ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k1_task8_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: 0.8028
• Qwk: 0.3574
• Mse: 0.8028
• Rmse: 0.8960

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	0.4	2	2.7384	-0.0626	2.7384	1.6548
No log	0.8	4	2.2079	0.0432	2.2079	1.4859
No log	1.2	6	0.8382	-0.0234	0.8382	0.9155
No log	1.6	8	0.6967	0.0750	0.6967	0.8347
No log	2.0	10	0.7143	0.2481	0.7143	0.8452
No log	2.4	12	0.6361	0.3562	0.6361	0.7976
No log	2.8	14	0.6220	0.3690	0.6220	0.7887
No log	3.2	16	0.6678	0.1014	0.6678	0.8172
No log	3.6	18	0.7259	0.0236	0.7259	0.8520
No log	4.0	20	0.7120	0.0236	0.7120	0.8438
No log	4.4	22	0.6702	0.0647	0.6702	0.8187
No log	4.8	24	0.6448	0.1950	0.6448	0.8030
No log	5.2	26	0.6157	0.2498	0.6157	0.7847
No log	5.6	28	0.6134	0.0	0.6134	0.7832
No log	6.0	30	0.6034	0.0750	0.6034	0.7768
No log	6.4	32	0.6015	0.1542	0.6015	0.7756
No log	6.8	34	0.6067	0.1430	0.6067	0.7789
No log	7.2	36	0.6278	0.1830	0.6278	0.7923
No log	7.6	38	0.6540	0.1644	0.6540	0.8087
No log	8.0	40	0.6469	0.2318	0.6469	0.8043
No log	8.4	42	0.6158	0.2641	0.6158	0.7848
No log	8.8	44	0.5949	0.4728	0.5949	0.7713
No log	9.2	46	0.5970	0.4402	0.5970	0.7727
No log	9.6	48	0.5837	0.4859	0.5837	0.7640
No log	10.0	50	0.5997	0.4314	0.5997	0.7744
No log	10.4	52	0.5992	0.4449	0.5992	0.7741
No log	10.8	54	0.6380	0.3763	0.6380	0.7988
No log	11.2	56	0.7728	0.2886	0.7728	0.8791
No log	11.6	58	0.8680	0.1886	0.8680	0.9316
No log	12.0	60	0.7542	0.3451	0.7542	0.8685
No log	12.4	62	0.6916	0.3661	0.6916	0.8316
No log	12.8	64	0.7524	0.4350	0.7524	0.8674
No log	13.2	66	0.7225	0.4493	0.7225	0.8500
No log	13.6	68	0.6810	0.4167	0.6810	0.8252
No log	14.0	70	0.6803	0.3840	0.6803	0.8248
No log	14.4	72	0.7010	0.3972	0.7010	0.8372
No log	14.8	74	0.6966	0.3253	0.6966	0.8346
No log	15.2	76	0.6828	0.4132	0.6828	0.8263
No log	15.6	78	0.6851	0.3849	0.6851	0.8277
No log	16.0	80	0.6722	0.3553	0.6722	0.8199
No log	16.4	82	0.6705	0.2480	0.6705	0.8188
No log	16.8	84	0.7143	0.3115	0.7143	0.8452
No log	17.2	86	0.6808	0.2975	0.6808	0.8251
No log	17.6	88	0.6240	0.3704	0.6240	0.7899
No log	18.0	90	0.6234	0.3585	0.6234	0.7895
No log	18.4	92	0.6919	0.3399	0.6919	0.8318
No log	18.8	94	0.9206	0.3779	0.9206	0.9595
No log	19.2	96	1.0173	0.3775	1.0173	1.0086
No log	19.6	98	0.8991	0.4140	0.8991	0.9482
No log	20.0	100	0.7816	0.3817	0.7816	0.8841
No log	20.4	102	0.7226	0.3887	0.7226	0.8501
No log	20.8	104	0.7370	0.4451	0.7370	0.8585
No log	21.2	106	0.6996	0.4052	0.6996	0.8364
No log	21.6	108	0.6547	0.4126	0.6547	0.8091
No log	22.0	110	0.6714	0.4147	0.6714	0.8194
No log	22.4	112	0.7622	0.4328	0.7622	0.8730
No log	22.8	114	0.8344	0.4205	0.8344	0.9135
No log	23.2	116	0.7719	0.4389	0.7719	0.8786
No log	23.6	118	0.6971	0.4402	0.6971	0.8349
No log	24.0	120	0.6877	0.4402	0.6877	0.8293
No log	24.4	122	0.7600	0.4093	0.7600	0.8718
No log	24.8	124	0.8304	0.4432	0.8304	0.9113
No log	25.2	126	0.8100	0.4261	0.8100	0.9000
No log	25.6	128	0.7086	0.4328	0.7086	0.8418
No log	26.0	130	0.6502	0.4375	0.6502	0.8064
No log	26.4	132	0.6388	0.4161	0.6388	0.7992
No log	26.8	134	0.6906	0.4350	0.6906	0.8310
No log	27.2	136	0.7110	0.3968	0.7110	0.8432
No log	27.6	138	0.7100	0.3968	0.7100	0.8426
No log	28.0	140	0.6444	0.3840	0.6444	0.8028
No log	28.4	142	0.6285	0.4161	0.6285	0.7928
No log	28.8	144	0.6776	0.4052	0.6776	0.8232
No log	29.2	146	0.7381	0.4328	0.7381	0.8591
No log	29.6	148	0.7115	0.4451	0.7115	0.8435
No log	30.0	150	0.6635	0.3780	0.6635	0.8146
No log	30.4	152	0.7103	0.4451	0.7103	0.8428
No log	30.8	154	0.7548	0.4493	0.7548	0.8688
No log	31.2	156	0.7584	0.4587	0.7584	0.8709
No log	31.6	158	0.7039	0.4660	0.7039	0.8390
No log	32.0	160	0.6906	0.4253	0.6906	0.8310
No log	32.4	162	0.6817	0.4217	0.6817	0.8256
No log	32.8	164	0.7035	0.4218	0.7035	0.8387
No log	33.2	166	0.7616	0.4261	0.7616	0.8727
No log	33.6	168	0.7671	0.4261	0.7671	0.8758
No log	34.0	170	0.8001	0.4018	0.8001	0.8945
No log	34.4	172	0.8273	0.3344	0.8273	0.9096
No log	34.8	174	0.7988	0.3243	0.7988	0.8938
No log	35.2	176	0.7820	0.3574	0.7820	0.8843
No log	35.6	178	0.7952	0.3574	0.7952	0.8917
No log	36.0	180	0.8471	0.3271	0.8471	0.9204
No log	36.4	182	0.8404	0.3271	0.8404	0.9167
No log	36.8	184	0.7654	0.4051	0.7654	0.8748
No log	37.2	186	0.7326	0.4142	0.7326	0.8559
No log	37.6	188	0.7587	0.4018	0.7587	0.8710
No log	38.0	190	0.7916	0.3753	0.7916	0.8897
No log	38.4	192	0.8318	0.3451	0.8318	0.9120
No log	38.8	194	0.7966	0.3962	0.7966	0.8925
No log	39.2	196	0.8254	0.3506	0.8254	0.9085
No log	39.6	198	0.8255	0.3506	0.8255	0.9086
No log	40.0	200	0.9013	0.3779	0.9013	0.9493
No log	40.4	202	0.9652	0.3807	0.9652	0.9824
No log	40.8	204	0.8917	0.3676	0.8917	0.9443
No log	41.2	206	0.7486	0.4218	0.7486	0.8652
No log	41.6	208	0.6823	0.4253	0.6823	0.8260
No log	42.0	210	0.6557	0.3933	0.6557	0.8097
No log	42.4	212	0.6600	0.3933	0.6600	0.8124
No log	42.8	214	0.6489	0.3599	0.6489	0.8055
No log	43.2	216	0.6617	0.4161	0.6617	0.8134
No log	43.6	218	0.7421	0.2790	0.7421	0.8614
No log	44.0	220	0.7990	0.3202	0.7990	0.8939
No log	44.4	222	0.7890	0.3202	0.7890	0.8882
No log	44.8	224	0.7393	0.2725	0.7393	0.8598
No log	45.2	226	0.6836	0.3836	0.6836	0.8268
No log	45.6	228	0.6716	0.3808	0.6716	0.8195
No log	46.0	230	0.6836	0.4126	0.6836	0.8268
No log	46.4	232	0.7279	0.3713	0.7279	0.8532
No log	46.8	234	0.8244	0.3109	0.8244	0.9079
No log	47.2	236	1.0042	0.3513	1.0042	1.0021
No log	47.6	238	1.1849	0.3308	1.1849	1.0885
No log	48.0	240	1.2319	0.3457	1.2319	1.1099
No log	48.4	242	1.1411	0.3287	1.1411	1.0682
No log	48.8	244	0.9720	0.3456	0.9720	0.9859
No log	49.2	246	0.8012	0.3873	0.8012	0.8951
No log	49.6	248	0.7048	0.3846	0.7048	0.8395
No log	50.0	250	0.6793	0.3425	0.6793	0.8242
No log	50.4	252	0.6950	0.3558	0.6950	0.8337
No log	50.8	254	0.7471	0.3685	0.7471	0.8644
No log	51.2	256	0.8147	0.3594	0.8147	0.9026
No log	51.6	258	0.8774	0.3733	0.8774	0.9367
No log	52.0	260	0.8907	0.3733	0.8907	0.9438
No log	52.4	262	0.8483	0.3440	0.8483	0.9210
No log	52.8	264	0.8447	0.3440	0.8447	0.9191
No log	53.2	266	0.8219	0.3331	0.8219	0.9066
No log	53.6	268	0.7636	0.3594	0.7636	0.8738
No log	54.0	270	0.7006	0.3651	0.7006	0.8370
No log	54.4	272	0.6818	0.3302	0.6818	0.8257
No log	54.8	274	0.6893	0.3207	0.6893	0.8302
No log	55.2	276	0.7084	0.3651	0.7084	0.8417
No log	55.6	278	0.7490	0.3466	0.7490	0.8655
No log	56.0	280	0.7810	0.3466	0.7810	0.8838
No log	56.4	282	0.8200	0.3466	0.8200	0.9055
No log	56.8	284	0.8566	0.3145	0.8566	0.9255
No log	57.2	286	0.8916	0.3733	0.8916	0.9442
No log	57.6	288	0.9139	0.3899	0.9139	0.9560
No log	58.0	290	0.8703	0.3694	0.8703	0.9329
No log	58.4	292	0.7734	0.3663	0.7734	0.8794
No log	58.8	294	0.7058	0.4315	0.7058	0.8401
No log	59.2	296	0.6901	0.4147	0.6901	0.8307
No log	59.6	298	0.7024	0.4147	0.7024	0.8381
No log	60.0	300	0.7199	0.3817	0.7199	0.8485
No log	60.4	302	0.7495	0.4123	0.7495	0.8658
No log	60.8	304	0.7950	0.3938	0.7950	0.8916
No log	61.2	306	0.8456	0.3988	0.8456	0.9196
No log	61.6	308	0.8443	0.3988	0.8443	0.9188
No log	62.0	310	0.7958	0.3783	0.7958	0.8921
No log	62.4	312	0.7362	0.3243	0.7362	0.8580
No log	62.8	314	0.7054	0.3942	0.7054	0.8399
No log	63.2	316	0.6847	0.4044	0.6847	0.8275
No log	63.6	318	0.6981	0.3942	0.6981	0.8355
No log	64.0	320	0.7406	0.3723	0.7406	0.8606
No log	64.4	322	0.8114	0.3938	0.8114	0.9008
No log	64.8	324	0.8484	0.3783	0.8484	0.9211
No log	65.2	326	0.8344	0.3574	0.8344	0.9134
No log	65.6	328	0.7937	0.3938	0.7937	0.8909
No log	66.0	330	0.7645	0.3938	0.7645	0.8744
No log	66.4	332	0.7133	0.4350	0.7133	0.8446
No log	66.8	334	0.6935	0.4044	0.6935	0.8328
No log	67.2	336	0.6986	0.4044	0.6986	0.8358
No log	67.6	338	0.7359	0.4123	0.7359	0.8579
No log	68.0	340	0.7930	0.3938	0.7930	0.8905
No log	68.4	342	0.8265	0.4051	0.8265	0.9091
No log	68.8	344	0.8264	0.4051	0.8264	0.9091
No log	69.2	346	0.7965	0.3849	0.7965	0.8925
No log	69.6	348	0.7457	0.4030	0.7457	0.8636
No log	70.0	350	0.7224	0.3723	0.7224	0.8499
No log	70.4	352	0.7119	0.3817	0.7119	0.8437
No log	70.8	354	0.7300	0.3723	0.7300	0.8544
No log	71.2	356	0.7590	0.3938	0.7590	0.8712
No log	71.6	358	0.7775	0.3938	0.7775	0.8818
No log	72.0	360	0.7868	0.3938	0.7868	0.8870
No log	72.4	362	0.7930	0.3938	0.7930	0.8905
No log	72.8	364	0.7720	0.4030	0.7720	0.8786
No log	73.2	366	0.7403	0.3630	0.7403	0.8604
No log	73.6	368	0.7193	0.4044	0.7193	0.8481
No log	74.0	370	0.7305	0.4044	0.7305	0.8547
No log	74.4	372	0.7758	0.4030	0.7758	0.8808
No log	74.8	374	0.8169	0.4142	0.8169	0.9038
No log	75.2	376	0.8530	0.4051	0.8530	0.9236
No log	75.6	378	0.8541	0.4051	0.8541	0.9242
No log	76.0	380	0.8427	0.4051	0.8427	0.9180
No log	76.4	382	0.7999	0.3938	0.7999	0.8944
No log	76.8	384	0.7668	0.4123	0.7668	0.8757
No log	77.2	386	0.7323	0.3914	0.7323	0.8557
No log	77.6	388	0.7260	0.3914	0.7260	0.8520
No log	78.0	390	0.7257	0.3914	0.7257	0.8519
No log	78.4	392	0.7397	0.3914	0.7397	0.8600
No log	78.8	394	0.7692	0.3817	0.7692	0.8770
No log	79.2	396	0.7892	0.3754	0.7892	0.8884
No log	79.6	398	0.7908	0.3630	0.7908	0.8893
No log	80.0	400	0.7699	0.3723	0.7699	0.8774
No log	80.4	402	0.7360	0.4147	0.7360	0.8579
No log	80.8	404	0.7189	0.4147	0.7189	0.8479
No log	81.2	406	0.7176	0.4147	0.7176	0.8471
No log	81.6	408	0.7279	0.4147	0.7279	0.8532
No log	82.0	410	0.7477	0.3942	0.7477	0.8647
No log	82.4	412	0.7713	0.3333	0.7713	0.8782
No log	82.8	414	0.8043	0.3155	0.8043	0.8968
No log	83.2	416	0.8194	0.3574	0.8194	0.9052
No log	83.6	418	0.8203	0.3754	0.8203	0.9057
No log	84.0	420	0.8043	0.3846	0.8043	0.8968
No log	84.4	422	0.7749	0.3817	0.7749	0.8803
No log	84.8	424	0.7572	0.4147	0.7572	0.8702
No log	85.2	426	0.7565	0.4147	0.7565	0.8697
No log	85.6	428	0.7634	0.4147	0.7634	0.8737
No log	86.0	430	0.7759	0.3846	0.7759	0.8808
No log	86.4	432	0.7887	0.3938	0.7887	0.8881
No log	86.8	434	0.7947	0.3938	0.7947	0.8914
No log	87.2	436	0.7870	0.3846	0.7870	0.8871
No log	87.6	438	0.7763	0.4067	0.7763	0.8811
No log	88.0	440	0.7723	0.3637	0.7723	0.8788
No log	88.4	442	0.7713	0.3539	0.7713	0.8782
No log	88.8	444	0.7807	0.3539	0.7807	0.8836
No log	89.2	446	0.8004	0.3873	0.8004	0.8947
No log	89.6	448	0.8179	0.3783	0.8179	0.9044
No log	90.0	450	0.8214	0.3783	0.8214	0.9063
No log	90.4	452	0.8124	0.3783	0.8124	0.9013
No log	90.8	454	0.8050	0.3873	0.8050	0.8972
No log	91.2	456	0.7909	0.3770	0.7909	0.8893
No log	91.6	458	0.7760	0.3539	0.7760	0.8809
No log	92.0	460	0.7671	0.3539	0.7671	0.8758
No log	92.4	462	0.7666	0.3637	0.7666	0.8755
No log	92.8	464	0.7672	0.3637	0.7672	0.8759
No log	93.2	466	0.7713	0.3539	0.7713	0.8782
No log	93.6	468	0.7803	0.3443	0.7803	0.8833
No log	94.0	470	0.7884	0.3243	0.7884	0.8879
No log	94.4	472	0.7929	0.3574	0.7929	0.8904
No log	94.8	474	0.7924	0.3574	0.7924	0.8902
No log	95.2	476	0.7891	0.3574	0.7891	0.8883
No log	95.6	478	0.7872	0.3663	0.7872	0.8872
No log	96.0	480	0.7873	0.3663	0.7873	0.8873
No log	96.4	482	0.7894	0.3754	0.7894	0.8885
No log	96.8	484	0.7885	0.3754	0.7885	0.8880
No log	97.2	486	0.7905	0.3754	0.7905	0.8891
No log	97.6	488	0.7942	0.3754	0.7942	0.8912
No log	98.0	490	0.7975	0.3663	0.7975	0.8930
No log	98.4	492	0.7996	0.3663	0.7996	0.8942
No log	98.8	494	0.8012	0.3574	0.8012	0.8951
No log	99.2	496	0.8026	0.3574	0.8026	0.8959
No log	99.6	498	0.8027	0.3574	0.8027	0.8959
0.2205	100.0	500	0.8028	0.3574	0.8028	0.8960

Framework versions

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