arabert_baseline_grammar_task6_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: 0.7851
• Qwk: 0.7296
• Mse: 0.7851

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	0.5	2	1.4135	-0.0678	1.4135
No log	1.0	4	0.9828	0.5032	0.9828
No log	1.5	6	1.1603	0.3288	1.1603
No log	2.0	8	1.0440	0.2036	1.0440
No log	2.5	10	0.8854	0.2383	0.8854
No log	3.0	12	0.7492	0.4348	0.7492
No log	3.5	14	0.7513	0.4348	0.7513
No log	4.0	16	0.8038	0.6500	0.8038
No log	4.5	18	0.8093	0.6500	0.8093
No log	5.0	20	0.8924	0.6847	0.8924
No log	5.5	22	1.0282	0.6805	1.0282
No log	6.0	24	0.9757	0.7296	0.9757
No log	6.5	26	0.9823	0.7296	0.9823
No log	7.0	28	0.9823	0.6957	0.9823
No log	7.5	30	0.8153	0.7296	0.8153
No log	8.0	32	0.7571	0.6192	0.7571
No log	8.5	34	0.7411	0.7014	0.7411
No log	9.0	36	0.7685	0.7296	0.7685
No log	9.5	38	0.7773	0.7296	0.7773
No log	10.0	40	0.7851	0.7296	0.7851

Framework versions

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