ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k8_task1_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: 0.8558
• Qwk: 0.6580
• Mse: 0.8558
• Rmse: 0.9251

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	0.0426	2	5.1393	-0.0067	5.1393	2.2670
No log	0.0851	4	3.4942	0.0445	3.4942	1.8693
No log	0.1277	6	1.9882	0.1357	1.9882	1.4100
No log	0.1702	8	1.4040	0.1036	1.4040	1.1849
No log	0.2128	10	1.3856	0.0971	1.3856	1.1771
No log	0.2553	12	1.3829	0.0815	1.3829	1.1760
No log	0.2979	14	1.4383	0.1669	1.4383	1.1993
No log	0.3404	16	1.5382	0.2736	1.5382	1.2403
No log	0.3830	18	1.4321	0.1840	1.4321	1.1967
No log	0.4255	20	1.2267	0.1303	1.2267	1.1076
No log	0.4681	22	1.2078	0.2408	1.2078	1.0990
No log	0.5106	24	1.2286	0.2390	1.2286	1.1084
No log	0.5532	26	1.2621	0.1035	1.2621	1.1235
No log	0.5957	28	1.2344	0.1668	1.2344	1.1110
No log	0.6383	30	1.1056	0.3525	1.1056	1.0515
No log	0.6809	32	1.0567	0.3867	1.0567	1.0280
No log	0.7234	34	0.9140	0.4717	0.9140	0.9560
No log	0.7660	36	0.8035	0.5123	0.8035	0.8964
No log	0.8085	38	0.7746	0.5484	0.7746	0.8801
No log	0.8511	40	0.7673	0.5782	0.7673	0.8760
No log	0.8936	42	0.7862	0.5789	0.7862	0.8867
No log	0.9362	44	0.7660	0.5843	0.7660	0.8752
No log	0.9787	46	0.7500	0.6085	0.7500	0.8660
No log	1.0213	48	0.7702	0.5206	0.7702	0.8776
No log	1.0638	50	0.7359	0.5937	0.7359	0.8578
No log	1.1064	52	0.7114	0.6193	0.7114	0.8434
No log	1.1489	54	0.7420	0.6108	0.7420	0.8614
No log	1.1915	56	0.8806	0.6267	0.8806	0.9384
No log	1.2340	58	0.9304	0.5823	0.9304	0.9646
No log	1.2766	60	0.8086	0.6049	0.8086	0.8992
No log	1.3191	62	0.7877	0.6530	0.7877	0.8875
No log	1.3617	64	0.7857	0.6596	0.7857	0.8864
No log	1.4043	66	0.9151	0.5934	0.9151	0.9566
No log	1.4468	68	1.0010	0.5926	1.0010	1.0005
No log	1.4894	70	0.9096	0.5875	0.9096	0.9537
No log	1.5319	72	0.7851	0.6385	0.7851	0.8860
No log	1.5745	74	0.7136	0.6581	0.7136	0.8447
No log	1.6170	76	0.6808	0.6992	0.6808	0.8251
No log	1.6596	78	0.7177	0.6784	0.7177	0.8472
No log	1.7021	80	0.8362	0.5991	0.8362	0.9144
No log	1.7447	82	0.9090	0.6327	0.9090	0.9534
No log	1.7872	84	1.0964	0.5069	1.0964	1.0471
No log	1.8298	86	1.0990	0.5080	1.0990	1.0483
No log	1.8723	88	0.9039	0.6051	0.9039	0.9507
No log	1.9149	90	0.7890	0.6649	0.7890	0.8883
No log	1.9574	92	0.7470	0.6245	0.7470	0.8643
No log	2.0	94	0.7795	0.6459	0.7795	0.8829
No log	2.0426	96	0.8120	0.6283	0.8120	0.9011
No log	2.0851	98	0.9076	0.6172	0.9076	0.9527
No log	2.1277	100	1.0235	0.5980	1.0235	1.0117
No log	2.1702	102	1.1132	0.5983	1.1132	1.0551
No log	2.2128	104	1.1515	0.5797	1.1515	1.0731
No log	2.2553	106	1.0288	0.6048	1.0288	1.0143
No log	2.2979	108	0.9622	0.6381	0.9622	0.9809
No log	2.3404	110	0.9672	0.6275	0.9672	0.9834
No log	2.3830	112	0.9937	0.5773	0.9937	0.9969
No log	2.4255	114	0.9281	0.6079	0.9281	0.9634
No log	2.4681	116	0.8082	0.6790	0.8082	0.8990
No log	2.5106	118	0.7539	0.7066	0.7539	0.8683
No log	2.5532	120	0.7449	0.7228	0.7449	0.8631
No log	2.5957	122	0.8068	0.6743	0.8068	0.8982
No log	2.6383	124	0.9362	0.6427	0.9362	0.9676
No log	2.6809	126	0.9576	0.6128	0.9576	0.9786
No log	2.7234	128	0.9622	0.6033	0.9622	0.9809
No log	2.7660	130	0.8662	0.6350	0.8662	0.9307
No log	2.8085	132	0.7815	0.6459	0.7815	0.8840
No log	2.8511	134	0.7361	0.7072	0.7361	0.8580
No log	2.8936	136	0.7578	0.6811	0.7578	0.8705
No log	2.9362	138	0.8348	0.6637	0.8348	0.9137
No log	2.9787	140	0.9937	0.6496	0.9937	0.9969
No log	3.0213	142	1.0362	0.6519	1.0362	1.0179
No log	3.0638	144	1.0210	0.6460	1.0210	1.0105
No log	3.1064	146	1.0092	0.6460	1.0092	1.0046
No log	3.1489	148	0.9492	0.6821	0.9492	0.9743
No log	3.1915	150	1.0293	0.6696	1.0293	1.0145
No log	3.2340	152	1.1812	0.6307	1.1812	1.0869
No log	3.2766	154	1.3781	0.6052	1.3781	1.1739
No log	3.3191	156	1.4760	0.5965	1.4760	1.2149
No log	3.3617	158	1.4285	0.5931	1.4285	1.1952
No log	3.4043	160	1.2383	0.5987	1.2383	1.1128
No log	3.4468	162	1.0936	0.6093	1.0936	1.0457
No log	3.4894	164	0.9784	0.6410	0.9784	0.9891
No log	3.5319	166	0.8462	0.6630	0.8462	0.9199
No log	3.5745	168	0.7516	0.6973	0.7516	0.8670
No log	3.6170	170	0.7722	0.6870	0.7722	0.8787
No log	3.6596	172	0.8295	0.6521	0.8295	0.9108
No log	3.7021	174	0.8754	0.6181	0.8754	0.9356
No log	3.7447	176	0.9790	0.5983	0.9790	0.9894
No log	3.7872	178	0.9781	0.5960	0.9781	0.9890
No log	3.8298	180	0.9245	0.6166	0.9245	0.9615
No log	3.8723	182	0.8455	0.6471	0.8455	0.9195
No log	3.9149	184	0.8012	0.6497	0.8012	0.8951
No log	3.9574	186	0.8386	0.6616	0.8386	0.9158
No log	4.0	188	0.8742	0.6421	0.8742	0.9350
No log	4.0426	190	1.0119	0.6389	1.0119	1.0059
No log	4.0851	192	1.1769	0.6313	1.1769	1.0849
No log	4.1277	194	1.1754	0.6397	1.1754	1.0841
No log	4.1702	196	1.0923	0.6446	1.0923	1.0451
No log	4.2128	198	1.1083	0.6475	1.1083	1.0528
No log	4.2553	200	1.1726	0.6402	1.1726	1.0829
No log	4.2979	202	1.2526	0.6188	1.2526	1.1192
No log	4.3404	204	1.1944	0.6109	1.1944	1.0929
No log	4.3830	206	1.0734	0.6163	1.0734	1.0360
No log	4.4255	208	0.8849	0.6177	0.8849	0.9407
No log	4.4681	210	0.7553	0.6545	0.7553	0.8691
No log	4.5106	212	0.7300	0.6642	0.7300	0.8544
No log	4.5532	214	0.7499	0.6716	0.7499	0.8660
No log	4.5957	216	0.7918	0.6698	0.7918	0.8899
No log	4.6383	218	0.8652	0.6395	0.8652	0.9301
No log	4.6809	220	0.9297	0.6258	0.9297	0.9642
No log	4.7234	222	0.9368	0.6346	0.9368	0.9679
No log	4.7660	224	0.8864	0.6381	0.8864	0.9415
No log	4.8085	226	0.7974	0.6601	0.7974	0.8930
No log	4.8511	228	0.8036	0.6645	0.8036	0.8964
No log	4.8936	230	0.8341	0.6690	0.8341	0.9133
No log	4.9362	232	0.8711	0.6344	0.8711	0.9333
No log	4.9787	234	0.8551	0.6299	0.8551	0.9247
No log	5.0213	236	0.8355	0.6105	0.8355	0.9140
No log	5.0638	238	0.8661	0.6266	0.8661	0.9307
No log	5.1064	240	0.8499	0.6234	0.8499	0.9219
No log	5.1489	242	0.8201	0.6438	0.8201	0.9056
No log	5.1915	244	0.7784	0.6517	0.7784	0.8823
No log	5.2340	246	0.7669	0.6629	0.7669	0.8757
No log	5.2766	248	0.7856	0.6629	0.7856	0.8863
No log	5.3191	250	0.8500	0.6497	0.8500	0.9219
No log	5.3617	252	0.8694	0.6544	0.8694	0.9324
No log	5.4043	254	0.8548	0.6595	0.8548	0.9246
No log	5.4468	256	0.8559	0.6613	0.8559	0.9252
No log	5.4894	258	0.8309	0.6432	0.8309	0.9115
No log	5.5319	260	0.8378	0.6432	0.8378	0.9153
No log	5.5745	262	0.8065	0.6538	0.8065	0.8980
No log	5.6170	264	0.7571	0.6794	0.7571	0.8701
No log	5.6596	266	0.7187	0.6882	0.7187	0.8478
No log	5.7021	268	0.7162	0.7018	0.7162	0.8463
No log	5.7447	270	0.7217	0.6974	0.7217	0.8495
No log	5.7872	272	0.7805	0.6804	0.7805	0.8835
No log	5.8298	274	0.8416	0.6603	0.8416	0.9174
No log	5.8723	276	0.9267	0.6521	0.9267	0.9627
No log	5.9149	278	0.9359	0.6581	0.9359	0.9674
No log	5.9574	280	0.8795	0.6828	0.8795	0.9378
No log	6.0	282	0.7865	0.6836	0.7865	0.8868
No log	6.0426	284	0.7241	0.7230	0.7241	0.8509
No log	6.0851	286	0.6905	0.7363	0.6905	0.8310
No log	6.1277	288	0.6802	0.7284	0.6802	0.8247
No log	6.1702	290	0.7183	0.6700	0.7183	0.8475
No log	6.2128	292	0.8102	0.6333	0.8102	0.9001
No log	6.2553	294	0.8910	0.6311	0.8910	0.9439
No log	6.2979	296	0.9193	0.6371	0.9193	0.9588
No log	6.3404	298	0.9132	0.6352	0.9132	0.9556
No log	6.3830	300	0.9268	0.6290	0.9268	0.9627
No log	6.4255	302	0.9075	0.6284	0.9075	0.9526
No log	6.4681	304	0.8532	0.6332	0.8532	0.9237
No log	6.5106	306	0.8042	0.6570	0.8042	0.8968
No log	6.5532	308	0.7718	0.6512	0.7718	0.8785
No log	6.5957	310	0.7680	0.6504	0.7680	0.8763
No log	6.6383	312	0.8021	0.6577	0.8021	0.8956
No log	6.6809	314	0.8532	0.6454	0.8532	0.9237
No log	6.7234	316	0.8830	0.6433	0.8830	0.9397
No log	6.7660	318	0.8670	0.6557	0.8670	0.9311
No log	6.8085	320	0.8360	0.6770	0.8360	0.9143
No log	6.8511	322	0.8025	0.6798	0.8025	0.8958
No log	6.8936	324	0.8131	0.6788	0.8131	0.9017
No log	6.9362	326	0.8537	0.6639	0.8537	0.9240
No log	6.9787	328	0.9004	0.6484	0.9004	0.9489
No log	7.0213	330	0.9278	0.6496	0.9278	0.9632
No log	7.0638	332	0.9351	0.6497	0.9351	0.9670
No log	7.1064	334	0.9625	0.6410	0.9625	0.9811
No log	7.1489	336	0.9836	0.6376	0.9836	0.9918
No log	7.1915	338	1.0183	0.6336	1.0183	1.0091
No log	7.2340	340	1.0741	0.6239	1.0741	1.0364
No log	7.2766	342	1.1249	0.6386	1.1249	1.0606
No log	7.3191	344	1.1329	0.6241	1.1329	1.0644
No log	7.3617	346	1.0782	0.6430	1.0782	1.0384
No log	7.4043	348	0.9922	0.6402	0.9922	0.9961
No log	7.4468	350	0.9026	0.6418	0.9026	0.9501
No log	7.4894	352	0.8732	0.6399	0.8732	0.9344
No log	7.5319	354	0.8762	0.6459	0.8762	0.9361
No log	7.5745	356	0.9158	0.6316	0.9158	0.9569
No log	7.6170	358	0.9354	0.6357	0.9354	0.9671
No log	7.6596	360	0.9073	0.6463	0.9073	0.9525
No log	7.7021	362	0.8563	0.6572	0.8563	0.9254
No log	7.7447	364	0.7982	0.6693	0.7982	0.8934
No log	7.7872	366	0.7534	0.6891	0.7534	0.8680
No log	7.8298	368	0.7548	0.6875	0.7548	0.8688
No log	7.8723	370	0.7933	0.6875	0.7933	0.8907
No log	7.9149	372	0.8362	0.6875	0.8362	0.9144
No log	7.9574	374	0.8939	0.6709	0.8939	0.9454
No log	8.0	376	0.9216	0.6574	0.9216	0.9600
No log	8.0426	378	0.9158	0.6652	0.9158	0.9570
No log	8.0851	380	0.9200	0.6637	0.9200	0.9592
No log	8.1277	382	0.9346	0.6599	0.9346	0.9668
No log	8.1702	384	0.9282	0.6599	0.9282	0.9634
No log	8.2128	386	0.9219	0.6520	0.9219	0.9602
No log	8.2553	388	0.9070	0.6445	0.9070	0.9524
No log	8.2979	390	0.8802	0.6538	0.8802	0.9382
No log	8.3404	392	0.8565	0.6697	0.8565	0.9255
No log	8.3830	394	0.8224	0.6720	0.8224	0.9069
No log	8.4255	396	0.7998	0.6678	0.7998	0.8943
No log	8.4681	398	0.7820	0.6801	0.7820	0.8843
No log	8.5106	400	0.7870	0.6768	0.7870	0.8871
No log	8.5532	402	0.7972	0.6678	0.7972	0.8929
No log	8.5957	404	0.8055	0.6768	0.8055	0.8975
No log	8.6383	406	0.8353	0.6445	0.8353	0.9140
No log	8.6809	408	0.8601	0.6445	0.8601	0.9274
No log	8.7234	410	0.8644	0.6466	0.8644	0.9298
No log	8.7660	412	0.8581	0.6466	0.8581	0.9264
No log	8.8085	414	0.8664	0.6466	0.8664	0.9308
No log	8.8511	416	0.8843	0.6371	0.8843	0.9404
No log	8.8936	418	0.9096	0.6343	0.9096	0.9537
No log	8.9362	420	0.9473	0.6277	0.9473	0.9733
No log	8.9787	422	0.9830	0.6277	0.9830	0.9915
No log	9.0213	424	0.9990	0.6237	0.9990	0.9995
No log	9.0638	426	1.0095	0.6237	1.0095	1.0047
No log	9.1064	428	1.0103	0.6237	1.0103	1.0051
No log	9.1489	430	1.0184	0.6237	1.0184	1.0092
No log	9.1915	432	1.0191	0.6264	1.0191	1.0095
No log	9.2340	434	1.0060	0.6304	1.0060	1.0030
No log	9.2766	436	0.9838	0.6337	0.9838	0.9919
No log	9.3191	438	0.9501	0.6376	0.9501	0.9747
No log	9.3617	440	0.9195	0.6397	0.9195	0.9589
No log	9.4043	442	0.8976	0.6404	0.8976	0.9474
No log	9.4468	444	0.8788	0.6552	0.8788	0.9375
No log	9.4894	446	0.8666	0.6552	0.8666	0.9309
No log	9.5319	448	0.8603	0.6552	0.8603	0.9275
No log	9.5745	450	0.8589	0.6552	0.8589	0.9268
No log	9.6170	452	0.8558	0.6495	0.8558	0.9251
No log	9.6596	454	0.8514	0.6580	0.8514	0.9227
No log	9.7021	456	0.8470	0.6595	0.8470	0.9203
No log	9.7447	458	0.8442	0.6595	0.8442	0.9188
No log	9.7872	460	0.8444	0.6595	0.8444	0.9189
No log	9.8298	462	0.8482	0.6580	0.8482	0.9210
No log	9.8723	464	0.8502	0.6580	0.8502	0.9221
No log	9.9149	466	0.8529	0.6580	0.8529	0.9235
No log	9.9574	468	0.8548	0.6580	0.8548	0.9246
No log	10.0	470	0.8558	0.6580	0.8558	0.9251

Framework versions

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