ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run1_AugV5_k5_task3_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: 1.0286
• Qwk: 0.1524
• Mse: 1.0286
• Rmse: 1.0142

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	0.0741	2	3.1615	-0.0293	3.1615	1.7781
No log	0.1481	4	1.5828	0.0210	1.5828	1.2581
No log	0.2222	6	1.2781	0.0325	1.2781	1.1305
No log	0.2963	8	0.6602	0.0556	0.6602	0.8125
No log	0.3704	10	0.6133	-0.0159	0.6133	0.7831
No log	0.4444	12	0.7417	0.0	0.7417	0.8612
No log	0.5185	14	0.7457	0.1902	0.7457	0.8636
No log	0.5926	16	1.0196	0.0957	1.0196	1.0098
No log	0.6667	18	1.4504	0.0286	1.4504	1.2043
No log	0.7407	20	0.8422	0.0569	0.8422	0.9177
No log	0.8148	22	0.7969	0.0717	0.7969	0.8927
No log	0.8889	24	0.8398	0.0244	0.8398	0.9164
No log	0.9630	26	0.6489	0.0638	0.6489	0.8055
No log	1.0370	28	0.5882	-0.0081	0.5882	0.7669
No log	1.1111	30	0.5822	-0.0081	0.5822	0.7630
No log	1.1852	32	0.5759	-0.0081	0.5759	0.7589
No log	1.2593	34	0.5778	0.0	0.5778	0.7601
No log	1.3333	36	0.5730	0.0	0.5730	0.7570
No log	1.4074	38	0.5791	-0.0081	0.5791	0.7610
No log	1.4815	40	0.6212	-0.0076	0.6212	0.7881
No log	1.5556	42	0.6576	-0.0149	0.6576	0.8109
No log	1.6296	44	0.6785	-0.0286	0.6785	0.8237
No log	1.7037	46	0.6949	0.0476	0.6949	0.8336
No log	1.7778	48	0.8122	-0.0575	0.8122	0.9012
No log	1.8519	50	0.7892	-0.0424	0.7892	0.8884
No log	1.9259	52	0.8097	0.0244	0.8097	0.8999
No log	2.0	54	0.9031	0.0707	0.9031	0.9503
No log	2.0741	56	0.8136	0.0805	0.8136	0.9020
No log	2.1481	58	0.7721	0.1345	0.7721	0.8787
No log	2.2222	60	0.7910	0.0807	0.7910	0.8894
No log	2.2963	62	0.7979	0.0983	0.7979	0.8932
No log	2.3704	64	0.8736	0.1416	0.8736	0.9347
No log	2.4444	66	0.9514	0.1111	0.9514	0.9754
No log	2.5185	68	1.1990	0.0345	1.1990	1.0950
No log	2.5926	70	1.1030	0.0551	1.1030	1.0502
No log	2.6667	72	0.7771	0.2340	0.7771	0.8816
No log	2.7407	74	0.6688	0.0870	0.6688	0.8178
No log	2.8148	76	0.6614	0.1746	0.6614	0.8132
No log	2.8889	78	0.6980	0.1818	0.6980	0.8355
No log	2.9630	80	0.8737	0.1927	0.8737	0.9347
No log	3.0370	82	0.7659	0.1832	0.7659	0.8751
No log	3.1111	84	0.6460	0.1529	0.6460	0.8037
No log	3.1852	86	0.6264	0.0732	0.6264	0.7915
No log	3.2593	88	0.7281	0.2323	0.7281	0.8533
No log	3.3333	90	1.1420	0.0303	1.1420	1.0686
No log	3.4074	92	1.1954	0.0303	1.1954	1.0933
No log	3.4815	94	0.8473	0.2000	0.8473	0.9205
No log	3.5556	96	0.8103	0.1683	0.8103	0.9002
No log	3.6296	98	1.1860	0.0747	1.1860	1.0890
No log	3.7037	100	1.6107	0.0975	1.6107	1.2691
No log	3.7778	102	1.4154	0.0675	1.4154	1.1897
No log	3.8519	104	0.8079	0.2157	0.8079	0.8989
No log	3.9259	106	0.8618	0.2212	0.8618	0.9284
No log	4.0	108	1.0822	0.1062	1.0822	1.0403
No log	4.0741	110	1.0209	0.1515	1.0209	1.0104
No log	4.1481	112	0.7184	0.2609	0.7184	0.8476
No log	4.2222	114	0.8705	0.2900	0.8705	0.9330
No log	4.2963	116	1.0953	0.1450	1.0953	1.0466
No log	4.3704	118	1.0003	0.2569	1.0003	1.0002
No log	4.4444	120	0.8611	0.1340	0.8611	0.9280
No log	4.5185	122	0.9935	0.2269	0.9935	0.9967
No log	4.5926	124	1.2655	0.0137	1.2655	1.1249
No log	4.6667	126	1.2133	0.0662	1.2133	1.1015
No log	4.7407	128	0.9520	0.2258	0.9520	0.9757
No log	4.8148	130	0.9023	0.2605	0.9023	0.9499
No log	4.8889	132	1.0633	0.2472	1.0633	1.0312
No log	4.9630	134	1.1090	0.2174	1.1090	1.0531
No log	5.0370	136	0.9557	0.2782	0.9557	0.9776
No log	5.1111	138	0.8004	0.2208	0.8004	0.8946
No log	5.1852	140	0.7200	0.2075	0.7200	0.8485
No log	5.2593	142	0.8427	0.2605	0.8427	0.9180
No log	5.3333	144	1.1026	0.1418	1.1026	1.0500
No log	5.4074	146	1.4484	0.0843	1.4484	1.2035
No log	5.4815	148	1.4323	0.1068	1.4323	1.1968
No log	5.5556	150	1.2593	0.0993	1.2593	1.1222
No log	5.6296	152	1.2740	0.0993	1.2740	1.1287
No log	5.7037	154	1.3168	0.0993	1.3168	1.1475
No log	5.7778	156	1.3443	0.1010	1.3443	1.1594
No log	5.8519	158	1.0492	0.2778	1.0492	1.0243
No log	5.9259	160	1.0110	0.2537	1.0110	1.0055
No log	6.0	162	1.3230	0.0489	1.3230	1.1502
No log	6.0741	164	1.4515	0.0336	1.4515	1.2048
No log	6.1481	166	1.2586	0.1246	1.2586	1.1219
No log	6.2222	168	1.1852	0.1429	1.1852	1.0887
No log	6.2963	170	1.3166	0.0489	1.3166	1.1474
No log	6.3704	172	1.7018	0.0705	1.7018	1.3045
No log	6.4444	174	1.7770	0.0476	1.7770	1.3330
No log	6.5185	176	1.5219	0.0061	1.5219	1.2337
No log	6.5926	178	1.2379	0.0621	1.2379	1.1126
No log	6.6667	180	1.0684	0.2281	1.0684	1.0336
No log	6.7407	182	1.0703	0.1206	1.0703	1.0345
No log	6.8148	184	1.2383	0.0667	1.2383	1.1128
No log	6.8889	186	1.4223	0.0409	1.4223	1.1926
No log	6.9630	188	1.3683	0.1056	1.3683	1.1698
No log	7.0370	190	1.1351	0.0657	1.1351	1.0654
No log	7.1111	192	0.8830	0.2134	0.8830	0.9397
No log	7.1852	194	0.8186	0.2150	0.8186	0.9048
No log	7.2593	196	0.8309	0.2511	0.8309	0.9115
No log	7.3333	198	0.9169	0.2356	0.9169	0.9575
No log	7.4074	200	1.1386	0.1206	1.1386	1.0671
No log	7.4815	202	1.3135	0.1083	1.3135	1.1461
No log	7.5556	204	1.3280	0.0846	1.3280	1.1524
No log	7.6296	206	1.1776	0.0941	1.1776	1.0852
No log	7.7037	208	0.9744	0.1533	0.9744	0.9871
No log	7.7778	210	0.9348	0.2374	0.9348	0.9668
No log	7.8519	212	0.9876	0.1724	0.9876	0.9938
No log	7.9259	214	1.0251	0.1724	1.0251	1.0125
No log	8.0	216	0.9896	0.2366	0.9896	0.9948
No log	8.0741	218	1.0137	0.2366	1.0137	1.0068
No log	8.1481	220	1.1104	0.1877	1.1104	1.0537
No log	8.2222	222	1.1911	0.0815	1.1911	1.0914
No log	8.2963	224	1.2734	0.0644	1.2734	1.1284
No log	8.3704	226	1.2140	0.0036	1.2140	1.1018
No log	8.4444	228	1.1505	0.0861	1.1505	1.0726
No log	8.5185	230	1.1065	0.1264	1.1065	1.0519
No log	8.5926	232	1.0579	0.1867	1.0579	1.0286
No log	8.6667	234	1.0170	0.1746	1.0170	1.0084
No log	8.7407	236	1.0066	0.1746	1.0066	1.0033
No log	8.8148	238	1.0069	0.1746	1.0069	1.0035
No log	8.8889	240	1.0068	0.2062	1.0068	1.0034
No log	8.9630	242	1.0463	0.1524	1.0463	1.0229
No log	9.0370	244	1.0683	0.1524	1.0683	1.0336
No log	9.1111	246	1.0588	0.1524	1.0588	1.0290
No log	9.1852	248	1.0772	0.1524	1.0772	1.0379
No log	9.2593	250	1.1154	0.1278	1.1154	1.0561
No log	9.3333	252	1.1273	0.1292	1.1273	1.0618
No log	9.4074	254	1.1147	0.1292	1.1147	1.0558
No log	9.4815	256	1.0908	0.1278	1.0908	1.0444
No log	9.5556	258	1.0622	0.1278	1.0622	1.0306
No log	9.6296	260	1.0295	0.1524	1.0295	1.0146
No log	9.7037	262	1.0056	0.1496	1.0056	1.0028
No log	9.7778	264	1.0035	0.1815	1.0035	1.0018
No log	9.8519	266	1.0130	0.1818	1.0130	1.0065
No log	9.9259	268	1.0227	0.1524	1.0227	1.0113
No log	10.0	270	1.0286	0.1524	1.0286	1.0142

Framework versions

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