ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k6_task2_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: 0.8016
• Qwk: 0.4272
• Mse: 0.8016
• Rmse: 0.8953

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	0.1	2	4.5411	0.0010	4.5411	2.1310
No log	0.2	4	2.4527	0.0332	2.4527	1.5661
No log	0.3	6	1.9812	-0.0303	1.9812	1.4076
No log	0.4	8	1.5672	0.0	1.5672	1.2519
No log	0.5	10	1.3129	0.0077	1.3129	1.1458
No log	0.6	12	1.1929	0.1417	1.1929	1.0922
No log	0.7	14	1.3074	0.0119	1.3074	1.1434
No log	0.8	16	2.6756	0.0038	2.6756	1.6357
No log	0.9	18	2.9526	-0.0233	2.9526	1.7183
No log	1.0	20	2.0728	0.0693	2.0728	1.4397
No log	1.1	22	1.2818	0.0547	1.2818	1.1322
No log	1.2	24	1.2599	0.1416	1.2599	1.1225
No log	1.3	26	1.3074	0.0454	1.3074	1.1434
No log	1.4	28	1.2544	0.0941	1.2544	1.1200
No log	1.5	30	1.2227	0.1671	1.2227	1.1058
No log	1.6	32	1.2858	0.1168	1.2858	1.1339
No log	1.7	34	1.6096	0.0169	1.6096	1.2687
No log	1.8	36	1.6247	0.0317	1.6247	1.2746
No log	1.9	38	1.5455	0.0317	1.5455	1.2432
No log	2.0	40	1.4255	0.0488	1.4255	1.1939
No log	2.1	42	1.2140	0.2498	1.2140	1.1018
No log	2.2	44	1.1202	0.3291	1.1202	1.0584
No log	2.3	46	1.1121	0.2579	1.1121	1.0546
No log	2.4	48	1.1722	0.2432	1.1722	1.0827
No log	2.5	50	1.3739	0.1106	1.3739	1.1721
No log	2.6	52	1.4933	0.0331	1.4933	1.2220
No log	2.7	54	1.3893	0.1784	1.3893	1.1787
No log	2.8	56	1.1064	0.2520	1.1064	1.0518
No log	2.9	58	1.1563	0.0612	1.1563	1.0753
No log	3.0	60	1.2603	0.1020	1.2603	1.1226
No log	3.1	62	1.2883	0.1344	1.2883	1.1350
No log	3.2	64	1.3205	0.0843	1.3205	1.1491
No log	3.3	66	1.3161	0.1005	1.3161	1.1472
No log	3.4	68	1.3450	0.1313	1.3450	1.1597
No log	3.5	70	1.2675	0.2541	1.2675	1.1258
No log	3.6	72	1.2517	0.2271	1.2517	1.1188
No log	3.7	74	1.2382	0.2775	1.2382	1.1127
No log	3.8	76	1.2147	0.2584	1.2147	1.1022
No log	3.9	78	1.1430	0.3134	1.1430	1.0691
No log	4.0	80	1.0593	0.3621	1.0593	1.0292
No log	4.1	82	1.0517	0.2752	1.0517	1.0255
No log	4.2	84	1.1419	0.2650	1.1419	1.0686
No log	4.3	86	1.1928	0.2634	1.1928	1.0922
No log	4.4	88	1.0868	0.2466	1.0868	1.0425
No log	4.5	90	1.0524	0.2466	1.0524	1.0259
No log	4.6	92	1.0239	0.3317	1.0239	1.0119
No log	4.7	94	0.9515	0.3666	0.9515	0.9754
No log	4.8	96	0.9367	0.4157	0.9367	0.9678
No log	4.9	98	1.2089	0.2961	1.2089	1.0995
No log	5.0	100	1.1951	0.3192	1.1951	1.0932
No log	5.1	102	0.8788	0.4313	0.8788	0.9374
No log	5.2	104	0.8153	0.5223	0.8153	0.9029
No log	5.3	106	0.8704	0.4775	0.8704	0.9330
No log	5.4	108	1.0698	0.4217	1.0698	1.0343
No log	5.5	110	1.0825	0.4137	1.0825	1.0404
No log	5.6	112	1.1194	0.4722	1.1194	1.0580
No log	5.7	114	1.1789	0.4016	1.1789	1.0858
No log	5.8	116	1.1609	0.2864	1.1609	1.0775
No log	5.9	118	1.1085	0.2864	1.1085	1.0529
No log	6.0	120	1.0090	0.4236	1.0090	1.0045
No log	6.1	122	0.9478	0.5318	0.9478	0.9735
No log	6.2	124	0.9447	0.4969	0.9447	0.9720
No log	6.3	126	0.8781	0.5344	0.8781	0.9371
No log	6.4	128	0.9035	0.4088	0.9035	0.9505
No log	6.5	130	1.2197	0.3561	1.2197	1.1044
No log	6.6	132	1.1322	0.4012	1.1322	1.0640
No log	6.7	134	0.8974	0.4176	0.8974	0.9473
No log	6.8	136	0.9048	0.5345	0.9048	0.9512
No log	6.9	138	0.9862	0.4661	0.9862	0.9931
No log	7.0	140	0.9486	0.4715	0.9486	0.9739
No log	7.1	142	0.8965	0.4996	0.8965	0.9468
No log	7.2	144	0.8852	0.4736	0.8852	0.9408
No log	7.3	146	0.9029	0.4646	0.9029	0.9502
No log	7.4	148	0.8273	0.4884	0.8273	0.9096
No log	7.5	150	0.8435	0.5042	0.8435	0.9184
No log	7.6	152	0.8423	0.5042	0.8423	0.9178
No log	7.7	154	0.8065	0.5305	0.8065	0.8981
No log	7.8	156	0.8275	0.4852	0.8275	0.9096
No log	7.9	158	0.8285	0.4852	0.8285	0.9102
No log	8.0	160	0.8392	0.4583	0.8392	0.9161
No log	8.1	162	0.8509	0.4450	0.8509	0.9224
No log	8.2	164	0.8940	0.4373	0.8940	0.9455
No log	8.3	166	0.9214	0.4067	0.9214	0.9599
No log	8.4	168	0.9389	0.3936	0.9389	0.9690
No log	8.5	170	0.9598	0.4037	0.9599	0.9797
No log	8.6	172	0.9085	0.4681	0.9085	0.9532
No log	8.7	174	0.8552	0.4123	0.8552	0.9248
No log	8.8	176	0.8476	0.5059	0.8476	0.9206
No log	8.9	178	0.9554	0.4580	0.9554	0.9775
No log	9.0	180	1.0162	0.4332	1.0162	1.0081
No log	9.1	182	0.8908	0.4829	0.8908	0.9438
No log	9.2	184	0.8058	0.5816	0.8058	0.8977
No log	9.3	186	0.8347	0.5565	0.8347	0.9136
No log	9.4	188	0.8320	0.4978	0.8320	0.9122
No log	9.5	190	0.8486	0.4944	0.8486	0.9212
No log	9.6	192	0.8380	0.5041	0.8380	0.9154
No log	9.7	194	0.8479	0.4945	0.8479	0.9208
No log	9.8	196	0.8546	0.4760	0.8546	0.9244
No log	9.9	198	0.8560	0.4087	0.8560	0.9252
No log	10.0	200	1.0294	0.4886	1.0294	1.0146
No log	10.1	202	1.1824	0.3884	1.1824	1.0874
No log	10.2	204	1.0572	0.4306	1.0572	1.0282
No log	10.3	206	0.9956	0.4076	0.9956	0.9978
No log	10.4	208	0.9034	0.4275	0.9034	0.9504
No log	10.5	210	0.8952	0.3842	0.8952	0.9461
No log	10.6	212	0.8896	0.4534	0.8896	0.9432
No log	10.7	214	0.9769	0.4700	0.9769	0.9884
No log	10.8	216	1.0103	0.4957	1.0103	1.0051
No log	10.9	218	0.9175	0.4838	0.9175	0.9579
No log	11.0	220	0.8238	0.5351	0.8238	0.9076
No log	11.1	222	0.8192	0.5143	0.8192	0.9051
No log	11.2	224	0.8120	0.5223	0.8120	0.9011
No log	11.3	226	0.8785	0.4920	0.8785	0.9373
No log	11.4	228	0.9068	0.4783	0.9068	0.9523
No log	11.5	230	0.8349	0.4142	0.8349	0.9138
No log	11.6	232	0.8155	0.4324	0.8155	0.9030
No log	11.7	234	0.8020	0.4423	0.8020	0.8955
No log	11.8	236	0.7922	0.4512	0.7922	0.8900
No log	11.9	238	0.8143	0.5352	0.8143	0.9024
No log	12.0	240	0.8244	0.5447	0.8244	0.9080
No log	12.1	242	0.8051	0.4884	0.8051	0.8973
No log	12.2	244	0.8433	0.4792	0.8433	0.9183
No log	12.3	246	0.8419	0.4514	0.8419	0.9175
No log	12.4	248	0.8480	0.5012	0.8480	0.9208
No log	12.5	250	0.8572	0.4931	0.8572	0.9258
No log	12.6	252	0.8690	0.5467	0.8690	0.9322
No log	12.7	254	0.9402	0.4894	0.9402	0.9697
No log	12.8	256	0.9967	0.4565	0.9967	0.9984
No log	12.9	258	0.9355	0.4826	0.9355	0.9672
No log	13.0	260	0.9293	0.5111	0.9293	0.9640
No log	13.1	262	0.9307	0.4666	0.9307	0.9648
No log	13.2	264	0.8790	0.4865	0.8790	0.9376
No log	13.3	266	0.8475	0.4356	0.8475	0.9206
No log	13.4	268	0.8368	0.4760	0.8368	0.9148
No log	13.5	270	0.8423	0.5773	0.8423	0.9178
No log	13.6	272	0.9374	0.4510	0.9374	0.9682
No log	13.7	274	0.9290	0.5042	0.9290	0.9638
No log	13.8	276	0.8699	0.5029	0.8699	0.9327
No log	13.9	278	0.8541	0.4534	0.8541	0.9242
No log	14.0	280	0.8772	0.4534	0.8772	0.9366
No log	14.1	282	0.8611	0.4534	0.8611	0.9279
No log	14.2	284	0.8901	0.4595	0.8901	0.9435
No log	14.3	286	1.0822	0.3916	1.0822	1.0403
No log	14.4	288	1.1942	0.4080	1.1942	1.0928
No log	14.5	290	1.0916	0.4138	1.0916	1.0448
No log	14.6	292	0.8935	0.5331	0.8935	0.9452
No log	14.7	294	0.8345	0.4563	0.8345	0.9135
No log	14.8	296	0.8754	0.4439	0.8754	0.9356
No log	14.9	298	0.8409	0.4671	0.8409	0.9170
No log	15.0	300	0.8291	0.5223	0.8291	0.9105
No log	15.1	302	0.8902	0.5175	0.8902	0.9435
No log	15.2	304	0.8684	0.5844	0.8684	0.9319
No log	15.3	306	0.8215	0.4780	0.8215	0.9064
No log	15.4	308	0.8815	0.4483	0.8815	0.9389
No log	15.5	310	0.8937	0.4624	0.8937	0.9454
No log	15.6	312	0.8451	0.4599	0.8451	0.9193
No log	15.7	314	0.8440	0.5076	0.8440	0.9187
No log	15.8	316	0.9088	0.5339	0.9088	0.9533
No log	15.9	318	0.9012	0.5451	0.9012	0.9493
No log	16.0	320	0.8337	0.5595	0.8337	0.9131
No log	16.1	322	0.8158	0.4912	0.8158	0.9032
No log	16.2	324	0.8160	0.4860	0.8160	0.9033
No log	16.3	326	0.8221	0.5247	0.8221	0.9067
No log	16.4	328	0.7988	0.4691	0.7988	0.8938
No log	16.5	330	0.8591	0.5013	0.8591	0.9269
No log	16.6	332	0.9083	0.4781	0.9083	0.9531
No log	16.7	334	0.8665	0.4459	0.8665	0.9308
No log	16.8	336	0.7949	0.4181	0.7949	0.8916
No log	16.9	338	0.7951	0.4839	0.7951	0.8917
No log	17.0	340	0.7947	0.4839	0.7947	0.8915
No log	17.1	342	0.8054	0.5059	0.8054	0.8974
No log	17.2	344	0.8909	0.4200	0.8909	0.9439
No log	17.3	346	0.9362	0.4685	0.9362	0.9676
No log	17.4	348	0.9446	0.4685	0.9446	0.9719
No log	17.5	350	0.8968	0.4425	0.8968	0.9470
No log	17.6	352	0.9177	0.4519	0.9177	0.9580
No log	17.7	354	0.9353	0.4165	0.9353	0.9671
No log	17.8	356	0.9069	0.4470	0.9069	0.9523
No log	17.9	358	0.8807	0.4079	0.8807	0.9385
No log	18.0	360	0.8713	0.4599	0.8713	0.9334
No log	18.1	362	0.8714	0.4377	0.8714	0.9335
No log	18.2	364	0.8885	0.4459	0.8885	0.9426
No log	18.3	366	0.8931	0.4663	0.8931	0.9451
No log	18.4	368	0.8454	0.4637	0.8454	0.9195
No log	18.5	370	0.8493	0.4806	0.8493	0.9215
No log	18.6	372	0.8403	0.4941	0.8403	0.9167
No log	18.7	374	0.8212	0.5027	0.8212	0.9062
No log	18.8	376	0.8527	0.4983	0.8527	0.9234
No log	18.9	378	0.8389	0.5220	0.8389	0.9159
No log	19.0	380	0.7949	0.5194	0.7949	0.8916
No log	19.1	382	0.8019	0.5381	0.8019	0.8955
No log	19.2	384	0.8620	0.4817	0.8620	0.9285
No log	19.3	386	0.8470	0.5007	0.8470	0.9203
No log	19.4	388	0.7984	0.5381	0.7984	0.8935
No log	19.5	390	0.8246	0.5012	0.8246	0.9081
No log	19.6	392	0.9181	0.5014	0.9181	0.9582
No log	19.7	394	0.9305	0.4593	0.9305	0.9646
No log	19.8	396	0.8615	0.4359	0.8615	0.9282
No log	19.9	398	0.8233	0.5076	0.8233	0.9074
No log	20.0	400	0.8255	0.4413	0.8255	0.9086
No log	20.1	402	0.8309	0.4942	0.8309	0.9115
No log	20.2	404	0.8377	0.4278	0.8377	0.9152
No log	20.3	406	0.8896	0.4331	0.8896	0.9432
No log	20.4	408	1.0221	0.4440	1.0221	1.0110
No log	20.5	410	1.0920	0.4487	1.0920	1.0450
No log	20.6	412	1.0381	0.4539	1.0381	1.0189
No log	20.7	414	0.9241	0.4082	0.9241	0.9613
No log	20.8	416	0.8761	0.4114	0.8761	0.9360
No log	20.9	418	0.8262	0.4238	0.8262	0.9090
No log	21.0	420	0.8079	0.4865	0.8079	0.8988
No log	21.1	422	0.8010	0.5028	0.8010	0.8950
No log	21.2	424	0.8035	0.4960	0.8035	0.8964
No log	21.3	426	0.8247	0.4737	0.8247	0.9082
No log	21.4	428	0.8417	0.4079	0.8417	0.9174
No log	21.5	430	0.8570	0.4079	0.8570	0.9257
No log	21.6	432	0.8553	0.3705	0.8553	0.9248
No log	21.7	434	0.8505	0.3715	0.8505	0.9222
No log	21.8	436	0.8762	0.3584	0.8762	0.9360
No log	21.9	438	0.8730	0.3756	0.8730	0.9343
No log	22.0	440	0.8773	0.3970	0.8773	0.9367
No log	22.1	442	0.9137	0.4067	0.9137	0.9559
No log	22.2	444	0.9103	0.3335	0.9103	0.9541
No log	22.3	446	0.8964	0.3596	0.8964	0.9468
No log	22.4	448	0.8835	0.3596	0.8835	0.9400
No log	22.5	450	0.8635	0.4002	0.8635	0.9293
No log	22.6	452	0.8815	0.4775	0.8815	0.9389
No log	22.7	454	0.9100	0.4076	0.9100	0.9540
No log	22.8	456	0.8843	0.4420	0.8843	0.9403
No log	22.9	458	0.8623	0.4331	0.8623	0.9286
No log	23.0	460	0.8270	0.4595	0.8270	0.9094
No log	23.1	462	0.8086	0.4726	0.8086	0.8992
No log	23.2	464	0.8077	0.4635	0.8077	0.8987
No log	23.3	466	0.8036	0.4359	0.8036	0.8964
No log	23.4	468	0.8017	0.4039	0.8017	0.8954
No log	23.5	470	0.8043	0.4278	0.8043	0.8968
No log	23.6	472	0.7983	0.4077	0.7983	0.8935
No log	23.7	474	0.7939	0.4466	0.7939	0.8910
No log	23.8	476	0.7851	0.4181	0.7851	0.8860
No log	23.9	478	0.7768	0.4318	0.7768	0.8813
No log	24.0	480	0.7781	0.5226	0.7781	0.8821
No log	24.1	482	0.7696	0.5093	0.7696	0.8773
No log	24.2	484	0.7736	0.5562	0.7736	0.8795
No log	24.3	486	0.7775	0.5562	0.7775	0.8818
No log	24.4	488	0.7793	0.5233	0.7793	0.8828
No log	24.5	490	0.7922	0.4859	0.7922	0.8901
No log	24.6	492	0.8023	0.4871	0.8023	0.8957
No log	24.7	494	0.7858	0.5233	0.7858	0.8864
No log	24.8	496	0.7818	0.5093	0.7818	0.8842
No log	24.9	498	0.7837	0.4681	0.7837	0.8853
0.3436	25.0	500	0.8165	0.4587	0.8165	0.9036
0.3436	25.1	502	0.8867	0.4314	0.8867	0.9417
0.3436	25.2	504	0.9397	0.4282	0.9397	0.9694
0.3436	25.3	506	0.9371	0.4282	0.9371	0.9681
0.3436	25.4	508	0.8784	0.4404	0.8784	0.9372
0.3436	25.5	510	0.8016	0.4272	0.8016	0.8953

Framework versions

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