arabert_baseline_development_task5_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: 1.0419
• Qwk: 0.5183
• Mse: 1.0419

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	1.6380	0.0929	1.6380
No log	0.6667	4	1.5106	0.0	1.5106
No log	1.0	6	1.3471	0.0	1.3471
No log	1.3333	8	1.2335	0.0	1.2335
No log	1.6667	10	1.2261	0.1576	1.2261
No log	2.0	12	1.2476	0.2560	1.2476
No log	2.3333	14	1.2739	0.2628	1.2739
No log	2.6667	16	1.2494	0.2628	1.2494
No log	3.0	18	1.1857	0.4062	1.1857
No log	3.3333	20	1.1005	0.3598	1.1005
No log	3.6667	22	1.1228	0.3976	1.1228
No log	4.0	24	1.0985	0.3976	1.0985
No log	4.3333	26	1.0341	0.375	1.0341
No log	4.6667	28	0.9989	0.5789	0.9989
No log	5.0	30	0.9963	0.5789	0.9963
No log	5.3333	32	0.9852	0.5361	0.9852
No log	5.6667	34	0.9961	0.5991	0.9961
No log	6.0	36	1.0348	0.4725	1.0348
No log	6.3333	38	1.0147	0.5238	1.0147
No log	6.6667	40	1.0123	0.5238	1.0123
No log	7.0	42	0.9900	0.5833	0.9900
No log	7.3333	44	0.9764	0.4872	0.9764
No log	7.6667	46	0.9850	0.4872	0.9850
No log	8.0	48	0.9775	0.5327	0.9775
No log	8.3333	50	0.9860	0.5047	0.9860
No log	8.6667	52	0.9983	0.5183	0.9983
No log	9.0	54	1.0128	0.5183	1.0128
No log	9.3333	56	1.0321	0.5183	1.0321
No log	9.6667	58	1.0407	0.5183	1.0407
No log	10.0	60	1.0419	0.5183	1.0419

Framework versions

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