arabert_baseline_augmented_organization_task3_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: 0.6870
• Qwk: 0.0
• Mse: 0.6870
• Rmse: 0.8289

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	0.25	2	3.0017	0.0	3.0017	1.7325
No log	0.5	4	1.7535	0.0041	1.7535	1.3242
No log	0.75	6	1.1832	0.0	1.1832	1.0877
No log	1.0	8	0.8572	0.0	0.8572	0.9259
No log	1.25	10	0.7372	0.0	0.7372	0.8586
No log	1.5	12	0.7099	0.0	0.7099	0.8426
No log	1.75	14	0.7538	0.0	0.7538	0.8682
No log	2.0	16	0.7221	0.0	0.7221	0.8498
No log	2.25	18	0.6594	0.0	0.6594	0.8121
No log	2.5	20	0.6429	0.0	0.6429	0.8018
No log	2.75	22	0.7069	0.0	0.7069	0.8408
No log	3.0	24	0.7990	0.0	0.7990	0.8939
No log	3.25	26	0.8706	0.0	0.8706	0.9330
No log	3.5	28	0.8292	0.0	0.8292	0.9106
No log	3.75	30	0.7187	0.0	0.7187	0.8478
No log	4.0	32	0.6536	0.0	0.6536	0.8084
No log	4.25	34	0.6361	0.0120	0.6361	0.7975
No log	4.5	36	0.6221	0.0	0.6221	0.7887
No log	4.75	38	0.6403	0.0	0.6403	0.8002
No log	5.0	40	0.6953	0.0	0.6953	0.8338
No log	5.25	42	0.7277	0.0	0.7277	0.8531
No log	5.5	44	0.7986	0.0	0.7986	0.8936
No log	5.75	46	0.8216	0.0	0.8216	0.9064
No log	6.0	48	0.7997	0.0	0.7997	0.8942
No log	6.25	50	0.7653	0.0	0.7653	0.8748
No log	6.5	52	0.6746	0.0	0.6746	0.8213
No log	6.75	54	0.6183	0.0	0.6183	0.7863
No log	7.0	56	0.6150	0.0	0.6150	0.7842
No log	7.25	58	0.6335	0.0	0.6335	0.7959
No log	7.5	60	0.6561	0.0	0.6561	0.8100
No log	7.75	62	0.6978	0.0	0.6978	0.8354
No log	8.0	64	0.7100	0.0	0.7100	0.8426
No log	8.25	66	0.6931	0.0	0.6931	0.8325
No log	8.5	68	0.6783	0.0	0.6783	0.8236
No log	8.75	70	0.6841	0.0	0.6841	0.8271
No log	9.0	72	0.6870	0.0	0.6870	0.8289
No log	9.25	74	0.6781	0.0	0.6781	0.8235
No log	9.5	76	0.6776	0.0	0.6776	0.8232
No log	9.75	78	0.6845	0.0	0.6845	0.8274
No log	10.0	80	0.6870	0.0	0.6870	0.8289

Framework versions

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