ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k19_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: 0.7214
• Qwk: 0.4267
• Mse: 0.7214
• Rmse: 0.8493

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0417	2	4.3322	-0.0048	4.3322	2.0814
No log	0.0833	4	2.5281	-0.0340	2.5281	1.5900
No log	0.125	6	1.4897	0.0185	1.4897	1.2205
No log	0.1667	8	1.1472	0.2343	1.1472	1.0711
No log	0.2083	10	1.4258	0.0343	1.4258	1.1941
No log	0.25	12	1.4676	0.0568	1.4676	1.2114
No log	0.2917	14	1.1440	0.1848	1.1440	1.0696
No log	0.3333	16	1.0720	0.1313	1.0720	1.0354
No log	0.375	18	1.0918	0.1864	1.0918	1.0449
No log	0.4167	20	1.0645	0.0422	1.0645	1.0318
No log	0.4583	22	1.1121	0.1076	1.1121	1.0546
No log	0.5	24	1.1023	0.0824	1.1023	1.0499
No log	0.5417	26	1.1543	0.1203	1.1543	1.0744
No log	0.5833	28	1.0460	0.1263	1.0460	1.0228
No log	0.625	30	0.9569	0.2865	0.9569	0.9782
No log	0.6667	32	0.9375	0.2865	0.9375	0.9682
No log	0.7083	34	0.9329	0.2671	0.9329	0.9659
No log	0.75	36	1.0419	0.1881	1.0419	1.0207
No log	0.7917	38	1.4336	-0.0270	1.4336	1.1973
No log	0.8333	40	1.3413	-0.0112	1.3413	1.1581
No log	0.875	42	0.8825	0.3221	0.8825	0.9394
No log	0.9167	44	0.9190	0.4406	0.9190	0.9587
No log	0.9583	46	0.9979	0.2956	0.9979	0.9989
No log	1.0	48	0.9045	0.4357	0.9045	0.9510
No log	1.0417	50	0.8200	0.4210	0.8200	0.9055
No log	1.0833	52	0.8961	0.3815	0.8961	0.9466
No log	1.125	54	0.9969	0.2956	0.9969	0.9984
No log	1.1667	56	1.1032	0.2038	1.1032	1.0503
No log	1.2083	58	1.1889	0.1426	1.1889	1.0904
No log	1.25	60	0.9552	0.3958	0.9552	0.9773
No log	1.2917	62	0.8357	0.5472	0.8357	0.9142
No log	1.3333	64	0.8712	0.5062	0.8712	0.9334
No log	1.375	66	0.8265	0.5195	0.8265	0.9091
No log	1.4167	68	0.7830	0.5107	0.7830	0.8849
No log	1.4583	70	0.7917	0.5528	0.7917	0.8898
No log	1.5	72	0.8603	0.5279	0.8603	0.9275
No log	1.5417	74	0.8340	0.5183	0.8340	0.9132
No log	1.5833	76	0.7311	0.5329	0.7311	0.8550
No log	1.625	78	0.7282	0.5748	0.7282	0.8533
No log	1.6667	80	0.7276	0.5650	0.7276	0.8530
No log	1.7083	82	0.7115	0.5797	0.7115	0.8435
No log	1.75	84	0.8166	0.4921	0.8166	0.9037
No log	1.7917	86	0.7272	0.5654	0.7272	0.8528
No log	1.8333	88	0.7993	0.5339	0.7993	0.8941
No log	1.875	90	1.4456	0.3099	1.4456	1.2023
No log	1.9167	92	1.4957	0.3138	1.4957	1.2230
No log	1.9583	94	1.1015	0.3539	1.1015	1.0495
No log	2.0	96	0.7592	0.4838	0.7592	0.8713
No log	2.0417	98	0.8232	0.4962	0.8232	0.9073
No log	2.0833	100	1.0543	0.3040	1.0543	1.0268
No log	2.125	102	1.0385	0.3424	1.0385	1.0191
No log	2.1667	104	0.8155	0.5245	0.8155	0.9031
No log	2.2083	106	0.7862	0.5575	0.7862	0.8867
No log	2.25	108	0.8147	0.4810	0.8147	0.9026
No log	2.2917	110	0.8344	0.3800	0.8344	0.9134
No log	2.3333	112	0.8142	0.5342	0.8142	0.9023
No log	2.375	114	0.9227	0.4482	0.9227	0.9606
No log	2.4167	116	0.9353	0.4577	0.9353	0.9671
No log	2.4583	118	0.8401	0.4966	0.8401	0.9166
No log	2.5	120	0.7965	0.5450	0.7965	0.8925
No log	2.5417	122	0.8057	0.4996	0.8057	0.8976
No log	2.5833	124	0.7873	0.5124	0.7873	0.8873
No log	2.625	126	0.8080	0.4964	0.8080	0.8989
No log	2.6667	128	0.8035	0.4969	0.8035	0.8964
No log	2.7083	130	0.7780	0.5451	0.7780	0.8821
No log	2.75	132	0.8098	0.5300	0.8098	0.8999
No log	2.7917	134	0.7938	0.5038	0.7938	0.8909
No log	2.8333	136	0.8025	0.5261	0.8025	0.8958
No log	2.875	138	0.8010	0.4903	0.8010	0.8950
No log	2.9167	140	0.8132	0.5463	0.8132	0.9018
No log	2.9583	142	0.9191	0.4521	0.9191	0.9587
No log	3.0	144	1.0142	0.3959	1.0142	1.0071
No log	3.0417	146	0.9964	0.4150	0.9964	0.9982
No log	3.0833	148	0.8910	0.3993	0.8910	0.9439
No log	3.125	150	0.8635	0.4910	0.8635	0.9293
No log	3.1667	152	0.8781	0.4956	0.8781	0.9371
No log	3.2083	154	0.8687	0.5002	0.8687	0.9320
No log	3.25	156	0.9480	0.4244	0.9480	0.9737
No log	3.2917	158	0.9393	0.4098	0.9393	0.9692
No log	3.3333	160	0.8499	0.5135	0.8499	0.9219
No log	3.375	162	0.8727	0.3908	0.8727	0.9342
No log	3.4167	164	0.8658	0.3908	0.8658	0.9305
No log	3.4583	166	0.8206	0.4676	0.8206	0.9059
No log	3.5	168	0.8540	0.4599	0.8540	0.9241
No log	3.5417	170	0.9223	0.4695	0.9223	0.9603
No log	3.5833	172	0.8505	0.4510	0.8505	0.9222
No log	3.625	174	0.7662	0.5621	0.7662	0.8753
No log	3.6667	176	0.8113	0.5098	0.8113	0.9007
No log	3.7083	178	0.7761	0.5253	0.7761	0.8809
No log	3.75	180	0.7377	0.5752	0.7377	0.8589
No log	3.7917	182	0.7214	0.5822	0.7214	0.8493
No log	3.8333	184	0.7139	0.5572	0.7139	0.8449
No log	3.875	186	0.6895	0.5247	0.6895	0.8304
No log	3.9167	188	0.6717	0.5747	0.6717	0.8196
No log	3.9583	190	0.6501	0.5871	0.6501	0.8063
No log	4.0	192	0.6237	0.6076	0.6237	0.7898
No log	4.0417	194	0.6414	0.6179	0.6414	0.8009
No log	4.0833	196	0.6531	0.6512	0.6531	0.8082
No log	4.125	198	0.6099	0.5742	0.6099	0.7810
No log	4.1667	200	0.6751	0.6082	0.6751	0.8216
No log	4.2083	202	0.7348	0.5857	0.7348	0.8572
No log	4.25	204	0.6798	0.5548	0.6798	0.8245
No log	4.2917	206	0.6473	0.5577	0.6473	0.8046
No log	4.3333	208	0.7071	0.5837	0.7071	0.8409
No log	4.375	210	0.7084	0.5746	0.7084	0.8417
No log	4.4167	212	0.6768	0.5391	0.6768	0.8227
No log	4.4583	214	0.6886	0.5214	0.6886	0.8298
No log	4.5	216	0.8265	0.5271	0.8265	0.9091
No log	4.5417	218	0.8966	0.5070	0.8966	0.9469
No log	4.5833	220	0.7729	0.5345	0.7729	0.8792
No log	4.625	222	0.6848	0.5396	0.6848	0.8275
No log	4.6667	224	0.7349	0.5585	0.7349	0.8573
No log	4.7083	226	0.7812	0.4560	0.7812	0.8839
No log	4.75	228	0.7739	0.3882	0.7739	0.8797
No log	4.7917	230	0.7752	0.4373	0.7752	0.8804
No log	4.8333	232	0.7590	0.4071	0.7590	0.8712
No log	4.875	234	0.7372	0.4124	0.7372	0.8586
No log	4.9167	236	0.7290	0.5025	0.7290	0.8538
No log	4.9583	238	0.7666	0.4973	0.7666	0.8756
No log	5.0	240	0.8061	0.4952	0.8061	0.8978
No log	5.0417	242	0.8560	0.5458	0.8560	0.9252
No log	5.0833	244	0.7851	0.4597	0.7851	0.8860
No log	5.125	246	0.7183	0.5734	0.7183	0.8475
No log	5.1667	248	0.7068	0.5171	0.7068	0.8407
No log	5.2083	250	0.8155	0.4578	0.8155	0.9031
No log	5.25	252	0.9047	0.4280	0.9047	0.9512
No log	5.2917	254	0.8423	0.4489	0.8423	0.9177
No log	5.3333	256	0.7295	0.5329	0.7295	0.8541
No log	5.375	258	0.7373	0.5232	0.7373	0.8586
No log	5.4167	260	0.8105	0.4697	0.8105	0.9003
No log	5.4583	262	0.7897	0.5088	0.7897	0.8886
No log	5.5	264	0.7731	0.5304	0.7731	0.8793
No log	5.5417	266	0.7663	0.5303	0.7663	0.8754
No log	5.5833	268	0.7688	0.4835	0.7688	0.8768
No log	5.625	270	0.8095	0.4513	0.8095	0.8997
No log	5.6667	272	0.7791	0.4069	0.7791	0.8826
No log	5.7083	274	0.8005	0.4714	0.8005	0.8947
No log	5.75	276	0.8907	0.4310	0.8907	0.9438
No log	5.7917	278	0.8928	0.4318	0.8928	0.9449
No log	5.8333	280	0.8490	0.4439	0.8490	0.9214
No log	5.875	282	0.8732	0.4310	0.8732	0.9344
No log	5.9167	284	0.8688	0.4310	0.8688	0.9321
No log	5.9583	286	0.8039	0.4714	0.8039	0.8966
No log	6.0	288	0.7564	0.4748	0.7564	0.8697
No log	6.0417	290	0.7625	0.4748	0.7625	0.8732
No log	6.0833	292	0.8001	0.4461	0.8001	0.8945
No log	6.125	294	0.8790	0.4054	0.8790	0.9376
No log	6.1667	296	0.9745	0.4197	0.9745	0.9872
No log	6.2083	298	0.9613	0.3953	0.9613	0.9805
No log	6.25	300	0.8767	0.4558	0.8767	0.9363
No log	6.2917	302	0.7745	0.5305	0.7745	0.8801
No log	6.3333	304	0.7047	0.4883	0.7047	0.8395
No log	6.375	306	0.6875	0.5142	0.6875	0.8292
No log	6.4167	308	0.6810	0.5129	0.6810	0.8252
No log	6.4583	310	0.7018	0.5220	0.7018	0.8377
No log	6.5	312	0.7431	0.5663	0.7431	0.8621
No log	6.5417	314	0.7139	0.5467	0.7139	0.8449
No log	6.5833	316	0.6934	0.5510	0.6934	0.8327
No log	6.625	318	0.7026	0.5843	0.7026	0.8382
No log	6.6667	320	0.6987	0.5510	0.6987	0.8359
No log	6.7083	322	0.6997	0.5510	0.6997	0.8365
No log	6.75	324	0.7055	0.5342	0.7055	0.8400
No log	6.7917	326	0.7427	0.5599	0.7427	0.8618
No log	6.8333	328	0.8391	0.5735	0.8391	0.9160
No log	6.875	330	0.8495	0.4907	0.8495	0.9217
No log	6.9167	332	0.7640	0.5964	0.7640	0.8741
No log	6.9583	334	0.6996	0.4903	0.6996	0.8364
No log	7.0	336	0.7319	0.5005	0.7319	0.8555
No log	7.0417	338	0.7225	0.4765	0.7225	0.8500
No log	7.0833	340	0.6851	0.5033	0.6851	0.8277
No log	7.125	342	0.7618	0.5292	0.7618	0.8728
No log	7.1667	344	0.8910	0.4216	0.8910	0.9439
No log	7.2083	346	0.9214	0.4216	0.9214	0.9599
No log	7.25	348	0.9050	0.3565	0.9050	0.9513
No log	7.2917	350	0.8857	0.3222	0.8857	0.9411
No log	7.3333	352	0.8399	0.3169	0.8399	0.9164
No log	7.375	354	0.7881	0.3902	0.7881	0.8877
No log	7.4167	356	0.7739	0.4180	0.7739	0.8797
No log	7.4583	358	0.7879	0.4911	0.7879	0.8876
No log	7.5	360	0.7896	0.5555	0.7896	0.8886
No log	7.5417	362	0.8325	0.5636	0.8325	0.9124
No log	7.5833	364	0.8015	0.6247	0.8015	0.8953
No log	7.625	366	0.7141	0.6109	0.7141	0.8451
No log	7.6667	368	0.6836	0.5688	0.6836	0.8268
No log	7.7083	370	0.6774	0.5722	0.6774	0.8230
No log	7.75	372	0.6879	0.4781	0.6879	0.8294
No log	7.7917	374	0.6915	0.5153	0.6915	0.8315
No log	7.8333	376	0.7049	0.5380	0.7049	0.8396
No log	7.875	378	0.7396	0.5865	0.7396	0.8600
No log	7.9167	380	0.7394	0.5865	0.7394	0.8599
No log	7.9583	382	0.7059	0.6082	0.7059	0.8402
No log	8.0	384	0.6679	0.5577	0.6679	0.8173
No log	8.0417	386	0.6748	0.5629	0.6748	0.8214
No log	8.0833	388	0.6800	0.5629	0.6800	0.8246
No log	8.125	390	0.6748	0.5629	0.6748	0.8215
No log	8.1667	392	0.6830	0.5089	0.6830	0.8264
No log	8.2083	394	0.6867	0.5585	0.6867	0.8287
No log	8.25	396	0.6862	0.5171	0.6862	0.8284
No log	8.2917	398	0.6983	0.5316	0.6983	0.8357
No log	8.3333	400	0.7047	0.4878	0.7047	0.8394
No log	8.375	402	0.7493	0.5429	0.7493	0.8656
No log	8.4167	404	0.7459	0.5429	0.7459	0.8636
No log	8.4583	406	0.7357	0.4987	0.7357	0.8578
No log	8.5	408	0.7390	0.4987	0.7390	0.8597
No log	8.5417	410	0.7242	0.5142	0.7242	0.8510
No log	8.5833	412	0.7280	0.4705	0.7280	0.8532
No log	8.625	414	0.7288	0.4455	0.7288	0.8537
No log	8.6667	416	0.7287	0.5142	0.7287	0.8537
No log	8.7083	418	0.7585	0.5446	0.7585	0.8709
No log	8.75	420	0.7668	0.5622	0.7668	0.8757
No log	8.7917	422	0.7737	0.5451	0.7737	0.8796
No log	8.8333	424	0.7401	0.5729	0.7401	0.8603
No log	8.875	426	0.7208	0.4757	0.7208	0.8490
No log	8.9167	428	0.7183	0.5002	0.7183	0.8475
No log	8.9583	430	0.7182	0.5032	0.7182	0.8475
No log	9.0	432	0.7319	0.4161	0.7319	0.8555
No log	9.0417	434	0.7182	0.4472	0.7182	0.8475
No log	9.0833	436	0.6945	0.5399	0.6945	0.8334
No log	9.125	438	0.6958	0.5569	0.6958	0.8341
No log	9.1667	440	0.7148	0.5711	0.7148	0.8455
No log	9.2083	442	0.7867	0.5658	0.7867	0.8870
No log	9.25	444	0.8087	0.5443	0.8087	0.8993
No log	9.2917	446	0.7375	0.6042	0.7375	0.8588
No log	9.3333	448	0.6813	0.5142	0.6813	0.8254
No log	9.375	450	0.7097	0.4393	0.7097	0.8424
No log	9.4167	452	0.7355	0.4998	0.7355	0.8576
No log	9.4583	454	0.7108	0.4393	0.7108	0.8431
No log	9.5	456	0.6830	0.5287	0.6830	0.8264
No log	9.5417	458	0.7045	0.6154	0.7045	0.8393
No log	9.5833	460	0.7963	0.5455	0.7963	0.8924
No log	9.625	462	0.8554	0.5526	0.8554	0.9249
No log	9.6667	464	0.8141	0.5455	0.8141	0.9023
No log	9.7083	466	0.7598	0.5777	0.7598	0.8717
No log	9.75	468	0.7402	0.6053	0.7402	0.8603
No log	9.7917	470	0.7447	0.5846	0.7447	0.8630
No log	9.8333	472	0.7528	0.5733	0.7528	0.8677
No log	9.875	474	0.7515	0.5244	0.7515	0.8669
No log	9.9167	476	0.7378	0.5003	0.7378	0.8590
No log	9.9583	478	0.7245	0.5040	0.7245	0.8512
No log	10.0	480	0.7197	0.5040	0.7197	0.8484
No log	10.0417	482	0.7205	0.4762	0.7205	0.8488
No log	10.0833	484	0.7476	0.5380	0.7476	0.8647
No log	10.125	486	0.7935	0.5602	0.7935	0.8908
No log	10.1667	488	0.7784	0.5718	0.7784	0.8822
No log	10.2083	490	0.7068	0.4981	0.7068	0.8407
No log	10.25	492	0.6840	0.5185	0.6840	0.8270
No log	10.2917	494	0.7070	0.4998	0.7070	0.8408
No log	10.3333	496	0.6949	0.4977	0.6949	0.8336
No log	10.375	498	0.6890	0.5747	0.6890	0.8301
0.2996	10.4167	500	0.7316	0.5333	0.7316	0.8553
0.2996	10.4583	502	0.7620	0.5872	0.7620	0.8729
0.2996	10.5	504	0.7768	0.5170	0.7768	0.8814
0.2996	10.5417	506	0.7909	0.4318	0.7909	0.8893
0.2996	10.5833	508	0.8165	0.4318	0.8165	0.9036
0.2996	10.625	510	0.8057	0.4952	0.8057	0.8976
0.2996	10.6667	512	0.7758	0.5688	0.7758	0.8808
0.2996	10.7083	514	0.7632	0.5570	0.7632	0.8736
0.2996	10.75	516	0.7681	0.6073	0.7681	0.8764
0.2996	10.7917	518	0.7367	0.5996	0.7367	0.8583
0.2996	10.8333	520	0.7127	0.5690	0.7127	0.8442
0.2996	10.875	522	0.7296	0.6014	0.7296	0.8541
0.2996	10.9167	524	0.7389	0.5666	0.7389	0.8596
0.2996	10.9583	526	0.6985	0.5402	0.6985	0.8358
0.2996	11.0	528	0.6941	0.5060	0.6941	0.8331
0.2996	11.0417	530	0.7216	0.5209	0.7216	0.8494
0.2996	11.0833	532	0.7694	0.5333	0.7694	0.8772
0.2996	11.125	534	0.7622	0.5541	0.7622	0.8730
0.2996	11.1667	536	0.7158	0.5299	0.7158	0.8460
0.2996	11.2083	538	0.7268	0.6177	0.7268	0.8525
0.2996	11.25	540	0.7815	0.5697	0.7815	0.8840
0.2996	11.2917	542	0.7783	0.5521	0.7783	0.8822
0.2996	11.3333	544	0.7236	0.5010	0.7236	0.8507
0.2996	11.375	546	0.7057	0.4810	0.7057	0.8401
0.2996	11.4167	548	0.7296	0.4571	0.7296	0.8542
0.2996	11.4583	550	0.7358	0.4571	0.7358	0.8578
0.2996	11.5	552	0.7214	0.4267	0.7214	0.8493

Framework versions

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