arabert_baseline_organization_task5_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: 0.8569
• Qwk: 0.4778
• Mse: 0.8569

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: 16
• eval_batch_size: 16
• 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
No log	0.3333	2	2.4863	-0.0641	2.4863
No log	0.6667	4	1.3863	0.0	1.3863
No log	1.0	6	1.0547	0.1389	1.0547
No log	1.3333	8	1.0296	0.2049	1.0296
No log	1.6667	10	0.9224	0.2049	0.9224
No log	2.0	12	0.8332	0.3787	0.8332
No log	2.3333	14	0.8196	0.2895	0.8196
No log	2.6667	16	0.8152	0.2895	0.8152
No log	3.0	18	0.8909	0.2895	0.8909
No log	3.3333	20	0.9518	0.2736	0.9518
No log	3.6667	22	0.8848	0.2895	0.8848
No log	4.0	24	0.9478	0.4663	0.9478
No log	4.3333	26	1.0547	0.3316	1.0547
No log	4.6667	28	1.0817	0.3516	1.0817
No log	5.0	30	1.0055	0.4643	1.0055
No log	5.3333	32	0.8978	0.5068	0.8978
No log	5.6667	34	0.8372	0.5479	0.8372
No log	6.0	36	0.8407	0.5455	0.8407
No log	6.3333	38	0.9061	0.4778	0.9061
No log	6.6667	40	0.9725	0.4643	0.9725
No log	7.0	42	0.9463	0.4778	0.9463
No log	7.3333	44	0.8661	0.5455	0.8661
No log	7.6667	46	0.8220	0.5844	0.8220
No log	8.0	48	0.8110	0.5844	0.8110
No log	8.3333	50	0.8224	0.5844	0.8224
No log	8.6667	52	0.8540	0.4778	0.8540
No log	9.0	54	0.8631	0.4778	0.8631
No log	9.3333	56	0.8567	0.4778	0.8567
No log	9.6667	58	0.8579	0.4778	0.8579
No log	10.0	60	0.8569	0.4778	0.8569

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1