arabert_baseline_vocabulary_task7_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: 0.3528
• Qwk: 0.6935
• Mse: 0.3528

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	1.5791	0.0862	1.5791
No log	0.6667	4	0.7772	0.4706	0.7772
No log	1.0	6	0.7965	0.4532	0.7965
No log	1.3333	8	0.6398	0.4532	0.6398
No log	1.6667	10	0.3283	0.6814	0.3283
No log	2.0	12	0.3264	0.6814	0.3264
No log	2.3333	14	0.5269	0.5702	0.5269
No log	2.6667	16	0.5821	0.4880	0.5821
No log	3.0	18	0.5634	0.4918	0.5634
No log	3.3333	20	0.3969	0.6316	0.3969
No log	3.6667	22	0.3136	0.6792	0.3136
No log	4.0	24	0.3010	0.7265	0.3010
No log	4.3333	26	0.3722	0.6850	0.3722
No log	4.6667	28	0.5081	0.6769	0.5081
No log	5.0	30	0.5267	0.6788	0.5267
No log	5.3333	32	0.4329	0.6935	0.4329
No log	5.6667	34	0.2874	0.7797	0.2874
No log	6.0	36	0.2708	0.7797	0.2708
No log	6.3333	38	0.2866	0.7797	0.2866
No log	6.6667	40	0.3412	0.7355	0.3412
No log	7.0	42	0.4474	0.6935	0.4474
No log	7.3333	44	0.4536	0.6947	0.4536
No log	7.6667	46	0.3805	0.6935	0.3805
No log	8.0	48	0.3311	0.7355	0.3311
No log	8.3333	50	0.3056	0.7797	0.3056
No log	8.6667	52	0.3214	0.7355	0.3214
No log	9.0	54	0.3432	0.6935	0.3432
No log	9.3333	56	0.3493	0.6935	0.3493
No log	9.6667	58	0.3560	0.6935	0.3560
No log	10.0	60	0.3528	0.6935	0.3528

Framework versions

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