arabert_baseline_style_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: 0.4351
• Qwk: 0.7772
• Mse: 0.4351

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	3.0281	0.0186	3.0281
No log	0.6667	4	1.1102	0.0	1.1102
No log	1.0	6	0.6207	0.3478	0.6207
No log	1.3333	8	0.5268	0.3462	0.5268
No log	1.6667	10	0.5443	0.2941	0.5443
No log	2.0	12	0.4954	0.2941	0.4954
No log	2.3333	14	0.3975	0.3314	0.3975
No log	2.6667	16	0.3492	0.4828	0.3492
No log	3.0	18	0.3545	0.5238	0.3545
No log	3.3333	20	0.3763	0.6839	0.3763
No log	3.6667	22	0.4022	0.7472	0.4022
No log	4.0	24	0.4557	0.7772	0.4557
No log	4.3333	26	0.4928	0.7549	0.4928
No log	4.6667	28	0.4922	0.7549	0.4922
No log	5.0	30	0.4857	0.6939	0.4857
No log	5.3333	32	0.4759	0.6939	0.4759
No log	5.6667	34	0.4948	0.7549	0.4948
No log	6.0	36	0.4684	0.7772	0.4684
No log	6.3333	38	0.4446	0.7772	0.4446
No log	6.6667	40	0.4305	0.7772	0.4305
No log	7.0	42	0.4345	0.7222	0.4345
No log	7.3333	44	0.4345	0.6324	0.4345
No log	7.6667	46	0.4215	0.75	0.4215
No log	8.0	48	0.4192	0.7772	0.4192
No log	8.3333	50	0.4335	0.7772	0.4335
No log	8.6667	52	0.4440	0.7549	0.4440
No log	9.0	54	0.4449	0.7549	0.4449
No log	9.3333	56	0.4405	0.7549	0.4405
No log	9.6667	58	0.4375	0.7772	0.4375
No log	10.0	60	0.4351	0.7772	0.4351

Framework versions

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