arabert_baseline_mechanics_task1_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: 0.6765
• Qwk: 0.4590
• Mse: 0.6922

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	4.5225	-0.0658	4.5651
No log	0.6667	4	1.8523	0.1370	1.8774
No log	1.0	6	0.9383	0.2326	0.9611
No log	1.3333	8	0.8679	0.3119	0.8947
No log	1.6667	10	0.8994	0.4015	0.9273
No log	2.0	12	1.2109	0.0582	1.2468
No log	2.3333	14	1.0652	0.0783	1.0979
No log	2.6667	16	0.8918	0.4726	0.9192
No log	3.0	18	0.9069	0.3931	0.9346
No log	3.3333	20	0.8533	0.3636	0.8812
No log	3.6667	22	0.7332	0.4582	0.7567
No log	4.0	24	0.7505	0.5333	0.7733
No log	4.3333	26	0.7390	0.475	0.7612
No log	4.6667	28	0.7760	0.3824	0.8000
No log	5.0	30	0.8078	0.3913	0.8335
No log	5.3333	32	0.7440	0.4450	0.7671
No log	5.6667	34	0.7175	0.4906	0.7395
No log	6.0	36	0.7050	0.5254	0.7261
No log	6.3333	38	0.7088	0.4450	0.7299
No log	6.6667	40	0.6952	0.4727	0.7141
No log	7.0	42	0.6847	0.4770	0.7014
No log	7.3333	44	0.6839	0.5054	0.7003
No log	7.6667	46	0.6830	0.4822	0.6983
No log	8.0	48	0.6803	0.4822	0.6954
No log	8.3333	50	0.6819	0.4279	0.6979
No log	8.6667	52	0.6851	0.4360	0.7017
No log	9.0	54	0.6844	0.4360	0.7010
No log	9.3333	56	0.6804	0.4360	0.6965
No log	9.6667	58	0.6769	0.4590	0.6926
No log	10.0	60	0.6765	0.4590	0.6922

Framework versions

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