ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k2_task7_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: 0.4576
• Qwk: 0.5927
• Mse: 0.4576
• Rmse: 0.6765

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	0.25	2	2.4023	0.0052	2.4023	1.5499
No log	0.5	4	1.1655	0.1259	1.1655	1.0796
No log	0.75	6	0.7541	0.1372	0.7541	0.8684
No log	1.0	8	0.7285	0.2319	0.7285	0.8535
No log	1.25	10	0.6985	0.2783	0.6985	0.8357
No log	1.5	12	0.8415	0.2375	0.8415	0.9173
No log	1.75	14	0.6713	0.3029	0.6713	0.8194
No log	2.0	16	0.6546	0.3690	0.6546	0.8091
No log	2.25	18	0.7346	0.4074	0.7346	0.8571
No log	2.5	20	0.6949	0.4172	0.6949	0.8336
No log	2.75	22	0.5933	0.4569	0.5933	0.7703
No log	3.0	24	0.5082	0.5046	0.5082	0.7129
No log	3.25	26	0.4662	0.4656	0.4662	0.6828
No log	3.5	28	0.4559	0.5488	0.4559	0.6752
No log	3.75	30	0.4866	0.6052	0.4866	0.6976
No log	4.0	32	0.5134	0.5950	0.5134	0.7165
No log	4.25	34	0.4695	0.4471	0.4695	0.6852
No log	4.5	36	0.6077	0.5112	0.6077	0.7795
No log	4.75	38	0.4910	0.5373	0.4910	0.7007
No log	5.0	40	0.4398	0.5939	0.4398	0.6632
No log	5.25	42	0.4167	0.6517	0.4167	0.6456
No log	5.5	44	0.4541	0.5779	0.4541	0.6738
No log	5.75	46	0.5788	0.5587	0.5788	0.7608
No log	6.0	48	0.8070	0.4464	0.8070	0.8983
No log	6.25	50	0.7189	0.4633	0.7189	0.8479
No log	6.5	52	0.4613	0.6017	0.4613	0.6792
No log	6.75	54	0.3903	0.6929	0.3903	0.6247
No log	7.0	56	0.4025	0.6598	0.4025	0.6345
No log	7.25	58	0.4032	0.6339	0.4032	0.6349
No log	7.5	60	0.4184	0.6946	0.4184	0.6468
No log	7.75	62	0.4943	0.6047	0.4943	0.7031
No log	8.0	64	0.4830	0.6114	0.4830	0.6950
No log	8.25	66	0.4557	0.6010	0.4557	0.6751
No log	8.5	68	0.4602	0.6068	0.4602	0.6784
No log	8.75	70	0.4620	0.5985	0.4620	0.6797
No log	9.0	72	0.4760	0.6514	0.4760	0.6899
No log	9.25	74	0.4553	0.6828	0.4553	0.6748
No log	9.5	76	0.4966	0.5514	0.4966	0.7047
No log	9.75	78	0.4454	0.6241	0.4454	0.6674
No log	10.0	80	0.4358	0.7012	0.4358	0.6601
No log	10.25	82	0.4307	0.7012	0.4307	0.6563
No log	10.5	84	0.4486	0.6252	0.4486	0.6698
No log	10.75	86	0.4646	0.5723	0.4646	0.6816
No log	11.0	88	0.4691	0.5723	0.4691	0.6849
No log	11.25	90	0.4434	0.5993	0.4434	0.6659
No log	11.5	92	0.4549	0.5738	0.4549	0.6745
No log	11.75	94	0.4713	0.5723	0.4713	0.6865
No log	12.0	96	0.4415	0.6277	0.4415	0.6644
No log	12.25	98	0.4275	0.6762	0.4275	0.6538
No log	12.5	100	0.4192	0.6753	0.4192	0.6475
No log	12.75	102	0.4486	0.6124	0.4486	0.6698
No log	13.0	104	0.4329	0.6484	0.4329	0.6579
No log	13.25	106	0.4311	0.7022	0.4311	0.6566
No log	13.5	108	0.5081	0.6206	0.5081	0.7128
No log	13.75	110	0.4859	0.6379	0.4859	0.6971
No log	14.0	112	0.4557	0.6877	0.4557	0.6751
No log	14.25	114	0.4858	0.6547	0.4858	0.6970
No log	14.5	116	0.4244	0.7022	0.4244	0.6515
No log	14.75	118	0.4236	0.6359	0.4236	0.6509
No log	15.0	120	0.4187	0.6326	0.4187	0.6471
No log	15.25	122	0.4221	0.6326	0.4221	0.6497
No log	15.5	124	0.4048	0.7022	0.4048	0.6362
No log	15.75	126	0.4144	0.6326	0.4144	0.6438
No log	16.0	128	0.5280	0.6479	0.5280	0.7266
No log	16.25	130	0.4433	0.6445	0.4433	0.6658
No log	16.5	132	0.4188	0.6886	0.4188	0.6471
No log	16.75	134	0.4298	0.6651	0.4298	0.6556
No log	17.0	136	0.4390	0.6572	0.4390	0.6626
No log	17.25	138	0.4419	0.5853	0.4419	0.6647
No log	17.5	140	0.4444	0.5612	0.4444	0.6667
No log	17.75	142	0.4383	0.6154	0.4383	0.6620
No log	18.0	144	0.4405	0.6140	0.4405	0.6637
No log	18.25	146	0.4829	0.5836	0.4829	0.6949
No log	18.5	148	0.4950	0.6201	0.4950	0.7036
No log	18.75	150	0.4552	0.5970	0.4552	0.6747
No log	19.0	152	0.4379	0.5915	0.4379	0.6617
No log	19.25	154	0.4380	0.6229	0.4380	0.6618
No log	19.5	156	0.4409	0.5985	0.4409	0.6640
No log	19.75	158	0.4424	0.5999	0.4424	0.6651
No log	20.0	160	0.4504	0.6414	0.4504	0.6711
No log	20.25	162	0.4310	0.5861	0.4310	0.6565
No log	20.5	164	0.4239	0.6032	0.4239	0.6510
No log	20.75	166	0.4393	0.6032	0.4393	0.6628
No log	21.0	168	0.4710	0.5731	0.4710	0.6863
No log	21.25	170	0.4833	0.5050	0.4833	0.6952
No log	21.5	172	0.4495	0.5731	0.4495	0.6705
No log	21.75	174	0.4360	0.6257	0.4360	0.6603
No log	22.0	176	0.4186	0.6648	0.4186	0.6470
No log	22.25	178	0.4254	0.6292	0.4254	0.6522
No log	22.5	180	0.4260	0.6435	0.4260	0.6527
No log	22.75	182	0.4317	0.6039	0.4317	0.6570
No log	23.0	184	0.4493	0.5479	0.4493	0.6703
No log	23.25	186	0.4427	0.5698	0.4427	0.6654
No log	23.5	188	0.4802	0.5289	0.4802	0.6929
No log	23.75	190	0.4974	0.5289	0.4974	0.7053
No log	24.0	192	0.4530	0.5927	0.4530	0.6731
No log	24.25	194	0.4368	0.5698	0.4368	0.6609
No log	24.5	196	0.4760	0.5352	0.4760	0.6899
No log	24.75	198	0.4422	0.5687	0.4422	0.6650
No log	25.0	200	0.4377	0.5868	0.4377	0.6616
No log	25.25	202	0.5572	0.5508	0.5572	0.7464
No log	25.5	204	0.5383	0.6038	0.5383	0.7337
No log	25.75	206	0.4304	0.6317	0.4304	0.6560
No log	26.0	208	0.4293	0.6183	0.4293	0.6552
No log	26.25	210	0.4338	0.5985	0.4338	0.6586
No log	26.5	212	0.4310	0.6403	0.4310	0.6565
No log	26.75	214	0.4627	0.6276	0.4627	0.6802
No log	27.0	216	0.4413	0.6186	0.4413	0.6643
No log	27.25	218	0.4315	0.6435	0.4315	0.6569
No log	27.5	220	0.4288	0.5956	0.4288	0.6548
No log	27.75	222	0.4258	0.6632	0.4258	0.6525
No log	28.0	224	0.4690	0.6768	0.4690	0.6848
No log	28.25	226	0.4593	0.6768	0.4593	0.6777
No log	28.5	228	0.4275	0.6377	0.4275	0.6539
No log	28.75	230	0.4219	0.6087	0.4219	0.6495
No log	29.0	232	0.4317	0.6269	0.4317	0.6571
No log	29.25	234	0.4392	0.6321	0.4392	0.6627
No log	29.5	236	0.4492	0.5836	0.4492	0.6702
No log	29.75	238	0.4791	0.5467	0.4791	0.6922
No log	30.0	240	0.5088	0.6262	0.5088	0.7133
No log	30.25	242	0.4730	0.6368	0.4730	0.6877
No log	30.5	244	0.4292	0.6076	0.4292	0.6551
No log	30.75	246	0.4429	0.5414	0.4429	0.6655
No log	31.0	248	0.4813	0.4997	0.4813	0.6938
No log	31.25	250	0.4923	0.5470	0.4923	0.7017
No log	31.5	252	0.4335	0.5339	0.4335	0.6584
No log	31.75	254	0.4170	0.6634	0.4170	0.6457
No log	32.0	256	0.4165	0.6446	0.4165	0.6454
No log	32.25	258	0.4122	0.6555	0.4122	0.6420
No log	32.5	260	0.4217	0.5846	0.4217	0.6494
No log	32.75	262	0.4247	0.5339	0.4247	0.6517
No log	33.0	264	0.4086	0.6542	0.4086	0.6392
No log	33.25	266	0.4120	0.6435	0.4120	0.6419
No log	33.5	268	0.4219	0.5714	0.4219	0.6495
No log	33.75	270	0.4309	0.5414	0.4309	0.6564
No log	34.0	272	0.4333	0.5493	0.4333	0.6582
No log	34.25	274	0.4310	0.5493	0.4310	0.6565
No log	34.5	276	0.4499	0.5927	0.4499	0.6708
No log	34.75	278	0.4750	0.5819	0.4750	0.6892
No log	35.0	280	0.4687	0.5927	0.4687	0.6847
No log	35.25	282	0.4441	0.5367	0.4441	0.6664
No log	35.5	284	0.4285	0.5714	0.4285	0.6546
No log	35.75	286	0.4240	0.6730	0.4240	0.6511
No log	36.0	288	0.4246	0.6890	0.4246	0.6516
No log	36.25	290	0.4256	0.6723	0.4256	0.6524
No log	36.5	292	0.4323	0.6712	0.4323	0.6575
No log	36.75	294	0.4295	0.6034	0.4295	0.6553
No log	37.0	296	0.4452	0.5904	0.4452	0.6673
No log	37.25	298	0.4418	0.5339	0.4418	0.6647
No log	37.5	300	0.4328	0.5681	0.4328	0.6579
No log	37.75	302	0.4488	0.6101	0.4488	0.6699
No log	38.0	304	0.4423	0.6060	0.4423	0.6650
No log	38.25	306	0.4348	0.5122	0.4348	0.6594
No log	38.5	308	0.4384	0.5386	0.4384	0.6621
No log	38.75	310	0.4313	0.5710	0.4313	0.6567
No log	39.0	312	0.4301	0.5943	0.4301	0.6559
No log	39.25	314	0.4292	0.5836	0.4292	0.6552
No log	39.5	316	0.4262	0.5782	0.4262	0.6529
No log	39.75	318	0.4833	0.5584	0.4833	0.6952
No log	40.0	320	0.5017	0.5384	0.5017	0.7083
No log	40.25	322	0.4492	0.5248	0.4492	0.6702
No log	40.5	324	0.4377	0.5927	0.4377	0.6616
No log	40.75	326	0.4599	0.5819	0.4599	0.6782
No log	41.0	328	0.4611	0.5819	0.4611	0.6791
No log	41.25	330	0.4541	0.5927	0.4541	0.6739
No log	41.5	332	0.4525	0.5927	0.4525	0.6727
No log	41.75	334	0.4694	0.5819	0.4694	0.6852
No log	42.0	336	0.4719	0.5819	0.4719	0.6869
No log	42.25	338	0.4759	0.5819	0.4759	0.6899
No log	42.5	340	0.4905	0.5819	0.4905	0.7004
No log	42.75	342	0.5242	0.5289	0.5242	0.7240
No log	43.0	344	0.5326	0.6073	0.5326	0.7298
No log	43.25	346	0.4803	0.6289	0.4803	0.6930
No log	43.5	348	0.4618	0.6293	0.4618	0.6795
No log	43.75	350	0.4606	0.5488	0.4606	0.6787
No log	44.0	352	0.4656	0.5567	0.4656	0.6824
No log	44.25	354	0.4712	0.5567	0.4712	0.6864
No log	44.5	356	0.4806	0.4847	0.4806	0.6933
No log	44.75	358	0.4861	0.4847	0.4861	0.6972
No log	45.0	360	0.4981	0.5693	0.4981	0.7058
No log	45.25	362	0.5049	0.6289	0.5049	0.7106
No log	45.5	364	0.4914	0.5503	0.4914	0.7010
No log	45.75	366	0.4749	0.5044	0.4749	0.6891
No log	46.0	368	0.4729	0.4795	0.4729	0.6877
No log	46.25	370	0.4659	0.5044	0.4659	0.6826
No log	46.5	372	0.4699	0.4847	0.4699	0.6855
No log	46.75	374	0.4642	0.4847	0.4642	0.6813
No log	47.0	376	0.4640	0.5044	0.4640	0.6811
No log	47.25	378	0.4690	0.5044	0.4690	0.6848
No log	47.5	380	0.4760	0.4847	0.4760	0.6899
No log	47.75	382	0.4879	0.5693	0.4879	0.6985
No log	48.0	384	0.4949	0.5819	0.4949	0.7035
No log	48.25	386	0.4916	0.6171	0.4916	0.7011
No log	48.5	388	0.4853	0.5955	0.4853	0.6966
No log	48.75	390	0.4741	0.5267	0.4741	0.6886
No log	49.0	392	0.4699	0.5044	0.4699	0.6855
No log	49.25	394	0.4807	0.4724	0.4807	0.6933
No log	49.5	396	0.4899	0.4471	0.4899	0.6999
No log	49.75	398	0.4765	0.4795	0.4765	0.6903
No log	50.0	400	0.4661	0.4847	0.4661	0.6827
No log	50.25	402	0.4847	0.6171	0.4847	0.6962
No log	50.5	404	0.4883	0.5614	0.4883	0.6988
No log	50.75	406	0.4891	0.5614	0.4891	0.6993
No log	51.0	408	0.4635	0.5819	0.4635	0.6808
No log	51.25	410	0.4503	0.6076	0.4503	0.6711
No log	51.5	412	0.4472	0.5208	0.4472	0.6687
No log	51.75	414	0.4463	0.5208	0.4463	0.6681
No log	52.0	416	0.4472	0.5440	0.4472	0.6687
No log	52.25	418	0.4472	0.5440	0.4472	0.6687
No log	52.5	420	0.4451	0.5986	0.4451	0.6672
No log	52.75	422	0.4496	0.6076	0.4496	0.6705
No log	53.0	424	0.4448	0.5986	0.4448	0.6670
No log	53.25	426	0.4429	0.5986	0.4429	0.6655
No log	53.5	428	0.4463	0.4970	0.4463	0.6680
No log	53.75	430	0.4492	0.4970	0.4492	0.6702
No log	54.0	432	0.4501	0.4970	0.4501	0.6709
No log	54.25	434	0.4478	0.5227	0.4478	0.6692
No log	54.5	436	0.4476	0.5152	0.4476	0.6690
No log	54.75	438	0.4495	0.5479	0.4495	0.6704
No log	55.0	440	0.4430	0.5248	0.4430	0.6656
No log	55.25	442	0.4418	0.5640	0.4418	0.6647
No log	55.5	444	0.4441	0.5846	0.4441	0.6664
No log	55.75	446	0.4431	0.5227	0.4431	0.6657
No log	56.0	448	0.4504	0.5079	0.4504	0.6711
No log	56.25	450	0.4560	0.5248	0.4560	0.6753
No log	56.5	452	0.4524	0.5079	0.4524	0.6726
No log	56.75	454	0.4506	0.5227	0.4506	0.6713
No log	57.0	456	0.4511	0.5719	0.4511	0.6716
No log	57.25	458	0.4619	0.5937	0.4619	0.6796
No log	57.5	460	0.4694	0.6038	0.4694	0.6851
No log	57.75	462	0.4731	0.6038	0.4731	0.6878
No log	58.0	464	0.4600	0.5937	0.4600	0.6782
No log	58.25	466	0.4473	0.5926	0.4473	0.6688
No log	58.5	468	0.4539	0.5321	0.4539	0.6737
No log	58.75	470	0.4689	0.5495	0.4689	0.6847
No log	59.0	472	0.4632	0.5266	0.4632	0.6806
No log	59.25	474	0.4454	0.5227	0.4454	0.6674
No log	59.5	476	0.4401	0.5521	0.4401	0.6634
No log	59.75	478	0.4524	0.5819	0.4524	0.6726
No log	60.0	480	0.4539	0.5927	0.4539	0.6737
No log	60.25	482	0.4487	0.6169	0.4487	0.6698
No log	60.5	484	0.4468	0.5367	0.4468	0.6684
No log	60.75	486	0.4503	0.5227	0.4503	0.6711
No log	61.0	488	0.4533	0.5227	0.4533	0.6733
No log	61.25	490	0.4593	0.4990	0.4593	0.6777
No log	61.5	492	0.4662	0.4746	0.4662	0.6828
No log	61.75	494	0.4553	0.4990	0.4553	0.6748
No log	62.0	496	0.4437	0.5227	0.4437	0.6661
No log	62.25	498	0.4413	0.6169	0.4413	0.6643
0.193	62.5	500	0.4562	0.5927	0.4562	0.6754
0.193	62.75	502	0.4710	0.5927	0.4710	0.6863
0.193	63.0	504	0.4713	0.5927	0.4713	0.6865
0.193	63.25	506	0.4707	0.5927	0.4707	0.6861
0.193	63.5	508	0.4640	0.5927	0.4640	0.6811
0.193	63.75	510	0.4576	0.5927	0.4576	0.6765

Framework versions

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