ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k9_task5_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: 0.8637
• Qwk: 0.5006
• Mse: 0.8637
• Rmse: 0.9294

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0833	2	4.1156	0.0024	4.1156	2.0287
No log	0.1667	4	1.9847	0.0633	1.9847	1.4088
No log	0.25	6	1.2650	0.0232	1.2650	1.1247
No log	0.3333	8	1.1427	0.1296	1.1427	1.0690
No log	0.4167	10	1.4212	0.0273	1.4212	1.1921
No log	0.5	12	1.4854	0.1438	1.4854	1.2188
No log	0.5833	14	1.3519	0.0170	1.3519	1.1627
No log	0.6667	16	1.3687	0.0712	1.3687	1.1699
No log	0.75	18	1.0846	0.2539	1.0846	1.0414
No log	0.8333	20	1.0034	0.2035	1.0034	1.0017
No log	0.9167	22	1.1764	0.0427	1.1764	1.0846
No log	1.0	24	1.6202	0.0399	1.6202	1.2729
No log	1.0833	26	1.7089	0.0651	1.7089	1.3073
No log	1.1667	28	1.2862	-0.0296	1.2862	1.1341
No log	1.25	30	1.0896	0.2734	1.0896	1.0438
No log	1.3333	32	1.1734	0.2150	1.1734	1.0833
No log	1.4167	34	1.1268	0.1910	1.1268	1.0615
No log	1.5	36	1.1471	0.1910	1.1471	1.0710
No log	1.5833	38	1.2530	0.0380	1.2530	1.1194
No log	1.6667	40	1.1814	0.1910	1.1814	1.0869
No log	1.75	42	1.1412	0.2150	1.1412	1.0683
No log	1.8333	44	1.1151	0.2150	1.1151	1.0560
No log	1.9167	46	1.1561	0.2295	1.1561	1.0752
No log	2.0	48	1.1455	0.2150	1.1455	1.0703
No log	2.0833	50	1.1505	0.2150	1.1505	1.0726
No log	2.1667	52	1.0827	0.1979	1.0827	1.0405
No log	2.25	54	1.0039	0.2416	1.0039	1.0019
No log	2.3333	56	0.9863	0.2068	0.9863	0.9931
No log	2.4167	58	1.0020	0.2441	1.0020	1.0010
No log	2.5	60	1.1079	0.2175	1.1079	1.0526
No log	2.5833	62	1.1474	0.2143	1.1474	1.0712
No log	2.6667	64	0.9963	0.2781	0.9963	0.9981
No log	2.75	66	0.9530	0.2390	0.9530	0.9762
No log	2.8333	68	1.0258	0.0445	1.0258	1.0128
No log	2.9167	70	0.9939	0.1076	0.9939	0.9970
No log	3.0	72	0.9553	0.2912	0.9553	0.9774
No log	3.0833	74	1.0256	0.2731	1.0256	1.0127
No log	3.1667	76	1.1163	0.2260	1.1163	1.0566
No log	3.25	78	1.0419	0.3131	1.0419	1.0207
No log	3.3333	80	0.9537	0.3370	0.9537	0.9766
No log	3.4167	82	0.9233	0.4438	0.9233	0.9609
No log	3.5	84	0.9231	0.4275	0.9231	0.9608
No log	3.5833	86	0.9396	0.4365	0.9396	0.9693
No log	3.6667	88	0.9266	0.4915	0.9266	0.9626
No log	3.75	90	0.8538	0.4769	0.8538	0.9240
No log	3.8333	92	0.7824	0.6133	0.7824	0.8845
No log	3.9167	94	0.7449	0.5035	0.7449	0.8631
No log	4.0	96	0.7973	0.4421	0.7973	0.8929
No log	4.0833	98	1.0362	0.3283	1.0362	1.0180
No log	4.1667	100	1.1811	0.3001	1.1811	1.0868
No log	4.25	102	1.0545	0.3218	1.0545	1.0269
No log	4.3333	104	0.7491	0.4949	0.7491	0.8655
No log	4.4167	106	0.6625	0.5446	0.6625	0.8139
No log	4.5	108	0.6912	0.5329	0.6912	0.8314
No log	4.5833	110	0.7396	0.4444	0.7396	0.8600
No log	4.6667	112	0.7370	0.5057	0.7370	0.8585
No log	4.75	114	0.7602	0.5127	0.7602	0.8719
No log	4.8333	116	0.7782	0.4615	0.7782	0.8821
No log	4.9167	118	0.8226	0.5065	0.8226	0.9070
No log	5.0	120	0.9131	0.4051	0.9131	0.9556
No log	5.0833	122	0.8026	0.5079	0.8026	0.8959
No log	5.1667	124	0.7402	0.4962	0.7402	0.8603
No log	5.25	126	0.7355	0.5512	0.7355	0.8576
No log	5.3333	128	0.8009	0.5181	0.8009	0.8950
No log	5.4167	130	0.9723	0.4252	0.9723	0.9860
No log	5.5	132	0.8379	0.5538	0.8379	0.9154
No log	5.5833	134	0.7056	0.5692	0.7056	0.8400
No log	5.6667	136	0.8537	0.5019	0.8537	0.9240
No log	5.75	138	0.7698	0.4893	0.7698	0.8774
No log	5.8333	140	0.6772	0.5949	0.6772	0.8229
No log	5.9167	142	0.7273	0.5540	0.7273	0.8528
No log	6.0	144	0.6866	0.6043	0.6866	0.8286
No log	6.0833	146	0.6664	0.5485	0.6664	0.8163
No log	6.1667	148	0.6526	0.5262	0.6526	0.8079
No log	6.25	150	0.6654	0.6325	0.6654	0.8157
No log	6.3333	152	0.6916	0.6315	0.6916	0.8316
No log	6.4167	154	0.6888	0.5980	0.6888	0.8300
No log	6.5	156	0.7031	0.5980	0.7031	0.8385
No log	6.5833	158	0.7387	0.5869	0.7387	0.8595
No log	6.6667	160	0.7054	0.5680	0.7054	0.8399
No log	6.75	162	0.7433	0.5759	0.7433	0.8621
No log	6.8333	164	0.7516	0.5890	0.7516	0.8669
No log	6.9167	166	0.7267	0.5659	0.7267	0.8525
No log	7.0	168	0.7372	0.5204	0.7372	0.8586
No log	7.0833	170	0.6637	0.6307	0.6637	0.8147
No log	7.1667	172	0.6463	0.6762	0.6463	0.8040
No log	7.25	174	0.6659	0.5955	0.6659	0.8160
No log	7.3333	176	0.6305	0.6610	0.6305	0.7941
No log	7.4167	178	0.7525	0.5735	0.7525	0.8675
No log	7.5	180	0.7804	0.5443	0.7804	0.8834
No log	7.5833	182	0.6914	0.5546	0.6914	0.8315
No log	7.6667	184	0.6455	0.6456	0.6455	0.8035
No log	7.75	186	0.6756	0.6165	0.6756	0.8220
No log	7.8333	188	0.7470	0.5397	0.7470	0.8643
No log	7.9167	190	0.7351	0.5751	0.7351	0.8574
No log	8.0	192	0.7066	0.6724	0.7066	0.8406
No log	8.0833	194	0.7464	0.5774	0.7464	0.8639
No log	8.1667	196	0.8733	0.4470	0.8733	0.9345
No log	8.25	198	0.8660	0.4588	0.8660	0.9306
No log	8.3333	200	0.8049	0.5195	0.8049	0.8972
No log	8.4167	202	0.7886	0.5160	0.7886	0.8880
No log	8.5	204	0.8057	0.5301	0.8057	0.8976
No log	8.5833	206	0.7984	0.5017	0.7984	0.8935
No log	8.6667	208	0.8061	0.4375	0.8061	0.8978
No log	8.75	210	0.7886	0.4757	0.7886	0.8880
No log	8.8333	212	0.7849	0.4757	0.7849	0.8860
No log	8.9167	214	0.7977	0.4974	0.7977	0.8931
No log	9.0	216	0.7873	0.5261	0.7873	0.8873
No log	9.0833	218	0.7912	0.5248	0.7912	0.8895
No log	9.1667	220	0.7933	0.5473	0.7933	0.8907
No log	9.25	222	0.7869	0.5798	0.7869	0.8871
No log	9.3333	224	0.7804	0.5607	0.7804	0.8834
No log	9.4167	226	0.7603	0.5540	0.7603	0.8720
No log	9.5	228	0.7409	0.5614	0.7409	0.8607
No log	9.5833	230	0.7791	0.5425	0.7791	0.8826
No log	9.6667	232	0.7731	0.5635	0.7731	0.8793
No log	9.75	234	0.8072	0.5480	0.8072	0.8984
No log	9.8333	236	0.8572	0.4834	0.8572	0.9259
No log	9.9167	238	0.8640	0.4450	0.8640	0.9295
No log	10.0	240	0.8661	0.4537	0.8661	0.9306
No log	10.0833	242	0.8893	0.4455	0.8893	0.9430
No log	10.1667	244	0.9922	0.4021	0.9922	0.9961
No log	10.25	246	0.9191	0.4749	0.9191	0.9587
No log	10.3333	248	0.8825	0.4524	0.8825	0.9394
No log	10.4167	250	0.9169	0.4517	0.9169	0.9576
No log	10.5	252	0.8244	0.4871	0.8244	0.9080
No log	10.5833	254	0.8333	0.4849	0.8333	0.9128
No log	10.6667	256	0.8249	0.5393	0.8249	0.9082
No log	10.75	258	0.8161	0.5518	0.8161	0.9034
No log	10.8333	260	0.8809	0.4533	0.8809	0.9386
No log	10.9167	262	0.8583	0.4954	0.8583	0.9264
No log	11.0	264	0.8377	0.5796	0.8377	0.9153
No log	11.0833	266	0.8677	0.4963	0.8677	0.9315
No log	11.1667	268	0.8346	0.5692	0.8346	0.9136
No log	11.25	270	0.8804	0.4440	0.8804	0.9383
No log	11.3333	272	0.9052	0.4601	0.9052	0.9514
No log	11.4167	274	0.8369	0.4812	0.8369	0.9148
No log	11.5	276	0.7762	0.5657	0.7762	0.8810
No log	11.5833	278	0.7999	0.5266	0.7999	0.8944
No log	11.6667	280	0.8398	0.5358	0.8398	0.9164
No log	11.75	282	0.8308	0.4917	0.8308	0.9115
No log	11.8333	284	0.8018	0.5167	0.8018	0.8954
No log	11.9167	286	0.7511	0.6122	0.7511	0.8667
No log	12.0	288	0.7322	0.6133	0.7322	0.8557
No log	12.0833	290	0.7247	0.5880	0.7247	0.8513
No log	12.1667	292	0.8142	0.5179	0.8142	0.9023
No log	12.25	294	0.8001	0.5769	0.8001	0.8945
No log	12.3333	296	0.6968	0.5763	0.6968	0.8348
No log	12.4167	298	0.6928	0.5523	0.6928	0.8323
No log	12.5	300	0.7125	0.5996	0.7125	0.8441
No log	12.5833	302	0.8755	0.4563	0.8755	0.9357
No log	12.6667	304	1.0060	0.4458	1.0060	1.0030
No log	12.75	306	0.9694	0.4458	0.9694	0.9846
No log	12.8333	308	0.8415	0.5030	0.8415	0.9174
No log	12.9167	310	0.7671	0.5875	0.7671	0.8758
No log	13.0	312	0.8096	0.5030	0.8096	0.8998
No log	13.0833	314	0.7883	0.4923	0.7883	0.8879
No log	13.1667	316	0.7140	0.5869	0.7140	0.8450
No log	13.25	318	0.7027	0.5455	0.7027	0.8383
No log	13.3333	320	0.7335	0.5291	0.7335	0.8564
No log	13.4167	322	0.7474	0.4952	0.7474	0.8645
No log	13.5	324	0.7092	0.5597	0.7092	0.8422
No log	13.5833	326	0.7149	0.5107	0.7149	0.8455
No log	13.6667	328	0.7031	0.6032	0.7031	0.8385
No log	13.75	330	0.6923	0.6272	0.6923	0.8320
No log	13.8333	332	0.6705	0.6282	0.6705	0.8188
No log	13.9167	334	0.7330	0.6099	0.7330	0.8562
No log	14.0	336	0.8160	0.5414	0.8160	0.9033
No log	14.0833	338	0.7365	0.5988	0.7365	0.8582
No log	14.1667	340	0.6825	0.5869	0.6825	0.8261
No log	14.25	342	0.6908	0.5676	0.6908	0.8311
No log	14.3333	344	0.6769	0.5610	0.6769	0.8227
No log	14.4167	346	0.6834	0.6154	0.6834	0.8267
No log	14.5	348	0.7136	0.6272	0.7136	0.8448
No log	14.5833	350	0.6757	0.6605	0.6757	0.8220
No log	14.6667	352	0.6621	0.5736	0.6621	0.8137
No log	14.75	354	0.6884	0.5311	0.6884	0.8297
No log	14.8333	356	0.6680	0.5843	0.6680	0.8173
No log	14.9167	358	0.6779	0.6282	0.6779	0.8234
No log	15.0	360	0.7273	0.6343	0.7273	0.8528
No log	15.0833	362	0.6737	0.6282	0.6737	0.8208
No log	15.1667	364	0.6618	0.5536	0.6618	0.8135
No log	15.25	366	0.6695	0.5190	0.6695	0.8182
No log	15.3333	368	0.6731	0.5032	0.6731	0.8204
No log	15.4167	370	0.7753	0.5253	0.7753	0.8805
No log	15.5	372	0.8483	0.5094	0.8483	0.9210
No log	15.5833	374	0.7973	0.4885	0.7973	0.8929
No log	15.6667	376	0.7028	0.5626	0.7028	0.8383
No log	15.75	378	0.6902	0.5821	0.6902	0.8308
No log	15.8333	380	0.7244	0.5798	0.7244	0.8511
No log	15.9167	382	0.7382	0.5821	0.7382	0.8592
No log	16.0	384	0.7499	0.5729	0.7499	0.8660
No log	16.0833	386	0.7119	0.4759	0.7119	0.8438
No log	16.1667	388	0.7239	0.4708	0.7239	0.8508
No log	16.25	390	0.7921	0.4140	0.7921	0.8900
No log	16.3333	392	0.7892	0.4169	0.7892	0.8884
No log	16.4167	394	0.7330	0.4722	0.7330	0.8562
No log	16.5	396	0.7031	0.5342	0.7031	0.8385
No log	16.5833	398	0.7007	0.5648	0.7007	0.8370
No log	16.6667	400	0.6922	0.5487	0.6922	0.8320
No log	16.75	402	0.7131	0.5204	0.7131	0.8445
No log	16.8333	404	0.6935	0.4838	0.6935	0.8328
No log	16.9167	406	0.6818	0.5610	0.6818	0.8257
No log	17.0	408	0.6771	0.6165	0.6771	0.8229
No log	17.0833	410	0.6718	0.6165	0.6718	0.8196
No log	17.1667	412	0.6608	0.5822	0.6608	0.8129
No log	17.25	414	0.6583	0.6046	0.6583	0.8114
No log	17.3333	416	0.6529	0.6249	0.6529	0.8080
No log	17.4167	418	0.6515	0.5842	0.6515	0.8071
No log	17.5	420	0.6582	0.6045	0.6582	0.8113
No log	17.5833	422	0.6435	0.5842	0.6435	0.8022
No log	17.6667	424	0.6573	0.5843	0.6573	0.8107
No log	17.75	426	0.6720	0.5300	0.6720	0.8198
No log	17.8333	428	0.7136	0.4879	0.7136	0.8447
No log	17.9167	430	0.7204	0.4990	0.7204	0.8487
No log	18.0	432	0.6941	0.4976	0.6941	0.8331
No log	18.0833	434	0.6901	0.5822	0.6901	0.8307
No log	18.1667	436	0.7176	0.5607	0.7176	0.8471
No log	18.25	438	0.6984	0.5880	0.6984	0.8357
No log	18.3333	440	0.7001	0.5785	0.7001	0.8367
No log	18.4167	442	0.7379	0.5494	0.7379	0.8590
No log	18.5	444	0.7438	0.5688	0.7438	0.8624
No log	18.5833	446	0.7111	0.5763	0.7111	0.8433
No log	18.6667	448	0.6999	0.5415	0.6999	0.8366
No log	18.75	450	0.7056	0.5542	0.7056	0.8400
No log	18.8333	452	0.6932	0.5415	0.6932	0.8326
No log	18.9167	454	0.7013	0.5626	0.7013	0.8374
No log	19.0	456	0.7402	0.5852	0.7402	0.8604
No log	19.0833	458	0.7169	0.5607	0.7169	0.8467
No log	19.1667	460	0.7088	0.5682	0.7088	0.8419
No log	19.25	462	0.7549	0.5313	0.7549	0.8688
No log	19.3333	464	0.7513	0.5192	0.7513	0.8668
No log	19.4167	466	0.7330	0.5534	0.7330	0.8561
No log	19.5	468	0.7360	0.6018	0.7360	0.8579
No log	19.5833	470	0.7205	0.5224	0.7205	0.8488
No log	19.6667	472	0.7119	0.4787	0.7119	0.8438
No log	19.75	474	0.7099	0.5054	0.7099	0.8426
No log	19.8333	476	0.7128	0.5135	0.7128	0.8443
No log	19.9167	478	0.7651	0.6035	0.7651	0.8747
No log	20.0	480	0.8247	0.5030	0.8247	0.9081
No log	20.0833	482	0.8015	0.5650	0.8015	0.8953
No log	20.1667	484	0.7547	0.6018	0.7547	0.8688
No log	20.25	486	0.7733	0.5365	0.7733	0.8794
No log	20.3333	488	0.7717	0.5494	0.7717	0.8785
No log	20.4167	490	0.7635	0.6014	0.7635	0.8738
No log	20.5	492	0.7776	0.5305	0.7776	0.8818
No log	20.5833	494	0.7680	0.5274	0.7680	0.8764
No log	20.6667	496	0.7627	0.5260	0.7627	0.8733
No log	20.75	498	0.7770	0.5410	0.7770	0.8815
0.3443	20.8333	500	0.7779	0.5410	0.7779	0.8820
0.3443	20.9167	502	0.7935	0.5267	0.7935	0.8908
0.3443	21.0	504	0.7742	0.5395	0.7742	0.8799
0.3443	21.0833	506	0.7391	0.5763	0.7391	0.8597
0.3443	21.1667	508	0.7404	0.4802	0.7404	0.8604
0.3443	21.25	510	0.7505	0.4802	0.7505	0.8663
0.3443	21.3333	512	0.7737	0.5392	0.7737	0.8796
0.3443	21.4167	514	0.8642	0.5211	0.8642	0.9296
0.3443	21.5	516	0.8637	0.5006	0.8637	0.9294

Framework versions

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