0.3649
No log	0.9333	14	0.3192	0.3366	0.3192
No log	1.0667	16	0.3134	0.3522	0.3134
No log	1.2	18	0.2989	0.3399	0.2989
No log	1.3333	20	0.3038	0.3248	0.3038
No log	1.4667	22	0.3097	0.3239	0.3097
No log	1.6	24	0.2998	0.3258	0.2998
No log	1.7333	26	0.2810	0.3516	0.2810
No log	1.8667	28	0.2789	0.3522	0.2789
No log	2.0	30	0.2800	0.3509	0.2800
No log	2.1333	32	0.2906	0.3375	0.2906
No log	2.2667	34	0.3124	0.2959	0.3124
No log	2.4	36	0.3211	0.3784	0.3211
No log	2.5333	38	0.3001	0.3428	0.3001
No log	2.6667	40	0.2852	0.3575	0.2852
No log	2.8	42	0.2865	0.3529	0.2865
No log	2.9333	44	0.2806	0.3509	0.2806
No log	3.0667	46	0.2874	0.3391	0.2874
No log	3.2	48	0.3047	0.3615	0.3047
No log	3.3333	50	0.3111	0.3705	0.3111
No log	3.4667	52	0.3016	0.3428	0.3016
No log	3.6	54	0.2849	0.3391	0.2849
No log	3.7333	56	0.2726	0.3502	0.2726
No log	3.8667	58	0.2737	0.3515	0.2737
No log	4.0	60	0.2771	0.3515	0.2771
No log	4.1333	62	0.2716	0.3509	0.2716
No log	4.2667	64	0.2745	0.3480	0.2745
No log	4.4	66	0.2815	0.3431	0.2815
No log	4.5333	68	0.2772	0.3599	0.2772
No log	4.6667	70	0.2685	0.3637	0.2685
No log	4.8	72	0.2627	0.3536	0.2627
No log	4.9333	74	0.2621	0.3549	0.2621
No log	5.0667	76	0.2604	0.3640	0.2604
No log	5.2	78	0.2644	0.3909	0.2644
No log	5.3333	80	0.2834	0.4063	0.2834
No log	5.4667	82	0.2855	0.3857	0.2855
No log	5.6	84	0.2777	0.3709	0.2777
No log	5.7333	86	0.2703	0.3543	0.2703
No log	5.8667	88	0.2731	0.3495	0.2731
No log	6.0	90	0.2756	0.3509	0.2756
No log	6.1333	92	0.2782	0.3538	0.2782
No log	6.2667	94	0.2856	0.3720	0.2856
No log	6.4	96	0.2950	0.4113	0.2950
No log	6.5333	98	0.3066	0.4735	0.3066
No log	6.6667	100	0.2982	0.4566	0.2982
No log	6.8	102	0.2915	0.4196	0.2915
No log	6.9333	104	0.2806	0.3842	0.2806
No log	7.0667	106	0.2757	0.3868	0.2757
No log	7.2	108	0.2790	0.3895	0.2790
No log	7.3333	110	0.2776	0.3868	0.2776
No log	7.4667	112	0.2706	0.3605	0.2706
No log	7.6	114	0.2683	0.3518	0.2683
No log	7.7333	116	0.2688	0.3518	0.2688
No log	7.8667	118	0.2706	0.3617	0.2706
No log	8.0	120	0.2740	0.3712	0.2740
No log	8.1333	122	0.2770	0.3712	0.2770
No log	8.2667	124	0.2813	0.3756	0.2813
No log	8.4	126	0.2862	0.3730	0.2862
No log	8.5333	128	0.2926	0.4157	0.2926
No log	8.6667	130	0.2956	0.4209	0.2956
No log	8.8	132	0.2928	0.4211	0.2928
No log	8.9333	134	0.2870	0.4052	0.2870
No log	9.0667	136	0.2834	0.3945	0.2834
No log	9.2	138	0.2828	0.4002	0.2828
No log	9.3333	140	0.2815	0.3952	0.2815
No log	9.4667	142	0.2814	0.4057	0.2814
No log	9.6	144	0.2807	0.4057	0.2807
No log	9.7333	146	0.2801	0.4057	0.2801
No log	9.8667	148	0.2799	0.4057	0.2799
No log	10.0	150	0.2800	0.4057	0.2800

Framework versions

Transformers 4.44.0
Pytorch 2.4.0
Datasets 2.21.0
Tokenizers 0.19.1

salbatarni
/

arabert_cross_relevance_task1_fold3

arabert_cross_relevance_task1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for salbatarni/arabert_cross_relevance_task1_fold3

Evaluation results