ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k13_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: 0.7134
• Qwk: 0.7266
• Mse: 0.7134
• Rmse: 0.8446

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	0.0417	2	2.4064	0.0072	2.4064	1.5513
No log	0.0833	4	1.6722	0.1421	1.6722	1.2931
No log	0.125	6	1.6845	0.0009	1.6845	1.2979
No log	0.1667	8	1.8346	-0.0310	1.8346	1.3545
No log	0.2083	10	1.8099	0.0436	1.8099	1.3453
No log	0.25	12	1.7210	0.0657	1.7210	1.3119
No log	0.2917	14	1.5146	0.1150	1.5146	1.2307
No log	0.3333	16	1.4600	0.0645	1.4600	1.2083
No log	0.375	18	1.4259	0.0811	1.4259	1.1941
No log	0.4167	20	1.3985	0.1022	1.3985	1.1826
No log	0.4583	22	1.4357	0.2172	1.4357	1.1982
No log	0.5	24	1.4508	0.3389	1.4508	1.2045
No log	0.5417	26	1.3344	0.3303	1.3344	1.1552
No log	0.5833	28	1.3241	0.3555	1.3241	1.1507
No log	0.625	30	1.4384	0.4149	1.4384	1.1993
No log	0.6667	32	1.3513	0.4150	1.3513	1.1625
No log	0.7083	34	1.3954	0.4150	1.3954	1.1813
No log	0.75	36	1.3612	0.4150	1.3612	1.1667
No log	0.7917	38	1.2584	0.4151	1.2584	1.1218
No log	0.8333	40	1.1717	0.4402	1.1717	1.0825
No log	0.875	42	1.0905	0.4410	1.0905	1.0443
No log	0.9167	44	1.0425	0.4723	1.0425	1.0210
No log	0.9583	46	1.0174	0.4797	1.0174	1.0086
No log	1.0	48	0.9469	0.5220	0.9469	0.9731
No log	1.0417	50	0.8617	0.5473	0.8617	0.9283
No log	1.0833	52	0.9451	0.5131	0.9451	0.9722
No log	1.125	54	0.9462	0.4915	0.9462	0.9727
No log	1.1667	56	0.8635	0.5562	0.8635	0.9292
No log	1.2083	58	0.9104	0.5632	0.9104	0.9542
No log	1.25	60	0.9452	0.5142	0.9452	0.9722
No log	1.2917	62	0.8927	0.5701	0.8927	0.9448
No log	1.3333	64	0.8279	0.5807	0.8279	0.9099
No log	1.375	66	0.8047	0.5991	0.8047	0.8970
No log	1.4167	68	0.8015	0.5991	0.8015	0.8952
No log	1.4583	70	0.8237	0.5989	0.8237	0.9076
No log	1.5	72	0.9349	0.5627	0.9349	0.9669
No log	1.5417	74	1.1855	0.4881	1.1855	1.0888
No log	1.5833	76	1.2331	0.4644	1.2331	1.1105
No log	1.625	78	1.0243	0.5545	1.0243	1.0121
No log	1.6667	80	0.8223	0.6167	0.8223	0.9068
No log	1.7083	82	0.7704	0.6654	0.7704	0.8777
No log	1.75	84	0.8307	0.6546	0.8307	0.9114
No log	1.7917	86	1.0897	0.5695	1.0897	1.0439
No log	1.8333	88	1.2601	0.5688	1.2601	1.1225
No log	1.875	90	1.0749	0.5846	1.0749	1.0368
No log	1.9167	92	0.7795	0.7015	0.7795	0.8829
No log	1.9583	94	0.7055	0.7120	0.7055	0.8399
No log	2.0	96	0.7070	0.7159	0.7070	0.8409
No log	2.0417	98	0.7623	0.6910	0.7623	0.8731
No log	2.0833	100	1.0460	0.5332	1.0460	1.0227
No log	2.125	102	1.3920	0.4767	1.3920	1.1798
No log	2.1667	104	1.3895	0.4579	1.3895	1.1788
No log	2.2083	106	1.1391	0.5273	1.1391	1.0673
No log	2.25	108	0.8924	0.6481	0.8924	0.9447
No log	2.2917	110	0.7729	0.7074	0.7729	0.8791
No log	2.3333	112	0.8011	0.7052	0.8011	0.8950
No log	2.375	114	0.8151	0.6169	0.8151	0.9029
No log	2.4167	116	0.8570	0.6126	0.8570	0.9257
No log	2.4583	118	0.9010	0.6204	0.9010	0.9492
No log	2.5	120	0.8019	0.6531	0.8019	0.8955
No log	2.5417	122	0.7540	0.6359	0.7540	0.8683
No log	2.5833	124	0.7196	0.6469	0.7196	0.8483
No log	2.625	126	0.7287	0.6765	0.7287	0.8536
No log	2.6667	128	0.7369	0.6827	0.7369	0.8584
No log	2.7083	130	0.7957	0.6722	0.7957	0.8920
No log	2.75	132	0.8581	0.6402	0.8581	0.9263
No log	2.7917	134	0.8265	0.6470	0.8265	0.9091
No log	2.8333	136	0.7557	0.6988	0.7557	0.8693
No log	2.875	138	0.7566	0.7050	0.7566	0.8698
No log	2.9167	140	0.8615	0.6646	0.8615	0.9282
No log	2.9583	142	1.0893	0.5948	1.0893	1.0437
No log	3.0	144	1.0764	0.6141	1.0764	1.0375
No log	3.0417	146	0.9386	0.6311	0.9386	0.9688
No log	3.0833	148	0.8939	0.6563	0.8939	0.9455
No log	3.125	150	0.9096	0.6787	0.9096	0.9538
No log	3.1667	152	0.9567	0.6484	0.9567	0.9781
No log	3.2083	154	0.9312	0.6615	0.9312	0.9650
No log	3.25	156	0.7946	0.6836	0.7946	0.8914
No log	3.2917	158	0.7255	0.7133	0.7255	0.8518
No log	3.3333	160	0.7327	0.7126	0.7327	0.8560
No log	3.375	162	0.8114	0.7046	0.8114	0.9008
No log	3.4167	164	0.9719	0.6464	0.9719	0.9858
No log	3.4583	166	0.9955	0.6049	0.9955	0.9977
No log	3.5	168	0.9501	0.6602	0.9501	0.9748
No log	3.5417	170	0.8212	0.6777	0.8212	0.9062
No log	3.5833	172	0.6902	0.7124	0.6902	0.8308
No log	3.625	174	0.6444	0.7489	0.6444	0.8028
No log	3.6667	176	0.6714	0.7154	0.6714	0.8194
No log	3.7083	178	0.7495	0.7229	0.7495	0.8658
No log	3.75	180	0.8051	0.6530	0.8051	0.8973
No log	3.7917	182	0.8070	0.6498	0.8070	0.8983
No log	3.8333	184	0.7942	0.6367	0.7942	0.8912
No log	3.875	186	0.7235	0.7156	0.7235	0.8506
No log	3.9167	188	0.7205	0.7179	0.7205	0.8489
No log	3.9583	190	0.7512	0.6906	0.7512	0.8667
No log	4.0	192	0.7114	0.7317	0.7114	0.8435
No log	4.0417	194	0.6922	0.7092	0.6922	0.8320
No log	4.0833	196	0.6824	0.7092	0.6824	0.8261
No log	4.125	198	0.6847	0.7130	0.6847	0.8274
No log	4.1667	200	0.7413	0.7099	0.7413	0.8610
No log	4.2083	202	0.8454	0.6854	0.8454	0.9195
No log	4.25	204	0.9129	0.6741	0.9129	0.9554
No log	4.2917	206	0.9138	0.6776	0.9138	0.9559
No log	4.3333	208	0.8410	0.6714	0.8410	0.9171
No log	4.375	210	0.8550	0.6652	0.8550	0.9247
No log	4.4167	212	0.8891	0.6554	0.8891	0.9429
No log	4.4583	214	0.8367	0.6653	0.8367	0.9147
No log	4.5	216	0.7339	0.7184	0.7339	0.8567
No log	4.5417	218	0.6864	0.7684	0.6864	0.8285
No log	4.5833	220	0.6848	0.7449	0.6848	0.8275
No log	4.625	222	0.6780	0.7380	0.6780	0.8234
No log	4.6667	224	0.7131	0.7258	0.7131	0.8445
No log	4.7083	226	0.7194	0.7347	0.7194	0.8482
No log	4.75	228	0.6686	0.7615	0.6686	0.8177
No log	4.7917	230	0.6664	0.7577	0.6664	0.8163
No log	4.8333	232	0.7321	0.7157	0.7321	0.8556
No log	4.875	234	0.8373	0.6697	0.8373	0.9150
No log	4.9167	236	0.8774	0.6843	0.8774	0.9367
No log	4.9583	238	0.8427	0.6783	0.8427	0.9180
No log	5.0	240	0.7344	0.7457	0.7344	0.8570
No log	5.0417	242	0.6731	0.7603	0.6731	0.8205
No log	5.0833	244	0.6412	0.7325	0.6412	0.8008
No log	5.125	246	0.6677	0.7674	0.6677	0.8171
No log	5.1667	248	0.7304	0.7402	0.7304	0.8546
No log	5.2083	250	0.8822	0.7117	0.8822	0.9392
No log	5.25	252	0.9930	0.6604	0.9930	0.9965
No log	5.2917	254	0.9615	0.6462	0.9615	0.9805
No log	5.3333	256	0.8656	0.6877	0.8656	0.9304
No log	5.375	258	0.7931	0.6941	0.7931	0.8906
No log	5.4167	260	0.7439	0.7206	0.7439	0.8625
No log	5.4583	262	0.7228	0.7331	0.7228	0.8502
No log	5.5	264	0.7182	0.7294	0.7182	0.8474
No log	5.5417	266	0.7379	0.7209	0.7379	0.8590
No log	5.5833	268	0.7302	0.7510	0.7302	0.8545
No log	5.625	270	0.6890	0.7485	0.6890	0.8300
No log	5.6667	272	0.6967	0.7485	0.6967	0.8347
No log	5.7083	274	0.7394	0.7223	0.7394	0.8599
No log	5.75	276	0.7876	0.6842	0.7876	0.8875
No log	5.7917	278	0.7676	0.7080	0.7676	0.8761
No log	5.8333	280	0.6912	0.7549	0.6912	0.8314
No log	5.875	282	0.6425	0.7398	0.6425	0.8016
No log	5.9167	284	0.6233	0.7229	0.6233	0.7895
No log	5.9583	286	0.6332	0.7262	0.6332	0.7958
No log	6.0	288	0.6670	0.7454	0.6670	0.8167
No log	6.0417	290	0.7258	0.7510	0.7258	0.8519
No log	6.0833	292	0.7635	0.7113	0.7635	0.8738
No log	6.125	294	0.7604	0.7288	0.7604	0.8720
No log	6.1667	296	0.7543	0.7329	0.7543	0.8685
No log	6.2083	298	0.7118	0.7259	0.7118	0.8437
No log	6.25	300	0.6834	0.7427	0.6834	0.8267
No log	6.2917	302	0.6589	0.7414	0.6589	0.8118
No log	6.3333	304	0.6409	0.7406	0.6409	0.8006
No log	6.375	306	0.6541	0.7357	0.6541	0.8088
No log	6.4167	308	0.7065	0.7252	0.7065	0.8406
No log	6.4583	310	0.7265	0.7166	0.7265	0.8524
No log	6.5	312	0.7020	0.7252	0.7020	0.8378
No log	6.5417	314	0.6642	0.7301	0.6642	0.8150
No log	6.5833	316	0.6412	0.7343	0.6412	0.8008
No log	6.625	318	0.6216	0.7383	0.6216	0.7884
No log	6.6667	320	0.6042	0.7352	0.6042	0.7773
No log	6.7083	322	0.5964	0.7508	0.5964	0.7723
No log	6.75	324	0.5993	0.7508	0.5993	0.7741
No log	6.7917	326	0.6146	0.7283	0.6146	0.7839
No log	6.8333	328	0.6506	0.7205	0.6506	0.8066
No log	6.875	330	0.6683	0.7350	0.6683	0.8175
No log	6.9167	332	0.6938	0.7513	0.6938	0.8330
No log	6.9583	334	0.7151	0.7413	0.7151	0.8456
No log	7.0	336	0.7340	0.7329	0.7340	0.8567
No log	7.0417	338	0.7156	0.7413	0.7156	0.8459
No log	7.0833	340	0.6827	0.7457	0.6827	0.8263
No log	7.125	342	0.6571	0.7458	0.6571	0.8106
No log	7.1667	344	0.6341	0.7540	0.6341	0.7963
No log	7.2083	346	0.6240	0.7445	0.6240	0.7899
No log	7.25	348	0.6247	0.7445	0.6247	0.7904
No log	7.2917	350	0.6494	0.7408	0.6494	0.8058
No log	7.3333	352	0.6778	0.7370	0.6778	0.8233
No log	7.375	354	0.6996	0.7496	0.6996	0.8364
No log	7.4167	356	0.7236	0.7329	0.7236	0.8506
No log	7.4583	358	0.7372	0.7329	0.7372	0.8586
No log	7.5	360	0.7518	0.7288	0.7518	0.8670
No log	7.5417	362	0.7484	0.7288	0.7484	0.8651
No log	7.5833	364	0.7555	0.7161	0.7555	0.8692
No log	7.625	366	0.7594	0.7041	0.7594	0.8714
No log	7.6667	368	0.7407	0.7126	0.7407	0.8607
No log	7.7083	370	0.7019	0.7393	0.7019	0.8378
No log	7.75	372	0.6703	0.7492	0.6703	0.8187
No log	7.7917	374	0.6699	0.7492	0.6699	0.8185
No log	7.8333	376	0.6820	0.7446	0.6820	0.8259
No log	7.875	378	0.6891	0.7379	0.6891	0.8301
No log	7.9167	380	0.7020	0.7510	0.7020	0.8378
No log	7.9583	382	0.7197	0.7449	0.7197	0.8483
No log	8.0	384	0.7532	0.7323	0.7532	0.8679
No log	8.0417	386	0.7657	0.7323	0.7657	0.8750
No log	8.0833	388	0.7876	0.7141	0.7876	0.8875
No log	8.125	390	0.7939	0.7099	0.7939	0.8910
No log	8.1667	392	0.7757	0.7379	0.7757	0.8808
No log	8.2083	394	0.7389	0.7288	0.7389	0.8596
No log	8.25	396	0.6979	0.7399	0.6979	0.8354
No log	8.2917	398	0.6710	0.7336	0.6710	0.8191
No log	8.3333	400	0.6655	0.7380	0.6655	0.8158
No log	8.375	402	0.6768	0.7336	0.6768	0.8227
No log	8.4167	404	0.6962	0.7357	0.6962	0.8344
No log	8.4583	406	0.7123	0.7351	0.7123	0.8440
No log	8.5	408	0.7328	0.7288	0.7328	0.8560
No log	8.5417	410	0.7514	0.7323	0.7514	0.8668
No log	8.5833	412	0.7605	0.7323	0.7605	0.8721
No log	8.625	414	0.7556	0.7323	0.7556	0.8692
No log	8.6667	416	0.7405	0.7323	0.7405	0.8605
No log	8.7083	418	0.7314	0.7266	0.7314	0.8552
No log	8.75	420	0.7376	0.7266	0.7376	0.8588
No log	8.7917	422	0.7468	0.7203	0.7468	0.8642
No log	8.8333	424	0.7551	0.7161	0.7551	0.8690
No log	8.875	426	0.7547	0.7161	0.7547	0.8687
No log	8.9167	428	0.7561	0.7161	0.7561	0.8695
No log	8.9583	430	0.7428	0.7203	0.7428	0.8619
No log	9.0	432	0.7236	0.7323	0.7236	0.8506
No log	9.0417	434	0.7146	0.7387	0.7146	0.8454
No log	9.0833	436	0.7107	0.7351	0.7107	0.8430
No log	9.125	438	0.6980	0.7415	0.6980	0.8355
No log	9.1667	440	0.6859	0.7329	0.6859	0.8282
No log	9.2083	442	0.6773	0.7372	0.6773	0.8230
No log	9.25	444	0.6762	0.7372	0.6762	0.8223
No log	9.2917	446	0.6807	0.7329	0.6807	0.8251
No log	9.3333	448	0.6897	0.7323	0.6897	0.8305
No log	9.375	450	0.6999	0.7415	0.6999	0.8366
No log	9.4167	452	0.7128	0.7366	0.7128	0.8443
No log	9.4583	454	0.7201	0.7266	0.7201	0.8486
No log	9.5	456	0.7221	0.7266	0.7221	0.8498
No log	9.5417	458	0.7205	0.7266	0.7205	0.8488
No log	9.5833	460	0.7164	0.7266	0.7164	0.8464
No log	9.625	462	0.7162	0.7266	0.7162	0.8463
No log	9.6667	464	0.7152	0.7266	0.7152	0.8457
No log	9.7083	466	0.7167	0.7266	0.7167	0.8466
No log	9.75	468	0.7153	0.7266	0.7153	0.8458
No log	9.7917	470	0.7136	0.7266	0.7136	0.8447
No log	9.8333	472	0.7141	0.7266	0.7141	0.8450
No log	9.875	474	0.7145	0.7266	0.7145	0.8453
No log	9.9167	476	0.7141	0.7266	0.7141	0.8450
No log	9.9583	478	0.7138	0.7266	0.7138	0.8449
No log	10.0	480	0.7134	0.7266	0.7134	0.8446

Framework versions

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