arabert_baseline_vocabulary_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: 0.8715
• Qwk: 0.6491
• Mse: 0.8715

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	2.2168	0.1714	2.2168
No log	0.6667	4	2.0041	0.0	2.0041
No log	1.0	6	1.8058	0.0	1.8058
No log	1.3333	8	1.6307	0.0	1.6307
No log	1.6667	10	1.5228	0.1055	1.5228
No log	2.0	12	1.4956	0.1325	1.4956
No log	2.3333	14	1.4414	0.1842	1.4414
No log	2.6667	16	1.3583	0.3623	1.3583
No log	3.0	18	1.2822	0.4602	1.2822
No log	3.3333	20	1.2058	0.4783	1.2058
No log	3.6667	22	1.1388	0.5430	1.1388
No log	4.0	24	1.0848	0.5778	1.0848
No log	4.3333	26	1.0520	0.5161	1.0520
No log	4.6667	28	1.0213	0.5161	1.0213
No log	5.0	30	0.9946	0.4866	0.9946
No log	5.3333	32	0.9759	0.5368	0.9759
No log	5.6667	34	0.9511	0.5368	0.9511
No log	6.0	36	0.9260	0.5662	0.9260
No log	6.3333	38	0.9142	0.5662	0.9142
No log	6.6667	40	0.8995	0.5662	0.8995
No log	7.0	42	0.9024	0.5940	0.9024
No log	7.3333	44	0.9102	0.5368	0.9102
No log	7.6667	46	0.9036	0.6258	0.9036
No log	8.0	48	0.8943	0.6304	0.8943
No log	8.3333	50	0.8872	0.6042	0.8872
No log	8.6667	52	0.8828	0.6042	0.8828
No log	9.0	54	0.8785	0.6491	0.8785
No log	9.3333	56	0.8747	0.6491	0.8747
No log	9.6667	58	0.8725	0.6491	0.8725
No log	10.0	60	0.8715	0.6491	0.8715

Framework versions

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