ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k7_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: 1.0429
• Qwk: 0.6362
• Mse: 1.0429
• Rmse: 1.0212

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	0.0741	2	2.3972	0.0170	2.3972	1.5483
No log	0.1481	4	1.6085	0.1330	1.6085	1.2683
No log	0.2222	6	1.5299	0.1198	1.5299	1.2369
No log	0.2963	8	1.5999	0.1275	1.5999	1.2649
No log	0.3704	10	1.6021	0.2848	1.6021	1.2657
No log	0.4444	12	1.5626	0.2738	1.5626	1.2500
No log	0.5185	14	1.4832	0.1575	1.4832	1.2179
No log	0.5926	16	1.4411	0.1423	1.4411	1.2005
No log	0.6667	18	1.4138	0.2183	1.4138	1.1890
No log	0.7407	20	1.5182	0.3441	1.5182	1.2321
No log	0.8148	22	1.5211	0.3851	1.5211	1.2333
No log	0.8889	24	1.4659	0.3867	1.4659	1.2108
No log	0.9630	26	1.3633	0.4070	1.3633	1.1676
No log	1.0370	28	1.2665	0.4087	1.2665	1.1254
No log	1.1111	30	1.1290	0.4590	1.1290	1.0626
No log	1.1852	32	1.1597	0.4314	1.1597	1.0769
No log	1.2593	34	1.1223	0.4853	1.1223	1.0594
No log	1.3333	36	1.0506	0.4419	1.0506	1.0250
No log	1.4074	38	1.0409	0.4707	1.0409	1.0202
No log	1.4815	40	1.2011	0.4753	1.2011	1.0960
No log	1.5556	42	1.4313	0.3323	1.4313	1.1964
No log	1.6296	44	1.5697	0.1842	1.5697	1.2529
No log	1.7037	46	1.7893	-0.0927	1.7893	1.3376
No log	1.7778	48	1.7652	-0.1077	1.7652	1.3286
No log	1.8519	50	1.5867	0.0313	1.5867	1.2596
No log	1.9259	52	1.3874	0.1588	1.3874	1.1779
No log	2.0	54	1.2445	0.2156	1.2445	1.1155
No log	2.0741	56	1.1405	0.2653	1.1405	1.0679
No log	2.1481	58	1.0987	0.3697	1.0987	1.0482
No log	2.2222	60	1.1027	0.4125	1.1027	1.0501
No log	2.2963	62	1.1954	0.4306	1.1954	1.0933
No log	2.3704	64	1.2723	0.3565	1.2723	1.1280
No log	2.4444	66	1.2067	0.4047	1.2067	1.0985
No log	2.5185	68	1.0752	0.4752	1.0752	1.0369
No log	2.5926	70	1.0054	0.4748	1.0054	1.0027
No log	2.6667	72	0.9753	0.4803	0.9753	0.9876
No log	2.7407	74	0.9520	0.4954	0.9520	0.9757
No log	2.8148	76	0.9539	0.4776	0.9539	0.9767
No log	2.8889	78	0.9913	0.4390	0.9913	0.9956
No log	2.9630	80	0.9211	0.5027	0.9211	0.9598
No log	3.0370	82	0.9152	0.5217	0.9152	0.9567
No log	3.1111	84	0.9056	0.5385	0.9056	0.9516
No log	3.1852	86	0.9430	0.5531	0.9430	0.9711
No log	3.2593	88	0.9886	0.5860	0.9886	0.9943
No log	3.3333	90	1.0102	0.5545	1.0102	1.0051
No log	3.4074	92	1.0699	0.5455	1.0699	1.0343
No log	3.4815	94	1.0491	0.5589	1.0491	1.0243
No log	3.5556	96	0.8925	0.6286	0.8925	0.9447
No log	3.6296	98	0.8490	0.5787	0.8490	0.9214
No log	3.7037	100	0.8573	0.6207	0.8573	0.9259
No log	3.7778	102	0.8844	0.6504	0.8844	0.9404
No log	3.8519	104	1.0276	0.5682	1.0276	1.0137
No log	3.9259	106	1.1837	0.5141	1.1837	1.0880
No log	4.0	108	1.2389	0.4878	1.2389	1.1131
No log	4.0741	110	1.1213	0.5507	1.1213	1.0589
No log	4.1481	112	1.0133	0.5855	1.0133	1.0066
No log	4.2222	114	0.9018	0.5844	0.9018	0.9496
No log	4.2963	116	0.8767	0.6272	0.8767	0.9363
No log	4.3704	118	0.8474	0.6371	0.8474	0.9206
No log	4.4444	120	0.8289	0.6461	0.8289	0.9104
No log	4.5185	122	0.8966	0.6493	0.8966	0.9469
No log	4.5926	124	1.1218	0.5821	1.1218	1.0592
No log	4.6667	126	1.3003	0.5551	1.3003	1.1403
No log	4.7407	128	1.2771	0.5592	1.2771	1.1301
No log	4.8148	130	1.1205	0.6038	1.1205	1.0585
No log	4.8889	132	1.0790	0.6152	1.0790	1.0387
No log	4.9630	134	0.9254	0.5973	0.9254	0.9620
No log	5.0370	136	0.9085	0.6073	0.9085	0.9532
No log	5.1111	138	1.0522	0.5870	1.0522	1.0258
No log	5.1852	140	1.2835	0.5436	1.2835	1.1329
No log	5.2593	142	1.4743	0.4895	1.4743	1.2142
No log	5.3333	144	1.7274	0.4766	1.7274	1.3143
No log	5.4074	146	1.6366	0.4704	1.6366	1.2793
No log	5.4815	148	1.3581	0.5164	1.3581	1.1654
No log	5.5556	150	1.0576	0.6242	1.0576	1.0284
No log	5.6296	152	0.8658	0.6397	0.8658	0.9305
No log	5.7037	154	0.7787	0.6402	0.7787	0.8824
No log	5.7778	156	0.7573	0.6510	0.7573	0.8702
No log	5.8519	158	0.8068	0.6547	0.8068	0.8982
No log	5.9259	160	0.9824	0.6478	0.9824	0.9912
No log	6.0	162	1.3412	0.5403	1.3412	1.1581
No log	6.0741	164	1.5496	0.5296	1.5496	1.2448
No log	6.1481	166	1.6841	0.5177	1.6841	1.2977
No log	6.2222	168	1.5781	0.5189	1.5781	1.2562
No log	6.2963	170	1.3216	0.5354	1.3216	1.1496
No log	6.3704	172	1.0609	0.6341	1.0609	1.0300
No log	6.4444	174	0.9138	0.6625	0.9138	0.9559
No log	6.5185	176	0.8935	0.6651	0.8935	0.9452
No log	6.5926	178	0.9570	0.6251	0.9570	0.9783
No log	6.6667	180	1.1210	0.6009	1.1210	1.0588
No log	6.7407	182	1.3501	0.5249	1.3501	1.1620
No log	6.8148	184	1.4308	0.5402	1.4308	1.1962
No log	6.8889	186	1.3486	0.5288	1.3486	1.1613
No log	6.9630	188	1.1707	0.5860	1.1707	1.0820
No log	7.0370	190	0.9656	0.6477	0.9656	0.9827
No log	7.1111	192	0.8356	0.6648	0.8356	0.9141
No log	7.1852	194	0.8092	0.6829	0.8092	0.8995
No log	7.2593	196	0.8348	0.6804	0.8348	0.9137
No log	7.3333	198	0.9170	0.6582	0.9170	0.9576
No log	7.4074	200	1.0772	0.5935	1.0772	1.0379
No log	7.4815	202	1.2264	0.5807	1.2264	1.1074
No log	7.5556	204	1.2622	0.5797	1.2622	1.1235
No log	7.6296	206	1.2119	0.5807	1.2120	1.1009
No log	7.7037	208	1.0892	0.5963	1.0892	1.0436
No log	7.7778	210	0.9517	0.6535	0.9517	0.9756
No log	7.8519	212	0.8935	0.6723	0.8935	0.9452
No log	7.9259	214	0.8854	0.6723	0.8854	0.9409
No log	8.0	216	0.9268	0.6645	0.9268	0.9627
No log	8.0741	218	0.9758	0.6427	0.9758	0.9878
No log	8.1481	220	1.0041	0.6488	1.0041	1.0021
No log	8.2222	222	1.0396	0.6499	1.0396	1.0196
No log	8.2963	224	1.0734	0.6362	1.0734	1.0360
No log	8.3704	226	1.0653	0.6362	1.0653	1.0321
No log	8.4444	228	1.0849	0.6362	1.0849	1.0416
No log	8.5185	230	1.1092	0.6275	1.1092	1.0532
No log	8.5926	232	1.1141	0.6101	1.1141	1.0555
No log	8.6667	234	1.1343	0.6101	1.1343	1.0650
No log	8.7407	236	1.1119	0.6187	1.1119	1.0545
No log	8.8148	238	1.0659	0.6439	1.0659	1.0324
No log	8.8889	240	1.0046	0.6587	1.0046	1.0023
No log	8.9630	242	0.9814	0.6577	0.9814	0.9907
No log	9.0370	244	0.9595	0.6585	0.9595	0.9795
No log	9.1111	246	0.9594	0.6595	0.9594	0.9795
No log	9.1852	248	0.9787	0.6485	0.9787	0.9893
No log	9.2593	250	0.9962	0.6427	0.9962	0.9981
No log	9.3333	252	1.0098	0.6488	1.0098	1.0049
No log	9.4074	254	1.0137	0.6488	1.0137	1.0068
No log	9.4815	256	1.0120	0.6488	1.0120	1.0060
No log	9.5556	258	1.0173	0.6488	1.0173	1.0086
No log	9.6296	260	1.0311	0.6488	1.0311	1.0154
No log	9.7037	262	1.0396	0.6350	1.0396	1.0196
No log	9.7778	264	1.0449	0.6362	1.0449	1.0222
No log	9.8519	266	1.0454	0.6362	1.0454	1.0225
No log	9.9259	268	1.0441	0.6362	1.0441	1.0218
No log	10.0	270	1.0429	0.6362	1.0429	1.0212

Framework versions

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