ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k10_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: 0.9066
• Qwk: 0.6938
• Mse: 0.9066
• Rmse: 0.9522

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	0.0417	2	2.2703	0.0081	2.2703	1.5068
No log	0.0833	4	1.5616	0.1720	1.5616	1.2497
No log	0.125	6	1.3879	0.2376	1.3879	1.1781
No log	0.1667	8	1.3112	0.2123	1.3112	1.1451
No log	0.2083	10	1.3398	0.2139	1.3398	1.1575
No log	0.25	12	1.4467	0.2527	1.4467	1.2028
No log	0.2917	14	1.5851	0.1200	1.5851	1.2590
No log	0.3333	16	1.7170	0.0442	1.7170	1.3104
No log	0.375	18	1.7910	0.0060	1.7910	1.3383
No log	0.4167	20	1.4769	0.1666	1.4769	1.2153
No log	0.4583	22	1.3304	0.2165	1.3304	1.1534
No log	0.5	24	1.4489	0.3739	1.4489	1.2037
No log	0.5417	26	1.3007	0.2225	1.3007	1.1405
No log	0.5833	28	1.1619	0.3115	1.1619	1.0779
No log	0.625	30	1.1436	0.3291	1.1436	1.0694
No log	0.6667	32	1.1304	0.3912	1.1304	1.0632
No log	0.7083	34	1.1186	0.4033	1.1186	1.0576
No log	0.75	36	1.0828	0.4230	1.0828	1.0406
No log	0.7917	38	1.0550	0.4650	1.0550	1.0271
No log	0.8333	40	1.0306	0.4732	1.0306	1.0152
No log	0.875	42	1.0009	0.4971	1.0009	1.0005
No log	0.9167	44	0.9848	0.5155	0.9848	0.9923
No log	0.9583	46	0.9664	0.4875	0.9664	0.9831
No log	1.0	48	1.0324	0.5266	1.0324	1.0161
No log	1.0417	50	1.1485	0.4809	1.1485	1.0717
No log	1.0833	52	1.1543	0.4664	1.1543	1.0744
No log	1.125	54	1.1153	0.4716	1.1153	1.0561
No log	1.1667	56	1.0038	0.5041	1.0038	1.0019
No log	1.2083	58	0.9263	0.5192	0.9263	0.9624
No log	1.25	60	0.9615	0.5059	0.9615	0.9806
No log	1.2917	62	0.9143	0.5664	0.9143	0.9562
No log	1.3333	64	0.9445	0.5295	0.9445	0.9719
No log	1.375	66	1.0287	0.5427	1.0287	1.0143
No log	1.4167	68	0.9394	0.5162	0.9394	0.9692
No log	1.4583	70	0.8959	0.5790	0.8959	0.9465
No log	1.5	72	0.8865	0.6083	0.8865	0.9416
No log	1.5417	74	0.8816	0.5817	0.8816	0.9390
No log	1.5833	76	0.9661	0.5053	0.9661	0.9829
No log	1.625	78	0.9640	0.5229	0.9640	0.9818
No log	1.6667	80	0.8579	0.5817	0.8579	0.9262
No log	1.7083	82	1.0566	0.5954	1.0566	1.0279
No log	1.75	84	1.3365	0.4823	1.3365	1.1561
No log	1.7917	86	1.1676	0.5322	1.1676	1.0806
No log	1.8333	88	0.8767	0.5433	0.8767	0.9363
No log	1.875	90	0.9412	0.5189	0.9412	0.9701
No log	1.9167	92	0.9573	0.5028	0.9573	0.9784
No log	1.9583	94	0.8625	0.5714	0.8625	0.9287
No log	2.0	96	0.8840	0.5656	0.8840	0.9402
No log	2.0417	98	1.0551	0.6177	1.0551	1.0272
No log	2.0833	100	1.0963	0.6041	1.0963	1.0471
No log	2.125	102	0.9190	0.6445	0.9190	0.9586
No log	2.1667	104	0.7907	0.6394	0.7907	0.8892
No log	2.2083	106	0.7909	0.6763	0.7909	0.8893
No log	2.25	108	0.9917	0.6374	0.9917	0.9958
No log	2.2917	110	1.2299	0.5865	1.2299	1.1090
No log	2.3333	112	1.1823	0.6145	1.1823	1.0873
No log	2.375	114	0.9382	0.6685	0.9382	0.9686
No log	2.4167	116	0.7388	0.6605	0.7388	0.8595
No log	2.4583	118	0.7341	0.6614	0.7341	0.8568
No log	2.5	120	0.8454	0.6451	0.8454	0.9195
No log	2.5417	122	1.0259	0.6440	1.0259	1.0129
No log	2.5833	124	1.3283	0.5745	1.3283	1.1525
No log	2.625	126	1.4860	0.4949	1.4860	1.2190
No log	2.6667	128	1.3136	0.5704	1.3136	1.1461
No log	2.7083	130	0.8845	0.6679	0.8845	0.9405
No log	2.75	132	0.6894	0.6754	0.6894	0.8303
No log	2.7917	134	0.6833	0.6497	0.6833	0.8266
No log	2.8333	136	0.7641	0.6482	0.7641	0.8741
No log	2.875	138	1.1395	0.5821	1.1395	1.0675
No log	2.9167	140	1.5976	0.4861	1.5976	1.2639
No log	2.9583	142	1.6780	0.4857	1.6780	1.2954
No log	3.0	144	1.4274	0.4999	1.4274	1.1947
No log	3.0417	146	1.0403	0.6207	1.0403	1.0199
No log	3.0833	148	0.7585	0.6378	0.7585	0.8709
No log	3.125	150	0.7455	0.6540	0.7455	0.8634
No log	3.1667	152	0.8011	0.6276	0.8011	0.8950
No log	3.2083	154	1.0303	0.6353	1.0303	1.0150
No log	3.25	156	1.3325	0.5307	1.3325	1.1543
No log	3.2917	158	1.3499	0.4971	1.3499	1.1618
No log	3.3333	160	1.1709	0.5602	1.1709	1.0821
No log	3.375	162	0.8959	0.6434	0.8959	0.9465
No log	3.4167	164	0.7815	0.6089	0.7815	0.8840
No log	3.4583	166	0.7716	0.6326	0.7716	0.8784
No log	3.5	168	0.7912	0.6195	0.7912	0.8895
No log	3.5417	170	0.8722	0.6424	0.8722	0.9339
No log	3.5833	172	0.9521	0.6616	0.9521	0.9758
No log	3.625	174	1.0655	0.6335	1.0655	1.0322
No log	3.6667	176	1.1863	0.5775	1.1863	1.0892
No log	3.7083	178	1.2788	0.5765	1.2788	1.1308
No log	3.75	180	1.1235	0.5915	1.1235	1.0599
No log	3.7917	182	0.9206	0.6953	0.9206	0.9595
No log	3.8333	184	0.7858	0.6638	0.7858	0.8864
No log	3.875	186	0.7984	0.6584	0.7984	0.8936
No log	3.9167	188	0.8730	0.6907	0.8730	0.9343
No log	3.9583	190	0.9510	0.6723	0.9510	0.9752
No log	4.0	192	1.0290	0.6271	1.0290	1.0144
No log	4.0417	194	0.9955	0.6508	0.9955	0.9977
No log	4.0833	196	0.9097	0.6795	0.9097	0.9538
No log	4.125	198	0.8775	0.6732	0.8775	0.9368
No log	4.1667	200	0.8509	0.6865	0.8509	0.9224
No log	4.2083	202	0.8314	0.6694	0.8314	0.9118
No log	4.25	204	0.9338	0.6696	0.9338	0.9663
No log	4.2917	206	1.0840	0.6159	1.0840	1.0411
No log	4.3333	208	1.0525	0.6097	1.0525	1.0259
No log	4.375	210	0.9074	0.6466	0.9074	0.9525
No log	4.4167	212	0.7841	0.6602	0.7841	0.8855
No log	4.4583	214	0.7266	0.6302	0.7266	0.8524
No log	4.5	216	0.7555	0.6653	0.7555	0.8692
No log	4.5417	218	0.8895	0.6769	0.8895	0.9431
No log	4.5833	220	1.0728	0.6064	1.0728	1.0358
No log	4.625	222	1.0542	0.6064	1.0542	1.0267
No log	4.6667	224	1.0201	0.6461	1.0201	1.0100
No log	4.7083	226	0.9886	0.6461	0.9886	0.9943
No log	4.75	228	0.9261	0.6524	0.9261	0.9624
No log	4.7917	230	0.9330	0.6469	0.9330	0.9659
No log	4.8333	232	0.9844	0.6289	0.9844	0.9922
No log	4.875	234	1.0500	0.5991	1.0500	1.0247
No log	4.9167	236	0.9982	0.6220	0.9982	0.9991
No log	4.9583	238	0.8733	0.6924	0.8733	0.9345
No log	5.0	240	0.8594	0.6832	0.8594	0.9270
No log	5.0417	242	0.8739	0.6894	0.8739	0.9348
No log	5.0833	244	0.8819	0.6984	0.8819	0.9391
No log	5.125	246	0.8493	0.6984	0.8493	0.9216
No log	5.1667	248	0.8200	0.7060	0.8200	0.9056
No log	5.2083	250	0.8479	0.7079	0.8479	0.9208
No log	5.25	252	0.9768	0.6533	0.9768	0.9883
No log	5.2917	254	1.0070	0.6410	1.0070	1.0035
No log	5.3333	256	1.0215	0.6476	1.0215	1.0107
No log	5.375	258	0.9150	0.6655	0.9150	0.9566
No log	5.4167	260	0.7832	0.7073	0.7832	0.8850
No log	5.4583	262	0.8208	0.7201	0.8208	0.9060
No log	5.5	264	0.9212	0.6648	0.9212	0.9598
No log	5.5417	266	1.1330	0.6004	1.1330	1.0644
No log	5.5833	268	1.2364	0.5672	1.2364	1.1120
No log	5.625	270	1.1397	0.5941	1.1397	1.0676
No log	5.6667	272	0.9388	0.7080	0.9388	0.9689
No log	5.7083	274	0.8262	0.6995	0.8262	0.9090
No log	5.75	276	0.8059	0.7086	0.8059	0.8977
No log	5.7917	278	0.8437	0.6976	0.8437	0.9185
No log	5.8333	280	0.9478	0.6914	0.9478	0.9736
No log	5.875	282	1.0022	0.6503	1.0022	1.0011
No log	5.9167	284	0.9191	0.6879	0.9191	0.9587
No log	5.9583	286	0.8389	0.6882	0.8389	0.9159
No log	6.0	288	0.8280	0.6844	0.8280	0.9099
No log	6.0417	290	0.7967	0.6984	0.7967	0.8926
No log	6.0833	292	0.8190	0.7093	0.8190	0.9050
No log	6.125	294	0.9241	0.6773	0.9241	0.9613
No log	6.1667	296	1.0325	0.6429	1.0325	1.0161
No log	6.2083	298	1.1626	0.5999	1.1626	1.0782
No log	6.25	300	1.1446	0.6058	1.1446	1.0699
No log	6.2917	302	1.0233	0.6506	1.0233	1.0116
No log	6.3333	304	0.8603	0.7007	0.8603	0.9275
No log	6.375	306	0.7344	0.6930	0.7344	0.8569
No log	6.4167	308	0.6994	0.6498	0.6994	0.8363
No log	6.4583	310	0.7077	0.6456	0.7077	0.8412
No log	6.5	312	0.7478	0.6665	0.7478	0.8648
No log	6.5417	314	0.8376	0.6887	0.8376	0.9152
No log	6.5833	316	0.9465	0.6654	0.9465	0.9729
No log	6.625	318	0.9858	0.6242	0.9858	0.9929
No log	6.6667	320	0.9780	0.6630	0.9780	0.9889
No log	6.7083	322	0.9142	0.6950	0.9142	0.9562
No log	6.75	324	0.8224	0.7181	0.8224	0.9069
No log	6.7917	326	0.8313	0.7107	0.8313	0.9118
No log	6.8333	328	0.8909	0.6926	0.8909	0.9439
No log	6.875	330	0.9544	0.6901	0.9544	0.9769
No log	6.9167	332	0.9649	0.6743	0.9649	0.9823
No log	6.9583	334	0.9696	0.6743	0.9696	0.9847
No log	7.0	336	0.9064	0.6981	0.9064	0.9520
No log	7.0417	338	0.8616	0.6976	0.8616	0.9282
No log	7.0833	340	0.7952	0.7101	0.7952	0.8918
No log	7.125	342	0.8006	0.7101	0.8006	0.8948
No log	7.1667	344	0.8669	0.6894	0.8669	0.9311
No log	7.2083	346	0.9291	0.6903	0.9291	0.9639
No log	7.25	348	0.9156	0.6903	0.9156	0.9569
No log	7.2917	350	0.8259	0.7246	0.8259	0.9088
No log	7.3333	352	0.7789	0.7317	0.7789	0.8826
No log	7.375	354	0.7500	0.7228	0.7500	0.8661
No log	7.4167	356	0.7480	0.7265	0.7480	0.8649
No log	7.4583	358	0.7666	0.7281	0.7666	0.8756
No log	7.5	360	0.7811	0.7083	0.7811	0.8838
No log	7.5417	362	0.8322	0.7136	0.8322	0.9123
No log	7.5833	364	0.8978	0.7123	0.8978	0.9475
No log	7.625	366	0.9581	0.6472	0.9581	0.9788
No log	7.6667	368	0.9562	0.6758	0.9562	0.9778
No log	7.7083	370	0.9663	0.6689	0.9663	0.9830
No log	7.75	372	0.9317	0.6973	0.9317	0.9653
No log	7.7917	374	0.8704	0.7154	0.8704	0.9329
No log	7.8333	376	0.8378	0.7138	0.8378	0.9153
No log	7.875	378	0.8116	0.7102	0.8116	0.9009
No log	7.9167	380	0.8236	0.7102	0.8236	0.9075
No log	7.9583	382	0.8317	0.7102	0.8317	0.9120
No log	8.0	384	0.8312	0.7102	0.8312	0.9117
No log	8.0417	386	0.8338	0.7102	0.8338	0.9131
No log	8.0833	388	0.8799	0.7071	0.8799	0.9381
No log	8.125	390	0.9395	0.6969	0.9395	0.9693
No log	8.1667	392	0.9822	0.6196	0.9822	0.9911
No log	8.2083	394	0.9945	0.6196	0.9945	0.9973
No log	8.25	396	0.9661	0.6479	0.9661	0.9829
No log	8.2917	398	0.9768	0.6479	0.9768	0.9883
No log	8.3333	400	0.9906	0.6383	0.9906	0.9953
No log	8.375	402	0.9696	0.6705	0.9696	0.9847
No log	8.4167	404	0.9576	0.6746	0.9576	0.9786
No log	8.4583	406	0.9559	0.6839	0.9559	0.9777
No log	8.5	408	0.9622	0.6839	0.9622	0.9809
No log	8.5417	410	0.9446	0.6839	0.9446	0.9719
No log	8.5833	412	0.9242	0.7004	0.9242	0.9613
No log	8.625	414	0.9323	0.7004	0.9323	0.9655
No log	8.6667	416	0.9575	0.6434	0.9575	0.9785
No log	8.7083	418	0.9761	0.6391	0.9761	0.9880
No log	8.75	420	0.9831	0.6271	0.9831	0.9915
No log	8.7917	422	0.9733	0.6271	0.9733	0.9866
No log	8.8333	424	0.9747	0.6271	0.9747	0.9873
No log	8.875	426	0.9969	0.6271	0.9969	0.9985
No log	8.9167	428	1.0280	0.6125	1.0280	1.0139
No log	8.9583	430	1.0383	0.6128	1.0383	1.0190
No log	9.0	432	1.0311	0.6230	1.0311	1.0154
No log	9.0417	434	1.0167	0.6215	1.0167	1.0083
No log	9.0833	436	1.0009	0.6152	1.0009	1.0005
No log	9.125	438	0.9773	0.6441	0.9773	0.9886
No log	9.1667	440	0.9503	0.6775	0.9503	0.9748
No log	9.2083	442	0.9147	0.6938	0.9147	0.9564
No log	9.25	444	0.8798	0.7048	0.8798	0.9380
No log	9.2917	446	0.8524	0.7076	0.8524	0.9233
No log	9.3333	448	0.8379	0.7076	0.8379	0.9153
No log	9.375	450	0.8225	0.7076	0.8225	0.9069
No log	9.4167	452	0.8117	0.7072	0.8117	0.9009
No log	9.4583	454	0.8080	0.7072	0.8080	0.8989
No log	9.5	456	0.8146	0.7076	0.8146	0.9025
No log	9.5417	458	0.8296	0.7076	0.8296	0.9108
No log	9.5833	460	0.8472	0.7055	0.8472	0.9205
No log	9.625	462	0.8632	0.7138	0.8632	0.9291
No log	9.6667	464	0.8794	0.7078	0.8794	0.9377
No log	9.7083	466	0.8928	0.7035	0.8928	0.9449
No log	9.75	468	0.9034	0.7035	0.9034	0.9505
No log	9.7917	470	0.9070	0.6938	0.9070	0.9524
No log	9.8333	472	0.9095	0.6938	0.9095	0.9537
No log	9.875	474	0.9109	0.6938	0.9109	0.9544
No log	9.9167	476	0.9095	0.6938	0.9095	0.9537
No log	9.9583	478	0.9077	0.6938	0.9077	0.9528
No log	10.0	480	0.9066	0.6938	0.9066	0.9522

Framework versions

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