ArabicNewSplits4_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k8_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: 0.6947
• Qwk: 0.1675
• Mse: 0.6947
• Rmse: 0.8335

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	0.0556	2	3.7111	0.0	3.7111	1.9264
No log	0.1111	4	2.4117	-0.0163	2.4117	1.5530
No log	0.1667	6	1.4622	0.0255	1.4622	1.2092
No log	0.2222	8	1.0519	0.0632	1.0519	1.0256
No log	0.2778	10	0.6496	0.1020	0.6496	0.8060
No log	0.3333	12	0.6119	0.0569	0.6119	0.7822
No log	0.3889	14	0.6217	0.0569	0.6217	0.7884
No log	0.4444	16	0.7361	0.1475	0.7361	0.8579
No log	0.5	18	0.6389	0.1030	0.6389	0.7993
No log	0.5556	20	0.6311	0.0569	0.6311	0.7944
No log	0.6111	22	0.6515	0.0	0.6515	0.8072
No log	0.6667	24	0.5680	0.0569	0.5680	0.7537
No log	0.7222	26	0.8891	0.0823	0.8891	0.9429
No log	0.7778	28	0.9588	0.0617	0.9588	0.9792
No log	0.8333	30	0.7530	0.1712	0.7530	0.8678
No log	0.8889	32	0.5959	0.0303	0.5959	0.7720
No log	0.9444	34	0.6484	0.0	0.6484	0.8052
No log	1.0	36	0.7096	0.0	0.7096	0.8424
No log	1.0556	38	0.6402	0.0	0.6402	0.8001
No log	1.1111	40	0.6079	0.0222	0.6079	0.7797
No log	1.1667	42	0.7106	0.1638	0.7106	0.8430
No log	1.2222	44	0.7750	0.0918	0.7750	0.8803
No log	1.2778	46	0.6087	0.1111	0.6087	0.7802
No log	1.3333	48	0.6242	0.0	0.6242	0.7901
No log	1.3889	50	0.6590	0.0	0.6590	0.8118
No log	1.4444	52	0.6369	0.0909	0.6369	0.7981
No log	1.5	54	0.7216	0.0409	0.7216	0.8495
No log	1.5556	56	1.1468	0.0888	1.1468	1.0709
No log	1.6111	58	1.0263	0.0357	1.0263	1.0131
No log	1.6667	60	0.7526	0.1195	0.7526	0.8676
No log	1.7222	62	0.8995	0.0045	0.8995	0.9484
No log	1.7778	64	0.9511	-0.0396	0.9511	0.9753
No log	1.8333	66	0.8171	0.1186	0.8171	0.9039
No log	1.8889	68	0.8384	0.0417	0.8384	0.9156
No log	1.9444	70	0.7068	-0.0115	0.7068	0.8407
No log	2.0	72	1.1650	0.0040	1.1650	1.0794
No log	2.0556	74	1.5366	-0.0323	1.5366	1.2396
No log	2.1111	76	0.9921	0.0442	0.9921	0.9960
No log	2.1667	78	0.6773	0.2169	0.6773	0.8230
No log	2.2222	80	0.6838	0.1919	0.6838	0.8269
No log	2.2778	82	0.7907	0.1579	0.7907	0.8892
No log	2.3333	84	0.9283	0.0044	0.9283	0.9635
No log	2.3889	86	1.3364	0.1049	1.3364	1.1560
No log	2.4444	88	1.3190	0.1304	1.3190	1.1485
No log	2.5	90	0.6845	0.3371	0.6845	0.8273
No log	2.5556	92	0.6332	0.3333	0.6332	0.7957
No log	2.6111	94	0.7316	0.2332	0.7316	0.8553
No log	2.6667	96	1.5324	0.1084	1.5324	1.2379
No log	2.7222	98	1.7160	0.0659	1.7160	1.3099
No log	2.7778	100	0.8899	0.1111	0.8899	0.9433
No log	2.8333	102	0.8782	0.1712	0.8782	0.9371
No log	2.8889	104	1.1426	0.1571	1.1426	1.0689
No log	2.9444	106	0.7110	0.1675	0.7110	0.8432
No log	3.0	108	1.0958	0.0406	1.0958	1.0468
No log	3.0556	110	1.5838	0.0788	1.5838	1.2585
No log	3.1111	112	1.3244	0.0278	1.3244	1.1508
No log	3.1667	114	0.7076	0.2195	0.7076	0.8412
No log	3.2222	116	0.7701	0.0833	0.7701	0.8776
No log	3.2778	118	0.8158	0.1005	0.8158	0.9032
No log	3.3333	120	0.6633	0.1801	0.6633	0.8144
No log	3.3889	122	0.9320	0.1504	0.9320	0.9654
No log	3.4444	124	0.9196	0.1504	0.9196	0.9590
No log	3.5	126	0.7194	0.1345	0.7194	0.8482
No log	3.5556	128	0.9080	0.0685	0.9080	0.9529
No log	3.6111	130	0.9032	0.0631	0.9032	0.9503
No log	3.6667	132	0.7376	0.1732	0.7376	0.8588
No log	3.7222	134	0.9602	0.0769	0.9602	0.9799
No log	3.7778	136	0.8651	0.1287	0.8651	0.9301
No log	3.8333	138	0.7200	0.1732	0.7200	0.8485
No log	3.8889	140	0.7234	0.1364	0.7234	0.8505
No log	3.9444	142	0.7667	0.1828	0.7667	0.8756
No log	4.0	144	0.7990	0.1429	0.7990	0.8938
No log	4.0556	146	0.8138	0.1443	0.8138	0.9021
No log	4.1111	148	0.8245	0.1527	0.8245	0.9080
No log	4.1667	150	0.8029	0.1515	0.8029	0.8960
No log	4.2222	152	0.7834	0.2350	0.7834	0.8851
No log	4.2778	154	0.9610	0.0744	0.9610	0.9803
No log	4.3333	156	1.3290	0.1351	1.3290	1.1528
No log	4.3889	158	1.1534	0.0929	1.1534	1.0740
No log	4.4444	160	0.7770	0.2897	0.7770	0.8815
No log	4.5	162	0.7829	0.2838	0.7829	0.8848
No log	4.5556	164	0.9567	0.2069	0.9567	0.9781
No log	4.6111	166	1.3203	0.1560	1.3203	1.1490
No log	4.6667	168	1.1799	0.1572	1.1799	1.0862
No log	4.7222	170	0.7147	0.2251	0.7147	0.8454
No log	4.7778	172	0.6253	0.3023	0.6253	0.7908
No log	4.8333	174	0.6920	0.2360	0.6920	0.8318
No log	4.8889	176	0.8984	0.1864	0.8984	0.9479
No log	4.9444	178	0.7468	0.2941	0.7468	0.8642
No log	5.0	180	0.6126	0.3103	0.6126	0.7827
No log	5.0556	182	0.5965	0.3103	0.5965	0.7724
No log	5.1111	184	0.6570	0.2350	0.6570	0.8106
No log	5.1667	186	0.7761	0.2453	0.7761	0.8809
No log	5.2222	188	1.1119	0.1882	1.1119	1.0544
No log	5.2778	190	0.9522	0.2129	0.9522	0.9758
No log	5.3333	192	0.7116	0.1921	0.7116	0.8435
No log	5.3889	194	0.6372	0.3043	0.6372	0.7982
No log	5.4444	196	0.6442	0.3297	0.6442	0.8026
No log	5.5	198	0.7820	0.1373	0.7820	0.8843
No log	5.5556	200	1.0169	0.2119	1.0169	1.0084
No log	5.6111	202	0.9520	0.2126	0.9520	0.9757
No log	5.6667	204	0.7569	0.1373	0.7569	0.8700
No log	5.7222	206	0.7617	0.1269	0.7617	0.8728
No log	5.7778	208	0.8677	0.1781	0.8677	0.9315
No log	5.8333	210	0.9052	0.1781	0.9052	0.9514
No log	5.8889	212	0.7296	0.1915	0.7296	0.8542
No log	5.9444	214	0.7103	0.1398	0.7103	0.8428
No log	6.0	216	0.8342	0.1287	0.8342	0.9133
No log	6.0556	218	1.1701	0.1601	1.1701	1.0817
No log	6.1111	220	1.3063	0.1634	1.3063	1.1429
No log	6.1667	222	1.0346	0.1815	1.0346	1.0172
No log	6.2222	224	0.7352	0.2410	0.7352	0.8575
No log	6.2778	226	0.6371	0.2558	0.6371	0.7982
No log	6.3333	228	0.6286	0.3455	0.6286	0.7929
No log	6.3889	230	0.6358	0.1902	0.6358	0.7974
No log	6.4444	232	0.7068	0.125	0.7068	0.8407
No log	6.5	234	0.7811	0.1373	0.7811	0.8838
No log	6.5556	236	0.8398	0.1388	0.8398	0.9164
No log	6.6111	238	0.8278	0.1321	0.8278	0.9098
No log	6.6667	240	0.8601	0.1321	0.8601	0.9274
No log	6.7222	242	0.9158	0.1781	0.9158	0.9570
No log	6.7778	244	0.8034	0.1321	0.8034	0.8963
No log	6.8333	246	0.7088	0.1475	0.7088	0.8419
No log	6.8889	248	0.7147	0.1088	0.7147	0.8454
No log	6.9444	250	0.7387	0.1340	0.7387	0.8595
No log	7.0	252	0.7378	0.1340	0.7378	0.8590
No log	7.0556	254	0.7249	0.1269	0.7249	0.8514
No log	7.1111	256	0.6846	0.1828	0.6846	0.8274
No log	7.1667	258	0.6770	0.2688	0.6770	0.8228
No log	7.2222	260	0.6956	0.3333	0.6956	0.8340
No log	7.2778	262	0.7276	0.1340	0.7276	0.8530
No log	7.3333	264	0.8134	0.1456	0.8134	0.9019
No log	7.3889	266	0.9725	0.1795	0.9725	0.9862
No log	7.4444	268	0.9659	0.1795	0.9659	0.9828
No log	7.5	270	0.8483	0.0189	0.8483	0.9210
No log	7.5556	272	0.7372	0.1667	0.7372	0.8586
No log	7.6111	274	0.7210	0.3016	0.7210	0.8491
No log	7.6667	276	0.7247	0.3089	0.7247	0.8513
No log	7.7222	278	0.7046	0.2766	0.7046	0.8394
No log	7.7778	280	0.6817	0.3369	0.6817	0.8257
No log	7.8333	282	0.6632	0.2179	0.6632	0.8143
No log	7.8889	284	0.7102	0.1675	0.7102	0.8427
No log	7.9444	286	0.7655	0.0980	0.7655	0.8749
No log	8.0	288	0.7372	0.1287	0.7372	0.8586
No log	8.0556	290	0.6748	0.2165	0.6748	0.8215
No log	8.1111	292	0.6573	0.2179	0.6573	0.8107
No log	8.1667	294	0.6609	0.2179	0.6609	0.8130
No log	8.2222	296	0.6856	0.2536	0.6856	0.8280
No log	8.2778	298	0.7702	0.1402	0.7702	0.8776
No log	8.3333	300	0.8203	0.1416	0.8203	0.9057
No log	8.3889	302	0.7994	0.1402	0.7994	0.8941
No log	8.4444	304	0.7890	0.1402	0.7890	0.8883
No log	8.5	306	0.7869	0.1402	0.7869	0.8871
No log	8.5556	308	0.7517	0.0980	0.7517	0.8670
No log	8.6111	310	0.7036	0.2536	0.7036	0.8388
No log	8.6667	312	0.6633	0.2563	0.6633	0.8145
No log	8.7222	314	0.6457	0.2542	0.6457	0.8036
No log	8.7778	316	0.6437	0.2542	0.6437	0.8023
No log	8.8333	318	0.6599	0.2563	0.6599	0.8123
No log	8.8889	320	0.6996	0.2233	0.6996	0.8364
No log	8.9444	322	0.7634	0.0943	0.7634	0.8737
No log	9.0	324	0.8418	0.1429	0.8418	0.9175
No log	9.0556	326	0.8983	0.1504	0.8983	0.9478
No log	9.1111	328	0.9077	0.1515	0.9077	0.9527
No log	9.1667	330	0.8688	0.1855	0.8688	0.9321
No log	9.2222	332	0.7981	0.1416	0.7981	0.8934
No log	9.2778	334	0.7294	0.1304	0.7294	0.8540
No log	9.3333	336	0.6900	0.1675	0.6900	0.8306
No log	9.3889	338	0.6646	0.1503	0.6646	0.8152
No log	9.4444	340	0.6492	0.2563	0.6492	0.8057
No log	9.5	342	0.6452	0.2563	0.6452	0.8032
No log	9.5556	344	0.6512	0.2563	0.6512	0.8070
No log	9.6111	346	0.6589	0.1503	0.6589	0.8117
No log	9.6667	348	0.6670	0.1503	0.6670	0.8167
No log	9.7222	350	0.6757	0.1919	0.6757	0.8220
No log	9.7778	352	0.6870	0.1600	0.6870	0.8288
No log	9.8333	354	0.6930	0.1675	0.6930	0.8325
No log	9.8889	356	0.6950	0.1675	0.6950	0.8337
No log	9.9444	358	0.6948	0.1675	0.6948	0.8335
No log	10.0	360	0.6947	0.1675	0.6947	0.8335

Framework versions

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