arabert_cross_vocabulary_task1_fold3

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: 0.6543
• Qwk: 0.8547
• Mse: 0.6543

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	2.1991	0.1474	2.1991
No log	0.2667	4	1.6062	0.1520	1.6062
No log	0.4	6	1.5937	0.3436	1.5937
No log	0.5333	8	1.1613	0.6120	1.1613
No log	0.6667	10	1.0503	0.7478	1.0503
No log	0.8	12	0.7718	0.7837	0.7718
No log	0.9333	14	0.6578	0.7874	0.6578
No log	1.0667	16	0.6200	0.7876	0.6200
No log	1.2	18	0.6610	0.8102	0.6610
No log	1.3333	20	0.6508	0.8233	0.6508
No log	1.4667	22	0.6181	0.8360	0.6181
No log	1.6	24	0.6494	0.8333	0.6494
No log	1.7333	26	0.5220	0.7872	0.5220
No log	1.8667	28	0.5440	0.8098	0.5440
No log	2.0	30	0.6917	0.8299	0.6917
No log	2.1333	32	0.7100	0.8241	0.7100
No log	2.2667	34	0.6018	0.8256	0.6018
No log	2.4	36	0.5920	0.8362	0.5920
No log	2.5333	38	0.5900	0.8254	0.5900
No log	2.6667	40	0.5183	0.8071	0.5183
No log	2.8	42	0.5565	0.8214	0.5565
No log	2.9333	44	0.5828	0.8308	0.5828
No log	3.0667	46	0.6086	0.8345	0.6086
No log	3.2	48	0.9512	0.8040	0.9512
No log	3.3333	50	1.0514	0.7892	1.0514
No log	3.4667	52	0.7574	0.8307	0.7574
No log	3.6	54	0.5438	0.8157	0.5438
No log	3.7333	56	0.5688	0.8295	0.5688
No log	3.8667	58	0.7090	0.8272	0.7090
No log	4.0	60	0.6153	0.8315	0.6153
No log	4.1333	62	0.5938	0.8311	0.5938
No log	4.2667	64	0.5535	0.8284	0.5535
No log	4.4	66	0.7113	0.8397	0.7113
No log	4.5333	68	0.7956	0.8396	0.7956
No log	4.6667	70	0.6577	0.8415	0.6577
No log	4.8	72	0.5410	0.8175	0.5410
No log	4.9333	74	0.5447	0.8164	0.5447
No log	5.0667	76	0.6400	0.8362	0.6400
No log	5.2	78	0.6465	0.8350	0.6465
No log	5.3333	80	0.5521	0.8190	0.5521
No log	5.4667	82	0.5413	0.8159	0.5413
No log	5.6	84	0.5904	0.8356	0.5904
No log	5.7333	86	0.6050	0.8329	0.6050
No log	5.8667	88	0.5617	0.8344	0.5617
No log	6.0	90	0.5078	0.8086	0.5078
No log	6.1333	92	0.5744	0.8431	0.5744
No log	6.2667	94	0.8177	0.8508	0.8177
No log	6.4	96	0.9516	0.8372	0.9516
No log	6.5333	98	0.8522	0.8514	0.8522
No log	6.6667	100	0.6484	0.8513	0.6484
No log	6.8	102	0.5556	0.8426	0.5556
No log	6.9333	104	0.5410	0.8334	0.5410
No log	7.0667	106	0.6003	0.8457	0.6003
No log	7.2	108	0.6955	0.8578	0.6955
No log	7.3333	110	0.6870	0.8586	0.6870
No log	7.4667	112	0.6444	0.8510	0.6444
No log	7.6	114	0.5518	0.8355	0.5518
No log	7.7333	116	0.5347	0.8285	0.5347
No log	7.8667	118	0.5790	0.8402	0.5790
No log	8.0	120	0.6668	0.8499	0.6668
No log	8.1333	122	0.6878	0.8492	0.6878
No log	8.2667	124	0.6406	0.8545	0.6406
No log	8.4	126	0.6005	0.8510	0.6005
No log	8.5333	128	0.6017	0.8494	0.6017
No log	8.6667	130	0.5940	0.8481	0.5940
No log	8.8	132	0.5792	0.8445	0.5792
No log	8.9333	134	0.5857	0.8481	0.5857
No log	9.0667	136	0.6217	0.8492	0.6217
No log	9.2	138	0.6735	0.8562	0.6735
No log	9.3333	140	0.7067	0.8519	0.7067
No log	9.4667	142	0.7028	0.8584	0.7028
No log	9.6	144	0.7006	0.8584	0.7006
No log	9.7333	146	0.6820	0.8583	0.6820
No log	9.8667	148	0.6634	0.8629	0.6634
No log	10.0	150	0.6543	0.8547	0.6543

Framework versions

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