ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k10_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: 0.6689
• Qwk: 0.7573
• Mse: 0.6689
• Rmse: 0.8179

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	0.0513	2	2.2799	0.0370	2.2799	1.5099
No log	0.1026	4	1.4895	0.2002	1.4895	1.2205
No log	0.1538	6	1.5225	0.1085	1.5225	1.2339
No log	0.2051	8	1.4590	0.1209	1.4590	1.2079
No log	0.2564	10	1.4373	0.1057	1.4373	1.1989
No log	0.3077	12	1.4567	0.1009	1.4567	1.2069
No log	0.3590	14	1.5446	0.1132	1.5446	1.2428
No log	0.4103	16	1.6118	0.1735	1.6118	1.2696
No log	0.4615	18	1.5945	0.1563	1.5945	1.2627
No log	0.5128	20	1.5173	0.1412	1.5173	1.2318
No log	0.5641	22	1.4742	0.1758	1.4742	1.2142
No log	0.6154	24	1.4794	0.1911	1.4794	1.2163
No log	0.6667	26	1.4680	0.2093	1.4680	1.2116
No log	0.7179	28	1.3946	0.2726	1.3946	1.1809
No log	0.7692	30	1.3692	0.3595	1.3692	1.1701
No log	0.8205	32	1.2597	0.3214	1.2597	1.1224
No log	0.8718	34	1.2928	0.3884	1.2928	1.1370
No log	0.9231	36	1.2730	0.3441	1.2730	1.1283
No log	0.9744	38	1.2156	0.2932	1.2156	1.1025
No log	1.0256	40	1.1690	0.2601	1.1690	1.0812
No log	1.0769	42	1.1471	0.2601	1.1471	1.0710
No log	1.1282	44	1.1251	0.3739	1.1251	1.0607
No log	1.1795	46	1.1438	0.4171	1.1438	1.0695
No log	1.2308	48	1.3104	0.4199	1.3104	1.1447
No log	1.2821	50	1.2624	0.4201	1.2624	1.1236
No log	1.3333	52	1.0784	0.4447	1.0784	1.0385
No log	1.3846	54	0.9812	0.4718	0.9812	0.9906
No log	1.4359	56	0.9704	0.4759	0.9704	0.9851
No log	1.4872	58	0.9502	0.5255	0.9502	0.9748
No log	1.5385	60	1.0676	0.4847	1.0676	1.0333
No log	1.5897	62	1.1469	0.4599	1.1469	1.0709
No log	1.6410	64	1.2069	0.4422	1.2069	1.0986
No log	1.6923	66	1.2879	0.4642	1.2879	1.1349
No log	1.7436	68	1.2587	0.4511	1.2587	1.1219
No log	1.7949	70	1.0725	0.4613	1.0725	1.0356
No log	1.8462	72	0.9539	0.5418	0.9539	0.9767
No log	1.8974	74	0.9228	0.5217	0.9228	0.9606
No log	1.9487	76	0.9497	0.5601	0.9497	0.9745
No log	2.0	78	1.0161	0.4783	1.0161	1.0080
No log	2.0513	80	1.0208	0.4903	1.0208	1.0104
No log	2.1026	82	1.1312	0.4628	1.1312	1.0636
No log	2.1538	84	1.0307	0.4892	1.0307	1.0152
No log	2.2051	86	0.9093	0.5610	0.9093	0.9535
No log	2.2564	88	0.8910	0.5733	0.8910	0.9439
No log	2.3077	90	1.1036	0.4816	1.1036	1.0505
No log	2.3590	92	1.1993	0.4906	1.1993	1.0951
No log	2.4103	94	1.2661	0.4774	1.2661	1.1252
No log	2.4615	96	1.0730	0.5635	1.0730	1.0359
No log	2.5128	98	0.7651	0.6987	0.7651	0.8747
No log	2.5641	100	0.7106	0.7232	0.7106	0.8430
No log	2.6154	102	0.7028	0.7278	0.7028	0.8383
No log	2.6667	104	0.6842	0.7309	0.6842	0.8272
No log	2.7179	106	0.7962	0.7195	0.7962	0.8923
No log	2.7692	108	0.8277	0.7318	0.8277	0.9098
No log	2.8205	110	0.7043	0.7364	0.7043	0.8392
No log	2.8718	112	0.7109	0.7266	0.7109	0.8432
No log	2.9231	114	0.7663	0.7342	0.7663	0.8754
No log	2.9744	116	0.8543	0.6765	0.8543	0.9243
No log	3.0256	118	0.9221	0.6328	0.9221	0.9603
No log	3.0769	120	0.7695	0.6982	0.7695	0.8772
No log	3.1282	122	0.6604	0.7278	0.6604	0.8127
No log	3.1795	124	0.6612	0.7429	0.6612	0.8132
No log	3.2308	126	0.6359	0.7562	0.6359	0.7975
No log	3.2821	128	0.6677	0.7530	0.6677	0.8171
No log	3.3333	130	0.8117	0.6792	0.8117	0.9009
No log	3.3846	132	0.8038	0.6876	0.8038	0.8965
No log	3.4359	134	0.7688	0.7218	0.7687	0.8768
No log	3.4872	136	0.7998	0.6995	0.7998	0.8943
No log	3.5385	138	0.7958	0.6902	0.7958	0.8921
No log	3.5897	140	0.7521	0.7273	0.7521	0.8672
No log	3.6410	142	0.6782	0.7671	0.6782	0.8235
No log	3.6923	144	0.6821	0.7595	0.6821	0.8259
No log	3.7436	146	0.6914	0.7321	0.6914	0.8315
No log	3.7949	148	0.7213	0.7406	0.7213	0.8493
No log	3.8462	150	0.6743	0.7406	0.6743	0.8212
No log	3.8974	152	0.7139	0.7655	0.7139	0.8449
No log	3.9487	154	0.7102	0.7593	0.7102	0.8427
No log	4.0	156	0.7015	0.7544	0.7015	0.8375
No log	4.0513	158	0.6312	0.7774	0.6312	0.7945
No log	4.1026	160	0.6329	0.7849	0.6329	0.7955
No log	4.1538	162	0.6959	0.7581	0.6959	0.8342
No log	4.2051	164	0.8545	0.6770	0.8545	0.9244
No log	4.2564	166	0.9277	0.6770	0.9277	0.9632
No log	4.3077	168	0.8439	0.6763	0.8439	0.9186
No log	4.3590	170	0.7414	0.7389	0.7414	0.8610
No log	4.4103	172	0.7329	0.7311	0.7329	0.8561
No log	4.4615	174	0.6783	0.7232	0.6783	0.8236
No log	4.5128	176	0.6715	0.7309	0.6715	0.8195
No log	4.5641	178	0.7279	0.7453	0.7279	0.8532
No log	4.6154	180	0.7431	0.7345	0.7431	0.8620
No log	4.6667	182	0.7532	0.7345	0.7532	0.8679
No log	4.7179	184	0.6682	0.7551	0.6682	0.8174
No log	4.7692	186	0.6579	0.7646	0.6579	0.8111
No log	4.8205	188	0.6565	0.7646	0.6565	0.8102
No log	4.8718	190	0.6519	0.7545	0.6519	0.8074
No log	4.9231	192	0.7060	0.7449	0.7060	0.8402
No log	4.9744	194	0.7410	0.7399	0.7410	0.8608
No log	5.0256	196	0.7194	0.7235	0.7194	0.8482
No log	5.0769	198	0.6661	0.7350	0.6661	0.8161
No log	5.1282	200	0.6484	0.7425	0.6484	0.8052
No log	5.1795	202	0.6883	0.7485	0.6883	0.8297
No log	5.2308	204	0.7731	0.7168	0.7731	0.8793
No log	5.2821	206	0.7678	0.7210	0.7678	0.8763
No log	5.3333	208	0.7239	0.7583	0.7239	0.8508
No log	5.3846	210	0.6454	0.7613	0.6454	0.8034
No log	5.4359	212	0.6274	0.7805	0.6274	0.7921
No log	5.4872	214	0.6359	0.7685	0.6359	0.7975
No log	5.5385	216	0.6706	0.7613	0.6706	0.8189
No log	5.5897	218	0.7187	0.7317	0.7187	0.8478
No log	5.6410	220	0.7908	0.7112	0.7908	0.8893
No log	5.6923	222	0.7463	0.7317	0.7463	0.8639
No log	5.7436	224	0.6947	0.7243	0.6947	0.8335
No log	5.7949	226	0.6357	0.7512	0.6357	0.7973
No log	5.8462	228	0.6208	0.7627	0.6208	0.7879
No log	5.8974	230	0.6447	0.7372	0.6447	0.8030
No log	5.9487	232	0.7232	0.7361	0.7232	0.8504
No log	6.0	234	0.7511	0.7281	0.7511	0.8666
No log	6.0513	236	0.7188	0.7361	0.7188	0.8478
No log	6.1026	238	0.6529	0.7506	0.6529	0.8080
No log	6.1538	240	0.6140	0.7458	0.6140	0.7836
No log	6.2051	242	0.5961	0.7525	0.5961	0.7721
No log	6.2564	244	0.5989	0.7496	0.5989	0.7739
No log	6.3077	246	0.6258	0.7416	0.6258	0.7911
No log	6.3590	248	0.6635	0.7287	0.6635	0.8145
No log	6.4103	250	0.7121	0.7009	0.7121	0.8439
No log	6.4615	252	0.7600	0.7022	0.7600	0.8718
No log	6.5128	254	0.7260	0.7101	0.7260	0.8520
No log	6.5641	256	0.6508	0.7357	0.6508	0.8067
No log	6.6154	258	0.5958	0.7591	0.5958	0.7719
No log	6.6667	260	0.5892	0.7597	0.5892	0.7676
No log	6.7179	262	0.5999	0.7561	0.5999	0.7745
No log	6.7692	264	0.6156	0.7506	0.6156	0.7846
No log	6.8205	266	0.6550	0.7510	0.6550	0.8093
No log	6.8718	268	0.7131	0.7492	0.7131	0.8445
No log	6.9231	270	0.7242	0.7492	0.7242	0.8510
No log	6.9744	272	0.6972	0.7492	0.6972	0.8350
No log	7.0256	274	0.6328	0.7710	0.6328	0.7955
No log	7.0769	276	0.6176	0.7795	0.6176	0.7859
No log	7.1282	278	0.6203	0.7795	0.6203	0.7876
No log	7.1795	280	0.6586	0.7668	0.6586	0.8115
No log	7.2308	282	0.7264	0.7492	0.7264	0.8523
No log	7.2821	284	0.7600	0.7345	0.7600	0.8718
No log	7.3333	286	0.7324	0.7472	0.7324	0.8558
No log	7.3846	288	0.6707	0.7638	0.6707	0.8190
No log	7.4359	290	0.6391	0.7517	0.6391	0.7994
No log	7.4872	292	0.6316	0.7517	0.6316	0.7948
No log	7.5385	294	0.6188	0.7503	0.6188	0.7866
No log	7.5897	296	0.6341	0.7710	0.6341	0.7963
No log	7.6410	298	0.6589	0.7723	0.6589	0.8117
No log	7.6923	300	0.6841	0.7492	0.6841	0.8271
No log	7.7436	302	0.7084	0.7492	0.7084	0.8417
No log	7.7949	304	0.7096	0.7393	0.7096	0.8424
No log	7.8462	306	0.6752	0.7615	0.6752	0.8217
No log	7.8974	308	0.6409	0.7723	0.6409	0.8005
No log	7.9487	310	0.6132	0.7740	0.6132	0.7831
No log	8.0	312	0.5947	0.7591	0.5947	0.7712
No log	8.0513	314	0.6031	0.7512	0.6031	0.7766
No log	8.1026	316	0.6245	0.7437	0.6245	0.7903
No log	8.1538	318	0.6265	0.7437	0.6265	0.7915
No log	8.2051	320	0.6373	0.7574	0.6373	0.7983
No log	8.2564	322	0.6531	0.7657	0.6531	0.8081
No log	8.3077	324	0.6711	0.7573	0.6711	0.8192
No log	8.3590	326	0.6809	0.7472	0.6809	0.8252
No log	8.4103	328	0.6705	0.7573	0.6705	0.8188
No log	8.4615	330	0.6557	0.7699	0.6557	0.8097
No log	8.5128	332	0.6329	0.7692	0.6329	0.7955
No log	8.5641	334	0.5981	0.7691	0.5981	0.7734
No log	8.6154	336	0.5723	0.7525	0.5723	0.7565
No log	8.6667	338	0.5584	0.7695	0.5584	0.7473
No log	8.7179	340	0.5581	0.7695	0.5581	0.7470
No log	8.7692	342	0.5665	0.7574	0.5665	0.7527
No log	8.8205	344	0.5864	0.7678	0.5864	0.7658
No log	8.8718	346	0.6122	0.7704	0.6122	0.7824
No log	8.9231	348	0.6418	0.7574	0.6418	0.8011
No log	8.9744	350	0.6640	0.7573	0.6640	0.8149
No log	9.0256	352	0.6885	0.7573	0.6885	0.8298
No log	9.0769	354	0.7033	0.7472	0.7033	0.8386
No log	9.1282	356	0.7073	0.7508	0.7073	0.8410
No log	9.1795	358	0.6957	0.7573	0.6957	0.8341
No log	9.2308	360	0.6739	0.7420	0.6739	0.8209
No log	9.2821	362	0.6508	0.7443	0.6508	0.8067
No log	9.3333	364	0.6411	0.7443	0.6411	0.8007
No log	9.3846	366	0.6419	0.7487	0.6419	0.8012
No log	9.4359	368	0.6458	0.7564	0.6458	0.8036
No log	9.4872	370	0.6513	0.7521	0.6513	0.8070
No log	9.5385	372	0.6585	0.7596	0.6585	0.8115
No log	9.5897	374	0.6710	0.7573	0.6710	0.8191
No log	9.6410	376	0.6775	0.7573	0.6775	0.8231
No log	9.6923	378	0.6777	0.7573	0.6777	0.8232
No log	9.7436	380	0.6770	0.7573	0.6770	0.8228
No log	9.7949	382	0.6746	0.7573	0.6746	0.8214
No log	9.8462	384	0.6704	0.7573	0.6704	0.8188
No log	9.8974	386	0.6692	0.7573	0.6692	0.8180
No log	9.9487	388	0.6689	0.7573	0.6689	0.8179
No log	10.0	390	0.6689	0.7573	0.6689	0.8179

Framework versions

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