arabert_cross_organization_task3_fold2

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: 1.6024
• Qwk: 0.0538
• Mse: 1.6024

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	0.1111	2	4.4408	0.0040	4.4408
No log	0.2222	4	2.1445	-0.0019	2.1445
No log	0.3333	6	1.2335	-0.0070	1.2335
No log	0.4444	8	1.2037	-0.0160	1.2037
No log	0.5556	10	1.2041	-0.0073	1.2041
No log	0.6667	12	1.1517	0.0051	1.1517
No log	0.7778	14	1.2374	0.0328	1.2374
No log	0.8889	16	1.1607	-0.0476	1.1607
No log	1.0	18	1.1734	-0.0518	1.1734
No log	1.1111	20	1.2625	-0.0809	1.2625
No log	1.2222	22	1.3757	0.0003	1.3757
No log	1.3333	24	1.1818	-0.1060	1.1818
No log	1.4444	26	1.2926	0.0	1.2926
No log	1.5556	28	1.6227	-0.0906	1.6227
No log	1.6667	30	1.8505	0.0618	1.8505
No log	1.7778	32	1.4810	0.0402	1.4810
No log	1.8889	34	1.6514	0.0454	1.6514
No log	2.0	36	1.9399	0.0198	1.9399
No log	2.1111	38	1.6927	0.0351	1.6927
No log	2.2222	40	1.5365	0.0112	1.5365
No log	2.3333	42	1.7530	0.0199	1.7530
No log	2.4444	44	1.5376	0.0302	1.5376
No log	2.5556	46	1.4487	-0.0223	1.4487
No log	2.6667	48	1.7456	0.0144	1.7456
No log	2.7778	50	1.9590	0.0498	1.9590
No log	2.8889	52	1.6503	0.0145	1.6503
No log	3.0	54	1.4764	-0.0314	1.4764
No log	3.1111	56	1.6835	0.0294	1.6835
No log	3.2222	58	1.7955	0.0312	1.7955
No log	3.3333	60	1.7538	0.0635	1.7538
No log	3.4444	62	1.4927	0.0176	1.4927
No log	3.5556	64	1.6904	0.0720	1.6904
No log	3.6667	66	1.8393	0.0312	1.8393
No log	3.7778	68	1.8313	0.0254	1.8313
No log	3.8889	70	1.6934	0.0842	1.6934
No log	4.0	72	1.5049	0.0730	1.5049
No log	4.1111	74	1.6026	0.0175	1.6026
No log	4.2222	76	1.5882	0.0325	1.5882
No log	4.3333	78	1.6196	0.0264	1.6196
No log	4.4444	80	1.5514	0.0974	1.5514
No log	4.5556	82	1.4767	0.0909	1.4767
No log	4.6667	84	1.2836	0.1034	1.2836
No log	4.7778	86	1.3626	0.0270	1.3626
No log	4.8889	88	1.6465	0.0229	1.6465
No log	5.0	90	1.8343	-0.0220	1.8343
No log	5.1111	92	1.6557	0.0083	1.6557
No log	5.2222	94	1.3225	-0.0058	1.3225
No log	5.3333	96	1.2482	0.0470	1.2482
No log	5.4444	98	1.3076	0.0607	1.3076
No log	5.5556	100	1.6016	0.0775	1.6016
No log	5.6667	102	1.8225	0.0197	1.8225
No log	5.7778	104	1.7541	-0.0002	1.7541
No log	5.8889	106	1.5325	0.0489	1.5325
No log	6.0	108	1.4866	0.1203	1.4866
No log	6.1111	110	1.5168	0.0747	1.5168
No log	6.2222	112	1.5806	0.0628	1.5806
No log	6.3333	114	1.5301	0.0840	1.5301
No log	6.4444	116	1.5252	0.1176	1.5252
No log	6.5556	118	1.6195	0.0414	1.6195
No log	6.6667	120	1.7519	-0.0347	1.7519
No log	6.7778	122	1.7121	0.0055	1.7121
No log	6.8889	124	1.5662	0.0951	1.5662
No log	7.0	126	1.5098	0.1301	1.5098
No log	7.1111	128	1.5746	0.12	1.5746
No log	7.2222	130	1.7267	-0.0092	1.7267
No log	7.3333	132	1.7245	-0.0092	1.7245
No log	7.4444	134	1.5965	0.0502	1.5965
No log	7.5556	136	1.5245	0.0966	1.5245
No log	7.6667	138	1.4468	0.0095	1.4468
No log	7.7778	140	1.4564	0.0425	1.4564
No log	7.8889	142	1.5131	0.0840	1.5131
No log	8.0	144	1.6343	0.0606	1.6343
No log	8.1111	146	1.6708	0.0339	1.6708
No log	8.2222	148	1.7099	0.0339	1.7099
No log	8.3333	150	1.7246	0.0339	1.7246
No log	8.4444	152	1.7128	0.0339	1.7128
No log	8.5556	154	1.6734	0.0657	1.6734
No log	8.6667	156	1.6578	0.0520	1.6578
No log	8.7778	158	1.7162	0.0533	1.7162
No log	8.8889	160	1.7512	-0.0403	1.7512
No log	9.0	162	1.7393	-0.0034	1.7393
No log	9.1111	164	1.6847	0.0542	1.6847
No log	9.2222	166	1.6059	0.0442	1.6059
No log	9.3333	168	1.5649	0.0881	1.5649
No log	9.4444	170	1.5449	0.1090	1.5449
No log	9.5556	172	1.5536	0.1090	1.5536
No log	9.6667	174	1.5814	0.0419	1.5814
No log	9.7778	176	1.5969	0.0560	1.5969
No log	9.8889	178	1.6011	0.0560	1.6011
No log	10.0	180	1.6024	0.0538	1.6024

Framework versions

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