arabert_cross_organization_task2_fold5

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: 0.4864
• Qwk: 0.6953
• Mse: 0.4868

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	1.3091	0.2225	1.3089
No log	0.2667	4	0.8804	0.3887	0.8814
No log	0.4	6	1.3858	0.5574	1.3875
No log	0.5333	8	0.8835	0.6154	0.8852
No log	0.6667	10	0.7015	0.4522	0.7026
No log	0.8	12	0.6464	0.5054	0.6475
No log	0.9333	14	0.7433	0.7082	0.7448
No log	1.0667	16	0.8118	0.7522	0.8134
No log	1.2	18	0.6135	0.7499	0.6147
No log	1.3333	20	0.5249	0.6739	0.5259
No log	1.4667	22	0.5390	0.7248	0.5401
No log	1.6	24	0.6195	0.7729	0.6207
No log	1.7333	26	0.5748	0.7628	0.5759
No log	1.8667	28	0.5013	0.7261	0.5022
No log	2.0	30	0.5356	0.7773	0.5366
No log	2.1333	32	0.5953	0.7981	0.5964
No log	2.2667	34	0.6287	0.8036	0.6298
No log	2.4	36	0.5427	0.7642	0.5438
No log	2.5333	38	0.4766	0.6805	0.4773
No log	2.6667	40	0.4783	0.6777	0.4789
No log	2.8	42	0.5040	0.7282	0.5048
No log	2.9333	44	0.5170	0.7463	0.5179
No log	3.0667	46	0.4870	0.7115	0.4876
No log	3.2	48	0.5068	0.7429	0.5075
No log	3.3333	50	0.5038	0.7270	0.5044
No log	3.4667	52	0.4985	0.7013	0.4989
No log	3.6	54	0.4972	0.6846	0.4975
No log	3.7333	56	0.4943	0.6912	0.4947
No log	3.8667	58	0.5072	0.7104	0.5078
No log	4.0	60	0.5132	0.7203	0.5139
No log	4.1333	62	0.5679	0.7897	0.5689
No log	4.2667	64	0.5555	0.7899	0.5566
No log	4.4	66	0.4706	0.6934	0.4712
No log	4.5333	68	0.4707	0.6425	0.4710
No log	4.6667	70	0.4678	0.6421	0.4680
No log	4.8	72	0.4657	0.6697	0.4660
No log	4.9333	74	0.4644	0.7034	0.4648
No log	5.0667	76	0.4691	0.7052	0.4695
No log	5.2	78	0.4782	0.7024	0.4787
No log	5.3333	80	0.4778	0.6948	0.4782
No log	5.4667	82	0.4788	0.6806	0.4792
No log	5.6	84	0.4857	0.7050	0.4862
No log	5.7333	86	0.4827	0.7024	0.4832
No log	5.8667	88	0.4770	0.6872	0.4774
No log	6.0	90	0.4795	0.6277	0.4798
No log	6.1333	92	0.4708	0.6656	0.4712
No log	6.2667	94	0.4697	0.7074	0.4702
No log	6.4	96	0.4653	0.6945	0.4656
No log	6.5333	98	0.4668	0.6693	0.4671
No log	6.6667	100	0.4669	0.6885	0.4672
No log	6.8	102	0.4696	0.6978	0.4700
No log	6.9333	104	0.4724	0.6954	0.4727
No log	7.0667	106	0.4741	0.6619	0.4743
No log	7.2	108	0.4803	0.6229	0.4804
No log	7.3333	110	0.4719	0.6396	0.4721
No log	7.4667	112	0.4673	0.7015	0.4677
No log	7.6	114	0.4766	0.7129	0.4772
No log	7.7333	116	0.4720	0.7071	0.4725
No log	7.8667	118	0.4730	0.6457	0.4733
No log	8.0	120	0.4829	0.6097	0.4831
No log	8.1333	122	0.4865	0.6055	0.4866
No log	8.2667	124	0.4796	0.6640	0.4799
No log	8.4	126	0.4806	0.6954	0.4811
No log	8.5333	128	0.4865	0.7119	0.4870
No log	8.6667	130	0.4841	0.7139	0.4846
No log	8.8	132	0.4802	0.6936	0.4806
No log	8.9333	134	0.4820	0.6650	0.4823
No log	9.0667	136	0.4843	0.6546	0.4846
No log	9.2	138	0.4842	0.6572	0.4845
No log	9.3333	140	0.4837	0.6715	0.4840
No log	9.4667	142	0.4849	0.6959	0.4853
No log	9.6	144	0.4863	0.6988	0.4867
No log	9.7333	146	0.4865	0.6953	0.4869
No log	9.8667	148	0.4864	0.6953	0.4868
No log	10.0	150	0.4864	0.6953	0.4868

Framework versions

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