Arabic_FineTuningAraBERT_noAug_task1_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: 0.7133
• Qwk: 0.7390
• Mse: 0.7133
• Rmse: 0.8446

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	3.5265	-0.0430	3.5265	1.8779
No log	0.3636	4	2.1957	0.0	2.1957	1.4818
No log	0.5455	6	1.4276	0.0680	1.4276	1.1948
No log	0.7273	8	1.0890	0.1355	1.0890	1.0436
No log	0.9091	10	1.1657	-0.0161	1.1657	1.0797
No log	1.0909	12	1.0771	-0.0302	1.0771	1.0378
No log	1.2727	14	0.8451	-0.0284	0.8451	0.9193
No log	1.4545	16	0.7807	0.0606	0.7807	0.8835
No log	1.6364	18	0.7112	-0.0467	0.7112	0.8433
No log	1.8182	20	0.6604	-0.0096	0.6604	0.8126
No log	2.0	22	0.6288	0.4928	0.6288	0.7930
No log	2.1818	24	0.6238	0.4510	0.6238	0.7898
No log	2.3636	26	0.6134	0.4481	0.6134	0.7832
No log	2.5455	28	0.6019	0.5377	0.6019	0.7758
No log	2.7273	30	0.5898	0.5377	0.5898	0.7680
No log	2.9091	32	0.6678	0.6602	0.6678	0.8172
No log	3.0909	34	0.6491	0.6316	0.6491	0.8057
No log	3.2727	36	0.5608	0.6142	0.5608	0.7489
No log	3.4545	38	0.5107	0.5522	0.5107	0.7146
No log	3.6364	40	0.5347	0.5522	0.5347	0.7312
No log	3.8182	42	0.5437	0.6715	0.5437	0.7374
No log	4.0	44	0.6201	0.6343	0.6201	0.7875
No log	4.1818	46	0.8219	0.7055	0.8219	0.9066
No log	4.3636	48	0.8218	0.7055	0.8218	0.9065
No log	4.5455	50	0.7538	0.7055	0.7538	0.8682
No log	4.7273	52	0.6928	0.6859	0.6928	0.8323
No log	4.9091	54	0.6231	0.6729	0.6231	0.7894
No log	5.0909	56	0.6595	0.7358	0.6595	0.8121
No log	5.2727	58	0.8629	0.7336	0.8629	0.9289
No log	5.4545	60	0.8994	0.6667	0.8994	0.9483
No log	5.6364	62	0.7006	0.6529	0.7006	0.8370
No log	5.8182	64	0.5718	0.6142	0.5718	0.7562
No log	6.0	66	0.5318	0.5789	0.5318	0.7293
No log	6.1818	68	0.5621	0.6597	0.5621	0.7498
No log	6.3636	70	0.6267	0.6488	0.6267	0.7916
No log	6.5455	72	0.7690	0.6602	0.7690	0.8769
No log	6.7273	74	0.9500	0.7391	0.9500	0.9747
No log	6.9091	76	0.9727	0.7391	0.9727	0.9862
No log	7.0909	78	0.8586	0.7012	0.8586	0.9266
No log	7.2727	80	0.7628	0.7255	0.7628	0.8734
No log	7.4545	82	0.6330	0.6729	0.6330	0.7956
No log	7.6364	84	0.5902	0.7217	0.5902	0.7682
No log	7.8182	86	0.5896	0.7217	0.5896	0.7679
No log	8.0	88	0.6291	0.7358	0.6291	0.7931
No log	8.1818	90	0.6963	0.7308	0.6963	0.8345
No log	8.3636	92	0.7636	0.6784	0.7636	0.8739
No log	8.5455	94	0.8187	0.6784	0.8187	0.9048
No log	8.7273	96	0.8350	0.6784	0.8350	0.9138
No log	8.9091	98	0.8607	0.6784	0.8607	0.9277
No log	9.0909	100	0.8221	0.6784	0.8221	0.9067
No log	9.2727	102	0.7783	0.6784	0.7783	0.8822
No log	9.4545	104	0.7455	0.7390	0.7455	0.8634
No log	9.6364	106	0.7289	0.7390	0.7289	0.8538
No log	9.8182	108	0.7152	0.7390	0.7152	0.8457
No log	10.0	110	0.7133	0.7390	0.7133	0.8446

Framework versions

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