arabert_baseline_vocabulary_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: 0.5031
• Qwk: 0.5714
• Mse: 0.5016

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	4.1484	0.0038	4.1936
No log	0.6667	4	1.4862	0.0810	1.5068
No log	1.0	6	0.7072	0.0	0.7085
No log	1.3333	8	0.5919	0.0	0.5727
No log	1.6667	10	0.7019	0.0	0.6799
No log	2.0	12	0.4359	0.2329	0.4303
No log	2.3333	14	0.4598	0.1250	0.4561
No log	2.6667	16	0.4071	0.5145	0.3971
No log	3.0	18	0.5588	0.1732	0.5418
No log	3.3333	20	0.6199	0.1732	0.6015
No log	3.6667	22	0.4817	0.4400	0.4688
No log	4.0	24	0.3891	0.2959	0.3830
No log	4.3333	26	0.4411	0.1777	0.4351
No log	4.6667	28	0.4012	0.3959	0.3959
No log	5.0	30	0.4347	0.4765	0.4291
No log	5.3333	32	0.6742	0.4970	0.6581
No log	5.6667	34	0.7767	0.5273	0.7561
No log	6.0	36	0.7418	0.5836	0.7250
No log	6.3333	38	0.6070	0.4706	0.5993
No log	6.6667	40	0.4832	0.5714	0.4805
No log	7.0	42	0.4590	0.6196	0.4554
No log	7.3333	44	0.4604	0.6196	0.4573
No log	7.6667	46	0.4911	0.5714	0.4888
No log	8.0	48	0.5594	0.4415	0.5549
No log	8.3333	50	0.5973	0.5215	0.5910
No log	8.6667	52	0.5945	0.4415	0.5886
No log	9.0	54	0.5659	0.4415	0.5617
No log	9.3333	56	0.5343	0.5215	0.5317
No log	9.6667	58	0.5134	0.4976	0.5116
No log	10.0	60	0.5031	0.5714	0.5016

Framework versions

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