ArabicNewSplits6_FineTuningAraBERT_run1_AugV5_k8_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: 0.7431
• Qwk: 0.5374
• Mse: 0.7431
• Rmse: 0.8620

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	0.0476	2	4.2643	-0.0272	4.2643	2.0650
No log	0.0952	4	2.3674	-0.0155	2.3674	1.5386
No log	0.1429	6	1.7937	-0.0612	1.7937	1.3393
No log	0.1905	8	1.4498	-0.0147	1.4498	1.2041
No log	0.2381	10	0.8651	0.0116	0.8651	0.9301
No log	0.2857	12	0.7024	0.2285	0.7024	0.8381
No log	0.3333	14	1.1636	0.0614	1.1636	1.0787
No log	0.3810	16	1.7932	0.0766	1.7932	1.3391
No log	0.4286	18	1.3799	0.0696	1.3799	1.1747
No log	0.4762	20	0.8291	0.0721	0.8291	0.9105
No log	0.5238	22	0.7637	0.1427	0.7637	0.8739
No log	0.5714	24	0.8074	0.1094	0.8074	0.8986
No log	0.6190	26	0.8367	0.1514	0.8367	0.9147
No log	0.6667	28	0.9543	0.0605	0.9543	0.9769
No log	0.7143	30	1.0748	0.0324	1.0748	1.0367
No log	0.7619	32	1.0329	0.0837	1.0329	1.0163
No log	0.8095	34	0.8956	0.1675	0.8956	0.9463
No log	0.8571	36	0.7553	0.2493	0.7553	0.8691
No log	0.9048	38	0.6688	0.2541	0.6688	0.8178
No log	0.9524	40	0.6670	0.2886	0.6670	0.8167
No log	1.0	42	0.7782	0.1899	0.7782	0.8822
No log	1.0476	44	0.9945	0.0207	0.9945	0.9972
No log	1.0952	46	0.9893	0.0318	0.9893	0.9946
No log	1.1429	48	1.0038	0.0254	1.0038	1.0019
No log	1.1905	50	1.0579	0.0432	1.0579	1.0285
No log	1.2381	52	0.9902	0.0569	0.9902	0.9951
No log	1.2857	54	0.7999	0.1904	0.7999	0.8944
No log	1.3333	56	0.6517	0.36	0.6517	0.8073
No log	1.3810	58	0.6618	0.3862	0.6618	0.8135
No log	1.4286	60	0.6647	0.4350	0.6647	0.8153
No log	1.4762	62	0.6762	0.3962	0.6762	0.8223
No log	1.5238	64	0.8612	0.2603	0.8612	0.9280
No log	1.5714	66	1.1005	0.2324	1.1005	1.0490
No log	1.6190	68	1.2080	0.2675	1.2080	1.0991
No log	1.6667	70	1.2148	0.2596	1.2148	1.1022
No log	1.7143	72	1.0721	0.2825	1.0721	1.0354
No log	1.7619	74	0.8291	0.2752	0.8291	0.9106
No log	1.8095	76	0.6806	0.3763	0.6806	0.8250
No log	1.8571	78	0.6188	0.4055	0.6188	0.7866
No log	1.9048	80	0.6050	0.4524	0.6050	0.7778
No log	1.9524	82	0.6120	0.4055	0.6120	0.7823
No log	2.0	84	0.6267	0.3679	0.6267	0.7917
No log	2.0476	86	0.6266	0.3713	0.6266	0.7916
No log	2.0952	88	0.6115	0.3475	0.6115	0.7820
No log	2.1429	90	0.6082	0.3617	0.6082	0.7799
No log	2.1905	92	0.5993	0.3676	0.5993	0.7742
No log	2.2381	94	0.6105	0.4124	0.6104	0.7813
No log	2.2857	96	0.6030	0.4055	0.6030	0.7765
No log	2.3333	98	0.6579	0.4851	0.6579	0.8111
No log	2.3810	100	0.7684	0.4623	0.7684	0.8766
No log	2.4286	102	0.7660	0.4517	0.7660	0.8752
No log	2.4762	104	0.7412	0.5003	0.7412	0.8609
No log	2.5238	106	0.8013	0.4486	0.8013	0.8952
No log	2.5714	108	0.9928	0.4103	0.9928	0.9964
No log	2.6190	110	1.2224	0.3263	1.2224	1.1056
No log	2.6667	112	1.2344	0.3226	1.2344	1.1111
No log	2.7143	114	0.9693	0.4027	0.9693	0.9845
No log	2.7619	116	0.7182	0.4860	0.7182	0.8475
No log	2.8095	118	0.7037	0.5217	0.7037	0.8389
No log	2.8571	120	0.6845	0.5155	0.6845	0.8274
No log	2.9048	122	0.6743	0.5108	0.6743	0.8212
No log	2.9524	124	0.6883	0.4703	0.6883	0.8296
No log	3.0	126	0.6357	0.4744	0.6357	0.7973
No log	3.0476	128	0.6316	0.5152	0.6316	0.7947
No log	3.0952	130	0.6997	0.4826	0.6997	0.8365
No log	3.1429	132	0.6934	0.4779	0.6934	0.8327
No log	3.1905	134	0.6511	0.5391	0.6511	0.8069
No log	3.2381	136	0.7307	0.5007	0.7307	0.8548
No log	3.2857	138	0.9730	0.3697	0.9730	0.9864
No log	3.3333	140	1.0346	0.3800	1.0346	1.0172
No log	3.3810	142	0.9190	0.4154	0.9190	0.9587
No log	3.4286	144	0.7526	0.4813	0.7526	0.8675
No log	3.4762	146	0.7058	0.5078	0.7058	0.8401
No log	3.5238	148	0.7077	0.5384	0.7077	0.8412
No log	3.5714	150	0.6799	0.5384	0.6799	0.8245
No log	3.6190	152	0.6583	0.5144	0.6583	0.8114
No log	3.6667	154	0.6795	0.5269	0.6795	0.8243
No log	3.7143	156	0.6899	0.5014	0.6899	0.8306
No log	3.7619	158	0.7458	0.4884	0.7458	0.8636
No log	3.8095	160	0.7543	0.4884	0.7543	0.8685
No log	3.8571	162	0.6724	0.4891	0.6724	0.8200
No log	3.9048	164	0.6133	0.5208	0.6133	0.7832
No log	3.9524	166	0.6447	0.5053	0.6447	0.8029
No log	4.0	168	0.6902	0.4961	0.6902	0.8308
No log	4.0476	170	0.7093	0.4909	0.7093	0.8422
No log	4.0952	172	0.6953	0.5018	0.6953	0.8338
No log	4.1429	174	0.7325	0.5359	0.7325	0.8559
No log	4.1905	176	0.8178	0.4787	0.8178	0.9043
No log	4.2381	178	0.8477	0.4775	0.8477	0.9207
No log	4.2857	180	0.8415	0.4856	0.8415	0.9173
No log	4.3333	182	0.8428	0.5738	0.8428	0.9181
No log	4.3810	184	0.8483	0.5143	0.8483	0.9210
No log	4.4286	186	0.8365	0.5033	0.8365	0.9146
No log	4.4762	188	0.8308	0.5143	0.8308	0.9115
No log	4.5238	190	0.8240	0.5188	0.8240	0.9077
No log	4.5714	192	0.8062	0.5182	0.8062	0.8979
No log	4.6190	194	0.7907	0.5092	0.7907	0.8892
No log	4.6667	196	0.7820	0.4548	0.7820	0.8843
No log	4.7143	198	0.7536	0.4983	0.7536	0.8681
No log	4.7619	200	0.7307	0.5477	0.7307	0.8548
No log	4.8095	202	0.7217	0.5522	0.7217	0.8495
No log	4.8571	204	0.7172	0.5242	0.7172	0.8469
No log	4.9048	206	0.7080	0.5476	0.7080	0.8414
No log	4.9524	208	0.7560	0.4832	0.7560	0.8695
No log	5.0	210	0.8508	0.4605	0.8508	0.9224
No log	5.0476	212	0.8901	0.4621	0.8901	0.9434
No log	5.0952	214	0.8296	0.4605	0.8296	0.9108
No log	5.1429	216	0.7279	0.5162	0.7279	0.8532
No log	5.1905	218	0.6739	0.5490	0.6739	0.8209
No log	5.2381	220	0.6930	0.5281	0.6930	0.8325
No log	5.2857	222	0.7365	0.5211	0.7365	0.8582
No log	5.3333	224	0.7206	0.5153	0.7206	0.8489
No log	5.3810	226	0.6819	0.5660	0.6819	0.8258
No log	5.4286	228	0.6760	0.5419	0.6760	0.8222
No log	5.4762	230	0.6778	0.5446	0.6778	0.8233
No log	5.5238	232	0.7065	0.5495	0.7065	0.8405
No log	5.5714	234	0.7526	0.5272	0.7526	0.8675
No log	5.6190	236	0.8051	0.5119	0.8051	0.8973
No log	5.6667	238	0.8200	0.5269	0.8200	0.9055
No log	5.7143	240	0.7994	0.5295	0.7994	0.8941
No log	5.7619	242	0.8060	0.5129	0.8060	0.8978
No log	5.8095	244	0.8004	0.5020	0.8004	0.8947
No log	5.8571	246	0.7796	0.5367	0.7796	0.8830
No log	5.9048	248	0.7758	0.5577	0.7758	0.8808
No log	5.9524	250	0.7753	0.5523	0.7753	0.8805
No log	6.0	252	0.7865	0.5603	0.7865	0.8868
No log	6.0476	254	0.7977	0.5412	0.7977	0.8931
No log	6.0952	256	0.7979	0.5398	0.7979	0.8933
No log	6.1429	258	0.7718	0.5563	0.7718	0.8785
No log	6.1905	260	0.7581	0.5708	0.7581	0.8707
No log	6.2381	262	0.7644	0.5297	0.7644	0.8743
No log	6.2857	264	0.7336	0.5708	0.7336	0.8565
No log	6.3333	266	0.6949	0.5307	0.6949	0.8336
No log	6.3810	268	0.6972	0.4931	0.6972	0.8350
No log	6.4286	270	0.7076	0.5286	0.7076	0.8412
No log	6.4762	272	0.6866	0.5252	0.6866	0.8286
No log	6.5238	274	0.6649	0.4797	0.6649	0.8154
No log	6.5714	276	0.6748	0.5249	0.6748	0.8215
No log	6.6190	278	0.6993	0.5229	0.6993	0.8363
No log	6.6667	280	0.6964	0.5068	0.6964	0.8345
No log	6.7143	282	0.6892	0.5197	0.6892	0.8302
No log	6.7619	284	0.6935	0.5367	0.6935	0.8328
No log	6.8095	286	0.7097	0.5078	0.7097	0.8424
No log	6.8571	288	0.7249	0.4959	0.7249	0.8514
No log	6.9048	290	0.7414	0.5320	0.7414	0.8610
No log	6.9524	292	0.7677	0.5523	0.7677	0.8762
No log	7.0	294	0.7923	0.5510	0.7923	0.8901
No log	7.0476	296	0.8105	0.5341	0.8105	0.9003
No log	7.0952	298	0.8258	0.5309	0.8258	0.9087
No log	7.1429	300	0.8383	0.5179	0.8383	0.9156
No log	7.1905	302	0.8341	0.5183	0.8341	0.9133
No log	7.2381	304	0.8194	0.5108	0.8194	0.9052
No log	7.2857	306	0.8188	0.5310	0.8188	0.9049
No log	7.3333	308	0.8222	0.5019	0.8222	0.9067
No log	7.3810	310	0.8184	0.4948	0.8184	0.9046
No log	7.4286	312	0.8234	0.4741	0.8234	0.9074
No log	7.4762	314	0.7983	0.4947	0.7983	0.8935
No log	7.5238	316	0.7761	0.5098	0.7761	0.8810
No log	7.5714	318	0.7569	0.5124	0.7569	0.8700
No log	7.6190	320	0.7484	0.5349	0.7484	0.8651
No log	7.6667	322	0.7492	0.5293	0.7492	0.8656
No log	7.7143	324	0.7569	0.5022	0.7569	0.8700
No log	7.7619	326	0.7687	0.5052	0.7687	0.8768
No log	7.8095	328	0.7673	0.4918	0.7673	0.8759
No log	7.8571	330	0.7580	0.4935	0.7580	0.8706
No log	7.9048	332	0.7504	0.5113	0.7504	0.8663
No log	7.9524	334	0.7378	0.5130	0.7378	0.8590
No log	8.0	336	0.7317	0.5130	0.7317	0.8554
No log	8.0476	338	0.7300	0.5043	0.7300	0.8544
No log	8.0952	340	0.7266	0.4720	0.7266	0.8524
No log	8.1429	342	0.7240	0.5187	0.7240	0.8509
No log	8.1905	344	0.7311	0.4909	0.7311	0.8550
No log	8.2381	346	0.7443	0.5023	0.7443	0.8627
No log	8.2857	348	0.7549	0.5071	0.7549	0.8688
No log	8.3333	350	0.7570	0.4878	0.7570	0.8700
No log	8.3810	352	0.7603	0.4885	0.7603	0.8719
No log	8.4286	354	0.7582	0.4975	0.7582	0.8708
No log	8.4762	356	0.7587	0.4790	0.7587	0.8711
No log	8.5238	358	0.7622	0.4790	0.7622	0.8731
No log	8.5714	360	0.7662	0.5064	0.7662	0.8753
No log	8.6190	362	0.7698	0.5041	0.7698	0.8774
No log	8.6667	364	0.7763	0.5067	0.7763	0.8811
No log	8.7143	366	0.7825	0.5093	0.7825	0.8846
No log	8.7619	368	0.7830	0.5185	0.7830	0.8848
No log	8.8095	370	0.7844	0.5041	0.7844	0.8857
No log	8.8571	372	0.7864	0.5016	0.7864	0.8868
No log	8.9048	374	0.7889	0.4938	0.7889	0.8882
No log	8.9524	376	0.7939	0.4912	0.7939	0.8910
No log	9.0	378	0.8039	0.4750	0.8039	0.8966
No log	9.0476	380	0.8084	0.4911	0.8084	0.8991
No log	9.0952	382	0.8059	0.4965	0.8059	0.8977
No log	9.1429	384	0.8015	0.4965	0.8015	0.8953
No log	9.1905	386	0.7907	0.4918	0.7907	0.8892
No log	9.2381	388	0.7820	0.4810	0.7820	0.8843
No log	9.2857	390	0.7721	0.4975	0.7721	0.8787
No log	9.3333	392	0.7649	0.4975	0.7649	0.8746
No log	9.3810	394	0.7587	0.4975	0.7587	0.8711
No log	9.4286	396	0.7554	0.4975	0.7554	0.8691
No log	9.4762	398	0.7524	0.5048	0.7524	0.8674
No log	9.5238	400	0.7524	0.5097	0.7524	0.8674
No log	9.5714	402	0.7514	0.5097	0.7514	0.8668
No log	9.6190	404	0.7507	0.5097	0.7507	0.8664
No log	9.6667	406	0.7482	0.5097	0.7482	0.8650
No log	9.7143	408	0.7455	0.5097	0.7455	0.8634
No log	9.7619	410	0.7436	0.5170	0.7436	0.8623
No log	9.8095	412	0.7427	0.5170	0.7427	0.8618
No log	9.8571	414	0.7426	0.5374	0.7426	0.8617
No log	9.9048	416	0.7427	0.5374	0.7427	0.8618
No log	9.9524	418	0.7429	0.5374	0.7429	0.8619
No log	10.0	420	0.7431	0.5374	0.7431	0.8620

Framework versions

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