arabert_baseline_organization_task1_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: 0.6571
• Qwk: 0.7618
• Mse: 0.6571
• Rmse: 0.8106

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	4.7070	-0.0581	4.7070	2.1696
No log	0.3636	4	2.5400	0.0	2.5400	1.5937
No log	0.5455	6	1.5937	0.1750	1.5937	1.2624
No log	0.7273	8	1.0172	0.1582	1.0172	1.0086
No log	0.9091	10	0.9129	0.4929	0.9129	0.9555
No log	1.0909	12	0.8654	0.4763	0.8654	0.9302
No log	1.2727	14	0.8549	0.5268	0.8549	0.9246
No log	1.4545	16	0.7991	0.4934	0.7991	0.8939
No log	1.6364	18	0.8510	0.5288	0.8510	0.9225
No log	1.8182	20	0.8834	0.5288	0.8834	0.9399
No log	2.0	22	0.9534	0.5304	0.9534	0.9764
No log	2.1818	24	0.8760	0.5698	0.8760	0.9360
No log	2.3636	26	0.7263	0.6182	0.7263	0.8522
No log	2.5455	28	0.7632	0.5093	0.7632	0.8736
No log	2.7273	30	0.7407	0.5845	0.7407	0.8606
No log	2.9091	32	0.8857	0.5674	0.8857	0.9411
No log	3.0909	34	0.9844	0.6301	0.9844	0.9922
No log	3.2727	36	0.9963	0.6301	0.9963	0.9981
No log	3.4545	38	0.8665	0.6209	0.8665	0.9308
No log	3.6364	40	0.7832	0.6354	0.7832	0.8850
No log	3.8182	42	0.8425	0.6715	0.8425	0.9179
No log	4.0	44	0.8849	0.5591	0.8849	0.9407
No log	4.1818	46	0.8290	0.5862	0.8290	0.9105
No log	4.3636	48	0.7263	0.6866	0.7263	0.8523
No log	4.5455	50	0.7922	0.7786	0.7922	0.8901
No log	4.7273	52	0.9204	0.7037	0.9204	0.9594
No log	4.9091	54	0.8995	0.6836	0.8995	0.9484
No log	5.0909	56	0.7549	0.6968	0.7549	0.8688
No log	5.2727	58	0.6694	0.6539	0.6694	0.8182
No log	5.4545	60	0.6618	0.6102	0.6618	0.8135
No log	5.6364	62	0.6895	0.7449	0.6895	0.8304
No log	5.8182	64	0.7854	0.7181	0.7854	0.8863
No log	6.0	66	0.8328	0.7181	0.8328	0.9126
No log	6.1818	68	0.8134	0.6764	0.8134	0.9019
No log	6.3636	70	0.8151	0.7363	0.8151	0.9028
No log	6.5455	72	0.7853	0.7363	0.7853	0.8862
No log	6.7273	74	0.7443	0.7786	0.7443	0.8627
No log	6.9091	76	0.7261	0.7618	0.7261	0.8521
No log	7.0909	78	0.7315	0.7008	0.7315	0.8553
No log	7.2727	80	0.7472	0.7181	0.7472	0.8644
No log	7.4545	82	0.7769	0.7181	0.7769	0.8814
No log	7.6364	84	0.7755	0.6893	0.7755	0.8807
No log	7.8182	86	0.7231	0.7008	0.7231	0.8504
No log	8.0	88	0.6836	0.7008	0.6836	0.8268
No log	8.1818	90	0.6640	0.7618	0.6640	0.8148
No log	8.3636	92	0.6503	0.7618	0.6503	0.8064
No log	8.5455	94	0.6490	0.7371	0.6490	0.8056
No log	8.7273	96	0.6511	0.7618	0.6511	0.8069
No log	8.9091	98	0.6544	0.7618	0.6544	0.8090
No log	9.0909	100	0.6537	0.7618	0.6537	0.8085
No log	9.2727	102	0.6535	0.7618	0.6535	0.8084
No log	9.4545	104	0.6564	0.7618	0.6564	0.8102
No log	9.6364	106	0.6574	0.7618	0.6574	0.8108
No log	9.8182	108	0.6573	0.7618	0.6573	0.8107
No log	10.0	110	0.6571	0.7618	0.6571	0.8106

Framework versions

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