ArabicNewSplits6_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: 0.8211
• Qwk: 0.1193
• Mse: 0.8211
• Rmse: 0.9061

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	3.1765	-0.0160	3.1765	1.7823
No log	0.5714	4	1.5007	0.0255	1.5007	1.2250
No log	0.8571	6	0.8427	0.1111	0.8427	0.9180
No log	1.1429	8	0.5802	-0.0159	0.5802	0.7617
No log	1.4286	10	0.5509	0.0569	0.5509	0.7422
No log	1.7143	12	0.8223	0.1930	0.8223	0.9068
No log	2.0	14	0.6269	0.0952	0.6269	0.7917
No log	2.2857	16	0.5718	0.0	0.5718	0.7562
No log	2.5714	18	0.6289	0.0	0.6289	0.7930
No log	2.8571	20	0.5957	0.0	0.5957	0.7718
No log	3.1429	22	0.5658	0.0	0.5658	0.7522
No log	3.4286	24	0.5741	-0.0081	0.5741	0.7577
No log	3.7143	26	0.5795	-0.0159	0.5795	0.7613
No log	4.0	28	0.6032	0.0222	0.6032	0.7767
No log	4.2857	30	0.6178	0.0222	0.6178	0.7860
No log	4.5714	32	0.6542	0.0857	0.6542	0.8088
No log	4.8571	34	0.7212	0.2000	0.7212	0.8493
No log	5.1429	36	0.7614	0.1515	0.7614	0.8726
No log	5.4286	38	0.8428	0.1489	0.8428	0.9181
No log	5.7143	40	0.8818	0.0476	0.8818	0.9391
No log	6.0	42	0.9076	0.0531	0.9076	0.9527
No log	6.2857	44	0.9711	0.0588	0.9711	0.9854
No log	6.5714	46	0.9860	0.0918	0.9860	0.9930
No log	6.8571	48	0.9443	-0.0196	0.9443	0.9717
No log	7.1429	50	0.9518	0.0	0.9518	0.9756
No log	7.4286	52	0.9800	0.0270	0.9800	0.9900
No log	7.7143	54	0.9316	0.1636	0.9316	0.9652
No log	8.0	56	0.8356	0.0884	0.8356	0.9141
No log	8.2857	58	0.8030	0.0674	0.8030	0.8961
No log	8.5714	60	0.7978	0.1357	0.7978	0.8932
No log	8.8571	62	0.7915	0.0476	0.7915	0.8897
No log	9.1429	64	0.7919	0.0512	0.7919	0.8899
No log	9.4286	66	0.8062	0.1090	0.8062	0.8979
No log	9.7143	68	0.8171	0.1193	0.8171	0.9039
No log	10.0	70	0.8211	0.1193	0.8211	0.9061

Framework versions

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