ArabicNewSplits7_FineTuningAraBERT_run3_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: 0.8449
• Qwk: 0.4413
• Mse: 0.8449
• Rmse: 0.9192

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	2.6757	0.0038	2.6757	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	1.6097	0.0169	1.6097	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	1.1722
No log	2.6	52	1.4934	0.0331	1.4934	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	1.0519
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	1.3204	0.0843	1.3204	1.1491
No log	3.3	66	1.3160	0.1005	1.3160	1.1472
No log	3.4	68	1.3449	0.1313	1.3449	1.1597
No log	3.5	70	1.2674	0.2541	1.2674	1.1258
No log	3.6	72	1.2517	0.2271	1.2517	1.1188
No log	3.7	74	1.2381	0.2775	1.2381	1.1127
No log	3.8	76	1.2147	0.2584	1.2147	1.1021
No log	3.9	78	1.1430	0.3134	1.1430	1.0691
No log	4.0	80	1.0592	0.3621	1.0592	1.0292
No log	4.1	82	1.0516	0.2752	1.0516	1.0255
No log	4.2	84	1.1418	0.2650	1.1418	1.0685
No log	4.3	86	1.1927	0.2634	1.1927	1.0921
No log	4.4	88	1.0866	0.2466	1.0866	1.0424
No log	4.5	90	1.0522	0.2466	1.0522	1.0257
No log	4.6	92	1.0238	0.3317	1.0238	1.0118
No log	4.7	94	0.9515	0.3666	0.9515	0.9754
No log	4.8	96	0.9367	0.4157	0.9367	0.9679
No log	4.9	98	1.2090	0.2961	1.2090	1.0995
No log	5.0	100	1.1954	0.3192	1.1954	1.0933
No log	5.1	102	0.8789	0.4313	0.8789	0.9375
No log	5.2	104	0.8154	0.5223	0.8154	0.9030
No log	5.3	106	0.8704	0.4775	0.8704	0.9329
No log	5.4	108	1.0693	0.4217	1.0693	1.0341
No log	5.5	110	1.0822	0.4137	1.0822	1.0403
No log	5.6	112	1.1193	0.4722	1.1193	1.0580
No log	5.7	114	1.1790	0.4016	1.1790	1.0858
No log	5.8	116	1.1609	0.2864	1.1609	1.0775
No log	5.9	118	1.1086	0.2864	1.1086	1.0529
No log	6.0	120	1.0092	0.4236	1.0092	1.0046
No log	6.1	122	0.9480	0.5318	0.9480	0.9737
No log	6.2	124	0.9453	0.4969	0.9453	0.9722
No log	6.3	126	0.8785	0.5344	0.8785	0.9373
No log	6.4	128	0.9040	0.4088	0.9040	0.9508
No log	6.5	130	1.2200	0.3561	1.2200	1.1045
No log	6.6	132	1.1311	0.4012	1.1311	1.0635
No log	6.7	134	0.8967	0.4176	0.8967	0.9470
No log	6.8	136	0.9046	0.5345	0.9046	0.9511
No log	6.9	138	0.9851	0.4661	0.9851	0.9925
No log	7.0	140	0.9474	0.4715	0.9474	0.9734
No log	7.1	142	0.8964	0.4996	0.8964	0.9468
No log	7.2	144	0.8851	0.4736	0.8851	0.9408
No log	7.3	146	0.9026	0.4646	0.9026	0.9501
No log	7.4	148	0.8267	0.4884	0.8267	0.9092
No log	7.5	150	0.8440	0.5042	0.8440	0.9187
No log	7.6	152	0.8427	0.5057	0.8427	0.9180
No log	7.7	154	0.8062	0.5305	0.8062	0.8979
No log	7.8	156	0.8266	0.4852	0.8266	0.9092
No log	7.9	158	0.8275	0.4852	0.8275	0.9097
No log	8.0	160	0.8384	0.4583	0.8384	0.9157
No log	8.1	162	0.8500	0.4583	0.8500	0.9220
No log	8.2	164	0.8921	0.4373	0.8921	0.9445
No log	8.3	166	0.9204	0.4067	0.9204	0.9594
No log	8.4	168	0.9380	0.3936	0.9380	0.9685
No log	8.5	170	0.9575	0.4037	0.9575	0.9785
No log	8.6	172	0.9049	0.4681	0.9049	0.9513
No log	8.7	174	0.8527	0.4254	0.8527	0.9234
No log	8.8	176	0.8436	0.5059	0.8436	0.9185
No log	8.9	178	0.9440	0.4580	0.9440	0.9716
No log	9.0	180	1.0016	0.4551	1.0016	1.0008
No log	9.1	182	0.8798	0.4864	0.8798	0.9380
No log	9.2	184	0.8047	0.5816	0.8047	0.8970
No log	9.3	186	0.8360	0.5470	0.8360	0.9144
No log	9.4	188	0.8296	0.5320	0.8296	0.9108
No log	9.5	190	0.8470	0.4944	0.8470	0.9203
No log	9.6	192	0.8359	0.5041	0.8359	0.9143
No log	9.7	194	0.8458	0.4945	0.8458	0.9197
No log	9.8	196	0.8523	0.5107	0.8523	0.9232
No log	9.9	198	0.8534	0.4087	0.8534	0.9238
No log	10.0	200	1.0300	0.4886	1.0300	1.0149
No log	10.1	202	1.1843	0.4078	1.1843	1.0882
No log	10.2	204	1.0561	0.4304	1.0561	1.0277
No log	10.3	206	0.9906	0.4289	0.9906	0.9953
No log	10.4	208	0.8988	0.4181	0.8988	0.9480
No log	10.5	210	0.8909	0.3842	0.8909	0.9439
No log	10.6	212	0.8833	0.4534	0.8833	0.9398
No log	10.7	214	0.9636	0.4907	0.9636	0.9816
No log	10.8	216	0.9904	0.4957	0.9904	0.9952
No log	10.9	218	0.8984	0.4966	0.8984	0.9479
No log	11.0	220	0.8177	0.5351	0.8177	0.9043
No log	11.1	222	0.8156	0.5143	0.8156	0.9031
No log	11.2	224	0.8049	0.5223	0.8049	0.8971
No log	11.3	226	0.8669	0.5046	0.8669	0.9311
No log	11.4	228	0.8980	0.4783	0.8980	0.9476
No log	11.5	230	0.8311	0.4142	0.8311	0.9116
No log	11.6	232	0.8130	0.4075	0.8130	0.9017
No log	11.7	234	0.7991	0.4423	0.7991	0.8939
No log	11.8	236	0.7876	0.4512	0.7876	0.8875
No log	11.9	238	0.8055	0.5352	0.8055	0.8975
No log	12.0	240	0.8136	0.5474	0.8136	0.9020
No log	12.1	242	0.8005	0.5233	0.8005	0.8947
No log	12.2	244	0.8510	0.5255	0.8510	0.9225
No log	12.3	246	0.8441	0.4667	0.8441	0.9188
No log	12.4	248	0.8422	0.5012	0.8422	0.9177
No log	12.5	250	0.8481	0.5062	0.8481	0.9209
No log	12.6	252	0.8546	0.5030	0.8546	0.9244
No log	12.7	254	0.9189	0.4938	0.9189	0.9586
No log	12.8	256	0.9706	0.4572	0.9706	0.9852
No log	12.9	258	0.9184	0.4765	0.9184	0.9583
No log	13.0	260	0.9170	0.4666	0.9170	0.9576
No log	13.1	262	0.9137	0.4203	0.9137	0.9559
No log	13.2	264	0.8706	0.3938	0.8706	0.9330
No log	13.3	266	0.8484	0.4356	0.8484	0.9211
No log	13.4	268	0.8368	0.4962	0.8368	0.9148
No log	13.5	270	0.8542	0.5571	0.8542	0.9242
No log	13.6	272	0.8927	0.4984	0.8927	0.9448
No log	13.7	274	0.8429	0.5773	0.8429	0.9181
No log	13.8	276	0.8158	0.4962	0.8158	0.9032
No log	13.9	278	0.8344	0.4760	0.8344	0.9135
No log	14.0	280	0.8430	0.4534	0.8430	0.9182
No log	14.1	282	0.8405	0.4534	0.8405	0.9168
No log	14.2	284	0.8600	0.4409	0.8600	0.9273
No log	14.3	286	0.9454	0.4400	0.9454	0.9723
No log	14.4	288	0.9475	0.4396	0.9475	0.9734
No log	14.5	290	0.8428	0.5571	0.8428	0.9180
No log	14.6	292	0.8129	0.5458	0.8129	0.9016
No log	14.7	294	0.8237	0.5622	0.8237	0.9076
No log	14.8	296	0.8164	0.5387	0.8164	0.9035
No log	14.9	298	0.8069	0.4962	0.8069	0.8983
No log	15.0	300	0.7992	0.5580	0.7992	0.8940
No log	15.1	302	0.8131	0.5477	0.8131	0.9017
No log	15.2	304	0.8158	0.5213	0.8158	0.9032
No log	15.3	306	0.8289	0.4491	0.8289	0.9105
No log	15.4	308	0.8483	0.4258	0.8483	0.9210
No log	15.5	310	0.8685	0.4280	0.8685	0.9319
No log	15.6	312	0.8830	0.4242	0.8830	0.9397
No log	15.7	314	0.8707	0.3938	0.8707	0.9331
No log	15.8	316	0.8631	0.4220	0.8631	0.9290
No log	15.9	318	0.8423	0.4780	0.8423	0.9178
No log	16.0	320	0.8686	0.5543	0.8686	0.9320
No log	16.1	322	0.8602	0.5543	0.8602	0.9275
No log	16.2	324	0.8571	0.5428	0.8571	0.9258
No log	16.3	326	0.8324	0.5992	0.8324	0.9124
No log	16.4	328	0.8199	0.5595	0.8199	0.9055
No log	16.5	330	0.8303	0.5662	0.8303	0.9112
No log	16.6	332	0.8205	0.5203	0.8205	0.9058
No log	16.7	334	0.8341	0.4852	0.8341	0.9133
No log	16.8	336	0.8418	0.4852	0.8418	0.9175
No log	16.9	338	0.8523	0.4714	0.8523	0.9232
No log	17.0	340	0.8702	0.4714	0.8702	0.9328
No log	17.1	342	0.9519	0.4082	0.9519	0.9757
No log	17.2	344	0.9835	0.3765	0.9835	0.9917
No log	17.3	346	0.9276	0.4236	0.9276	0.9631
No log	17.4	348	0.8812	0.4714	0.8812	0.9387
No log	17.5	350	0.9158	0.4459	0.9158	0.9570
No log	17.6	352	1.0202	0.3928	1.0202	1.0101
No log	17.7	354	0.9811	0.4048	0.9811	0.9905
No log	17.8	356	0.8872	0.4808	0.8872	0.9419
No log	17.9	358	0.8658	0.5175	0.8658	0.9305
No log	18.0	360	0.8562	0.4737	0.8562	0.9253
No log	18.1	362	0.8571	0.5154	0.8571	0.9258
No log	18.2	364	0.9264	0.4724	0.9264	0.9625
No log	18.3	366	0.9060	0.4734	0.9060	0.9519
No log	18.4	368	0.8479	0.5059	0.8479	0.9208
No log	18.5	370	0.8399	0.5195	0.8399	0.9165
No log	18.6	372	0.8368	0.4927	0.8368	0.9147
No log	18.7	374	0.8584	0.5029	0.8584	0.9265
No log	18.8	376	0.8763	0.4796	0.8763	0.9361
No log	18.9	378	0.8476	0.5173	0.8476	0.9207
No log	19.0	380	0.8271	0.4976	0.8271	0.9094
No log	19.1	382	0.8962	0.4660	0.8962	0.9467
No log	19.2	384	1.0393	0.3511	1.0393	1.0195
No log	19.3	386	1.0144	0.3415	1.0144	1.0072
No log	19.4	388	0.8750	0.5364	0.8750	0.9354
No log	19.5	390	0.8365	0.5239	0.8365	0.9146
No log	19.6	392	0.9768	0.4365	0.9768	0.9883
No log	19.7	394	1.0744	0.4521	1.0744	1.0365
No log	19.8	396	0.9930	0.4332	0.9930	0.9965
No log	19.9	398	0.8794	0.4238	0.8794	0.9378
No log	20.0	400	0.8608	0.4499	0.8608	0.9278
No log	20.1	402	0.8615	0.4768	0.8615	0.9282
No log	20.2	404	0.8708	0.4405	0.8708	0.9331
No log	20.3	406	0.9350	0.3779	0.9350	0.9670
No log	20.4	408	1.1663	0.3765	1.1663	1.0800
No log	20.5	410	1.4375	0.3829	1.4375	1.1990
No log	20.6	412	1.5002	0.3311	1.5002	1.2248
No log	20.7	414	1.3348	0.3824	1.3348	1.1553
No log	20.8	416	1.1518	0.3765	1.1518	1.0732
No log	20.9	418	0.9788	0.3294	0.9788	0.9894
No log	21.0	420	0.9232	0.4013	0.9232	0.9608
No log	21.1	422	0.9040	0.4181	0.9040	0.9508
No log	21.2	424	0.9132	0.4181	0.9132	0.9556
No log	21.3	426	0.9312	0.4275	0.9312	0.9650
No log	21.4	428	1.0019	0.4201	1.0019	1.0010
No log	21.5	430	1.0498	0.4372	1.0498	1.0246
No log	21.6	432	1.0005	0.4724	1.0005	1.0003
No log	21.7	434	0.9038	0.4146	0.9038	0.9507
No log	21.8	436	0.8608	0.4180	0.8608	0.9278
No log	21.9	438	0.8594	0.4615	0.8594	0.9270
No log	22.0	440	0.8559	0.4587	0.8559	0.9251
No log	22.1	442	0.8448	0.3685	0.8448	0.9191
No log	22.2	444	0.8802	0.3868	0.8802	0.9382
No log	22.3	446	0.8844	0.3861	0.8844	0.9404
No log	22.4	448	0.8478	0.4142	0.8478	0.9207
No log	22.5	450	0.8256	0.4406	0.8256	0.9086
No log	22.6	452	0.8461	0.4301	0.8461	0.9198
No log	22.7	454	0.8364	0.4301	0.8364	0.9145
No log	22.8	456	0.8096	0.4406	0.8096	0.8998
No log	22.9	458	0.8058	0.5076	0.8058	0.8976
No log	23.0	460	0.8622	0.4969	0.8622	0.9286
No log	23.1	462	0.8614	0.4565	0.8614	0.9281
No log	23.2	464	0.8094	0.5059	0.8094	0.8997
No log	23.3	466	0.8074	0.4461	0.8074	0.8986
No log	23.4	468	0.8223	0.4908	0.8223	0.9068
No log	23.5	470	0.8276	0.4461	0.8276	0.9097
No log	23.6	472	0.8406	0.4278	0.8406	0.9169
No log	23.7	474	0.8751	0.4579	0.8751	0.9355
No log	23.8	476	0.9029	0.4672	0.9029	0.9502
No log	23.9	478	0.8718	0.4366	0.8718	0.9337
No log	24.0	480	0.8531	0.4548	0.8531	0.9236
No log	24.1	482	0.8685	0.4888	0.8685	0.9319
No log	24.2	484	0.8626	0.4455	0.8626	0.9288
No log	24.3	486	0.8670	0.4493	0.8670	0.9311
No log	24.4	488	0.8973	0.4359	0.8973	0.9473
No log	24.5	490	0.8955	0.4444	0.8955	0.9463
No log	24.6	492	0.8614	0.4493	0.8614	0.9281
No log	24.7	494	0.8398	0.5044	0.8398	0.9164
No log	24.8	496	0.8378	0.4826	0.8378	0.9153
No log	24.9	498	0.8332	0.4912	0.8332	0.9128
0.3441	25.0	500	0.8872	0.4449	0.8872	0.9419
0.3441	25.1	502	1.0105	0.4557	1.0105	1.0053
0.3441	25.2	504	1.0951	0.3995	1.0951	1.0465
0.3441	25.3	506	1.0642	0.4511	1.0642	1.0316
0.3441	25.4	508	0.9306	0.4902	0.9306	0.9647
0.3441	25.5	510	0.8191	0.5291	0.8191	0.9050
0.3441	25.6	512	0.7805	0.5073	0.7805	0.8834
0.3441	25.7	514	0.7672	0.5253	0.7672	0.8759
0.3441	25.8	516	0.7629	0.5253	0.7629	0.8735
0.3441	25.9	518	0.7622	0.5253	0.7622	0.8730
0.3441	26.0	520	0.7756	0.4768	0.7756	0.8807
0.3441	26.1	522	0.8478	0.4754	0.8478	0.9208
0.3441	26.2	524	0.9082	0.4938	0.9082	0.9530
0.3441	26.3	526	0.8831	0.4639	0.8831	0.9397
0.3441	26.4	528	0.8367	0.3908	0.8367	0.9147
0.3441	26.5	530	0.8354	0.4261	0.8354	0.9140
0.3441	26.6	532	0.8804	0.4938	0.8804	0.9383
0.3441	26.7	534	0.9277	0.4520	0.9277	0.9632
0.3441	26.8	536	0.8895	0.4520	0.8895	0.9431
0.3441	26.9	538	0.8117	0.5093	0.8117	0.9009
0.3441	27.0	540	0.7916	0.5477	0.7916	0.8897
0.3441	27.1	542	0.7881	0.5455	0.7881	0.8877
0.3441	27.2	544	0.7791	0.5526	0.7791	0.8826
0.3441	27.3	546	0.7844	0.5044	0.7844	0.8857
0.3441	27.4	548	0.7944	0.5404	0.7944	0.8913
0.3441	27.5	550	0.8031	0.4912	0.8031	0.8961
0.3441	27.6	552	0.8119	0.4540	0.8119	0.9010
0.3441	27.7	554	0.8307	0.3919	0.8307	0.9114
0.3441	27.8	556	0.8640	0.4672	0.8640	0.9295
0.3441	27.9	558	0.9307	0.4396	0.9307	0.9647
0.3441	28.0	560	0.9662	0.4396	0.9662	0.9829
0.3441	28.1	562	0.9373	0.4201	0.9373	0.9682
0.3441	28.2	564	0.8818	0.4013	0.8818	0.9390
0.3441	28.3	566	0.8449	0.4413	0.8449	0.9192

Framework versions

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