arabert_cross_organization_task4_fold1

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: 0.7438
• Qwk: 0.4143
• Mse: 0.7438

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	0.1176	2	3.2005	0.0155	3.2005
No log	0.2353	4	1.7053	-0.0034	1.7053
No log	0.3529	6	1.1027	0.1636	1.1027
No log	0.4706	8	1.0959	0.1953	1.0959
No log	0.5882	10	1.1008	0.2356	1.1008
No log	0.7059	12	0.7123	0.3763	0.7123
No log	0.8235	14	0.7466	0.4020	0.7466
No log	0.9412	16	0.9174	0.3522	0.9174
No log	1.0588	18	0.9416	0.3154	0.9416
No log	1.1765	20	0.7002	0.3766	0.7002
No log	1.2941	22	0.6826	0.3709	0.6826
No log	1.4118	24	0.6996	0.3822	0.6996
No log	1.5294	26	0.6165	0.4733	0.6165
No log	1.6471	28	0.5696	0.5228	0.5696
No log	1.7647	30	0.7076	0.4534	0.7076
No log	1.8824	32	0.7251	0.4533	0.7251
No log	2.0	34	0.5922	0.4921	0.5922
No log	2.1176	36	0.5428	0.5484	0.5428
No log	2.2353	38	0.5662	0.5159	0.5662
No log	2.3529	40	0.6256	0.4714	0.6256
No log	2.4706	42	0.6008	0.4805	0.6008
No log	2.5882	44	0.5493	0.5367	0.5493
No log	2.7059	46	0.5855	0.5042	0.5855
No log	2.8235	48	0.6888	0.4526	0.6888
No log	2.9412	50	0.6594	0.4838	0.6594
No log	3.0588	52	0.5913	0.5174	0.5913
No log	3.1765	54	0.5440	0.5485	0.5440
No log	3.2941	56	0.5766	0.5008	0.5766
No log	3.4118	58	0.7541	0.4405	0.7541
No log	3.5294	60	0.6666	0.4686	0.6666
No log	3.6471	62	0.5454	0.5289	0.5454
No log	3.7647	64	0.5373	0.5502	0.5373
No log	3.8824	66	0.5811	0.4814	0.5811
No log	4.0	68	0.8522	0.3958	0.8522
No log	4.1176	70	0.9611	0.3420	0.9611
No log	4.2353	72	0.7150	0.4366	0.7150
No log	4.3529	74	0.5129	0.5461	0.5129
No log	4.4706	76	0.5130	0.5731	0.5130
No log	4.5882	78	0.5549	0.5002	0.5549
No log	4.7059	80	0.6423	0.4682	0.6423
No log	4.8235	82	0.6433	0.4655	0.6433
No log	4.9412	84	0.6814	0.4383	0.6814
No log	5.0588	86	0.6506	0.4536	0.6506
No log	5.1765	88	0.6845	0.4340	0.6845
No log	5.2941	90	0.6105	0.4691	0.6105
No log	5.4118	92	0.5818	0.5096	0.5818
No log	5.5294	94	0.6505	0.4675	0.6505
No log	5.6471	96	0.8762	0.4031	0.8762
No log	5.7647	98	0.9354	0.3979	0.9354
No log	5.8824	100	0.7273	0.4370	0.7273
No log	6.0	102	0.5439	0.5370	0.5439
No log	6.1176	104	0.5275	0.5934	0.5275
No log	6.2353	106	0.5389	0.5407	0.5389
No log	6.3529	108	0.6632	0.4439	0.6632
No log	6.4706	110	0.7438	0.4262	0.7438
No log	6.5882	112	0.7194	0.4386	0.7194
No log	6.7059	114	0.6649	0.4611	0.6649
No log	6.8235	116	0.6469	0.4620	0.6469
No log	6.9412	118	0.6869	0.4426	0.6869
No log	7.0588	120	0.6784	0.4431	0.6784
No log	7.1765	122	0.6099	0.4604	0.6099
No log	7.2941	124	0.6103	0.4469	0.6103
No log	7.4118	126	0.6514	0.4384	0.6514
No log	7.5294	128	0.7174	0.4218	0.7174
No log	7.6471	130	0.7205	0.4218	0.7205
No log	7.7647	132	0.6510	0.4378	0.6510
No log	7.8824	134	0.5851	0.4688	0.5851
No log	8.0	136	0.5810	0.4909	0.5810
No log	8.1176	138	0.6226	0.4464	0.6226
No log	8.2353	140	0.7068	0.4404	0.7068
No log	8.3529	142	0.8169	0.4120	0.8169
No log	8.4706	144	0.8268	0.4106	0.8268
No log	8.5882	146	0.7821	0.4211	0.7821
No log	8.7059	148	0.7186	0.4252	0.7186
No log	8.8235	150	0.6896	0.4345	0.6896
No log	8.9412	152	0.6602	0.4409	0.6602
No log	9.0588	154	0.6525	0.4435	0.6525
No log	9.1765	156	0.6577	0.4435	0.6577
No log	9.2941	158	0.6779	0.4325	0.6779
No log	9.4118	160	0.7177	0.4166	0.7177
No log	9.5294	162	0.7502	0.4106	0.7502
No log	9.6471	164	0.7522	0.4057	0.7522
No log	9.7647	166	0.7503	0.4106	0.7503
No log	9.8824	168	0.7475	0.4150	0.7475
No log	10.0	170	0.7438	0.4143	0.7438

Framework versions

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