ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k7_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: 0.6732
• Qwk: 0.2994
• Mse: 0.6732
• Rmse: 0.8205

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	0.0588	2	3.0572	0.0014	3.0572	1.7485
No log	0.1176	4	1.5399	0.0210	1.5399	1.2409
No log	0.1765	6	0.7924	0.2233	0.7924	0.8902
No log	0.2353	8	0.9634	0.1130	0.9634	0.9815
No log	0.2941	10	0.7344	0.1600	0.7344	0.8570
No log	0.3529	12	0.5647	0.0569	0.5647	0.7515
No log	0.4118	14	0.5761	0.1515	0.5761	0.7590
No log	0.4706	16	1.1999	0.0745	1.1999	1.0954
No log	0.5294	18	1.4952	0.0210	1.4952	1.2228
No log	0.5882	20	1.0449	0.0	1.0449	1.0222
No log	0.6471	22	0.7352	0.1730	0.7352	0.8575
No log	0.7059	24	0.5838	0.0	0.5838	0.7640
No log	0.7647	26	0.5825	0.0	0.5825	0.7632
No log	0.8235	28	0.6009	0.0	0.6009	0.7752
No log	0.8824	30	0.5724	0.0	0.5724	0.7566
No log	0.9412	32	0.5905	-0.0233	0.5905	0.7685
No log	1.0	34	0.7928	0.2000	0.7928	0.8904
No log	1.0588	36	0.9465	0.1111	0.9465	0.9729
No log	1.1176	38	0.9741	0.1111	0.9741	0.9869
No log	1.1765	40	0.8197	0.1486	0.8197	0.9054
No log	1.2353	42	0.6753	0.1373	0.6753	0.8218
No log	1.2941	44	0.6825	0.1045	0.6825	0.8261
No log	1.3529	46	0.6740	0.1038	0.6740	0.8210
No log	1.4118	48	0.5908	0.0476	0.5908	0.7686
No log	1.4706	50	0.6017	0.0448	0.6017	0.7757
No log	1.5294	52	0.6436	0.0807	0.6436	0.8023
No log	1.5882	54	1.0377	0.1621	1.0377	1.0187
No log	1.6471	56	0.7794	0.0863	0.7794	0.8829
No log	1.7059	58	0.6388	0.0400	0.6388	0.7993
No log	1.7647	60	0.6065	-0.0233	0.6065	0.7788
No log	1.8235	62	0.6348	-0.0314	0.6348	0.7967
No log	1.8824	64	0.7645	0.2000	0.7645	0.8744
No log	1.9412	66	0.7341	0.1556	0.7341	0.8568
No log	2.0	68	0.6582	-0.0556	0.6582	0.8113
No log	2.0588	70	0.6547	-0.0496	0.6547	0.8091
No log	2.1176	72	0.6547	0.0811	0.6547	0.8091
No log	2.1765	74	0.7067	0.1186	0.7067	0.8407
No log	2.2353	76	1.0852	0.0817	1.0852	1.0417
No log	2.2941	78	0.9691	0.0598	0.9691	0.9844
No log	2.3529	80	0.6483	0.2000	0.6483	0.8052
No log	2.4118	82	0.6655	0.0388	0.6655	0.8158
No log	2.4706	84	0.6938	0.0388	0.6938	0.8330
No log	2.5294	86	0.6644	0.1795	0.6644	0.8151
No log	2.5882	88	0.8470	0.1245	0.8470	0.9203
No log	2.6471	90	0.9955	0.1405	0.9955	0.9978
No log	2.7059	92	0.7286	0.1264	0.7286	0.8536
No log	2.7647	94	0.7382	0.1045	0.7382	0.8592
No log	2.8235	96	0.8435	0.0811	0.8435	0.9184
No log	2.8824	98	0.8459	0.0909	0.8459	0.9197
No log	2.9412	100	0.6729	0.2727	0.6729	0.8203
No log	3.0	102	0.8209	0.0852	0.8209	0.9060
No log	3.0588	104	0.7661	0.1090	0.7661	0.8753
No log	3.1176	106	0.6875	0.2941	0.6875	0.8291
No log	3.1765	108	0.8761	0.0939	0.8761	0.9360
No log	3.2353	110	0.8548	0.0435	0.8548	0.9246
No log	3.2941	112	0.6867	0.2676	0.6867	0.8287
No log	3.3529	114	0.6170	0.1795	0.6170	0.7855
No log	3.4118	116	0.6008	0.2000	0.6008	0.7751
No log	3.4706	118	0.5602	0.3289	0.5602	0.7484
No log	3.5294	120	0.6645	0.0625	0.6645	0.8152
No log	3.5882	122	0.6314	0.1765	0.6314	0.7946
No log	3.6471	124	0.5330	0.3103	0.5330	0.7301
No log	3.7059	126	0.5195	0.3711	0.5195	0.7208
No log	3.7647	128	0.5757	0.4074	0.5757	0.7587
No log	3.8235	130	0.6610	0.1823	0.6610	0.8130
No log	3.8824	132	0.6316	0.1818	0.6316	0.7947
No log	3.9412	134	0.5468	0.4083	0.5468	0.7395
No log	4.0	136	0.5757	0.2093	0.5757	0.7588
No log	4.0588	138	0.5892	0.2727	0.5892	0.7676
No log	4.1176	140	0.6509	0.3016	0.6509	0.8068
No log	4.1765	142	0.7377	0.2086	0.7377	0.8589
No log	4.2353	144	0.7509	0.3301	0.7509	0.8665
No log	4.2941	146	0.8355	0.1525	0.8355	0.9141
No log	4.3529	148	0.8274	0.1931	0.8274	0.9096
No log	4.4118	150	0.8444	0.1730	0.8444	0.9189
No log	4.4706	152	0.8988	0.2414	0.8988	0.9481
No log	4.5294	154	0.9803	0.1525	0.9803	0.9901
No log	4.5882	156	1.2563	0.1065	1.2563	1.1208
No log	4.6471	158	1.3235	0.0307	1.3235	1.1504
No log	4.7059	160	1.0927	0.0843	1.0927	1.0453
No log	4.7647	162	0.8077	0.2233	0.8077	0.8987
No log	4.8235	164	0.7640	0.2000	0.7640	0.8741
No log	4.8824	166	0.7478	0.2593	0.7478	0.8647
No log	4.9412	168	0.7786	0.1841	0.7786	0.8824
No log	5.0	170	0.8073	0.0531	0.8073	0.8985
No log	5.0588	172	0.7785	0.0	0.7785	0.8823
No log	5.1176	174	0.7382	0.1818	0.7382	0.8592
No log	5.1765	176	0.7286	0.2179	0.7286	0.8536
No log	5.2353	178	0.7312	0.1489	0.7312	0.8551
No log	5.2941	180	0.7420	0.2088	0.7420	0.8614
No log	5.3529	182	0.7498	0.2323	0.7498	0.8659
No log	5.4118	184	0.7618	0.2239	0.7618	0.8728
No log	5.4706	186	0.7729	0.2709	0.7729	0.8791
No log	5.5294	188	0.7886	0.2079	0.7886	0.8880
No log	5.5882	190	0.8669	0.1402	0.8669	0.9311
No log	5.6471	192	1.0107	-0.0124	1.0107	1.0053
No log	5.7059	194	1.0140	0.0040	1.0140	1.0070
No log	5.7647	196	0.8449	0.1050	0.8449	0.9192
No log	5.8235	198	0.7283	0.2239	0.7283	0.8534
No log	5.8824	200	0.7399	0.2381	0.7399	0.8601
No log	5.9412	202	0.7176	0.2390	0.7176	0.8471
No log	6.0	204	0.7098	0.2626	0.7098	0.8425
No log	6.0588	206	0.7762	0.1925	0.7762	0.8810
No log	6.1176	208	0.9359	0.0916	0.9359	0.9674
No log	6.1765	210	0.9691	0.0400	0.9691	0.9844
No log	6.2353	212	0.8800	0.0169	0.8800	0.9381
No log	6.2941	214	0.7238	0.1638	0.7238	0.8508
No log	6.3529	216	0.6787	0.2644	0.6787	0.8238
No log	6.4118	218	0.7050	0.2169	0.7050	0.8396
No log	6.4706	220	0.6661	0.2644	0.6661	0.8162
No log	6.5294	222	0.6493	0.2883	0.6493	0.8058
No log	6.5882	224	0.7321	0.0805	0.7321	0.8556
No log	6.6471	226	0.7667	0.0435	0.7667	0.8756
No log	6.7059	228	0.7263	0.1209	0.7263	0.8523
No log	6.7647	230	0.6826	0.2281	0.6826	0.8262
No log	6.8235	232	0.6856	0.2889	0.6856	0.8280
No log	6.8824	234	0.6972	0.2889	0.6972	0.8350
No log	6.9412	236	0.7247	0.2609	0.7247	0.8513
No log	7.0	238	0.7565	0.1020	0.7565	0.8698
No log	7.0588	240	0.7813	0.1045	0.7813	0.8839
No log	7.1176	242	0.7740	0.2157	0.7740	0.8798
No log	7.1765	244	0.7652	0.2513	0.7652	0.8748
No log	7.2353	246	0.7631	0.2421	0.7631	0.8736
No log	7.2941	248	0.7717	0.2174	0.7717	0.8784
No log	7.3529	250	0.7785	0.1910	0.7785	0.8823
No log	7.4118	252	0.7937	0.0400	0.7937	0.8909
No log	7.4706	254	0.8102	0.0891	0.8102	0.9001
No log	7.5294	256	0.7720	0.0703	0.7720	0.8786
No log	7.5882	258	0.7687	0.1135	0.7687	0.8768
No log	7.6471	260	0.7386	0.1910	0.7386	0.8594
No log	7.7059	262	0.7144	0.2527	0.7144	0.8452
No log	7.7647	264	0.7123	0.2809	0.7123	0.8440
No log	7.8235	266	0.7080	0.2865	0.7080	0.8414
No log	7.8824	268	0.7195	0.1398	0.7195	0.8482
No log	7.9412	270	0.7944	0.0909	0.7944	0.8913
No log	8.0	272	0.8344	0.1416	0.8344	0.9134
No log	8.0588	274	0.8032	0.1416	0.8032	0.8962
No log	8.1176	276	0.7349	0.1135	0.7349	0.8573
No log	8.1765	278	0.6877	0.2273	0.6877	0.8292
No log	8.2353	280	0.6718	0.2626	0.6718	0.8196
No log	8.2941	282	0.6682	0.2626	0.6682	0.8174
No log	8.3529	284	0.6748	0.2273	0.6748	0.8215
No log	8.4118	286	0.6966	0.1158	0.6966	0.8346
No log	8.4706	288	0.7395	0.1220	0.7395	0.8599
No log	8.5294	290	0.7633	0.1005	0.7633	0.8737
No log	8.5882	292	0.7499	0.1304	0.7499	0.8660
No log	8.6471	294	0.7254	0.1158	0.7254	0.8517
No log	8.7059	296	0.7107	0.1837	0.7107	0.8430
No log	8.7647	298	0.7074	0.1837	0.7074	0.8411
No log	8.8235	300	0.7104	0.2258	0.7104	0.8429
No log	8.8824	302	0.7106	0.3369	0.7106	0.8430
No log	8.9412	304	0.7084	0.2994	0.7084	0.8417
No log	9.0	306	0.7062	0.2994	0.7062	0.8403
No log	9.0588	308	0.7005	0.2994	0.7005	0.8370
No log	9.1176	310	0.7040	0.2258	0.7040	0.8390
No log	9.1765	312	0.7185	0.1837	0.7185	0.8477
No log	9.2353	314	0.7454	0.1610	0.7454	0.8633
No log	9.2941	316	0.7597	0.0943	0.7597	0.8716
No log	9.3529	318	0.7557	0.0943	0.7557	0.8693
No log	9.4118	320	0.7361	0.1683	0.7361	0.8579
No log	9.4706	322	0.7111	0.1917	0.7111	0.8433
No log	9.5294	324	0.6958	0.2251	0.6958	0.8341
No log	9.5882	326	0.6852	0.2258	0.6852	0.8278
No log	9.6471	328	0.6798	0.2273	0.6798	0.8245
No log	9.7059	330	0.6761	0.2967	0.6761	0.8222
No log	9.7647	332	0.6750	0.2967	0.6750	0.8216
No log	9.8235	334	0.6737	0.2994	0.6737	0.8208
No log	9.8824	336	0.6733	0.2994	0.6733	0.8205
No log	9.9412	338	0.6732	0.2994	0.6732	0.8205
No log	10.0	340	0.6732	0.2994	0.6732	0.8205

Framework versions

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