arabert_no_augmentation_organization_task3_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: 0.5692
• Qwk: 0.2787
• Mse: 0.5692
• Rmse: 0.7545

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: 8
• eval_batch_size: 8
• 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	Rmse
No log	0.3333	2	3.5251	-0.0035	3.5251	1.8775
No log	0.6667	4	3.0669	0.0000	3.0669	1.7513
No log	1.0	6	0.8766	-0.0097	0.8766	0.9363
No log	1.3333	8	0.5134	0.1879	0.5134	0.7166
No log	1.6667	10	0.7733	0.0120	0.7733	0.8794
No log	2.0	12	0.7862	0.0	0.7862	0.8867
No log	2.3333	14	0.8025	0.0	0.8025	0.8958
No log	2.6667	16	0.7806	0.0	0.7806	0.8835
No log	3.0	18	0.7336	0.0	0.7336	0.8565
No log	3.3333	20	0.7123	0.0120	0.7123	0.8440
No log	3.6667	22	0.5665	0.1879	0.5665	0.7527
No log	4.0	24	0.5538	0.1437	0.5538	0.7442
No log	4.3333	26	0.5751	0.1437	0.5751	0.7583
No log	4.6667	28	0.5236	0.1646	0.5236	0.7236
No log	5.0	30	0.5102	0.1879	0.5102	0.7143
No log	5.3333	32	0.5278	0.2787	0.5278	0.7265
No log	5.6667	34	0.5239	0.2787	0.5239	0.7238
No log	6.0	36	0.5271	0.2787	0.5271	0.7260
No log	6.3333	38	0.5528	0.2787	0.5528	0.7435
No log	6.6667	40	0.5424	0.2787	0.5424	0.7365
No log	7.0	42	0.5288	0.2143	0.5288	0.7272
No log	7.3333	44	0.6313	0.0120	0.6313	0.7945
No log	7.6667	46	0.6472	0.0120	0.6472	0.8045
No log	8.0	48	0.5712	0.2143	0.5712	0.7558
No log	8.3333	50	0.5361	0.2143	0.5361	0.7322
No log	8.6667	52	0.5450	0.2787	0.5450	0.7382
No log	9.0	54	0.5602	0.2787	0.5602	0.7485
No log	9.3333	56	0.5743	0.2787	0.5743	0.7578
No log	9.6667	58	0.5732	0.2787	0.5732	0.7571
No log	10.0	60	0.5692	0.2787	0.5692	0.7545

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1