Arabic_FineTuningAraBERT_noAug_task2_organization_fold0

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: 0.6264
• Qwk: 0.3288
• Mse: 0.6264
• Rmse: 0.7915

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	3.1620	-0.0479	3.1620	1.7782
No log	0.3636	4	2.8548	-0.0581	2.8548	1.6896
No log	0.5455	6	1.2379	0.0245	1.2379	1.1126
No log	0.7273	8	0.8211	0.0491	0.8211	0.9062
No log	0.9091	10	0.7299	0.0	0.7299	0.8544
No log	1.0909	12	0.7277	0.0	0.7277	0.8530
No log	1.2727	14	0.6949	0.1213	0.6949	0.8336
No log	1.4545	16	0.6961	0.1923	0.6961	0.8343
No log	1.6364	18	0.6607	0.1564	0.6607	0.8129
No log	1.8182	20	0.6521	0.1923	0.6521	0.8075
No log	2.0	22	0.6520	0.1213	0.6520	0.8075
No log	2.1818	24	0.6509	0.1923	0.6509	0.8068
No log	2.3636	26	0.6949	0.1747	0.6949	0.8336
No log	2.5455	28	0.7266	0.2119	0.7266	0.8524
No log	2.7273	30	0.6957	0.2119	0.6957	0.8341
No log	2.9091	32	0.6570	0.2289	0.6570	0.8106
No log	3.0909	34	0.6278	0.1923	0.6278	0.7923
No log	3.2727	36	0.5718	0.1564	0.5718	0.7562
No log	3.4545	38	0.5862	0.1923	0.5862	0.7656
No log	3.6364	40	0.6304	0.2664	0.6304	0.7940
No log	3.8182	42	0.7073	0.3288	0.7073	0.8410
No log	4.0	44	0.7573	0.1168	0.7573	0.8702
No log	4.1818	46	0.7765	0.0339	0.7765	0.8812
No log	4.3636	48	0.7307	0.2150	0.7307	0.8548
No log	4.5455	50	0.6636	0.3837	0.6636	0.8146
No log	4.7273	52	0.5744	0.3581	0.5744	0.7579
No log	4.9091	54	0.5429	0.2252	0.5429	0.7368
No log	5.0909	56	0.6087	0.1189	0.6087	0.7802
No log	5.2727	58	0.6072	0.1189	0.6072	0.7792
No log	5.4545	60	0.5620	0.2252	0.5620	0.7496
No log	5.6364	62	0.6134	0.3438	0.6134	0.7832
No log	5.8182	64	0.7754	0.1962	0.7754	0.8806
No log	6.0	66	0.8309	0.0339	0.8309	0.9115
No log	6.1818	68	0.8393	-0.0387	0.8393	0.9161
No log	6.3636	70	0.8271	0.0339	0.8271	0.9095
No log	6.5455	72	0.7404	0.2553	0.7404	0.8605
No log	6.7273	74	0.6315	0.2889	0.6315	0.7947
No log	6.9091	76	0.5978	0.4901	0.5978	0.7732
No log	7.0909	78	0.5914	0.4498	0.5914	0.7691
No log	7.2727	80	0.5770	0.4498	0.5770	0.7596
No log	7.4545	82	0.5702	0.4498	0.5702	0.7551
No log	7.6364	84	0.5664	0.4498	0.5664	0.7526
No log	7.8182	86	0.5698	0.4498	0.5698	0.7549
No log	8.0	88	0.5935	0.3046	0.5935	0.7704
No log	8.1818	90	0.6117	0.3438	0.6117	0.7821
No log	8.3636	92	0.6593	0.2150	0.6593	0.8120
No log	8.5455	94	0.6916	0.2150	0.6916	0.8316
No log	8.7273	96	0.6893	0.2150	0.6893	0.8303
No log	8.9091	98	0.6759	0.2150	0.6759	0.8221
No log	9.0909	100	0.6641	0.2150	0.6641	0.8149
No log	9.2727	102	0.6429	0.2150	0.6429	0.8018
No log	9.4545	104	0.6259	0.3288	0.6259	0.7911
No log	9.6364	106	0.6218	0.3288	0.6218	0.7886
No log	9.8182	108	0.6246	0.3288	0.6246	0.7903
No log	10.0	110	0.6264	0.3288	0.6264	0.7915

Framework versions

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