ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run2_AugV5_k6_task1_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: 0.6163
• Qwk: 0.7303
• Mse: 0.6163
• Rmse: 0.7850

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	5.2278	-0.0378	5.2278	2.2864
No log	0.1111	4	2.9810	0.0830	2.9810	1.7266
No log	0.1667	6	1.9175	0.1305	1.9175	1.3847
No log	0.2222	8	1.4365	0.1481	1.4365	1.1985
No log	0.2778	10	1.1411	0.3930	1.1411	1.0682
No log	0.3333	12	0.9902	0.4895	0.9902	0.9951
No log	0.3889	14	0.9784	0.5051	0.9784	0.9892
No log	0.4444	16	0.8277	0.4771	0.8277	0.9098
No log	0.5	18	1.0165	0.4065	1.0165	1.0082
No log	0.5556	20	0.9229	0.5378	0.9229	0.9607
No log	0.6111	22	0.7574	0.5975	0.7574	0.8703
No log	0.6667	24	0.9566	0.4374	0.9566	0.9780
No log	0.7222	26	0.8166	0.5511	0.8166	0.9036
No log	0.7778	28	0.8315	0.5870	0.8315	0.9118
No log	0.8333	30	1.5601	0.3689	1.5601	1.2490
No log	0.8889	32	1.4080	0.3961	1.4080	1.1866
No log	0.9444	34	0.7987	0.6330	0.7987	0.8937
No log	1.0	36	0.7202	0.6503	0.7202	0.8486
No log	1.0556	38	0.8747	0.6250	0.8747	0.9353
No log	1.1111	40	1.1230	0.5169	1.1230	1.0597
No log	1.1667	42	0.9912	0.6178	0.9912	0.9956
No log	1.2222	44	0.7656	0.6992	0.7656	0.8750
No log	1.2778	46	0.6817	0.7270	0.6817	0.8256
No log	1.3333	48	0.7062	0.7178	0.7062	0.8403
No log	1.3889	50	0.8075	0.7079	0.8075	0.8986
No log	1.4444	52	0.8552	0.7006	0.8552	0.9248
No log	1.5	54	0.7097	0.7180	0.7097	0.8424
No log	1.5556	56	0.6338	0.7128	0.6338	0.7961
No log	1.6111	58	0.5986	0.7016	0.5986	0.7737
No log	1.6667	60	0.5829	0.6960	0.5829	0.7635
No log	1.7222	62	0.6385	0.6812	0.6385	0.7990
No log	1.7778	64	0.6112	0.7087	0.6112	0.7818
No log	1.8333	66	0.6330	0.7078	0.6330	0.7956
No log	1.8889	68	0.6386	0.7199	0.6386	0.7992
No log	1.9444	70	0.5987	0.7026	0.5987	0.7737
No log	2.0	72	0.6140	0.7297	0.6140	0.7836
No log	2.0556	74	0.6468	0.7228	0.6468	0.8042
No log	2.1111	76	0.6935	0.7261	0.6935	0.8328
No log	2.1667	78	0.7497	0.6805	0.7497	0.8658
No log	2.2222	80	0.9485	0.6055	0.9485	0.9739
No log	2.2778	82	0.9646	0.6011	0.9646	0.9821
No log	2.3333	84	1.0962	0.5342	1.0962	1.0470
No log	2.3889	86	0.9266	0.6535	0.9266	0.9626
No log	2.4444	88	0.6547	0.7340	0.6547	0.8091
No log	2.5	90	0.5607	0.7695	0.5607	0.7488
No log	2.5556	92	0.5581	0.7682	0.5581	0.7471
No log	2.6111	94	0.5445	0.7638	0.5445	0.7379
No log	2.6667	96	0.5708	0.7942	0.5708	0.7555
No log	2.7222	98	0.5457	0.7756	0.5457	0.7387
No log	2.7778	100	0.5346	0.7788	0.5346	0.7312
No log	2.8333	102	0.5405	0.7679	0.5405	0.7352
No log	2.8889	104	0.7034	0.6970	0.7034	0.8387
No log	2.9444	106	0.6987	0.6787	0.6987	0.8359
No log	3.0	108	0.5383	0.7659	0.5383	0.7337
No log	3.0556	110	0.5337	0.7827	0.5337	0.7306
No log	3.1111	112	0.5643	0.7642	0.5643	0.7512
No log	3.1667	114	0.6118	0.7560	0.6118	0.7822
No log	3.2222	116	0.5466	0.7527	0.5466	0.7393
No log	3.2778	118	0.5763	0.7678	0.5763	0.7591
No log	3.3333	120	0.6328	0.7528	0.6328	0.7955
No log	3.3889	122	0.5505	0.7613	0.5505	0.7419
No log	3.4444	124	0.5732	0.7383	0.5732	0.7571
No log	3.5	126	0.6974	0.6706	0.6974	0.8351
No log	3.5556	128	0.5915	0.7373	0.5915	0.7691
No log	3.6111	130	0.5447	0.7537	0.5447	0.7380
No log	3.6667	132	0.7717	0.6907	0.7717	0.8785
No log	3.7222	134	0.7500	0.7109	0.7500	0.8660
No log	3.7778	136	0.6246	0.7589	0.6246	0.7903
No log	3.8333	138	0.6043	0.7597	0.6043	0.7773
No log	3.8889	140	0.6114	0.7450	0.6114	0.7819
No log	3.9444	142	0.7183	0.7052	0.7183	0.8475
No log	4.0	144	0.7840	0.6926	0.7840	0.8854
No log	4.0556	146	0.6827	0.7347	0.6827	0.8263
No log	4.1111	148	0.5749	0.7519	0.5749	0.7582
No log	4.1667	150	0.5599	0.7615	0.5599	0.7483
No log	4.2222	152	0.5458	0.7652	0.5458	0.7388
No log	4.2778	154	0.6301	0.7559	0.6301	0.7938
No log	4.3333	156	0.7918	0.7104	0.7918	0.8898
No log	4.3889	158	0.7216	0.7294	0.7216	0.8495
No log	4.4444	160	0.6221	0.7728	0.6221	0.7887
No log	4.5	162	0.5997	0.7562	0.5997	0.7744
No log	4.5556	164	0.6820	0.7420	0.6820	0.8258
No log	4.6111	166	0.6947	0.7342	0.6947	0.8335
No log	4.6667	168	0.7344	0.7253	0.7344	0.8570
No log	4.7222	170	0.6648	0.7307	0.6648	0.8154
No log	4.7778	172	0.5731	0.7621	0.5731	0.7570
No log	4.8333	174	0.5566	0.7449	0.5566	0.7460
No log	4.8889	176	0.5765	0.7335	0.5765	0.7593
No log	4.9444	178	0.6064	0.7632	0.6064	0.7787
No log	5.0	180	0.5944	0.7490	0.5944	0.7710
No log	5.0556	182	0.6657	0.7575	0.6657	0.8159
No log	5.1111	184	0.8490	0.7191	0.8490	0.9214
No log	5.1667	186	0.8606	0.7152	0.8606	0.9277
No log	5.2222	188	0.6973	0.7612	0.6973	0.8350
No log	5.2778	190	0.5719	0.7539	0.5719	0.7562
No log	5.3333	192	0.5498	0.7281	0.5498	0.7415
No log	5.3889	194	0.5543	0.7458	0.5543	0.7445
No log	5.4444	196	0.5465	0.7253	0.5465	0.7393
No log	5.5	198	0.5771	0.7613	0.5771	0.7597
No log	5.5556	200	0.5903	0.7752	0.5903	0.7683
No log	5.6111	202	0.5569	0.7460	0.5569	0.7463
No log	5.6667	204	0.5614	0.7270	0.5614	0.7492
No log	5.7222	206	0.5530	0.7437	0.5530	0.7437
No log	5.7778	208	0.5695	0.7559	0.5695	0.7547
No log	5.8333	210	0.6011	0.7469	0.6011	0.7753
No log	5.8889	212	0.5985	0.7507	0.5985	0.7736
No log	5.9444	214	0.5928	0.7492	0.5928	0.7699
No log	6.0	216	0.6547	0.7616	0.6547	0.8092
No log	6.0556	218	0.7045	0.7474	0.7045	0.8393
No log	6.1111	220	0.6513	0.7634	0.6513	0.8071
No log	6.1667	222	0.6317	0.7474	0.6317	0.7948
No log	6.2222	224	0.6311	0.7474	0.6311	0.7944
No log	6.2778	226	0.5978	0.7480	0.5978	0.7732
No log	6.3333	228	0.5864	0.7432	0.5864	0.7658
No log	6.3889	230	0.5830	0.7258	0.5830	0.7636
No log	6.4444	232	0.5838	0.7399	0.5838	0.7641
No log	6.5	234	0.6088	0.7525	0.6088	0.7802
No log	6.5556	236	0.6821	0.7577	0.6821	0.8259
No log	6.6111	238	0.6788	0.7686	0.6788	0.8239
No log	6.6667	240	0.6105	0.7712	0.6105	0.7814
No log	6.7222	242	0.5941	0.7309	0.5941	0.7708
No log	6.7778	244	0.6120	0.7290	0.6120	0.7823
No log	6.8333	246	0.6071	0.7290	0.6071	0.7792
No log	6.8889	248	0.5881	0.7479	0.5881	0.7669
No log	6.9444	250	0.5983	0.7667	0.5983	0.7735
No log	7.0	252	0.6325	0.7684	0.6325	0.7953
No log	7.0556	254	0.6254	0.7684	0.6254	0.7908
No log	7.1111	256	0.5848	0.7443	0.5848	0.7647
No log	7.1667	258	0.5789	0.7318	0.5789	0.7608
No log	7.2222	260	0.5839	0.7264	0.5839	0.7642
No log	7.2778	262	0.5810	0.7272	0.5810	0.7622
No log	7.3333	264	0.6042	0.7512	0.6042	0.7773
No log	7.3889	266	0.6344	0.7535	0.6344	0.7965
No log	7.4444	268	0.6295	0.7535	0.6295	0.7934
No log	7.5	270	0.6014	0.7358	0.6014	0.7755
No log	7.5556	272	0.6003	0.7358	0.6003	0.7748
No log	7.6111	274	0.6142	0.7512	0.6142	0.7837
No log	7.6667	276	0.6058	0.7358	0.6058	0.7783
No log	7.7222	278	0.5989	0.7289	0.5989	0.7739
No log	7.7778	280	0.5987	0.7342	0.5987	0.7738
No log	7.8333	282	0.6173	0.7403	0.6173	0.7857
No log	7.8889	284	0.6653	0.7599	0.6653	0.8157
No log	7.9444	286	0.7247	0.7592	0.7247	0.8513
No log	8.0	288	0.7738	0.7290	0.7738	0.8797
No log	8.0556	290	0.7535	0.7430	0.7535	0.8680
No log	8.1111	292	0.6911	0.7704	0.6911	0.8313
No log	8.1667	294	0.6335	0.7371	0.6335	0.7959
No log	8.2222	296	0.6060	0.7214	0.6060	0.7785
No log	8.2778	298	0.6013	0.7189	0.6013	0.7754
No log	8.3333	300	0.6004	0.7160	0.6004	0.7749
No log	8.3889	302	0.6075	0.7162	0.6075	0.7794
No log	8.4444	304	0.6285	0.7206	0.6285	0.7928
No log	8.5	306	0.6486	0.7571	0.6486	0.8054
No log	8.5556	308	0.6612	0.7548	0.6612	0.8132
No log	8.6111	310	0.6610	0.7508	0.6610	0.8130
No log	8.6667	312	0.6373	0.7421	0.6373	0.7983
No log	8.7222	314	0.6230	0.7302	0.6230	0.7893
No log	8.7778	316	0.6050	0.7392	0.6050	0.7778
No log	8.8333	318	0.5960	0.7420	0.5960	0.7720
No log	8.8889	320	0.5921	0.7259	0.5921	0.7695
No log	8.9444	322	0.5930	0.7482	0.5930	0.7701
No log	9.0	324	0.5948	0.7482	0.5948	0.7712
No log	9.0556	326	0.6010	0.7521	0.6010	0.7753
No log	9.1111	328	0.6069	0.7521	0.6069	0.7790
No log	9.1667	330	0.6102	0.7392	0.6102	0.7811
No log	9.2222	332	0.6134	0.7325	0.6134	0.7832
No log	9.2778	334	0.6147	0.7303	0.6147	0.7840
No log	9.3333	336	0.6141	0.7303	0.6141	0.7837
No log	9.3889	338	0.6126	0.7325	0.6126	0.7827
No log	9.4444	340	0.6081	0.7521	0.6081	0.7798
No log	9.5	342	0.6039	0.7521	0.6039	0.7771
No log	9.5556	344	0.6025	0.7521	0.6025	0.7762
No log	9.6111	346	0.6009	0.7521	0.6009	0.7752
No log	9.6667	348	0.6021	0.7521	0.6021	0.7760
No log	9.7222	350	0.6041	0.7521	0.6041	0.7773
No log	9.7778	352	0.6078	0.7347	0.6078	0.7796
No log	9.8333	354	0.6112	0.7302	0.6112	0.7818
No log	9.8889	356	0.6142	0.7303	0.6142	0.7837
No log	9.9444	358	0.6156	0.7303	0.6156	0.7846
No log	10.0	360	0.6163	0.7303	0.6163	0.7850

Framework versions

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