ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k7_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: 0.6029
• Qwk: 0.3990
• Mse: 0.6029
• Rmse: 0.7765

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	3.6916	0.0026	3.6916	1.9214
No log	0.1111	4	2.0788	-0.0390	2.0788	1.4418
No log	0.1667	6	1.1693	0.0255	1.1693	1.0813
No log	0.2222	8	0.6727	0.0256	0.6727	0.8202
No log	0.2778	10	0.5930	0.0388	0.5930	0.7701
No log	0.3333	12	0.5944	0.0448	0.5944	0.7710
No log	0.3889	14	1.2561	-0.0113	1.2561	1.1208
No log	0.4444	16	0.9786	0.0427	0.9786	0.9892
No log	0.5	18	0.5815	0.0	0.5815	0.7626
No log	0.5556	20	0.5742	0.0	0.5742	0.7578
No log	0.6111	22	0.5718	0.0909	0.5718	0.7562
No log	0.6667	24	0.6079	0.2099	0.6079	0.7797
No log	0.7222	26	0.5782	0.0476	0.5782	0.7604
No log	0.7778	28	0.6699	-0.0081	0.6699	0.8184
No log	0.8333	30	0.6577	0.1565	0.6577	0.8110
No log	0.8889	32	0.7161	0.3208	0.7161	0.8462
No log	0.9444	34	0.7297	0.1543	0.7297	0.8542
No log	1.0	36	0.7214	0.1230	0.7214	0.8494
No log	1.0556	38	0.6215	0.2093	0.6215	0.7884
No log	1.1111	40	0.5671	0.3000	0.5671	0.7531
No log	1.1667	42	0.6030	0.2318	0.6030	0.7766
No log	1.2222	44	0.5568	0.2298	0.5568	0.7462
No log	1.2778	46	0.5741	0.2195	0.5741	0.7577
No log	1.3333	48	0.6271	0.2683	0.6271	0.7919
No log	1.3889	50	1.0261	0.0418	1.0261	1.0130
No log	1.4444	52	0.7517	0.1489	0.7517	0.8670
No log	1.5	54	0.6357	0.2086	0.6357	0.7973
No log	1.5556	56	0.6789	0.2897	0.6789	0.8240
No log	1.6111	58	0.7251	0.3004	0.7251	0.8515
No log	1.6667	60	0.7923	0.2146	0.7923	0.8901
No log	1.7222	62	1.1465	0.0813	1.1465	1.0707
No log	1.7778	64	0.6956	0.2821	0.6956	0.8340
No log	1.8333	66	0.8029	0.2727	0.8029	0.8960
No log	1.8889	68	0.6953	0.2893	0.6953	0.8338
No log	1.9444	70	0.6134	0.3939	0.6134	0.7832
No log	2.0	72	0.8634	0.1150	0.8634	0.9292
No log	2.0556	74	1.0340	0.1027	1.0340	1.0168
No log	2.1111	76	0.6392	0.3939	0.6392	0.7995
No log	2.1667	78	0.6201	0.3580	0.6201	0.7875
No log	2.2222	80	1.0766	0.0746	1.0766	1.0376
No log	2.2778	82	1.1756	0.0769	1.1756	1.0843
No log	2.3333	84	0.6455	0.2941	0.6455	0.8035
No log	2.3889	86	0.6437	0.2919	0.6437	0.8023
No log	2.4444	88	0.8580	0.1336	0.8580	0.9263
No log	2.5	90	0.9191	0.1712	0.9191	0.9587
No log	2.5556	92	0.8167	0.1304	0.8167	0.9037
No log	2.6111	94	0.6663	0.2088	0.6663	0.8163
No log	2.6667	96	0.9222	0.2137	0.9222	0.9603
No log	2.7222	98	0.9339	0.2134	0.9339	0.9664
No log	2.7778	100	0.6805	0.1746	0.6805	0.8250
No log	2.8333	102	0.7327	0.2000	0.7327	0.8560
No log	2.8889	104	0.7026	0.1828	0.7026	0.8382
No log	2.9444	106	0.7198	0.1579	0.7198	0.8484
No log	3.0	108	0.7281	0.1579	0.7281	0.8533
No log	3.0556	110	1.3779	0.0843	1.3779	1.1739
No log	3.1111	112	1.4781	0.0638	1.4781	1.2158
No log	3.1667	114	0.7928	0.1683	0.7928	0.8904
No log	3.2222	116	0.7047	0.3061	0.7047	0.8395
No log	3.2778	118	0.7196	0.2332	0.7196	0.8483
No log	3.3333	120	0.6195	0.1304	0.6195	0.7871
No log	3.3889	122	0.7157	0.2683	0.7157	0.8460
No log	3.4444	124	0.6100	0.1807	0.6100	0.7810
No log	3.5	126	0.6143	0.1648	0.6143	0.7838
No log	3.5556	128	0.7395	0.1919	0.7395	0.8600
No log	3.6111	130	1.3712	0.0789	1.3712	1.1710
No log	3.6667	132	1.1908	0.1738	1.1908	1.0913
No log	3.7222	134	0.6418	0.2174	0.6418	0.8011
No log	3.7778	136	0.6744	0.3010	0.6744	0.8212
No log	3.8333	138	0.6090	0.2360	0.6090	0.7804
No log	3.8889	140	0.8172	0.2511	0.8172	0.9040
No log	3.9444	142	0.6996	0.2233	0.6996	0.8364
No log	4.0	144	0.6002	0.2174	0.6002	0.7747
No log	4.0556	146	0.6682	0.2245	0.6682	0.8175
No log	4.1111	148	0.7301	0.1712	0.7301	0.8544
No log	4.1667	150	0.6236	0.2083	0.6236	0.7897
No log	4.2222	152	0.6168	0.2169	0.6168	0.7854
No log	4.2778	154	0.5880	0.3161	0.5880	0.7668
No log	4.3333	156	0.5542	0.3043	0.5542	0.7445
No log	4.3889	158	0.5385	0.2626	0.5385	0.7338
No log	4.4444	160	0.5748	0.3292	0.5748	0.7582
No log	4.5	162	0.7198	0.3061	0.7198	0.8484
No log	4.5556	164	0.6258	0.3182	0.6258	0.7911
No log	4.6111	166	0.5245	0.3478	0.5245	0.7242
No log	4.6667	168	0.6378	0.1770	0.6378	0.7986
No log	4.7222	170	0.5763	0.3535	0.5763	0.7591
No log	4.7778	172	0.5722	0.3297	0.5722	0.7564
No log	4.8333	174	0.8072	0.2857	0.8072	0.8984
No log	4.8889	176	0.7888	0.3021	0.7888	0.8882
No log	4.9444	178	0.6370	0.3200	0.6370	0.7981
No log	5.0	180	0.6610	0.3704	0.6610	0.8130
No log	5.0556	182	0.6684	0.3665	0.6684	0.8175
No log	5.1111	184	0.6869	0.3722	0.6869	0.8288
No log	5.1667	186	0.8406	0.3021	0.8406	0.9168
No log	5.2222	188	1.0100	0.2113	1.0100	1.0050
No log	5.2778	190	0.7348	0.3648	0.7348	0.8572
No log	5.3333	192	0.6389	0.3131	0.6389	0.7993
No log	5.3889	194	0.5887	0.4105	0.5887	0.7673
No log	5.4444	196	0.7035	0.2780	0.7035	0.8387
No log	5.5	198	0.8792	0.2066	0.8792	0.9377
No log	5.5556	200	0.9249	0.2062	0.9249	0.9617
No log	5.6111	202	0.7953	0.3128	0.7953	0.8918
No log	5.6667	204	0.6556	0.3103	0.6556	0.8097
No log	5.7222	206	0.5667	0.2457	0.5667	0.7528
No log	5.7778	208	0.6105	0.3862	0.6105	0.7813
No log	5.8333	210	0.7828	0.2348	0.7828	0.8847
No log	5.8889	212	0.8599	0.2397	0.8599	0.9273
No log	5.9444	214	0.7478	0.2464	0.7478	0.8647
No log	6.0	216	0.6042	0.3231	0.6042	0.7773
No log	6.0556	218	0.5825	0.2787	0.5825	0.7632
No log	6.1111	220	0.6628	0.2821	0.6628	0.8141
No log	6.1667	222	0.8542	0.2741	0.8542	0.9242
No log	6.2222	224	0.7601	0.2838	0.7601	0.8718
No log	6.2778	226	0.5784	0.3333	0.5784	0.7605
No log	6.3333	228	0.5546	0.2889	0.5546	0.7447
No log	6.3889	230	0.6102	0.2865	0.6102	0.7811
No log	6.4444	232	0.7286	0.3128	0.7286	0.8536
No log	6.5	234	0.6983	0.3663	0.6983	0.8356
No log	6.5556	236	0.6128	0.2893	0.6128	0.7828
No log	6.6111	238	0.5802	0.3297	0.5802	0.7617
No log	6.6667	240	0.6052	0.3402	0.6052	0.7779
No log	6.7222	242	0.6562	0.3369	0.6562	0.8101
No log	6.7778	244	0.5826	0.4157	0.5826	0.7633
No log	6.8333	246	0.5352	0.3224	0.5352	0.7316
No log	6.8889	248	0.5408	0.4162	0.5408	0.7354
No log	6.9444	250	0.6523	0.3508	0.6523	0.8077
No log	7.0	252	0.7531	0.3188	0.7531	0.8678
No log	7.0556	254	0.6835	0.3684	0.6835	0.8268
No log	7.1111	256	0.5888	0.4098	0.5888	0.7673
No log	7.1667	258	0.5278	0.3224	0.5278	0.7265
No log	7.2222	260	0.5251	0.3978	0.5251	0.7247
No log	7.2778	262	0.5307	0.3846	0.5307	0.7285
No log	7.3333	264	0.6219	0.3478	0.6219	0.7886
No log	7.3889	266	0.6700	0.3684	0.6700	0.8186
No log	7.4444	268	0.6775	0.3684	0.6775	0.8231
No log	7.5	270	0.6148	0.4105	0.6148	0.7841
No log	7.5556	272	0.5469	0.3797	0.5469	0.7396
No log	7.6111	274	0.5541	0.375	0.5541	0.7444
No log	7.6667	276	0.5587	0.375	0.5587	0.7475
No log	7.7222	278	0.5810	0.3402	0.5810	0.7622
No log	7.7778	280	0.6505	0.3684	0.6505	0.8065
No log	7.8333	282	0.6805	0.3684	0.6805	0.8249
No log	7.8889	284	0.6662	0.3684	0.6662	0.8162
No log	7.9444	286	0.5791	0.3730	0.5791	0.7610
No log	8.0	288	0.5493	0.4033	0.5493	0.7411
No log	8.0556	290	0.5374	0.3846	0.5374	0.7331
No log	8.1111	292	0.5544	0.4033	0.5544	0.7446
No log	8.1667	294	0.5764	0.4043	0.5764	0.7592
No log	8.2222	296	0.6286	0.3797	0.6286	0.7928
No log	8.2778	298	0.6822	0.3271	0.6822	0.8259
No log	8.3333	300	0.6879	0.3271	0.6879	0.8294
No log	8.3889	302	0.6343	0.3641	0.6343	0.7964
No log	8.4444	304	0.6149	0.3684	0.6149	0.7841
No log	8.5	306	0.6142	0.3684	0.6142	0.7837
No log	8.5556	308	0.6102	0.3990	0.6102	0.7812
No log	8.6111	310	0.6413	0.3641	0.6413	0.8008
No log	8.6667	312	0.6304	0.3939	0.6304	0.7940
No log	8.7222	314	0.6095	0.3990	0.6095	0.7807
No log	8.7778	316	0.6075	0.3990	0.6075	0.7794
No log	8.8333	318	0.6217	0.3990	0.6217	0.7885
No log	8.8889	320	0.6743	0.3267	0.6743	0.8211
No log	8.9444	322	0.7378	0.3188	0.7378	0.8590
No log	9.0	324	0.7336	0.3214	0.7336	0.8565
No log	9.0556	326	0.6872	0.2965	0.6872	0.8290
No log	9.1111	328	0.6333	0.3990	0.6333	0.7958
No log	9.1667	330	0.5995	0.4043	0.5995	0.7742
No log	9.2222	332	0.5933	0.3508	0.5933	0.7702
No log	9.2778	334	0.6007	0.4043	0.6007	0.7751
No log	9.3333	336	0.6194	0.3990	0.6194	0.7870
No log	9.3889	338	0.6394	0.3990	0.6394	0.7996
No log	9.4444	340	0.6454	0.3684	0.6454	0.8034
No log	9.5	342	0.6357	0.3990	0.6357	0.7973
No log	9.5556	344	0.6160	0.3990	0.6160	0.7849
No log	9.6111	346	0.6100	0.3990	0.6100	0.7810
No log	9.6667	348	0.6074	0.3990	0.6074	0.7794
No log	9.7222	350	0.6058	0.3990	0.6058	0.7784
No log	9.7778	352	0.6005	0.4043	0.6005	0.7749
No log	9.8333	354	0.6006	0.4043	0.6006	0.7750
No log	9.8889	356	0.6008	0.4043	0.6008	0.7751
No log	9.9444	358	0.6023	0.4043	0.6023	0.7761
No log	10.0	360	0.6029	0.3990	0.6029	0.7765

Framework versions

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