ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k10_task3_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: 0.4057
• Qwk: 0.6158
• Mse: 0.4057
• Rmse: 0.6370

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	0.0417	2	3.2800	-0.0149	3.2800	1.8111
No log	0.0833	4	1.7420	-0.0070	1.7420	1.3198
No log	0.125	6	0.9946	0.0632	0.9946	0.9973
No log	0.1667	8	0.7432	0.1133	0.7432	0.8621
No log	0.2083	10	1.3759	0.0929	1.3759	1.1730
No log	0.25	12	1.0108	0.0843	1.0108	1.0054
No log	0.2917	14	0.5327	0.0	0.5327	0.7299
No log	0.3333	16	0.5435	0.0	0.5435	0.7372
No log	0.375	18	0.5298	0.0	0.5298	0.7279
No log	0.4167	20	0.6333	0.2994	0.6333	0.7958
No log	0.4583	22	0.5867	0.1467	0.5867	0.7660
No log	0.5	24	0.5298	0.0	0.5298	0.7278
No log	0.5417	26	0.5736	0.2970	0.5736	0.7574
No log	0.5833	28	1.0613	0.1111	1.0613	1.0302
No log	0.625	30	0.7912	0.1481	0.7912	0.8895
No log	0.6667	32	0.5343	-0.0159	0.5343	0.7310
No log	0.7083	34	0.5447	-0.0233	0.5447	0.7381
No log	0.75	36	0.9096	0.1515	0.9096	0.9537
No log	0.7917	38	2.0911	-0.0695	2.0911	1.4461
No log	0.8333	40	2.1033	-0.0689	2.1033	1.4503
No log	0.875	42	1.2685	0.0	1.2685	1.1263
No log	0.9167	44	0.8033	0.1351	0.8033	0.8963
No log	0.9583	46	0.6137	-0.0159	0.6137	0.7834
No log	1.0	48	0.5925	-0.0435	0.5925	0.7697
No log	1.0417	50	0.8080	0.1481	0.8080	0.8989
No log	1.0833	52	0.8958	0.1795	0.8958	0.9465
No log	1.125	54	0.9473	0.1730	0.9473	0.9733
No log	1.1667	56	1.1900	0.1635	1.1900	1.0909
No log	1.2083	58	0.5212	0.2941	0.5212	0.7219
No log	1.25	60	0.4849	0.2298	0.4849	0.6964
No log	1.2917	62	0.5886	0.3118	0.5886	0.7672
No log	1.3333	64	0.5021	0.2653	0.5021	0.7086
No log	1.375	66	0.7052	0.3200	0.7052	0.8398
No log	1.4167	68	0.4991	0.1549	0.4991	0.7065
No log	1.4583	70	0.7292	0.3333	0.7292	0.8539
No log	1.5	72	0.8672	0.2511	0.8672	0.9313
No log	1.5417	74	0.6623	0.3892	0.6623	0.8138
No log	1.5833	76	0.5673	0.2941	0.5673	0.7532
No log	1.625	78	0.6276	0.3757	0.6276	0.7922
No log	1.6667	80	0.5394	0.1908	0.5394	0.7345
No log	1.7083	82	0.7329	0.2762	0.7329	0.8561
No log	1.75	84	0.5363	0.2967	0.5363	0.7323
No log	1.7917	86	0.4863	0.3171	0.4863	0.6973
No log	1.8333	88	0.4690	0.3810	0.4690	0.6848
No log	1.875	90	0.5414	0.2670	0.5414	0.7358
No log	1.9167	92	0.4747	0.4583	0.4747	0.6890
No log	1.9583	94	0.4715	0.4583	0.4715	0.6867
No log	2.0	96	0.5562	0.4	0.5562	0.7458
No log	2.0417	98	0.4710	0.4583	0.4710	0.6863
No log	2.0833	100	0.4832	0.4709	0.4832	0.6951
No log	2.125	102	0.5458	0.4819	0.5458	0.7388
No log	2.1667	104	0.7156	0.3398	0.7156	0.8459
No log	2.2083	106	0.5286	0.3469	0.5286	0.7270
No log	2.25	108	0.5644	0.3623	0.5644	0.7513
No log	2.2917	110	0.6531	0.4286	0.6531	0.8082
No log	2.3333	112	0.6843	0.3951	0.6843	0.8272
No log	2.375	114	0.5453	0.4450	0.5453	0.7385
No log	2.4167	116	0.5321	0.3263	0.5321	0.7294
No log	2.4583	118	0.4605	0.4033	0.4605	0.6786
No log	2.5	120	0.5322	0.4947	0.5322	0.7295
No log	2.5417	122	0.4819	0.4059	0.4819	0.6942
No log	2.5833	124	0.6181	0.5	0.6181	0.7862
No log	2.625	126	0.5754	0.4747	0.5754	0.7586
No log	2.6667	128	0.4803	0.4882	0.4803	0.6930
No log	2.7083	130	0.5851	0.5261	0.5851	0.7649
No log	2.75	132	0.5493	0.5261	0.5493	0.7412
No log	2.7917	134	0.4729	0.5215	0.4729	0.6877
No log	2.8333	136	0.6530	0.3821	0.6530	0.8081
No log	2.875	138	0.5868	0.4921	0.5868	0.7660
No log	2.9167	140	0.5168	0.4128	0.5168	0.7189
No log	2.9583	142	0.9626	0.2234	0.9626	0.9811
No log	3.0	144	0.7178	0.4380	0.7178	0.8472
No log	3.0417	146	0.5252	0.5357	0.5252	0.7247
No log	3.0833	148	0.8372	0.2698	0.8372	0.9150
No log	3.125	150	0.5932	0.3778	0.5932	0.7702
No log	3.1667	152	0.5817	0.3846	0.5817	0.7627
No log	3.2083	154	0.8369	0.2960	0.8369	0.9148
No log	3.25	156	0.5734	0.3663	0.5734	0.7573
No log	3.2917	158	0.4587	0.5	0.4587	0.6773
No log	3.3333	160	0.5202	0.4510	0.5202	0.7212
No log	3.375	162	0.4780	0.5183	0.4780	0.6914
No log	3.4167	164	0.4932	0.4510	0.4932	0.7023
No log	3.4583	166	0.5085	0.4019	0.5085	0.7131
No log	3.5	168	0.5011	0.4902	0.5011	0.7079
No log	3.5417	170	0.5516	0.4	0.5516	0.7427
No log	3.5833	172	0.4973	0.4615	0.4973	0.7052
No log	3.625	174	0.4752	0.4709	0.4752	0.6894
No log	3.6667	176	0.4655	0.5918	0.4655	0.6823
No log	3.7083	178	0.5113	0.4105	0.5113	0.7151
No log	3.75	180	0.4724	0.4468	0.4724	0.6873
No log	3.7917	182	0.4332	0.5779	0.4332	0.6582
No log	3.8333	184	0.4848	0.3797	0.4848	0.6963
No log	3.875	186	0.4403	0.56	0.4403	0.6635
No log	3.9167	188	0.5697	0.3951	0.5697	0.7548
No log	3.9583	190	0.5742	0.3427	0.5742	0.7578
No log	4.0	192	0.4589	0.56	0.4589	0.6774
No log	4.0417	194	0.4944	0.4286	0.4944	0.7031
No log	4.0833	196	0.5000	0.4930	0.5000	0.7071
No log	4.125	198	0.7090	0.3448	0.7090	0.8420
No log	4.1667	200	0.5395	0.4393	0.5395	0.7345
No log	4.2083	202	0.5597	0.4286	0.5597	0.7481
No log	4.25	204	0.7020	0.3214	0.7020	0.8378
No log	4.2917	206	0.5019	0.4081	0.5019	0.7084
No log	4.3333	208	0.4603	0.5152	0.4603	0.6785
No log	4.375	210	0.4692	0.4709	0.4692	0.6850
No log	4.4167	212	0.4447	0.5294	0.4447	0.6669
No log	4.4583	214	0.6102	0.3303	0.6102	0.7812
No log	4.5	216	0.5193	0.3469	0.5193	0.7206
No log	4.5417	218	0.4373	0.5464	0.4373	0.6613
No log	4.5833	220	0.4474	0.4652	0.4474	0.6689
No log	4.625	222	0.4612	0.4783	0.4612	0.6791
No log	4.6667	224	0.4807	0.3829	0.4807	0.6933
No log	4.7083	226	0.4736	0.3829	0.4736	0.6882
No log	4.75	228	0.4577	0.5833	0.4577	0.6765
No log	4.7917	230	0.4909	0.4123	0.4909	0.7006
No log	4.8333	232	0.4729	0.5294	0.4729	0.6877
No log	4.875	234	0.5053	0.4764	0.5053	0.7108
No log	4.9167	236	0.5651	0.4167	0.5651	0.7518
No log	4.9583	238	0.4453	0.5423	0.4453	0.6673
No log	5.0	240	0.4396	0.5468	0.4396	0.6630
No log	5.0417	242	0.4914	0.5027	0.4914	0.7010
No log	5.0833	244	0.5195	0.4924	0.5195	0.7208
No log	5.125	246	0.4221	0.5598	0.4221	0.6497
No log	5.1667	248	0.4309	0.5821	0.4309	0.6564
No log	5.2083	250	0.4260	0.5728	0.4260	0.6527
No log	5.25	252	0.5973	0.3607	0.5973	0.7728
No log	5.2917	254	0.5279	0.48	0.5279	0.7265
No log	5.3333	256	0.4536	0.5233	0.4536	0.6735
No log	5.375	258	0.4125	0.5319	0.4125	0.6423
No log	5.4167	260	0.3949	0.5165	0.3949	0.6284
No log	5.4583	262	0.4111	0.5217	0.4111	0.6412
No log	5.5	264	0.4245	0.4917	0.4245	0.6515
No log	5.5417	266	0.4167	0.4098	0.4167	0.6455
No log	5.5833	268	0.4908	0.3469	0.4908	0.7006
No log	5.625	270	0.4482	0.4286	0.4482	0.6695
No log	5.6667	272	0.4652	0.4973	0.4652	0.6820
No log	5.7083	274	0.6230	0.2963	0.6230	0.7893
No log	5.75	276	0.5820	0.3684	0.5820	0.7629
No log	5.7917	278	0.4453	0.5056	0.4453	0.6673
No log	5.8333	280	0.4403	0.4667	0.4403	0.6636
No log	5.875	282	0.4383	0.4483	0.4383	0.6620
No log	5.9167	284	0.4370	0.3789	0.4370	0.6610
No log	5.9583	286	0.4475	0.3000	0.4475	0.6690
No log	6.0	288	0.4972	0.4483	0.4972	0.7051
No log	6.0417	290	0.4655	0.4146	0.4655	0.6823
No log	6.0833	292	0.4294	0.4023	0.4294	0.6553
No log	6.125	294	0.4453	0.4157	0.4453	0.6673
No log	6.1667	296	0.4266	0.3609	0.4266	0.6532
No log	6.2083	298	0.4273	0.4356	0.4273	0.6537
No log	6.25	300	0.4360	0.4682	0.4360	0.6603
No log	6.2917	302	0.4551	0.4536	0.4551	0.6746
No log	6.3333	304	0.4413	0.5	0.4413	0.6643
No log	6.375	306	0.4303	0.3455	0.4303	0.6559
No log	6.4167	308	0.4282	0.4	0.4282	0.6544
No log	6.4583	310	0.4309	0.3374	0.4309	0.6564
No log	6.5	312	0.4229	0.3247	0.4229	0.6503
No log	6.5417	314	0.4211	0.2533	0.4211	0.6489
No log	6.5833	316	0.4207	0.2632	0.4207	0.6486
No log	6.625	318	0.4369	0.4214	0.4369	0.6610
No log	6.6667	320	0.4465	0.4146	0.4465	0.6682
No log	6.7083	322	0.4742	0.4023	0.4742	0.6887
No log	6.75	324	0.4712	0.4023	0.4712	0.6864
No log	6.7917	326	0.4300	0.4214	0.4300	0.6557
No log	6.8333	328	0.4110	0.3810	0.4110	0.6411
No log	6.875	330	0.4154	0.3810	0.4154	0.6445
No log	6.9167	332	0.4189	0.4802	0.4189	0.6472
No log	6.9583	334	0.4514	0.4023	0.4514	0.6718
No log	7.0	336	0.4355	0.5217	0.4355	0.6599
No log	7.0417	338	0.4148	0.4536	0.4148	0.6440
No log	7.0833	340	0.4130	0.4413	0.4130	0.6426
No log	7.125	342	0.4119	0.4413	0.4119	0.6418
No log	7.1667	344	0.4115	0.5056	0.4115	0.6415
No log	7.2083	346	0.4304	0.5801	0.4304	0.6561
No log	7.25	348	0.5562	0.4227	0.5562	0.7458
No log	7.2917	350	0.6302	0.3571	0.6302	0.7939
No log	7.3333	352	0.5608	0.4118	0.5608	0.7489
No log	7.375	354	0.4364	0.5847	0.4364	0.6606
No log	7.4167	356	0.4099	0.4413	0.4099	0.6403
No log	7.4583	358	0.4200	0.3488	0.4200	0.6481
No log	7.5	360	0.4196	0.3488	0.4196	0.6478
No log	7.5417	362	0.4068	0.4743	0.4068	0.6378
No log	7.5833	364	0.4483	0.4725	0.4483	0.6696
No log	7.625	366	0.4607	0.4725	0.4607	0.6788
No log	7.6667	368	0.4393	0.5111	0.4393	0.6628
No log	7.7083	370	0.4181	0.6023	0.4181	0.6466
No log	7.75	372	0.4195	0.5909	0.4195	0.6477
No log	7.7917	374	0.4267	0.5909	0.4267	0.6532
No log	7.8333	376	0.4420	0.4743	0.4420	0.6649
No log	7.875	378	0.4287	0.5145	0.4287	0.6547
No log	7.9167	380	0.4142	0.5663	0.4142	0.6436
No log	7.9583	382	0.4093	0.4884	0.4093	0.6397
No log	8.0	384	0.4120	0.5556	0.4120	0.6419
No log	8.0417	386	0.4282	0.5056	0.4282	0.6543
No log	8.0833	388	0.4205	0.5909	0.4205	0.6485
No log	8.125	390	0.4264	0.5056	0.4264	0.6530
No log	8.1667	392	0.4238	0.5056	0.4238	0.6510
No log	8.2083	394	0.4105	0.5909	0.4105	0.6407
No log	8.25	396	0.4063	0.5909	0.4063	0.6374
No log	8.2917	398	0.3973	0.5556	0.3973	0.6303
No log	8.3333	400	0.3914	0.5814	0.3914	0.6256
No log	8.375	402	0.3972	0.5909	0.3972	0.6303
No log	8.4167	404	0.4202	0.4419	0.4202	0.6482
No log	8.4583	406	0.4490	0.4023	0.4490	0.6701
No log	8.5	408	0.4462	0.4350	0.4462	0.6680
No log	8.5417	410	0.4299	0.4419	0.4299	0.6557
No log	8.5833	412	0.4116	0.4743	0.4116	0.6416
No log	8.625	414	0.3991	0.5909	0.3991	0.6318
No log	8.6667	416	0.3922	0.6201	0.3922	0.6263
No log	8.7083	418	0.3904	0.5410	0.3904	0.6248
No log	8.75	420	0.3919	0.5652	0.3919	0.6261
No log	8.7917	422	0.3913	0.5056	0.3913	0.6255
No log	8.8333	424	0.3950	0.5754	0.3950	0.6285
No log	8.875	426	0.4065	0.5801	0.4065	0.6376
No log	8.9167	428	0.4189	0.4743	0.4189	0.6472
No log	8.9583	430	0.4201	0.4743	0.4201	0.6482
No log	9.0	432	0.4138	0.4743	0.4138	0.6432
No log	9.0417	434	0.4075	0.5801	0.4075	0.6383
No log	9.0833	436	0.4015	0.5801	0.4015	0.6337
No log	9.125	438	0.3983	0.5604	0.3983	0.6311
No log	9.1667	440	0.3963	0.5056	0.3963	0.6295
No log	9.2083	442	0.3979	0.5652	0.3979	0.6308
No log	9.25	444	0.3978	0.5359	0.3978	0.6307
No log	9.2917	446	0.3975	0.5657	0.3975	0.6305
No log	9.3333	448	0.4003	0.6044	0.4003	0.6327
No log	9.375	450	0.4074	0.5506	0.4074	0.6382
No log	9.4167	452	0.4120	0.4743	0.4120	0.6419
No log	9.4583	454	0.4106	0.4743	0.4106	0.6408
No log	9.5	456	0.4092	0.5506	0.4092	0.6397
No log	9.5417	458	0.4069	0.5607	0.4069	0.6379
No log	9.5833	460	0.4072	0.5607	0.4072	0.6381
No log	9.625	462	0.4062	0.5754	0.4062	0.6374
No log	9.6667	464	0.4057	0.6044	0.4057	0.6369
No log	9.7083	466	0.4051	0.6044	0.4051	0.6365
No log	9.75	468	0.4052	0.5814	0.4052	0.6365
No log	9.7917	470	0.4050	0.5814	0.4050	0.6364
No log	9.8333	472	0.4048	0.5814	0.4048	0.6362
No log	9.875	474	0.4048	0.5814	0.4048	0.6363
No log	9.9167	476	0.4051	0.5814	0.4051	0.6365
No log	9.9583	478	0.4055	0.5814	0.4055	0.6368
No log	10.0	480	0.4057	0.6158	0.4057	0.6370

Framework versions

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