ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k8_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: 0.5450
• Qwk: 0.4225
• Mse: 0.5450
• Rmse: 0.7382

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	3.1660	-0.0114	3.1660	1.7793
No log	0.0833	4	1.4916	-0.0070	1.4916	1.2213
No log	0.125	6	0.8074	0.0991	0.8074	0.8985
No log	0.1667	8	0.8302	0.0717	0.8302	0.9112
No log	0.2083	10	0.8222	0.0085	0.8222	0.9067
No log	0.25	12	1.0170	0.0	1.0170	1.0085
No log	0.2917	14	1.4044	0.0	1.4044	1.1851
No log	0.3333	16	1.2413	0.0	1.2413	1.1142
No log	0.375	18	1.1141	0.0	1.1141	1.0555
No log	0.4167	20	0.8509	-0.0333	0.8509	0.9225
No log	0.4583	22	0.9091	0.0201	0.9091	0.9535
No log	0.5	24	1.0732	0.0	1.0732	1.0359
No log	0.5417	26	1.0068	0.0476	1.0068	1.0034
No log	0.5833	28	0.7776	0.2239	0.7776	0.8818
No log	0.625	30	0.7880	0.2549	0.7880	0.8877
No log	0.6667	32	0.8353	0.0647	0.8353	0.9140
No log	0.7083	34	1.1194	0.0476	1.1194	1.0580
No log	0.75	36	1.4695	0.0294	1.4695	1.2122
No log	0.7917	38	2.0555	-0.0440	2.0555	1.4337
No log	0.8333	40	1.8373	-0.0130	1.8373	1.3555
No log	0.875	42	1.4299	0.0345	1.4299	1.1958
No log	0.9167	44	1.0082	0.1111	1.0082	1.0041
No log	0.9583	46	0.8146	0.1605	0.8146	0.9026
No log	1.0	48	0.7422	0.2068	0.7422	0.8615
No log	1.0417	50	0.8104	0.1220	0.8104	0.9002
No log	1.0833	52	1.0338	0.1111	1.0338	1.0167
No log	1.125	54	1.1366	0.0345	1.1366	1.0661
No log	1.1667	56	1.2341	0.0345	1.2341	1.1109
No log	1.2083	58	1.0492	0.0745	1.0492	1.0243
No log	1.25	60	0.8001	0.1453	0.8001	0.8945
No log	1.2917	62	0.7366	0.3016	0.7366	0.8582
No log	1.3333	64	0.8872	0.1925	0.8872	0.9419
No log	1.375	66	1.6286	0.0353	1.6286	1.2762
No log	1.4167	68	2.1900	0.0675	2.1900	1.4799
No log	1.4583	70	1.5369	0.0638	1.5369	1.2397
No log	1.5	72	0.7729	0.1781	0.7729	0.8791
No log	1.5417	74	0.6453	0.25	0.6453	0.8033
No log	1.5833	76	0.5940	0.2444	0.5940	0.7707
No log	1.625	78	0.5978	0.2688	0.5978	0.7732
No log	1.6667	80	0.9231	0.0843	0.9231	0.9608
No log	1.7083	82	1.1207	0.1111	1.1207	1.0586
No log	1.75	84	0.8080	0.1515	0.8080	0.8989
No log	1.7917	86	0.4805	0.0303	0.4805	0.6932
No log	1.8333	88	0.5442	0.0	0.5442	0.7377
No log	1.875	90	0.4781	0.1884	0.4781	0.6914
No log	1.9167	92	0.7541	0.2072	0.7541	0.8684
No log	1.9583	94	1.2742	0.1059	1.2742	1.1288
No log	2.0	96	1.1690	0.1059	1.1690	1.0812
No log	2.0417	98	0.7321	0.1930	0.7321	0.8557
No log	2.0833	100	0.5330	0.2644	0.5330	0.7301
No log	2.125	102	0.5638	0.2350	0.5638	0.7508
No log	2.1667	104	0.6859	0.2762	0.6859	0.8282
No log	2.2083	106	0.6230	0.2239	0.6230	0.7893
No log	2.25	108	0.5508	0.2889	0.5508	0.7422
No log	2.2917	110	0.6408	0.2157	0.6408	0.8005
No log	2.3333	112	0.7400	0.2146	0.7400	0.8602
No log	2.375	114	0.5925	0.2644	0.5925	0.7697
No log	2.4167	116	0.5816	0.2970	0.5816	0.7626
No log	2.4583	118	0.6106	0.3548	0.6106	0.7814
No log	2.5	120	0.6910	0.2161	0.6910	0.8313
No log	2.5417	122	0.6314	0.4783	0.6314	0.7946
No log	2.5833	124	0.7117	0.2607	0.7117	0.8436
No log	2.625	126	0.6264	0.4051	0.6264	0.7914
No log	2.6667	128	0.5823	0.4	0.5823	0.7631
No log	2.7083	130	0.5670	0.4167	0.5670	0.7530
No log	2.75	132	0.6136	0.3369	0.6136	0.7833
No log	2.7917	134	0.5607	0.3684	0.5607	0.7488
No log	2.8333	136	0.7816	0.1235	0.7816	0.8841
No log	2.875	138	0.7245	0.2743	0.7245	0.8512
No log	2.9167	140	0.5760	0.3641	0.5760	0.7590
No log	2.9583	142	0.6339	0.3433	0.6339	0.7962
No log	3.0	144	0.6315	0.3365	0.6315	0.7947
No log	3.0417	146	0.6153	0.2653	0.6153	0.7844
No log	3.0833	148	0.6650	0.2593	0.6650	0.8155
No log	3.125	150	0.6383	0.3803	0.6383	0.7990
No log	3.1667	152	0.6589	0.2877	0.6589	0.8117
No log	3.2083	154	0.6411	0.2877	0.6411	0.8007
No log	3.25	156	0.6465	0.3498	0.6465	0.8040
No log	3.2917	158	0.7593	0.2727	0.7593	0.8714
No log	3.3333	160	0.7341	0.3739	0.7341	0.8568
No log	3.375	162	0.6692	0.2877	0.6692	0.8180
No log	3.4167	164	0.6569	0.3116	0.6569	0.8105
No log	3.4583	166	0.6835	0.3116	0.6835	0.8268
No log	3.5	168	0.8034	0.3202	0.8034	0.8963
No log	3.5417	170	0.7554	0.3202	0.7554	0.8691
No log	3.5833	172	0.6484	0.2850	0.6484	0.8053
No log	3.625	174	0.6456	0.2464	0.6456	0.8035
No log	3.6667	176	0.6092	0.3778	0.6092	0.7805
No log	3.7083	178	0.5980	0.3402	0.5980	0.7733
No log	3.75	180	0.6224	0.2157	0.6224	0.7889
No log	3.7917	182	0.6087	0.3299	0.6087	0.7802
No log	3.8333	184	0.6384	0.2830	0.6384	0.7990
No log	3.875	186	0.8745	0.2923	0.8745	0.9351
No log	3.9167	188	0.9519	0.2296	0.9519	0.9756
No log	3.9583	190	0.7137	0.3115	0.7137	0.8448
No log	4.0	192	0.7096	0.3043	0.7096	0.8424
No log	4.0417	194	0.9512	0.2115	0.9512	0.9753
No log	4.0833	196	0.7483	0.2469	0.7483	0.8651
No log	4.125	198	0.5830	0.4	0.5830	0.7636
No log	4.1667	200	1.1589	0.1186	1.1589	1.0765
No log	4.2083	202	1.5149	0.1000	1.5149	1.2308
No log	4.25	204	1.4170	0.1238	1.4170	1.1904
No log	4.2917	206	0.9591	0.2509	0.9591	0.9794
No log	4.3333	208	0.5562	0.3333	0.5562	0.7458
No log	4.375	210	0.6881	0.25	0.6881	0.8295
No log	4.4167	212	0.7765	0.2077	0.7765	0.8812
No log	4.4583	214	0.6449	0.3478	0.6449	0.8030
No log	4.5	216	0.6512	0.3242	0.6512	0.8070
No log	4.5417	218	0.7579	0.2618	0.7579	0.8706
No log	4.5833	220	0.6692	0.3645	0.6692	0.8181
No log	4.625	222	0.6415	0.2965	0.6415	0.8009
No log	4.6667	224	0.6716	0.2621	0.6716	0.8195
No log	4.7083	226	0.7129	0.2381	0.7129	0.8444
No log	4.75	228	0.7569	0.1919	0.7569	0.8700
No log	4.7917	230	0.7228	0.2000	0.7228	0.8502
No log	4.8333	232	0.6829	0.2323	0.6829	0.8264
No log	4.875	234	0.6753	0.3535	0.6753	0.8218
No log	4.9167	236	0.7129	0.2566	0.7129	0.8443
No log	4.9583	238	0.6722	0.3623	0.6722	0.8198
No log	5.0	240	0.6571	0.3905	0.6571	0.8106
No log	5.0417	242	0.6496	0.3878	0.6496	0.8060
No log	5.0833	244	0.6553	0.3508	0.6553	0.8095
No log	5.125	246	0.6989	0.3362	0.6989	0.8360
No log	5.1667	248	0.7233	0.2771	0.7233	0.8505
No log	5.2083	250	0.6694	0.2621	0.6694	0.8182
No log	5.25	252	0.6601	0.2653	0.6601	0.8125
No log	5.2917	254	0.6924	0.2000	0.6924	0.8321
No log	5.3333	256	0.6919	0.2287	0.6919	0.8318
No log	5.375	258	0.6660	0.2609	0.6660	0.8161
No log	5.4167	260	0.6579	0.2967	0.6579	0.8111
No log	5.4583	262	0.6342	0.2967	0.6342	0.7964
No log	5.5	264	0.6196	0.2967	0.6196	0.7871
No log	5.5417	266	0.6107	0.2967	0.6107	0.7815
No log	5.5833	268	0.5930	0.4043	0.5930	0.7701
No log	5.625	270	0.6265	0.3271	0.6265	0.7915
No log	5.6667	272	0.6573	0.2618	0.6573	0.8107
No log	5.7083	274	0.6268	0.3628	0.6268	0.7917
No log	5.75	276	0.5764	0.3208	0.5764	0.7592
No log	5.7917	278	0.5439	0.3892	0.5439	0.7375
No log	5.8333	280	0.5290	0.3978	0.5290	0.7273
No log	5.875	282	0.5323	0.4059	0.5323	0.7296
No log	5.9167	284	0.6029	0.3514	0.6029	0.7765
No log	5.9583	286	0.7476	0.3147	0.7476	0.8647
No log	6.0	288	0.7245	0.3171	0.7245	0.8512
No log	6.0417	290	0.5730	0.3524	0.5730	0.7570
No log	6.0833	292	0.4963	0.3149	0.4963	0.7045
No log	6.125	294	0.5294	0.3149	0.5294	0.7276
No log	6.1667	296	0.5040	0.3778	0.5040	0.7099
No log	6.2083	298	0.4952	0.3684	0.4952	0.7037
No log	6.25	300	0.5135	0.4167	0.5135	0.7166
No log	6.2917	302	0.5385	0.4171	0.5385	0.7338
No log	6.3333	304	0.5573	0.3769	0.5573	0.7465
No log	6.375	306	0.5809	0.3585	0.5809	0.7622
No log	6.4167	308	0.6207	0.3833	0.6207	0.7878
No log	6.4583	310	0.5834	0.4059	0.5834	0.7638
No log	6.5	312	0.5761	0.3939	0.5761	0.7590
No log	6.5417	314	0.5891	0.4286	0.5891	0.7676
No log	6.5833	316	0.5988	0.3939	0.5988	0.7738
No log	6.625	318	0.6456	0.3180	0.6456	0.8035
No log	6.6667	320	0.6925	0.3058	0.6925	0.8322
No log	6.7083	322	0.6745	0.3514	0.6745	0.8213
No log	6.75	324	0.6401	0.4051	0.6401	0.8001
No log	6.7917	326	0.6154	0.4526	0.6154	0.7845
No log	6.8333	328	0.6222	0.2593	0.6222	0.7888
No log	6.875	330	0.6131	0.2174	0.6131	0.7830
No log	6.9167	332	0.5919	0.4162	0.5919	0.7694
No log	6.9583	334	0.5820	0.4526	0.5820	0.7629
No log	7.0	336	0.6202	0.3684	0.6202	0.7875
No log	7.0417	338	0.6495	0.3333	0.6495	0.8059
No log	7.0833	340	0.5956	0.4396	0.5956	0.7717
No log	7.125	342	0.5400	0.4462	0.5400	0.7348
No log	7.1667	344	0.5584	0.3778	0.5584	0.7473
No log	7.2083	346	0.5541	0.3778	0.5541	0.7444
No log	7.25	348	0.5377	0.4462	0.5377	0.7333
No log	7.2917	350	0.5966	0.4067	0.5966	0.7724
No log	7.3333	352	0.7053	0.3043	0.7053	0.8398
No log	7.375	354	0.7115	0.3043	0.7115	0.8435
No log	7.4167	356	0.6259	0.3571	0.6259	0.7911
No log	7.4583	358	0.5384	0.4167	0.5384	0.7338
No log	7.5	360	0.5492	0.2994	0.5492	0.7411
No log	7.5417	362	0.5840	0.3043	0.5840	0.7642
No log	7.5833	364	0.5692	0.3591	0.5692	0.7545
No log	7.625	366	0.5480	0.4343	0.5480	0.7403
No log	7.6667	368	0.5929	0.4010	0.5929	0.7700
No log	7.7083	370	0.6133	0.3917	0.6133	0.7831
No log	7.75	372	0.5884	0.4010	0.5884	0.7671
No log	7.7917	374	0.5748	0.4167	0.5748	0.7582
No log	7.8333	376	0.5796	0.4167	0.5796	0.7613
No log	7.875	378	0.5931	0.3962	0.5931	0.7701
No log	7.9167	380	0.5837	0.4010	0.5837	0.7640
No log	7.9583	382	0.5538	0.4167	0.5538	0.7442
No log	8.0	384	0.5431	0.4747	0.5431	0.7369
No log	8.0417	386	0.5400	0.4819	0.5400	0.7349
No log	8.0833	388	0.5373	0.4819	0.5373	0.7330
No log	8.125	390	0.5460	0.4462	0.5460	0.7389
No log	8.1667	392	0.5607	0.3706	0.5607	0.7488
No log	8.2083	394	0.5969	0.3962	0.5969	0.7726
No log	8.25	396	0.6353	0.3874	0.6353	0.7971
No log	8.2917	398	0.6411	0.3874	0.6411	0.8007
No log	8.3333	400	0.6378	0.3917	0.6378	0.7986
No log	8.375	402	0.6111	0.3962	0.6111	0.7817
No log	8.4167	404	0.5784	0.4747	0.5784	0.7605
No log	8.4583	406	0.5768	0.4819	0.5768	0.7595
No log	8.5	408	0.5884	0.4051	0.5884	0.7671
No log	8.5417	410	0.6040	0.3617	0.6040	0.7772
No log	8.5833	412	0.5926	0.4051	0.5926	0.7698
No log	8.625	414	0.5727	0.4819	0.5727	0.7568
No log	8.6667	416	0.5744	0.4051	0.5744	0.7579
No log	8.7083	418	0.6084	0.3962	0.6084	0.7800
No log	8.75	420	0.6378	0.3917	0.6378	0.7986
No log	8.7917	422	0.6261	0.3962	0.6261	0.7913
No log	8.8333	424	0.5984	0.3962	0.5984	0.7735
No log	8.875	426	0.5816	0.4010	0.5816	0.7626
No log	8.9167	428	0.5676	0.4526	0.5676	0.7534
No log	8.9583	430	0.5577	0.4526	0.5577	0.7468
No log	9.0	432	0.5529	0.4595	0.5529	0.7436
No log	9.0417	434	0.5508	0.4595	0.5508	0.7422
No log	9.0833	436	0.5486	0.4595	0.5486	0.7407
No log	9.125	438	0.5491	0.4526	0.5491	0.7410
No log	9.1667	440	0.5486	0.4526	0.5486	0.7407
No log	9.2083	442	0.5519	0.4225	0.5519	0.7429
No log	9.25	444	0.5619	0.4225	0.5619	0.7496
No log	9.2917	446	0.5820	0.4010	0.5820	0.7629
No log	9.3333	448	0.5915	0.4010	0.5915	0.7691
No log	9.375	450	0.5844	0.4010	0.5844	0.7644
No log	9.4167	452	0.5731	0.4059	0.5731	0.7570
No log	9.4583	454	0.5600	0.4225	0.5600	0.7484
No log	9.5	456	0.5503	0.4225	0.5503	0.7418
No log	9.5417	458	0.5467	0.4225	0.5467	0.7394
No log	9.5833	460	0.5454	0.4225	0.5454	0.7385
No log	9.625	462	0.5435	0.4526	0.5435	0.7372
No log	9.6667	464	0.5426	0.4894	0.5426	0.7366
No log	9.7083	466	0.5421	0.4536	0.5421	0.7363
No log	9.75	468	0.5419	0.4819	0.5419	0.7361
No log	9.7917	470	0.5421	0.4819	0.5421	0.7363
No log	9.8333	472	0.5425	0.4526	0.5425	0.7366
No log	9.875	474	0.5433	0.4225	0.5433	0.7371
No log	9.9167	476	0.5440	0.4225	0.5440	0.7376
No log	9.9583	478	0.5447	0.4225	0.5447	0.7380
No log	10.0	480	0.5450	0.4225	0.5450	0.7382

Framework versions

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