ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k6_task2_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: 0.9675
• Qwk: 0.4801
• Mse: 0.9675
• Rmse: 0.9836

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	3.8910	0.0162	3.8910	1.9726
No log	0.1111	4	1.9242	0.0913	1.9242	1.3871
No log	0.1667	6	1.0246	0.0569	1.0246	1.0122
No log	0.2222	8	0.7245	0.2041	0.7245	0.8511
No log	0.2778	10	0.7010	0.2101	0.7010	0.8373
No log	0.3333	12	0.8726	0.1314	0.8726	0.9341
No log	0.3889	14	1.0098	-0.1056	1.0098	1.0049
No log	0.4444	16	0.8093	0.1469	0.8093	0.8996
No log	0.5	18	0.7692	0.1778	0.7692	0.8770
No log	0.5556	20	0.7372	0.1916	0.7372	0.8586
No log	0.6111	22	0.6816	0.1916	0.6816	0.8256
No log	0.6667	24	0.6355	0.2861	0.6355	0.7972
No log	0.7222	26	0.6411	0.2771	0.6411	0.8007
No log	0.7778	28	0.6381	0.3167	0.6381	0.7988
No log	0.8333	30	0.6889	0.2359	0.6889	0.8300
No log	0.8889	32	0.8114	0.2345	0.8114	0.9008
No log	0.9444	34	0.6965	0.2906	0.6965	0.8346
No log	1.0	36	0.6655	0.4254	0.6655	0.8158
No log	1.0556	38	0.6921	0.4134	0.6921	0.8319
No log	1.1111	40	0.7414	0.3667	0.7414	0.8610
No log	1.1667	42	0.8905	0.2880	0.8905	0.9437
No log	1.2222	44	0.8631	0.2947	0.8631	0.9291
No log	1.2778	46	0.6972	0.4372	0.6972	0.8350
No log	1.3333	48	0.8792	0.3724	0.8792	0.9377
No log	1.3889	50	0.9569	0.3999	0.9569	0.9782
No log	1.4444	52	0.9014	0.4317	0.9014	0.9494
No log	1.5	54	0.7541	0.4329	0.7541	0.8684
No log	1.5556	56	0.7852	0.4167	0.7852	0.8861
No log	1.6111	58	0.6748	0.5184	0.6748	0.8215
No log	1.6667	60	0.6693	0.4944	0.6693	0.8181
No log	1.7222	62	0.6589	0.4842	0.6589	0.8117
No log	1.7778	64	0.7104	0.5160	0.7104	0.8428
No log	1.8333	66	0.9447	0.4731	0.9447	0.9720
No log	1.8889	68	0.9071	0.4689	0.9071	0.9524
No log	1.9444	70	0.6185	0.4826	0.6185	0.7865
No log	2.0	72	0.9353	0.3353	0.9353	0.9671
No log	2.0556	74	0.8663	0.3804	0.8663	0.9308
No log	2.1111	76	0.6075	0.4548	0.6075	0.7794
No log	2.1667	78	0.8557	0.5393	0.8557	0.9250
No log	2.2222	80	0.8663	0.5250	0.8663	0.9308
No log	2.2778	82	0.5980	0.5179	0.5980	0.7733
No log	2.3333	84	0.6587	0.5086	0.6587	0.8116
No log	2.3889	86	0.6858	0.4649	0.6858	0.8281
No log	2.4444	88	0.6635	0.5136	0.6635	0.8146
No log	2.5	90	1.1719	0.4049	1.1719	1.0825
No log	2.5556	92	1.4932	0.4038	1.4932	1.2220
No log	2.6111	94	1.2264	0.4127	1.2264	1.1074
No log	2.6667	96	0.6615	0.5596	0.6615	0.8134
No log	2.7222	98	0.8474	0.4653	0.8474	0.9205
No log	2.7778	100	1.0001	0.3859	1.0001	1.0001
No log	2.8333	102	0.8127	0.4910	0.8127	0.9015
No log	2.8889	104	0.6800	0.5964	0.6800	0.8246
No log	2.9444	106	0.7953	0.5470	0.7953	0.8918
No log	3.0	108	0.8945	0.5558	0.8945	0.9458
No log	3.0556	110	0.8348	0.5709	0.8348	0.9137
No log	3.1111	112	0.9129	0.4763	0.9129	0.9555
No log	3.1667	114	0.9451	0.4766	0.9451	0.9722
No log	3.2222	116	1.0289	0.4861	1.0289	1.0144
No log	3.2778	118	1.1350	0.4750	1.1350	1.0653
No log	3.3333	120	1.1153	0.4784	1.1153	1.0561
No log	3.3889	122	0.8772	0.5182	0.8772	0.9366
No log	3.4444	124	0.7571	0.5250	0.7571	0.8701
No log	3.5	126	0.7469	0.5090	0.7469	0.8642
No log	3.5556	128	0.7817	0.5482	0.7817	0.8841
No log	3.6111	130	0.8285	0.5268	0.8285	0.9102
No log	3.6667	132	0.8223	0.5374	0.8223	0.9068
No log	3.7222	134	0.8860	0.5405	0.8860	0.9413
No log	3.7778	136	0.8939	0.5469	0.8939	0.9455
No log	3.8333	138	0.8092	0.5053	0.8092	0.8995
No log	3.8889	140	0.8145	0.4745	0.8145	0.9025
No log	3.9444	142	0.8811	0.5208	0.8811	0.9387
No log	4.0	144	1.1342	0.4853	1.1342	1.0650
No log	4.0556	146	1.1603	0.4584	1.1603	1.0772
No log	4.1111	148	0.9777	0.5220	0.9777	0.9888
No log	4.1667	150	0.8054	0.5454	0.8054	0.8975
No log	4.2222	152	0.8123	0.5495	0.8123	0.9013
No log	4.2778	154	0.9761	0.4959	0.9761	0.9880
No log	4.3333	156	1.0507	0.4909	1.0507	1.0251
No log	4.3889	158	1.0384	0.5056	1.0384	1.0190
No log	4.4444	160	1.0753	0.4689	1.0753	1.0370
No log	4.5	162	1.1138	0.4738	1.1138	1.0554
No log	4.5556	164	1.2150	0.4870	1.2150	1.1023
No log	4.6111	166	1.3546	0.4537	1.3546	1.1639
No log	4.6667	168	1.2917	0.4789	1.2917	1.1365
No log	4.7222	170	1.2019	0.4814	1.2019	1.0963
No log	4.7778	172	1.0664	0.4839	1.0664	1.0327
No log	4.8333	174	0.9870	0.5284	0.9870	0.9935
No log	4.8889	176	1.0169	0.5221	1.0169	1.0084
No log	4.9444	178	1.0204	0.5155	1.0204	1.0101
No log	5.0	180	1.0223	0.5160	1.0223	1.0111
No log	5.0556	182	1.1619	0.4766	1.1619	1.0779
No log	5.1111	184	1.2209	0.4570	1.2209	1.1049
No log	5.1667	186	1.2802	0.4279	1.2802	1.1314
No log	5.2222	188	1.2716	0.4361	1.2716	1.1277
No log	5.2778	190	1.1481	0.4602	1.1481	1.0715
No log	5.3333	192	0.9719	0.5343	0.9719	0.9858
No log	5.3889	194	0.9215	0.5257	0.9215	0.9599
No log	5.4444	196	0.8103	0.5695	0.8103	0.9001
No log	5.5	198	0.7416	0.5734	0.7416	0.8611
No log	5.5556	200	0.7722	0.5616	0.7722	0.8787
No log	5.6111	202	0.8547	0.5880	0.8547	0.9245
No log	5.6667	204	1.0304	0.5157	1.0304	1.0151
No log	5.7222	206	1.0840	0.4738	1.0840	1.0412
No log	5.7778	208	0.9757	0.5371	0.9757	0.9878
No log	5.8333	210	0.8925	0.5268	0.8925	0.9447
No log	5.8889	212	0.8798	0.5039	0.8798	0.9380
No log	5.9444	214	0.8785	0.5080	0.8785	0.9373
No log	6.0	216	0.8444	0.5201	0.8444	0.9189
No log	6.0556	218	0.8309	0.5386	0.8309	0.9116
No log	6.1111	220	0.8704	0.5741	0.8704	0.9330
No log	6.1667	222	0.8900	0.5248	0.8900	0.9434
No log	6.2222	224	0.8554	0.5671	0.8554	0.9249
No log	6.2778	226	0.8187	0.5423	0.8187	0.9048
No log	6.3333	228	0.8335	0.5268	0.8335	0.9130
No log	6.3889	230	0.9054	0.5315	0.9054	0.9515
No log	6.4444	232	1.0739	0.4761	1.0739	1.0363
No log	6.5	234	1.1473	0.4537	1.1473	1.0711
No log	6.5556	236	1.0589	0.4806	1.0589	1.0290
No log	6.6111	238	0.8938	0.5366	0.8938	0.9454
No log	6.6667	240	0.8544	0.5440	0.8544	0.9244
No log	6.7222	242	0.8528	0.5548	0.8528	0.9235
No log	6.7778	244	0.8706	0.5548	0.8706	0.9330
No log	6.8333	246	0.9462	0.5192	0.9462	0.9727
No log	6.8889	248	1.0485	0.4524	1.0485	1.0239
No log	6.9444	250	1.0549	0.4524	1.0549	1.0271
No log	7.0	252	1.0174	0.4962	1.0174	1.0087
No log	7.0556	254	0.9793	0.5152	0.9793	0.9896
No log	7.1111	256	0.9749	0.5251	0.9749	0.9874
No log	7.1667	258	0.9981	0.5071	0.9981	0.9990
No log	7.2222	260	0.9816	0.5181	0.9816	0.9907
No log	7.2778	262	1.0190	0.4696	1.0190	1.0094
No log	7.3333	264	1.0702	0.4813	1.0702	1.0345
No log	7.3889	266	1.0960	0.4589	1.0960	1.0469
No log	7.4444	268	1.0519	0.4703	1.0519	1.0256
No log	7.5	270	0.9539	0.4838	0.9539	0.9767
No log	7.5556	272	0.9185	0.5099	0.9185	0.9584
No log	7.6111	274	0.8622	0.5532	0.8622	0.9285
No log	7.6667	276	0.8433	0.5121	0.8433	0.9183
No log	7.7222	278	0.8563	0.5288	0.8563	0.9253
No log	7.7778	280	0.8936	0.5434	0.8936	0.9453
No log	7.8333	282	0.9790	0.4940	0.9790	0.9895
No log	7.8889	284	1.1041	0.4642	1.1041	1.0508
No log	7.9444	286	1.1461	0.4592	1.1461	1.0706
No log	8.0	288	1.1010	0.4642	1.1010	1.0493
No log	8.0556	290	1.0115	0.4728	1.0115	1.0057
No log	8.1111	292	0.9265	0.5304	0.9265	0.9625
No log	8.1667	294	0.8996	0.5413	0.8996	0.9485
No log	8.2222	296	0.9019	0.5511	0.9019	0.9497
No log	8.2778	298	0.9483	0.5305	0.9483	0.9738
No log	8.3333	300	1.0488	0.4640	1.0488	1.0241
No log	8.3889	302	1.1441	0.4545	1.1441	1.0696
No log	8.4444	304	1.1614	0.4632	1.1614	1.0777
No log	8.5	306	1.1119	0.4752	1.1119	1.0545
No log	8.5556	308	1.0288	0.4599	1.0288	1.0143
No log	8.6111	310	0.9372	0.5068	0.9372	0.9681
No log	8.6667	312	0.8834	0.5471	0.8834	0.9399
No log	8.7222	314	0.8732	0.5498	0.8732	0.9345
No log	8.7778	316	0.8825	0.5335	0.8825	0.9394
No log	8.8333	318	0.9094	0.5328	0.9094	0.9536
No log	8.8889	320	0.9508	0.4856	0.9508	0.9751
No log	8.9444	322	0.9803	0.4896	0.9803	0.9901
No log	9.0	324	1.0112	0.4823	1.0112	1.0056
No log	9.0556	326	1.0201	0.4823	1.0201	1.0100
No log	9.1111	328	0.9971	0.4888	0.9971	0.9985
No log	9.1667	330	0.9695	0.4801	0.9695	0.9846
No log	9.2222	332	0.9479	0.4856	0.9479	0.9736
No log	9.2778	334	0.9414	0.4856	0.9414	0.9702
No log	9.3333	336	0.9416	0.4865	0.9416	0.9704
No log	9.3889	338	0.9324	0.5035	0.9324	0.9656
No log	9.4444	340	0.9241	0.5391	0.9241	0.9613
No log	9.5	342	0.9159	0.5463	0.9159	0.9570
No log	9.5556	344	0.9172	0.5463	0.9172	0.9577
No log	9.6111	346	0.9220	0.54	0.9220	0.9602
No log	9.6667	348	0.9281	0.5150	0.9281	0.9634
No log	9.7222	350	0.9369	0.5035	0.9369	0.9680
No log	9.7778	352	0.9487	0.4865	0.9487	0.9740
No log	9.8333	354	0.9607	0.4810	0.9607	0.9802
No log	9.8889	356	0.9650	0.4810	0.9650	0.9823
No log	9.9444	358	0.9667	0.4801	0.9667	0.9832
No log	10.0	360	0.9675	0.4801	0.9675	0.9836

Framework versions

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