arabert_cross_organization_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: 0.8868
• Qwk: 0.5359
• Mse: 0.8876

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	5.2895	0.0054	5.2856
No log	0.2667	4	3.0949	0.0698	3.0914
No log	0.4	6	1.6236	0.2168	1.6216
No log	0.5333	8	1.1930	0.2638	1.1920
No log	0.6667	10	1.7940	0.2599	1.7930
No log	0.8	12	3.2795	0.1504	3.2772
No log	0.9333	14	2.3117	0.2122	2.3105
No log	1.0667	16	1.3259	0.3185	1.3250
No log	1.2	18	1.1156	0.3075	1.1147
No log	1.3333	20	1.0743	0.3306	1.0736
No log	1.4667	22	1.2168	0.3511	1.2161
No log	1.6	24	1.3139	0.3493	1.3135
No log	1.7333	26	1.2219	0.3893	1.2216
No log	1.8667	28	0.9789	0.4805	0.9789
No log	2.0	30	0.8254	0.5525	0.8256
No log	2.1333	32	0.8267	0.5514	0.8268
No log	2.2667	34	0.8956	0.4976	0.8958
No log	2.4	36	1.2761	0.3798	1.2761
No log	2.5333	38	1.5640	0.3427	1.5638
No log	2.6667	40	1.3598	0.3678	1.3596
No log	2.8	42	1.0347	0.4562	1.0345
No log	2.9333	44	0.9138	0.4910	0.9135
No log	3.0667	46	0.8461	0.5492	0.8459
No log	3.2	48	0.8243	0.5507	0.8244
No log	3.3333	50	1.0141	0.4952	1.0142
No log	3.4667	52	1.0921	0.4640	1.0921
No log	3.6	54	1.0221	0.4941	1.0220
No log	3.7333	56	0.8836	0.5285	0.8836
No log	3.8667	58	0.7919	0.5711	0.7921
No log	4.0	60	0.8281	0.5532	0.8283
No log	4.1333	62	0.9534	0.5227	0.9536
No log	4.2667	64	0.9598	0.5211	0.9601
No log	4.4	66	0.9166	0.5419	0.9169
No log	4.5333	68	0.8422	0.5565	0.8426
No log	4.6667	70	0.8553	0.5458	0.8556
No log	4.8	72	0.9644	0.5070	0.9646
No log	4.9333	74	0.9798	0.5192	0.9801
No log	5.0667	76	0.9185	0.5327	0.9189
No log	5.2	78	0.8475	0.5427	0.8479
No log	5.3333	80	0.8340	0.5557	0.8344
No log	5.4667	82	0.8878	0.5405	0.8882
No log	5.6	84	0.9622	0.5199	0.9627
No log	5.7333	86	0.9394	0.5278	0.9398
No log	5.8667	88	0.8872	0.5334	0.8876
No log	6.0	90	0.8248	0.5428	0.8252
No log	6.1333	92	0.8451	0.5371	0.8454
No log	6.2667	94	0.8324	0.5384	0.8326
No log	6.4	96	0.7920	0.5786	0.7922
No log	6.5333	98	0.8023	0.5742	0.8025
No log	6.6667	100	0.8667	0.5474	0.8670
No log	6.8	102	0.9364	0.5182	0.9367
No log	6.9333	104	0.9710	0.5093	0.9714
No log	7.0667	106	1.0089	0.4947	1.0094
No log	7.2	108	0.9682	0.5057	0.9687
No log	7.3333	110	0.8275	0.5472	0.8281
No log	7.4667	112	0.7651	0.5844	0.7658
No log	7.6	114	0.7873	0.5622	0.7879
No log	7.7333	116	0.8290	0.5478	0.8297
No log	7.8667	118	0.8907	0.5182	0.8914
No log	8.0	120	0.9161	0.5170	0.9168
No log	8.1333	122	0.9115	0.5170	0.9122
No log	8.2667	124	0.9104	0.5170	0.9111
No log	8.4	126	0.8932	0.5228	0.8940
No log	8.5333	128	0.8537	0.5382	0.8545
No log	8.6667	130	0.8599	0.5382	0.8607
No log	8.8	132	0.9062	0.5144	0.9070
No log	8.9333	134	0.9172	0.5132	0.9181
No log	9.0667	136	0.9365	0.5161	0.9374
No log	9.2	138	0.9530	0.5138	0.9539
No log	9.3333	140	0.9499	0.5138	0.9508
No log	9.4667	142	0.9352	0.5134	0.9361
No log	9.6	144	0.9147	0.5132	0.9155
No log	9.7333	146	0.8945	0.5311	0.8953
No log	9.8667	148	0.8886	0.5310	0.8894
No log	10.0	150	0.8868	0.5359	0.8876

Framework versions

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