ArabicNewSplits6_WithDuplicationsForScore5_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: 0.7872
• Qwk: 0.7164
• Mse: 0.7872
• Rmse: 0.8872

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	2.3471	-0.0077	2.3471	1.5320
No log	0.0976	4	1.5460	0.1697	1.5460	1.2434
No log	0.1463	6	1.6659	0.0837	1.6659	1.2907
No log	0.1951	8	1.5174	0.1828	1.5174	1.2318
No log	0.2439	10	1.5946	0.2481	1.5946	1.2628
No log	0.2927	12	1.7378	0.3066	1.7378	1.3182
No log	0.3415	14	1.5671	0.2493	1.5671	1.2518
No log	0.3902	16	1.4131	0.3257	1.4131	1.1887
No log	0.4390	18	1.2588	0.3554	1.2588	1.1220
No log	0.4878	20	1.3462	0.3712	1.3462	1.1603
No log	0.5366	22	1.4670	0.3038	1.4670	1.2112
No log	0.5854	24	1.4838	0.1544	1.4838	1.2181
No log	0.6341	26	1.4578	0.1022	1.4578	1.2074
No log	0.6829	28	1.4234	0.1308	1.4234	1.1931
No log	0.7317	30	1.3935	0.2266	1.3935	1.1805
No log	0.7805	32	1.3765	0.3018	1.3765	1.1732
No log	0.8293	34	1.3476	0.2506	1.3476	1.1609
No log	0.8780	36	1.3505	0.2389	1.3505	1.1621
No log	0.9268	38	1.3495	0.2389	1.3495	1.1617
No log	0.9756	40	1.3400	0.2808	1.3400	1.1576
No log	1.0244	42	1.2871	0.3171	1.2871	1.1345
No log	1.0732	44	1.2419	0.3443	1.2419	1.1144
No log	1.1220	46	1.1667	0.3632	1.1667	1.0802
No log	1.1707	48	1.1174	0.4527	1.1174	1.0571
No log	1.2195	50	1.1984	0.3428	1.1984	1.0947
No log	1.2683	52	1.1482	0.3680	1.1482	1.0715
No log	1.3171	54	1.0296	0.4706	1.0296	1.0147
No log	1.3659	56	1.1559	0.4297	1.1559	1.0751
No log	1.4146	58	1.2101	0.4587	1.2101	1.1001
No log	1.4634	60	1.0697	0.4470	1.0697	1.0343
No log	1.5122	62	1.0006	0.4401	1.0006	1.0003
No log	1.5610	64	0.9764	0.4732	0.9764	0.9881
No log	1.6098	66	0.9416	0.5166	0.9416	0.9704
No log	1.6585	68	1.0733	0.5315	1.0733	1.0360
No log	1.7073	70	1.4775	0.4594	1.4775	1.2155
No log	1.7561	72	1.6305	0.4265	1.6305	1.2769
No log	1.8049	74	1.2845	0.5291	1.2845	1.1334
No log	1.8537	76	0.9413	0.5469	0.9413	0.9702
No log	1.9024	78	0.8444	0.6042	0.8444	0.9189
No log	1.9512	80	0.8971	0.6083	0.8971	0.9472
No log	2.0	82	0.7647	0.5803	0.7647	0.8744
No log	2.0488	84	0.9929	0.5722	0.9929	0.9965
No log	2.0976	86	1.2560	0.5563	1.2560	1.1207
No log	2.1463	88	1.1605	0.5482	1.1605	1.0773
No log	2.1951	90	1.0385	0.5833	1.0385	1.0190
No log	2.2439	92	1.0589	0.5994	1.0589	1.0290
No log	2.2927	94	1.0328	0.6162	1.0328	1.0163
No log	2.3415	96	0.9887	0.6394	0.9887	0.9943
No log	2.3902	98	1.1963	0.5935	1.1963	1.0938
No log	2.4390	100	1.2541	0.5986	1.2541	1.1199
No log	2.4878	102	1.1535	0.6292	1.1535	1.0740
No log	2.5366	104	0.8485	0.6853	0.8485	0.9211
No log	2.5854	106	0.7604	0.6904	0.7604	0.8720
No log	2.6341	108	0.8353	0.6734	0.8353	0.9139
No log	2.6829	110	0.9564	0.6479	0.9564	0.9780
No log	2.7317	112	1.2874	0.5705	1.2874	1.1347
No log	2.7805	114	1.3898	0.5145	1.3898	1.1789
No log	2.8293	116	1.1320	0.5671	1.1320	1.0640
No log	2.8780	118	0.8801	0.6755	0.8801	0.9382
No log	2.9268	120	0.7917	0.7103	0.7917	0.8898
No log	2.9756	122	0.7987	0.7112	0.7987	0.8937
No log	3.0244	124	0.7622	0.7009	0.7622	0.8731
No log	3.0732	126	0.8465	0.7075	0.8465	0.9200
No log	3.1220	128	0.9488	0.6622	0.9488	0.9740
No log	3.1707	130	1.1294	0.6324	1.1294	1.0627
No log	3.2195	132	1.2860	0.5870	1.2860	1.1340
No log	3.2683	134	1.2583	0.5939	1.2583	1.1217
No log	3.3171	136	0.9716	0.6492	0.9716	0.9857
No log	3.3659	138	0.8081	0.6686	0.8081	0.8989
No log	3.4146	140	0.8025	0.6725	0.8025	0.8958
No log	3.4634	142	0.9142	0.6353	0.9142	0.9561
No log	3.5122	144	1.0670	0.5905	1.0670	1.0330
No log	3.5610	146	1.2446	0.5617	1.2446	1.1156
No log	3.6098	148	1.2706	0.5874	1.2706	1.1272
No log	3.6585	150	1.1227	0.6337	1.1227	1.0596
No log	3.7073	152	0.9176	0.7008	0.9176	0.9579
No log	3.7561	154	0.9210	0.7004	0.9210	0.9597
No log	3.8049	156	1.1021	0.6449	1.1021	1.0498
No log	3.8537	158	1.1717	0.6218	1.1717	1.0824
No log	3.9024	160	1.0645	0.6362	1.0645	1.0317
No log	3.9512	162	0.9508	0.6944	0.9508	0.9751
No log	4.0	164	0.7756	0.6944	0.7756	0.8807
No log	4.0488	166	0.7483	0.7047	0.7483	0.8650
No log	4.0976	168	0.8543	0.6809	0.8543	0.9243
No log	4.1463	170	1.1017	0.5695	1.1017	1.0496
No log	4.1951	172	1.1829	0.5685	1.1829	1.0876
No log	4.2439	174	1.0381	0.5918	1.0381	1.0189
No log	4.2927	176	0.8636	0.6957	0.8636	0.9293
No log	4.3415	178	0.8332	0.6803	0.8332	0.9128
No log	4.3902	180	0.8224	0.6859	0.8224	0.9068
No log	4.4390	182	0.9731	0.6634	0.9731	0.9865
No log	4.4878	184	1.0650	0.6193	1.0650	1.0320
No log	4.5366	186	0.9770	0.6534	0.9770	0.9884
No log	4.5854	188	0.8511	0.6679	0.8511	0.9225
No log	4.6341	190	0.8472	0.6771	0.8472	0.9204
No log	4.6829	192	0.8924	0.6467	0.8924	0.9447
No log	4.7317	194	0.9654	0.6420	0.9654	0.9825
No log	4.7805	196	1.1852	0.5777	1.1852	1.0887
No log	4.8293	198	1.2942	0.5815	1.2942	1.1376
No log	4.8780	200	1.1638	0.5767	1.1638	1.0788
No log	4.9268	202	0.9739	0.6608	0.9739	0.9868
No log	4.9756	204	0.8586	0.6672	0.8586	0.9266
No log	5.0244	206	0.8835	0.6722	0.8835	0.9399
No log	5.0732	208	0.9273	0.6689	0.9273	0.9629
No log	5.1220	210	0.8988	0.6521	0.8988	0.9480
No log	5.1707	212	0.8890	0.6639	0.8890	0.9429
No log	5.2195	214	0.8681	0.6825	0.8681	0.9317
No log	5.2683	216	0.8348	0.6801	0.8348	0.9137
No log	5.3171	218	0.8592	0.6592	0.8592	0.9269
No log	5.3659	220	0.9538	0.6545	0.9538	0.9766
No log	5.4146	222	1.0308	0.6333	1.0308	1.0153
No log	5.4634	224	1.0490	0.6291	1.0490	1.0242
No log	5.5122	226	0.9466	0.6537	0.9466	0.9729
No log	5.5610	228	0.8910	0.6758	0.8910	0.9439
No log	5.6098	230	0.8909	0.6689	0.8909	0.9439
No log	5.6585	232	0.9596	0.6374	0.9596	0.9796
No log	5.7073	234	0.9817	0.6245	0.9817	0.9908
No log	5.7561	236	0.9783	0.6340	0.9783	0.9891
No log	5.8049	238	1.0144	0.6326	1.0144	1.0072
No log	5.8537	240	0.9302	0.6598	0.9302	0.9645
No log	5.9024	242	0.9019	0.6898	0.9019	0.9497
No log	5.9512	244	0.9131	0.6680	0.9131	0.9556
No log	6.0	246	0.9062	0.6680	0.9062	0.9519
No log	6.0488	248	0.9406	0.6721	0.9406	0.9698
No log	6.0976	250	0.9235	0.6721	0.9235	0.9610
No log	6.1463	252	0.8749	0.6730	0.8749	0.9354
No log	6.1951	254	0.8792	0.6689	0.8792	0.9377
No log	6.2439	256	0.9375	0.6469	0.9375	0.9682
No log	6.2927	258	0.9466	0.6439	0.9466	0.9729
No log	6.3415	260	1.0086	0.6439	1.0086	1.0043
No log	6.3902	262	1.0174	0.6339	1.0174	1.0087
No log	6.4390	264	0.9305	0.6592	0.9305	0.9646
No log	6.4878	266	0.8046	0.6950	0.8046	0.8970
No log	6.5366	268	0.7426	0.7204	0.7426	0.8617
No log	6.5854	270	0.7535	0.7145	0.7535	0.8680
No log	6.6341	272	0.8469	0.6788	0.8469	0.9203
No log	6.6829	274	0.9471	0.6761	0.9471	0.9732
No log	6.7317	276	0.9834	0.6540	0.9834	0.9917
No log	6.7805	278	0.9386	0.6626	0.9386	0.9688
No log	6.8293	280	0.8417	0.6996	0.8417	0.9174
No log	6.8780	282	0.8138	0.7227	0.8138	0.9021
No log	6.9268	284	0.8132	0.7227	0.8132	0.9018
No log	6.9756	286	0.7884	0.7275	0.7884	0.8879
No log	7.0244	288	0.7572	0.7261	0.7572	0.8702
No log	7.0732	290	0.7649	0.7309	0.7649	0.8746
No log	7.1220	292	0.8082	0.6909	0.8082	0.8990
No log	7.1707	294	0.8558	0.7108	0.8558	0.9251
No log	7.2195	296	0.9018	0.6973	0.9018	0.9496
No log	7.2683	298	0.9090	0.6885	0.9090	0.9534
No log	7.3171	300	0.9033	0.6973	0.9033	0.9504
No log	7.3659	302	0.8820	0.7113	0.8820	0.9391
No log	7.4146	304	0.9210	0.6798	0.9210	0.9597
No log	7.4634	306	0.9493	0.6657	0.9493	0.9743
No log	7.5122	308	0.9811	0.6393	0.9811	0.9905
No log	7.5610	310	0.9434	0.6616	0.9434	0.9713
No log	7.6098	312	0.8811	0.6993	0.8811	0.9387
No log	7.6585	314	0.8384	0.7008	0.8384	0.9156
No log	7.7073	316	0.8153	0.7008	0.8153	0.9030
No log	7.7561	318	0.8450	0.6937	0.8450	0.9192
No log	7.8049	320	0.8931	0.6993	0.8931	0.9450
No log	7.8537	322	0.8895	0.6993	0.8895	0.9431
No log	7.9024	324	0.8413	0.6937	0.8413	0.9172
No log	7.9512	326	0.7891	0.7112	0.7891	0.8883
No log	8.0	328	0.7739	0.7132	0.7739	0.8797
No log	8.0488	330	0.7602	0.7227	0.7602	0.8719
No log	8.0976	332	0.7614	0.7184	0.7614	0.8726
No log	8.1463	334	0.7418	0.7019	0.7418	0.8613
No log	8.1951	336	0.7136	0.6985	0.7136	0.8448
No log	8.2439	338	0.7062	0.7013	0.7062	0.8404
No log	8.2927	340	0.7304	0.7014	0.7304	0.8546
No log	8.3415	342	0.7716	0.7085	0.7716	0.8784
No log	8.3902	344	0.7921	0.7027	0.7921	0.8900
No log	8.4390	346	0.8203	0.6891	0.8203	0.9057
No log	8.4878	348	0.8530	0.6948	0.8530	0.9236
No log	8.5366	350	0.8515	0.6948	0.8515	0.9228
No log	8.5854	352	0.8576	0.6948	0.8576	0.9261
No log	8.6341	354	0.8653	0.6948	0.8653	0.9302
No log	8.6829	356	0.8397	0.6948	0.8397	0.9163
No log	8.7317	358	0.7978	0.7027	0.7978	0.8932
No log	8.7805	360	0.7573	0.7003	0.7573	0.8702
No log	8.8293	362	0.7417	0.6999	0.7417	0.8612
No log	8.8780	364	0.7417	0.7019	0.7417	0.8612
No log	8.9268	366	0.7453	0.7019	0.7453	0.8633
No log	8.9756	368	0.7616	0.6999	0.7616	0.8727
No log	9.0244	370	0.7666	0.6999	0.7666	0.8755
No log	9.0732	372	0.7798	0.6960	0.7798	0.8830
No log	9.1220	374	0.8038	0.6741	0.8038	0.8966
No log	9.1707	376	0.8315	0.6783	0.8315	0.9119
No log	9.2195	378	0.8578	0.6948	0.8578	0.9262
No log	9.2683	380	0.8606	0.6948	0.8606	0.9277
No log	9.3171	382	0.8557	0.6948	0.8557	0.9250
No log	9.3659	384	0.8561	0.6948	0.8561	0.9252
No log	9.4146	386	0.8473	0.6948	0.8473	0.9205
No log	9.4634	388	0.8415	0.6891	0.8415	0.9173
No log	9.5122	390	0.8338	0.6891	0.8338	0.9131
No log	9.5610	392	0.8201	0.7008	0.8201	0.9056
No log	9.6098	394	0.8093	0.7008	0.8093	0.8996
No log	9.6585	396	0.8028	0.7049	0.8028	0.8960
No log	9.7073	398	0.8006	0.7049	0.8006	0.8948
No log	9.7561	400	0.7978	0.7049	0.7978	0.8932
No log	9.8049	402	0.7934	0.7068	0.7934	0.8907
No log	9.8537	404	0.7901	0.7164	0.7901	0.8889
No log	9.9024	406	0.7881	0.7164	0.7881	0.8877
No log	9.9512	408	0.7872	0.7164	0.7872	0.8872
No log	10.0	410	0.7872	0.7164	0.7872	0.8872

Framework versions

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