arabert_cross_organization_task1_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: 0.4714
• Qwk: 0.7597
• Mse: 0.4723

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	1.3842	0.1724	1.3839
No log	0.2667	4	0.9780	0.3534	0.9789
No log	0.4	6	1.4683	0.4626	1.4695
No log	0.5333	8	1.2844	0.5615	1.2856
No log	0.6667	10	0.8166	0.5501	0.8177
No log	0.8	12	0.6646	0.5615	0.6656
No log	0.9333	14	0.6181	0.6308	0.6192
No log	1.0667	16	0.6395	0.7598	0.6406
No log	1.2	18	0.5961	0.7503	0.5973
No log	1.3333	20	0.5222	0.7439	0.5233
No log	1.4667	22	0.5709	0.7564	0.5721
No log	1.6	24	0.5337	0.7493	0.5348
No log	1.7333	26	0.5381	0.7745	0.5392
No log	1.8667	28	0.5385	0.7823	0.5395
No log	2.0	30	0.5204	0.7694	0.5215
No log	2.1333	32	0.5481	0.7727	0.5492
No log	2.2667	34	0.4767	0.7478	0.4777
No log	2.4	36	0.4552	0.7226	0.4561
No log	2.5333	38	0.4590	0.7366	0.4599
No log	2.6667	40	0.4443	0.7177	0.4451
No log	2.8	42	0.4514	0.7415	0.4522
No log	2.9333	44	0.5579	0.8045	0.5590
No log	3.0667	46	0.7664	0.7863	0.7678
No log	3.2	48	0.6906	0.7958	0.6919
No log	3.3333	50	0.4951	0.7710	0.4961
No log	3.4667	52	0.4583	0.7404	0.4591
No log	3.6	54	0.4705	0.7615	0.4715
No log	3.7333	56	0.4873	0.7626	0.4884
No log	3.8667	58	0.4498	0.7546	0.4507
No log	4.0	60	0.4307	0.7203	0.4315
No log	4.1333	62	0.4439	0.7456	0.4449
No log	4.2667	64	0.4697	0.7618	0.4707
No log	4.4	66	0.4679	0.7644	0.4689
No log	4.5333	68	0.4351	0.7431	0.4359
No log	4.6667	70	0.4379	0.7504	0.4388
No log	4.8	72	0.4599	0.7566	0.4608
No log	4.9333	74	0.4597	0.7542	0.4606
No log	5.0667	76	0.4453	0.7436	0.4462
No log	5.2	78	0.4534	0.7462	0.4543
No log	5.3333	80	0.4416	0.7345	0.4424
No log	5.4667	82	0.4467	0.7332	0.4475
No log	5.6	84	0.4936	0.7561	0.4946
No log	5.7333	86	0.5611	0.7947	0.5622
No log	5.8667	88	0.5154	0.7747	0.5164
No log	6.0	90	0.4950	0.7700	0.4960
No log	6.1333	92	0.4817	0.7588	0.4827
No log	6.2667	94	0.4527	0.7499	0.4536
No log	6.4	96	0.4380	0.7228	0.4388
No log	6.5333	98	0.4383	0.7248	0.4391
No log	6.6667	100	0.4494	0.7409	0.4502
No log	6.8	102	0.4509	0.7297	0.4518
No log	6.9333	104	0.4765	0.7516	0.4775
No log	7.0667	106	0.4854	0.7631	0.4864
No log	7.2	108	0.4991	0.7766	0.5001
No log	7.3333	110	0.5297	0.7654	0.5308
No log	7.4667	112	0.5591	0.7862	0.5603
No log	7.6	114	0.5193	0.7711	0.5204
No log	7.7333	116	0.4710	0.7587	0.4719
No log	7.8667	118	0.4527	0.7448	0.4536
No log	8.0	120	0.4573	0.7500	0.4582
No log	8.1333	122	0.4652	0.7567	0.4661
No log	8.2667	124	0.4728	0.7600	0.4738
No log	8.4	126	0.4700	0.7563	0.4709
No log	8.5333	128	0.4667	0.7515	0.4677
No log	8.6667	130	0.4712	0.7538	0.4722
No log	8.8	132	0.4748	0.7555	0.4757
No log	8.9333	134	0.4694	0.7533	0.4703
No log	9.0667	136	0.4637	0.7429	0.4646
No log	9.2	138	0.4616	0.7432	0.4625
No log	9.3333	140	0.4664	0.7454	0.4673
No log	9.4667	142	0.4737	0.7588	0.4746
No log	9.6	144	0.4748	0.7567	0.4757
No log	9.7333	146	0.4743	0.7586	0.4752
No log	9.8667	148	0.4718	0.7597	0.4727
No log	10.0	150	0.4714	0.7597	0.4723

Framework versions

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