ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k1_task2_organization

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: 0.5536
• Qwk: 0.4021
• Mse: 0.5536
• Rmse: 0.7440

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	0.2857	2	4.0639	0.0162	4.0639	2.0159
No log	0.5714	4	2.3235	0.0699	2.3235	1.5243
No log	0.8571	6	1.1560	0.0951	1.1560	1.0752
No log	1.1429	8	0.9274	-0.0673	0.9274	0.9630
No log	1.4286	10	0.8136	0.0597	0.8136	0.9020
No log	1.7143	12	0.8452	0.1299	0.8452	0.9193
No log	2.0	14	0.8833	0.1299	0.8833	0.9398
No log	2.2857	16	0.8371	0.1819	0.8371	0.9149
No log	2.5714	18	0.8352	0.1819	0.8352	0.9139
No log	2.8571	20	0.8214	0.1677	0.8214	0.9063
No log	3.1429	22	0.8515	0.0772	0.8515	0.9228
No log	3.4286	24	0.8276	0.0772	0.8276	0.9097
No log	3.7143	26	0.7337	0.0918	0.7337	0.8565
No log	4.0	28	0.6956	0.1549	0.6956	0.8340
No log	4.2857	30	0.6612	0.2495	0.6612	0.8132
No log	4.5714	32	0.6311	0.2577	0.6311	0.7944
No log	4.8571	34	0.6153	0.3260	0.6153	0.7844
No log	5.1429	36	0.6187	0.2968	0.6187	0.7866
No log	5.4286	38	0.6281	0.2928	0.6281	0.7925
No log	5.7143	40	0.6362	0.2928	0.6362	0.7976
No log	6.0	42	0.6361	0.3274	0.6361	0.7975
No log	6.2857	44	0.6663	0.3582	0.6663	0.8163
No log	6.5714	46	0.6735	0.3594	0.6735	0.8207
No log	6.8571	48	0.6512	0.3695	0.6512	0.8070
No log	7.1429	50	0.6191	0.3685	0.6191	0.7868
No log	7.4286	52	0.5997	0.3868	0.5997	0.7744
No log	7.7143	54	0.5944	0.3868	0.5944	0.7710
No log	8.0	56	0.5776	0.4131	0.5776	0.7600
No log	8.2857	58	0.5729	0.4245	0.5729	0.7569
No log	8.5714	60	0.5646	0.4039	0.5646	0.7514
No log	8.8571	62	0.5593	0.4158	0.5593	0.7479
No log	9.1429	64	0.5566	0.4074	0.5566	0.7461
No log	9.4286	66	0.5547	0.4190	0.5547	0.7448
No log	9.7143	68	0.5537	0.4021	0.5537	0.7441
No log	10.0	70	0.5536	0.4021	0.5536	0.7440

Framework versions

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