ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k7_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: 0.8684
• Qwk: 0.6412
• Mse: 0.8684
• Rmse: 0.9319

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	0.0488	2	5.1883	-0.0452	5.1883	2.2778
No log	0.0976	4	3.6011	0.0666	3.6011	1.8977
No log	0.1463	6	2.0721	0.1164	2.0721	1.4395
No log	0.1951	8	1.6265	0.0533	1.6265	1.2753
No log	0.2439	10	1.5289	-0.0051	1.5289	1.2365
No log	0.2927	12	1.2304	0.1414	1.2304	1.1092
No log	0.3415	14	1.2100	0.1517	1.2100	1.1000
No log	0.3902	16	1.2530	0.2305	1.2530	1.1194
No log	0.4390	18	1.3693	0.1846	1.3693	1.1702
No log	0.4878	20	1.1382	0.4017	1.1382	1.0669
No log	0.5366	22	1.0129	0.3099	1.0129	1.0064
No log	0.5854	24	1.0771	0.3598	1.0771	1.0378
No log	0.6341	26	0.9456	0.4881	0.9456	0.9724
No log	0.6829	28	0.8675	0.5101	0.8675	0.9314
No log	0.7317	30	1.0667	0.4590	1.0667	1.0328
No log	0.7805	32	1.2966	0.3598	1.2966	1.1387
No log	0.8293	34	1.1022	0.4934	1.1022	1.0498
No log	0.8780	36	0.9170	0.5356	0.9170	0.9576
No log	0.9268	38	0.9424	0.5877	0.9424	0.9708
No log	0.9756	40	0.9169	0.6180	0.9169	0.9576
No log	1.0244	42	0.8249	0.5971	0.8249	0.9082
No log	1.0732	44	0.8188	0.6465	0.8188	0.9049
No log	1.1220	46	0.8243	0.6184	0.8243	0.9079
No log	1.1707	48	0.7949	0.6101	0.7949	0.8916
No log	1.2195	50	0.8723	0.5257	0.8723	0.9340
No log	1.2683	52	1.1197	0.5135	1.1197	1.0581
No log	1.3171	54	1.2852	0.4464	1.2852	1.1337
No log	1.3659	56	1.1028	0.4935	1.1028	1.0501
No log	1.4146	58	0.8008	0.5564	0.8008	0.8949
No log	1.4634	60	0.7526	0.5772	0.7526	0.8675
No log	1.5122	62	0.7496	0.5944	0.7496	0.8658
No log	1.5610	64	0.7299	0.6259	0.7299	0.8544
No log	1.6098	66	0.7198	0.6361	0.7198	0.8484
No log	1.6585	68	0.7643	0.6408	0.7643	0.8742
No log	1.7073	70	0.8157	0.6355	0.8157	0.9032
No log	1.7561	72	0.7621	0.6292	0.7621	0.8730
No log	1.8049	74	0.7412	0.6271	0.7412	0.8609
No log	1.8537	76	0.7525	0.6048	0.7525	0.8675
No log	1.9024	78	0.7267	0.6700	0.7267	0.8525
No log	1.9512	80	0.7659	0.6919	0.7659	0.8752
No log	2.0	82	0.8160	0.6681	0.8160	0.9033
No log	2.0488	84	1.0149	0.5854	1.0149	1.0074
No log	2.0976	86	0.9878	0.6160	0.9878	0.9939
No log	2.1463	88	0.8504	0.6662	0.8504	0.9222
No log	2.1951	90	0.7849	0.7049	0.7849	0.8860
No log	2.2439	92	0.7757	0.6944	0.7757	0.8807
No log	2.2927	94	0.7605	0.6982	0.7605	0.8721
No log	2.3415	96	0.7363	0.7100	0.7363	0.8581
No log	2.3902	98	0.6900	0.7195	0.6900	0.8307
No log	2.4390	100	0.6661	0.7177	0.6661	0.8161
No log	2.4878	102	0.6650	0.7177	0.6650	0.8155
No log	2.5366	104	0.7311	0.7153	0.7311	0.8551
No log	2.5854	106	0.7867	0.7036	0.7867	0.8870
No log	2.6341	108	0.9659	0.6635	0.9659	0.9828
No log	2.6829	110	1.0351	0.5869	1.0351	1.0174
No log	2.7317	112	1.0594	0.5720	1.0594	1.0293
No log	2.7805	114	0.9112	0.6265	0.9112	0.9545
No log	2.8293	116	0.7333	0.7095	0.7333	0.8563
No log	2.8780	118	0.7357	0.7217	0.7357	0.8577
No log	2.9268	120	0.6509	0.7414	0.6509	0.8068
No log	2.9756	122	0.7634	0.7037	0.7634	0.8737
No log	3.0244	124	0.7698	0.7207	0.7698	0.8774
No log	3.0732	126	0.7084	0.7179	0.7084	0.8417
No log	3.1220	128	0.9046	0.6837	0.9046	0.9511
No log	3.1707	130	1.2823	0.5927	1.2823	1.1324
No log	3.2195	132	1.2685	0.5936	1.2685	1.1263
No log	3.2683	134	1.1018	0.6169	1.1018	1.0497
No log	3.3171	136	1.0164	0.5948	1.0164	1.0082
No log	3.3659	138	1.0603	0.5722	1.0603	1.0297
No log	3.4146	140	1.1082	0.5586	1.1082	1.0527
No log	3.4634	142	0.8845	0.6274	0.8845	0.9405
No log	3.5122	144	0.6990	0.7005	0.6990	0.8361
No log	3.5610	146	0.6602	0.7126	0.6602	0.8126
No log	3.6098	148	0.6428	0.7065	0.6428	0.8017
No log	3.6585	150	0.6308	0.7201	0.6308	0.7942
No log	3.7073	152	0.6439	0.7065	0.6439	0.8025
No log	3.7561	154	0.7318	0.6958	0.7318	0.8554
No log	3.8049	156	0.7750	0.6895	0.7750	0.8804
No log	3.8537	158	0.7775	0.6895	0.7775	0.8818
No log	3.9024	160	0.8139	0.6550	0.8139	0.9022
No log	3.9512	162	0.7714	0.6662	0.7714	0.8783
No log	4.0	164	0.7402	0.6864	0.7402	0.8603
No log	4.0488	166	0.6851	0.7084	0.6851	0.8277
No log	4.0976	168	0.6057	0.7380	0.6057	0.7783
No log	4.1463	170	0.6129	0.7328	0.6129	0.7829
No log	4.1951	172	0.6762	0.7250	0.6762	0.8223
No log	4.2439	174	0.9506	0.6703	0.9506	0.9750
No log	4.2927	176	1.0966	0.6479	1.0966	1.0472
No log	4.3415	178	1.0755	0.6485	1.0755	1.0371
No log	4.3902	180	0.9028	0.7068	0.9028	0.9502
No log	4.4390	182	0.8483	0.6944	0.8483	0.9210
No log	4.4878	184	0.9457	0.6339	0.9457	0.9725
No log	4.5366	186	1.1747	0.5661	1.1747	1.0839
No log	4.5854	188	1.3973	0.5430	1.3973	1.1821
No log	4.6341	190	1.3572	0.5531	1.3572	1.1650
No log	4.6829	192	1.0513	0.6217	1.0513	1.0253
No log	4.7317	194	0.7952	0.6849	0.7952	0.8917
No log	4.7805	196	0.7028	0.6831	0.7028	0.8383
No log	4.8293	198	0.7666	0.6910	0.7666	0.8756
No log	4.8780	200	0.8769	0.6246	0.8769	0.9364
No log	4.9268	202	1.1601	0.5684	1.1601	1.0771
No log	4.9756	204	1.2871	0.5447	1.2871	1.1345
No log	5.0244	206	1.1916	0.5836	1.1916	1.0916
No log	5.0732	208	0.9202	0.6577	0.9202	0.9593
No log	5.1220	210	0.6904	0.7214	0.6904	0.8309
No log	5.1707	212	0.6464	0.7246	0.6464	0.8040
No log	5.2195	214	0.6522	0.7256	0.6522	0.8076
No log	5.2683	216	0.6860	0.7300	0.6860	0.8282
No log	5.3171	218	0.8043	0.6922	0.8043	0.8968
No log	5.3659	220	1.0434	0.6537	1.0434	1.0215
No log	5.4146	222	1.1560	0.6189	1.1560	1.0752
No log	5.4634	224	1.0517	0.6124	1.0517	1.0255
No log	5.5122	226	0.8937	0.6612	0.8937	0.9453
No log	5.5610	228	0.7939	0.6687	0.7939	0.8910
No log	5.6098	230	0.7977	0.6703	0.7977	0.8931
No log	5.6585	232	0.9097	0.6353	0.9097	0.9538
No log	5.7073	234	1.0548	0.6021	1.0548	1.0270
No log	5.7561	236	1.1866	0.6259	1.1866	1.0893
No log	5.8049	238	1.2006	0.6349	1.2006	1.0957
No log	5.8537	240	1.0786	0.6344	1.0786	1.0385
No log	5.9024	242	0.9775	0.6406	0.9775	0.9887
No log	5.9512	244	0.9773	0.6419	0.9773	0.9886
No log	6.0	246	0.9203	0.6500	0.9203	0.9593
No log	6.0488	248	0.8244	0.6849	0.8244	0.9079
No log	6.0976	250	0.7159	0.7201	0.7159	0.8461
No log	6.1463	252	0.6547	0.7247	0.6547	0.8091
No log	6.1951	254	0.6598	0.7305	0.6598	0.8123
No log	6.2439	256	0.7357	0.6968	0.7357	0.8577
No log	6.2927	258	0.9041	0.6520	0.9041	0.9508
No log	6.3415	260	1.0060	0.6058	1.0060	1.0030
No log	6.3902	262	0.9916	0.5971	0.9916	0.9958
No log	6.4390	264	0.9912	0.5945	0.9912	0.9956
No log	6.4878	266	0.9122	0.6306	0.9122	0.9551
No log	6.5366	268	0.8955	0.6417	0.8955	0.9463
No log	6.5854	270	0.9568	0.6459	0.9568	0.9782
No log	6.6341	272	1.0852	0.6207	1.0852	1.0417
No log	6.6829	274	1.1594	0.6249	1.1594	1.0768
No log	6.7317	276	1.1464	0.6249	1.1464	1.0707
No log	6.7805	278	0.9841	0.6569	0.9841	0.9920
No log	6.8293	280	0.7804	0.6809	0.7804	0.8834
No log	6.8780	282	0.7133	0.7066	0.7133	0.8446
No log	6.9268	284	0.7178	0.7066	0.7178	0.8473
No log	6.9756	286	0.7486	0.7033	0.7486	0.8652
No log	7.0244	288	0.7910	0.6800	0.7910	0.8894
No log	7.0732	290	0.8134	0.6719	0.8134	0.9019
No log	7.1220	292	0.9044	0.6331	0.9044	0.9510
No log	7.1707	294	1.0574	0.6116	1.0574	1.0283
No log	7.2195	296	1.1811	0.5947	1.1811	1.0868
No log	7.2683	298	1.1494	0.6076	1.1494	1.0721
No log	7.3171	300	1.0238	0.6043	1.0238	1.0118
No log	7.3659	302	0.9029	0.6164	0.9029	0.9502
No log	7.4146	304	0.7729	0.6943	0.7729	0.8792
No log	7.4634	306	0.7093	0.7234	0.7093	0.8422
No log	7.5122	308	0.6954	0.7155	0.6954	0.8339
No log	7.5610	310	0.6989	0.7127	0.6989	0.8360
No log	7.6098	312	0.7331	0.7018	0.7331	0.8562
No log	7.6585	314	0.7645	0.6683	0.7645	0.8743
No log	7.7073	316	0.8340	0.6590	0.8340	0.9132
No log	7.7561	318	0.8674	0.6104	0.8674	0.9313
No log	7.8049	320	0.8589	0.6124	0.8589	0.9267
No log	7.8537	322	0.8287	0.6503	0.8287	0.9103
No log	7.9024	324	0.7813	0.6634	0.7813	0.8839
No log	7.9512	326	0.7294	0.6685	0.7294	0.8540
No log	8.0	328	0.6976	0.6832	0.6976	0.8352
No log	8.0488	330	0.6818	0.7010	0.6818	0.8257
No log	8.0976	332	0.6937	0.6894	0.6937	0.8329
No log	8.1463	334	0.7281	0.6683	0.7281	0.8533
No log	8.1951	336	0.7936	0.6796	0.7936	0.8909
No log	8.2439	338	0.8936	0.6470	0.8936	0.9453
No log	8.2927	340	1.0078	0.6297	1.0078	1.0039
No log	8.3415	342	1.0394	0.6037	1.0394	1.0195
No log	8.3902	344	1.0149	0.6116	1.0149	1.0074
No log	8.4390	346	0.9550	0.6153	0.9550	0.9772
No log	8.4878	348	0.8976	0.6128	0.8976	0.9474
No log	8.5366	350	0.8524	0.6318	0.8524	0.9232
No log	8.5854	352	0.8199	0.6346	0.8199	0.9055
No log	8.6341	354	0.8098	0.6513	0.8098	0.8999
No log	8.6829	356	0.8264	0.6408	0.8264	0.9091
No log	8.7317	358	0.8665	0.6379	0.8665	0.9309
No log	8.7805	360	0.9226	0.6258	0.9226	0.9605
No log	8.8293	362	0.9761	0.6091	0.9761	0.9880
No log	8.8780	364	1.0164	0.6096	1.0164	1.0082
No log	8.9268	366	1.0234	0.6096	1.0234	1.0116
No log	8.9756	368	1.0116	0.6096	1.0116	1.0058
No log	9.0244	370	1.0052	0.6096	1.0052	1.0026
No log	9.0732	372	0.9696	0.6144	0.9696	0.9847
No log	9.1220	374	0.9462	0.6371	0.9462	0.9727
No log	9.1707	376	0.9269	0.6371	0.9269	0.9627
No log	9.2195	378	0.9261	0.6371	0.9261	0.9624
No log	9.2683	380	0.9315	0.6358	0.9315	0.9651
No log	9.3171	382	0.9300	0.6358	0.9300	0.9644
No log	9.3659	384	0.9252	0.6358	0.9252	0.9619
No log	9.4146	386	0.9067	0.6412	0.9067	0.9522
No log	9.4634	388	0.8978	0.6412	0.8978	0.9475
No log	9.5122	390	0.8938	0.6412	0.8938	0.9454
No log	9.5610	392	0.8935	0.6412	0.8935	0.9453
No log	9.6098	394	0.8922	0.6412	0.8922	0.9445
No log	9.6585	396	0.8845	0.6412	0.8845	0.9405
No log	9.7073	398	0.8751	0.6412	0.8751	0.9355
No log	9.7561	400	0.8683	0.6412	0.8683	0.9318
No log	9.8049	402	0.8651	0.6412	0.8651	0.9301
No log	9.8537	404	0.8661	0.6412	0.8661	0.9306
No log	9.9024	406	0.8671	0.6412	0.8671	0.9312
No log	9.9512	408	0.8685	0.6412	0.8685	0.9319
No log	10.0	410	0.8684	0.6412	0.8684	0.9319

Framework versions

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