arabert_cross_organization_task5_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: 0.9408
• Qwk: 0.3679
• Mse: 0.9408

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	5.0062	-0.0036	5.0062
No log	0.2667	4	2.2755	0.0402	2.2755
No log	0.4	6	0.9209	0.1375	0.9209
No log	0.5333	8	0.7216	0.2666	0.7216
No log	0.6667	10	2.2848	0.1146	2.2848
No log	0.8	12	2.4339	0.1213	2.4339
No log	0.9333	14	0.7615	0.3777	0.7615
No log	1.0667	16	0.6179	0.5173	0.6179
No log	1.2	18	0.6800	0.3857	0.6800
No log	1.3333	20	1.1833	0.3011	1.1833
No log	1.4667	22	1.1609	0.3150	1.1609
No log	1.6	24	0.6395	0.4537	0.6395
No log	1.7333	26	0.5534	0.5065	0.5534
No log	1.8667	28	0.6236	0.4420	0.6236
No log	2.0	30	0.6228	0.4306	0.6228
No log	2.1333	32	0.5518	0.4931	0.5518
No log	2.2667	34	0.6084	0.4242	0.6084
No log	2.4	36	0.7055	0.3694	0.7055
No log	2.5333	38	0.7175	0.3935	0.7175
No log	2.6667	40	0.6114	0.4689	0.6114
No log	2.8	42	0.7045	0.4030	0.7045
No log	2.9333	44	0.9915	0.3267	0.9915
No log	3.0667	46	1.0131	0.3023	1.0131
No log	3.2	48	0.7062	0.3732	0.7062
No log	3.3333	50	0.5236	0.5208	0.5236
No log	3.4667	52	0.5249	0.5718	0.5249
No log	3.6	54	0.5782	0.4935	0.5782
No log	3.7333	56	0.8300	0.4331	0.8300
No log	3.8667	58	1.0062	0.3503	1.0062
No log	4.0	60	0.8152	0.3857	0.8152
No log	4.1333	62	0.5614	0.4616	0.5614
No log	4.2667	64	0.5056	0.5013	0.5056
No log	4.4	66	0.5357	0.4729	0.5357
No log	4.5333	68	0.6479	0.4155	0.6479
No log	4.6667	70	0.8469	0.3777	0.8469
No log	4.8	72	0.8226	0.3870	0.8226
No log	4.9333	74	0.7370	0.4225	0.7370
No log	5.0667	76	0.7636	0.4313	0.7636
No log	5.2	78	0.8153	0.4219	0.8153
No log	5.3333	80	0.8004	0.4026	0.8004
No log	5.4667	82	0.7252	0.4152	0.7252
No log	5.6	84	0.7142	0.4140	0.7142
No log	5.7333	86	0.7743	0.3924	0.7743
No log	5.8667	88	0.6869	0.4122	0.6869
No log	6.0	90	0.6812	0.4211	0.6812
No log	6.1333	92	0.7593	0.4027	0.7593
No log	6.2667	94	0.9111	0.3581	0.9111
No log	6.4	96	0.9395	0.3469	0.9395
No log	6.5333	98	0.7996	0.3869	0.7996
No log	6.6667	100	0.6895	0.4088	0.6895
No log	6.8	102	0.6709	0.4175	0.6709
No log	6.9333	104	0.7444	0.4091	0.7444
No log	7.0667	106	0.9335	0.3874	0.9335
No log	7.2	108	1.1591	0.3347	1.1591
No log	7.3333	110	1.1745	0.3240	1.1745
No log	7.4667	112	1.0111	0.3414	1.0111
No log	7.6	114	0.7911	0.3951	0.7911
No log	7.7333	116	0.7124	0.4080	0.7124
No log	7.8667	118	0.7261	0.4029	0.7261
No log	8.0	120	0.7824	0.3852	0.7824
No log	8.1333	122	0.8528	0.3744	0.8528
No log	8.2667	124	0.8584	0.3744	0.8584
No log	8.4	126	0.8434	0.3747	0.8434
No log	8.5333	128	0.8058	0.3877	0.8058
No log	8.6667	130	0.7951	0.3938	0.7951
No log	8.8	132	0.8278	0.3925	0.8278
No log	8.9333	134	0.8301	0.3938	0.8301
No log	9.0667	136	0.8599	0.3885	0.8599
No log	9.2	138	0.9104	0.3734	0.9104
No log	9.3333	140	0.9438	0.3692	0.9438
No log	9.4667	142	0.9743	0.3664	0.9743
No log	9.6	144	0.9827	0.3664	0.9827
No log	9.7333	146	0.9690	0.3656	0.9690
No log	9.8667	148	0.9506	0.3654	0.9506
No log	10.0	150	0.9408	0.3679	0.9408

Framework versions

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