ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k1_task3_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: 0.9566
• Qwk: 0.0288
• Mse: 0.9566
• Rmse: 0.9780

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	0.2222	2	3.1042	0.0570	3.1042	1.7619
No log	0.4444	4	1.5008	0.0130	1.5008	1.2251
No log	0.6667	6	1.0057	-0.0741	1.0057	1.0028
No log	0.8889	8	0.9063	-0.0761	0.9063	0.9520
No log	1.1111	10	0.7399	0.0850	0.7399	0.8602
No log	1.3333	12	0.6181	0.0388	0.6181	0.7862
No log	1.5556	14	0.5982	0.0303	0.5982	0.7734
No log	1.7778	16	0.8010	-0.0051	0.8010	0.8950
No log	2.0	18	1.1590	0.0075	1.1590	1.0766
No log	2.2222	20	1.3779	0.0247	1.3779	1.1738
No log	2.4444	22	1.1177	0.0745	1.1177	1.0572
No log	2.6667	24	0.7246	0.1556	0.7246	0.8513
No log	2.8889	26	0.5859	0.0303	0.5859	0.7655
No log	3.1111	28	0.6443	-0.0159	0.6443	0.8027
No log	3.3333	30	0.6496	0.0303	0.6496	0.8059
No log	3.5556	32	0.6137	0.0400	0.6137	0.7834
No log	3.7778	34	0.7213	0.2323	0.7213	0.8493
No log	4.0	36	0.8958	0.1289	0.8958	0.9465
No log	4.2222	38	0.9591	0.1712	0.9591	0.9794
No log	4.4444	40	0.9244	0.2157	0.9244	0.9615
No log	4.6667	42	0.7060	0.0617	0.7060	0.8402
No log	4.8889	44	0.6781	0.0725	0.6781	0.8235
No log	5.1111	46	0.6958	0.0725	0.6958	0.8341
No log	5.3333	48	0.7158	0.0725	0.7158	0.8460
No log	5.5556	50	0.7786	-0.0105	0.7786	0.8824
No log	5.7778	52	0.8182	-0.0105	0.8182	0.9046
No log	6.0	54	0.7766	0.0629	0.7766	0.8813
No log	6.2222	56	0.8017	0.0345	0.8017	0.8954
No log	6.4444	58	0.8512	0.1083	0.8512	0.9226
No log	6.6667	60	0.8678	0.0123	0.8678	0.9316
No log	6.8889	62	0.8815	0.1515	0.8815	0.9389
No log	7.1111	64	0.8740	0.1675	0.8740	0.9349
No log	7.3333	66	0.9398	-0.0105	0.9398	0.9695
No log	7.5556	68	0.9948	-0.0385	0.9948	0.9974
No log	7.7778	70	0.9363	-0.0105	0.9363	0.9676
No log	8.0	72	0.8915	0.0553	0.8915	0.9442
No log	8.2222	74	0.8918	0.2453	0.8918	0.9444
No log	8.4444	76	0.9115	0.2074	0.9115	0.9547
No log	8.6667	78	0.9216	0.1429	0.9216	0.9600
No log	8.8889	80	0.9389	0.0252	0.9389	0.9690
No log	9.1111	82	0.9628	0.0	0.9628	0.9812
No log	9.3333	84	0.9710	0.0041	0.9710	0.9854
No log	9.5556	86	0.9663	0.0000	0.9663	0.9830
No log	9.7778	88	0.9584	0.0252	0.9584	0.9790
No log	10.0	90	0.9566	0.0288	0.9566	0.9780

Framework versions

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