arabert_baseline_vocabulary_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: 0.5505
• Qwk: 0.6767
• Mse: 0.5505

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	3.3545	0.0255	3.3545
No log	0.6667	4	1.6087	0.0	1.6087
No log	1.0	6	0.8536	0.2689	0.8536
No log	1.3333	8	0.7544	0.2289	0.7544
No log	1.6667	10	0.6504	0.2689	0.6504
No log	2.0	12	0.5598	0.3623	0.5598
No log	2.3333	14	0.5291	0.3623	0.5291
No log	2.6667	16	0.6356	0.4179	0.6356
No log	3.0	18	0.8795	0.2857	0.8795
No log	3.3333	20	0.7838	0.4434	0.7838
No log	3.6667	22	0.5344	0.6809	0.5344
No log	4.0	24	0.5107	0.6822	0.5107
No log	4.3333	26	0.5455	0.6822	0.5455
No log	4.6667	28	0.5959	0.6822	0.5959
No log	5.0	30	0.6155	0.6091	0.6155
No log	5.3333	32	0.5993	0.6146	0.5993
No log	5.6667	34	0.6037	0.7028	0.6037
No log	6.0	36	0.6613	0.6767	0.6613
No log	6.3333	38	0.6632	0.7005	0.6632
No log	6.6667	40	0.6185	0.6822	0.6185
No log	7.0	42	0.5683	0.7028	0.5683
No log	7.3333	44	0.5821	0.6040	0.5821
No log	7.6667	46	0.5844	0.6040	0.5844
No log	8.0	48	0.5500	0.6844	0.5500
No log	8.3333	50	0.5326	0.7028	0.5326
No log	8.6667	52	0.5428	0.6767	0.5428
No log	9.0	54	0.5510	0.6767	0.5510
No log	9.3333	56	0.5525	0.6767	0.5525
No log	9.6667	58	0.5510	0.6767	0.5510
No log	10.0	60	0.5505	0.6767	0.5505

Framework versions

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