arabert_baseline_organization_task1_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: 0.6156
• Qwk: 0.7263
• Mse: 0.5866

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	4.0016	-0.0094	4.0420
No log	0.6667	4	1.5678	0.0597	1.6106
No log	1.0	6	1.1107	0.125	1.1443
No log	1.3333	8	0.6987	0.2286	0.7156
No log	1.6667	10	0.6381	0.4661	0.6469
No log	2.0	12	0.5798	0.3984	0.5877
No log	2.3333	14	0.4646	0.552	0.4642
No log	2.6667	16	0.4683	0.6379	0.4526
No log	3.0	18	0.4347	0.7154	0.4182
No log	3.3333	20	0.4464	0.5977	0.4400
No log	3.6667	22	0.4523	0.6957	0.4373
No log	4.0	24	0.6917	0.7616	0.6664
No log	4.3333	26	0.8197	0.7485	0.7888
No log	4.6667	28	0.7131	0.7701	0.6829
No log	5.0	30	0.7249	0.7154	0.6941
No log	5.3333	32	0.8136	0.7572	0.7780
No log	5.6667	34	0.9048	0.7347	0.8646
No log	6.0	36	0.8073	0.7347	0.7664
No log	6.3333	38	0.7257	0.7840	0.6853
No log	6.6667	40	0.7345	0.7840	0.6936
No log	7.0	42	0.7184	0.7263	0.6797
No log	7.3333	44	0.6757	0.7263	0.6409
No log	7.6667	46	0.7056	0.7042	0.6701
No log	8.0	48	0.7177	0.7515	0.6822
No log	8.3333	50	0.7076	0.7515	0.6730
No log	8.6667	52	0.7003	0.7515	0.6663
No log	9.0	54	0.6732	0.7515	0.6407
No log	9.3333	56	0.6412	0.7042	0.6104
No log	9.6667	58	0.6207	0.7263	0.5913
No log	10.0	60	0.6156	0.7263	0.5866

Framework versions

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