ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k4_task5_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: 0.7182
• Qwk: 0.7254
• Mse: 0.7182
• Rmse: 0.8475

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	0.1053	2	2.3233	0.0562	2.3233	1.5242
No log	0.2105	4	1.6055	0.1441	1.6055	1.2671
No log	0.3158	6	1.5240	0.1300	1.5240	1.2345
No log	0.4211	8	1.7390	0.2491	1.7390	1.3187
No log	0.5263	10	1.8171	0.2657	1.8171	1.3480
No log	0.6316	12	1.6029	0.2184	1.6029	1.2661
No log	0.7368	14	1.5883	0.1606	1.5883	1.2603
No log	0.8421	16	1.4081	0.1063	1.4081	1.1866
No log	0.9474	18	1.2787	0.1963	1.2787	1.1308
No log	1.0526	20	1.2048	0.2540	1.2048	1.0976
No log	1.1579	22	1.1493	0.3942	1.1493	1.0720
No log	1.2632	24	1.1923	0.4070	1.1923	1.0919
No log	1.3684	26	1.0815	0.4955	1.0815	1.0399
No log	1.4737	28	0.9652	0.5270	0.9652	0.9824
No log	1.5789	30	0.9575	0.5025	0.9575	0.9785
No log	1.6842	32	0.9313	0.5569	0.9313	0.9650
No log	1.7895	34	0.9178	0.5282	0.9178	0.9580
No log	1.8947	36	0.9761	0.5183	0.9761	0.9880
No log	2.0	38	1.0214	0.5038	1.0214	1.0107
No log	2.1053	40	0.9524	0.5183	0.9524	0.9759
No log	2.2105	42	0.9054	0.5436	0.9054	0.9515
No log	2.3158	44	0.8765	0.5542	0.8765	0.9362
No log	2.4211	46	0.8504	0.5965	0.8504	0.9222
No log	2.5263	48	0.8556	0.5913	0.8556	0.9250
No log	2.6316	50	0.8663	0.5983	0.8663	0.9308
No log	2.7368	52	0.8020	0.6101	0.8020	0.8955
No log	2.8421	54	0.8558	0.5344	0.8558	0.9251
No log	2.9474	56	0.8550	0.5512	0.8550	0.9247
No log	3.0526	58	0.7616	0.6238	0.7616	0.8727
No log	3.1579	60	0.7378	0.6616	0.7378	0.8589
No log	3.2632	62	0.7430	0.7240	0.7430	0.8620
No log	3.3684	64	0.8000	0.6883	0.8000	0.8944
No log	3.4737	66	0.7494	0.7070	0.7494	0.8657
No log	3.5789	68	0.7326	0.6728	0.7326	0.8559
No log	3.6842	70	0.7551	0.6634	0.7551	0.8689
No log	3.7895	72	0.7756	0.6435	0.7756	0.8807
No log	3.8947	74	0.7908	0.5979	0.7908	0.8892
No log	4.0	76	0.7988	0.5859	0.7988	0.8938
No log	4.1053	78	0.8001	0.6119	0.8001	0.8945
No log	4.2105	80	0.8190	0.6129	0.8190	0.9050
No log	4.3158	82	0.8809	0.6284	0.8809	0.9385
No log	4.4211	84	0.8597	0.6269	0.8597	0.9272
No log	4.5263	86	0.7732	0.6547	0.7732	0.8793
No log	4.6316	88	0.7807	0.6261	0.7807	0.8836
No log	4.7368	90	0.7783	0.6279	0.7783	0.8822
No log	4.8421	92	0.7510	0.6759	0.7510	0.8666
No log	4.9474	94	0.8279	0.6449	0.8279	0.9099
No log	5.0526	96	0.8402	0.6555	0.8402	0.9166
No log	5.1579	98	0.7689	0.6922	0.7689	0.8768
No log	5.2632	100	0.7640	0.6655	0.7640	0.8741
No log	5.3684	102	0.8083	0.6632	0.8083	0.8991
No log	5.4737	104	0.8045	0.6590	0.8045	0.8970
No log	5.5789	106	0.7488	0.6798	0.7488	0.8653
No log	5.6842	108	0.7623	0.7150	0.7623	0.8731
No log	5.7895	110	0.8877	0.6370	0.8877	0.9422
No log	5.8947	112	0.9540	0.6294	0.9540	0.9767
No log	6.0	114	0.8877	0.6489	0.8877	0.9422
No log	6.1053	116	0.7683	0.6956	0.7683	0.8765
No log	6.2105	118	0.7278	0.6888	0.7278	0.8531
No log	6.3158	120	0.7292	0.6722	0.7292	0.8539
No log	6.4211	122	0.7468	0.6847	0.7468	0.8642
No log	6.5263	124	0.7783	0.6999	0.7783	0.8822
No log	6.6316	126	0.7850	0.7107	0.7850	0.8860
No log	6.7368	128	0.7494	0.7172	0.7494	0.8657
No log	6.8421	130	0.7352	0.7101	0.7352	0.8575
No log	6.9474	132	0.7386	0.7230	0.7386	0.8594
No log	7.0526	134	0.7333	0.7230	0.7333	0.8563
No log	7.1579	136	0.7207	0.6925	0.7207	0.8490
No log	7.2632	138	0.7147	0.6928	0.7147	0.8454
No log	7.3684	140	0.7111	0.7079	0.7111	0.8433
No log	7.4737	142	0.7096	0.7079	0.7096	0.8424
No log	7.5789	144	0.7105	0.7174	0.7105	0.8429
No log	7.6842	146	0.7107	0.7174	0.7107	0.8430
No log	7.7895	148	0.7304	0.7075	0.7304	0.8546
No log	7.8947	150	0.7810	0.7294	0.7810	0.8838
No log	8.0	152	0.7999	0.6911	0.7999	0.8943
No log	8.1053	154	0.7735	0.7294	0.7735	0.8795
No log	8.2105	156	0.7484	0.7227	0.7484	0.8651
No log	8.3158	158	0.7165	0.7058	0.7165	0.8465
No log	8.4211	160	0.7085	0.7125	0.7085	0.8417
No log	8.5263	162	0.7043	0.7107	0.7043	0.8392
No log	8.6316	164	0.7033	0.7107	0.7033	0.8386
No log	8.7368	166	0.7068	0.7107	0.7068	0.8407
No log	8.8421	168	0.7088	0.7107	0.7088	0.8419
No log	8.9474	170	0.7129	0.7168	0.7129	0.8443
No log	9.0526	172	0.7154	0.7146	0.7154	0.8458
No log	9.1579	174	0.7148	0.7168	0.7148	0.8454
No log	9.2632	176	0.7171	0.7314	0.7171	0.8468
No log	9.3684	178	0.7183	0.7291	0.7183	0.8475
No log	9.4737	180	0.7180	0.7313	0.7180	0.8474
No log	9.5789	182	0.7184	0.7254	0.7184	0.8476
No log	9.6842	184	0.7182	0.7254	0.7182	0.8475
No log	9.7895	186	0.7176	0.7253	0.7176	0.8471
No log	9.8947	188	0.7178	0.7253	0.7178	0.8473
No log	10.0	190	0.7182	0.7254	0.7182	0.8475

Framework versions

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