arabert_baseline_organization_task2_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: 0.4740
• Qwk: 0.5263
• Mse: 0.4884

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	2.7474	0.0719	2.8478
No log	0.6667	4	0.9337	0.1600	0.9879
No log	1.0	6	0.4534	0.0	0.4764
No log	1.3333	8	0.7904	-0.0408	0.7830
No log	1.6667	10	0.7018	0.0769	0.6973
No log	2.0	12	0.5298	0.2258	0.5356
No log	2.3333	14	0.4547	0.0	0.4751
No log	2.6667	16	0.4579	0.0	0.4810
No log	3.0	18	0.4621	0.0	0.4849
No log	3.3333	20	0.5042	0.1563	0.5232
No log	3.6667	22	0.5058	0.1905	0.5230
No log	4.0	24	0.4808	0.2623	0.4947
No log	4.3333	26	0.4464	0.4828	0.4576
No log	4.6667	28	0.3793	0.2258	0.3943
No log	5.0	30	0.3971	0.2623	0.4100
No log	5.3333	32	0.5018	0.5263	0.5120
No log	5.6667	34	0.5357	0.3390	0.5481
No log	6.0	36	0.4854	0.3000	0.5002
No log	6.3333	38	0.4022	0.2623	0.4219
No log	6.6667	40	0.4018	0.2597	0.4313
No log	7.0	42	0.4157	0.2597	0.4485
No log	7.3333	44	0.3858	0.2895	0.4130
No log	7.6667	46	0.3839	0.3200	0.4045
No log	8.0	48	0.4237	0.5263	0.4396
No log	8.3333	50	0.4462	0.5263	0.4608
No log	8.6667	52	0.4536	0.5263	0.4681
No log	9.0	54	0.4620	0.5263	0.4764
No log	9.3333	56	0.4700	0.5263	0.4842
No log	9.6667	58	0.4698	0.5263	0.4842
No log	10.0	60	0.4740	0.5263	0.4884

Framework versions

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