Arabic_FineTuningAraBERT_noAug_task2_organization_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: 0.4518
• Qwk: 0.3529
• Mse: 0.4518
• Rmse: 0.6722

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	0.1818	2	3.3301	0.0393	3.3301	1.8249
No log	0.3636	4	2.1739	0.0	2.1739	1.4744
No log	0.5455	6	1.5610	0.0	1.5610	1.2494
No log	0.7273	8	0.9952	-0.0465	0.9952	0.9976
No log	0.9091	10	0.6915	0.1379	0.6915	0.8316
No log	1.0909	12	0.6916	0.1667	0.6916	0.8316
No log	1.2727	14	0.6038	0.1667	0.6038	0.7771
No log	1.4545	16	0.3955	0.2623	0.3955	0.6289
No log	1.6364	18	0.3709	0.2895	0.3709	0.6090
No log	1.8182	20	0.5663	0.25	0.5663	0.7526
No log	2.0	22	0.5160	0.3390	0.5160	0.7184
No log	2.1818	24	0.7031	0.3040	0.7031	0.8385
No log	2.3636	26	1.0395	0.2360	1.0395	1.0195
No log	2.5455	28	0.7460	0.3710	0.7460	0.8637
No log	2.7273	30	0.5786	0.5185	0.5786	0.7607
No log	2.9091	32	0.6841	0.4231	0.6841	0.8271
No log	3.0909	34	0.6319	0.5075	0.6319	0.7949
No log	3.2727	36	0.6059	0.3208	0.6059	0.7784
No log	3.4545	38	0.7028	0.3710	0.7028	0.8383
No log	3.6364	40	0.6680	0.3359	0.6680	0.8173
No log	3.8182	42	0.4981	0.4	0.4981	0.7057
No log	4.0	44	0.4570	0.4324	0.4570	0.6760
No log	4.1818	46	0.4561	0.2373	0.4561	0.6754
No log	4.3636	48	0.4413	0.4324	0.4413	0.6643
No log	4.5455	50	0.4760	0.4103	0.4760	0.6899
No log	4.7273	52	0.6075	0.3710	0.6075	0.7794
No log	4.9091	54	0.5812	0.3710	0.5812	0.7623
No log	5.0909	56	0.5029	0.4220	0.5029	0.7092
No log	5.2727	58	0.4906	0.4894	0.4906	0.7004
No log	5.4545	60	0.4757	0.4894	0.4757	0.6897
No log	5.6364	62	0.4863	0.3590	0.4863	0.6973
No log	5.8182	64	0.4961	0.3710	0.4961	0.7043
No log	6.0	66	0.5642	0.3710	0.5642	0.7511
No log	6.1818	68	0.4859	0.3710	0.4859	0.6971
No log	6.3636	70	0.4060	0.4375	0.4060	0.6371
No log	6.5455	72	0.4107	0.4545	0.4107	0.6409
No log	6.7273	74	0.4135	0.4407	0.4135	0.6430
No log	6.9091	76	0.4101	0.4179	0.4101	0.6404
No log	7.0909	78	0.4123	0.4146	0.4123	0.6421
No log	7.2727	80	0.4229	0.4270	0.4229	0.6503
No log	7.4545	82	0.4499	0.3455	0.4499	0.6707
No log	7.6364	84	0.4670	0.3590	0.4670	0.6833
No log	7.8182	86	0.4711	0.3590	0.4711	0.6864
No log	8.0	88	0.4700	0.3455	0.4700	0.6855
No log	8.1818	90	0.4920	0.3590	0.4920	0.7014
No log	8.3636	92	0.5141	0.3710	0.5141	0.7170
No log	8.5455	94	0.5270	0.3710	0.5270	0.7259
No log	8.7273	96	0.5188	0.3710	0.5188	0.7203
No log	8.9091	98	0.5033	0.3710	0.5033	0.7095
No log	9.0909	100	0.4822	0.3710	0.4822	0.6944
No log	9.2727	102	0.4646	0.3455	0.4646	0.6816
No log	9.4545	104	0.4555	0.3529	0.4555	0.6749
No log	9.6364	106	0.4537	0.3529	0.4537	0.6736
No log	9.8182	108	0.4521	0.3529	0.4521	0.6724
No log	10.0	110	0.4518	0.3529	0.4518	0.6722

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1