ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k1_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: 0.4116
• Qwk: 0.6422
• Mse: 0.4116
• Rmse: 0.6416

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	0.4	2	2.7838	-0.0545	2.7838	1.6685
No log	0.8	4	1.3098	0.0997	1.3098	1.1445
No log	1.2	6	0.7967	0.1729	0.7967	0.8926
No log	1.6	8	0.6479	0.3865	0.6479	0.8049
No log	2.0	10	0.8932	0.3280	0.8932	0.9451
No log	2.4	12	0.6608	0.4369	0.6608	0.8129
No log	2.8	14	0.6157	0.5544	0.6157	0.7846
No log	3.2	16	0.7886	0.3401	0.7886	0.8880
No log	3.6	18	0.5747	0.3691	0.5747	0.7581
No log	4.0	20	0.6011	0.4330	0.6011	0.7753
No log	4.4	22	0.7116	0.4008	0.7116	0.8435
No log	4.8	24	0.8774	0.3555	0.8774	0.9367
No log	5.2	26	0.8523	0.3957	0.8523	0.9232
No log	5.6	28	0.6995	0.4308	0.6995	0.8363
No log	6.0	30	0.4720	0.5024	0.4720	0.6870
No log	6.4	32	0.5011	0.4052	0.5011	0.7079
No log	6.8	34	0.5033	0.5124	0.5033	0.7095
No log	7.2	36	0.4910	0.6091	0.4910	0.7007
No log	7.6	38	0.5262	0.5911	0.5262	0.7254
No log	8.0	40	0.6608	0.4959	0.6608	0.8129
No log	8.4	42	0.7199	0.4268	0.7199	0.8485
No log	8.8	44	0.5174	0.6322	0.5174	0.7193
No log	9.2	46	0.5813	0.5872	0.5813	0.7624
No log	9.6	48	0.5752	0.5272	0.5752	0.7584
No log	10.0	50	0.5502	0.4595	0.5502	0.7417
No log	10.4	52	0.5489	0.4595	0.5489	0.7409
No log	10.8	54	0.5511	0.5304	0.5511	0.7424
No log	11.2	56	0.5831	0.5463	0.5831	0.7636
No log	11.6	58	0.6222	0.4979	0.6222	0.7888
No log	12.0	60	0.5402	0.6279	0.5402	0.7350
No log	12.4	62	0.4811	0.6092	0.4811	0.6936
No log	12.8	64	0.4321	0.6554	0.4321	0.6573
No log	13.2	66	0.4361	0.6114	0.4361	0.6604
No log	13.6	68	0.4887	0.6273	0.4887	0.6991
No log	14.0	70	0.4648	0.6442	0.4648	0.6818
No log	14.4	72	0.5028	0.6642	0.5028	0.7091
No log	14.8	74	0.4706	0.6537	0.4706	0.6860
No log	15.2	76	0.4535	0.6806	0.4535	0.6734
No log	15.6	78	0.4823	0.6630	0.4823	0.6945
No log	16.0	80	0.4975	0.6198	0.4975	0.7053
No log	16.4	82	0.4968	0.5875	0.4968	0.7049
No log	16.8	84	0.4925	0.5430	0.4925	0.7018
No log	17.2	86	0.4873	0.5195	0.4873	0.6981
No log	17.6	88	0.4745	0.5980	0.4745	0.6889
No log	18.0	90	0.4823	0.5752	0.4823	0.6945
No log	18.4	92	0.4793	0.5768	0.4793	0.6923
No log	18.8	94	0.4721	0.5640	0.4721	0.6871
No log	19.2	96	0.5078	0.6601	0.5078	0.7126
No log	19.6	98	0.4995	0.6890	0.4995	0.7068
No log	20.0	100	0.4590	0.7151	0.4590	0.6775
No log	20.4	102	0.4179	0.6554	0.4179	0.6464
No log	20.8	104	0.4373	0.6567	0.4373	0.6613
No log	21.2	106	0.4586	0.6582	0.4586	0.6772
No log	21.6	108	0.4194	0.6091	0.4194	0.6476
No log	22.0	110	0.4253	0.5897	0.4253	0.6521
No log	22.4	112	0.4098	0.6115	0.4098	0.6402
No log	22.8	114	0.4299	0.6678	0.4299	0.6557
No log	23.2	116	0.5748	0.5792	0.5748	0.7581
No log	23.6	118	0.5475	0.5575	0.5475	0.7400
No log	24.0	120	0.4355	0.7062	0.4355	0.6599
No log	24.4	122	0.3962	0.6265	0.3962	0.6295
No log	24.8	124	0.4029	0.6620	0.4029	0.6347
No log	25.2	126	0.4154	0.7166	0.4154	0.6445
No log	25.6	128	0.5258	0.5280	0.5258	0.7251
No log	26.0	130	0.5335	0.5486	0.5335	0.7304
No log	26.4	132	0.4524	0.5544	0.4524	0.6726
No log	26.8	134	0.4049	0.6241	0.4049	0.6363
No log	27.2	136	0.4144	0.6530	0.4144	0.6437
No log	27.6	138	0.4093	0.6530	0.4093	0.6398
No log	28.0	140	0.4031	0.6443	0.4031	0.6349
No log	28.4	142	0.4497	0.6960	0.4497	0.6706
No log	28.8	144	0.4737	0.6431	0.4737	0.6883
No log	29.2	146	0.4333	0.6566	0.4333	0.6583
No log	29.6	148	0.4313	0.6156	0.4313	0.6567
No log	30.0	150	0.4541	0.6377	0.4541	0.6739
No log	30.4	152	0.4592	0.6377	0.4592	0.6776
No log	30.8	154	0.4528	0.6156	0.4528	0.6729
No log	31.2	156	0.4475	0.5941	0.4475	0.6689
No log	31.6	158	0.4379	0.6156	0.4379	0.6617
No log	32.0	160	0.4289	0.6530	0.4289	0.6549
No log	32.4	162	0.4396	0.6334	0.4396	0.6630
No log	32.8	164	0.4454	0.6777	0.4454	0.6674
No log	33.2	166	0.4460	0.6552	0.4460	0.6678
No log	33.6	168	0.4600	0.6667	0.4600	0.6782
No log	34.0	170	0.4459	0.6275	0.4459	0.6677
No log	34.4	172	0.4454	0.5886	0.4454	0.6674
No log	34.8	174	0.4526	0.5738	0.4526	0.6727
No log	35.2	176	0.4551	0.5517	0.4551	0.6746
No log	35.6	178	0.4551	0.5289	0.4551	0.6746
No log	36.0	180	0.4796	0.5934	0.4796	0.6925
No log	36.4	182	0.4998	0.6485	0.4998	0.7069
No log	36.8	184	0.4779	0.6214	0.4779	0.6913
No log	37.2	186	0.4470	0.5289	0.4470	0.6686
No log	37.6	188	0.4549	0.5133	0.4549	0.6745
No log	38.0	190	0.4562	0.4817	0.4562	0.6755
No log	38.4	192	0.4468	0.5609	0.4468	0.6684
No log	38.8	194	0.4451	0.5289	0.4451	0.6671
No log	39.2	196	0.4545	0.6004	0.4545	0.6742
No log	39.6	198	0.4543	0.5909	0.4543	0.6740
No log	40.0	200	0.4517	0.5909	0.4517	0.6721
No log	40.4	202	0.4422	0.6418	0.4422	0.6650
No log	40.8	204	0.4287	0.6158	0.4287	0.6548
No log	41.2	206	0.4396	0.5634	0.4396	0.6631
No log	41.6	208	0.4846	0.5587	0.4846	0.6961
No log	42.0	210	0.4915	0.5226	0.4915	0.7011
No log	42.4	212	0.4575	0.4977	0.4575	0.6764
No log	42.8	214	0.4248	0.6156	0.4248	0.6518
No log	43.2	216	0.4134	0.6616	0.4134	0.6430
No log	43.6	218	0.4348	0.6506	0.4348	0.6594
No log	44.0	220	0.4368	0.6506	0.4368	0.6609
No log	44.4	222	0.4198	0.6431	0.4198	0.6479
No log	44.8	224	0.4223	0.6431	0.4223	0.6498
No log	45.2	226	0.4427	0.5698	0.4427	0.6653
No log	45.6	228	0.4619	0.4838	0.4619	0.6796
No log	46.0	230	0.4503	0.5658	0.4503	0.6711
No log	46.4	232	0.4319	0.6156	0.4319	0.6572
No log	46.8	234	0.4159	0.6627	0.4159	0.6449
No log	47.2	236	0.4135	0.6627	0.4135	0.6430
No log	47.6	238	0.4090	0.6541	0.4090	0.6395
No log	48.0	240	0.4076	0.6541	0.4076	0.6384
No log	48.4	242	0.4103	0.6542	0.4103	0.6406
No log	48.8	244	0.4193	0.6542	0.4193	0.6476
No log	49.2	246	0.4190	0.6541	0.4190	0.6473
No log	49.6	248	0.4144	0.6541	0.4144	0.6437
No log	50.0	250	0.4144	0.6541	0.4144	0.6437
No log	50.4	252	0.4129	0.6541	0.4129	0.6426
No log	50.8	254	0.4141	0.6541	0.4141	0.6435
No log	51.2	256	0.4225	0.6914	0.4225	0.6500
No log	51.6	258	0.4252	0.6277	0.4252	0.6521
No log	52.0	260	0.4236	0.6078	0.4236	0.6508
No log	52.4	262	0.4153	0.6346	0.4153	0.6444
No log	52.8	264	0.4139	0.6346	0.4139	0.6433
No log	53.2	266	0.4105	0.6720	0.4105	0.6407
No log	53.6	268	0.4094	0.6712	0.4094	0.6398
No log	54.0	270	0.4097	0.6712	0.4097	0.6401
No log	54.4	272	0.4049	0.7144	0.4049	0.6363
No log	54.8	274	0.4059	0.7166	0.4059	0.6371
No log	55.2	276	0.4266	0.6515	0.4266	0.6531
No log	55.6	278	0.4446	0.5970	0.4446	0.6668
No log	56.0	280	0.4419	0.6223	0.4419	0.6648
No log	56.4	282	0.4162	0.6282	0.4162	0.6451
No log	56.8	284	0.3938	0.6957	0.3938	0.6275
No log	57.2	286	0.3827	0.6750	0.3827	0.6186
No log	57.6	288	0.3809	0.6828	0.3809	0.6172
No log	58.0	290	0.3821	0.7003	0.3821	0.6181
No log	58.4	292	0.3820	0.7003	0.3820	0.6181
No log	58.8	294	0.3831	0.7247	0.3831	0.6190
No log	59.2	296	0.3922	0.7166	0.3922	0.6262
No log	59.6	298	0.3985	0.7246	0.3985	0.6313
No log	60.0	300	0.3911	0.7221	0.3911	0.6254
No log	60.4	302	0.3924	0.7160	0.3924	0.6264
No log	60.8	304	0.3850	0.6943	0.3850	0.6205
No log	61.2	306	0.3771	0.7123	0.3771	0.6141
No log	61.6	308	0.3771	0.6939	0.3771	0.6141
No log	62.0	310	0.3808	0.6939	0.3808	0.6171
No log	62.4	312	0.3817	0.6939	0.3817	0.6178
No log	62.8	314	0.3873	0.6818	0.3873	0.6223
No log	63.2	316	0.3901	0.6639	0.3901	0.6246
No log	63.6	318	0.3925	0.6643	0.3925	0.6265
No log	64.0	320	0.4002	0.6841	0.4002	0.6326
No log	64.4	322	0.4055	0.6655	0.4055	0.6368
No log	64.8	324	0.4110	0.6655	0.4110	0.6411
No log	65.2	326	0.4138	0.6761	0.4138	0.6432
No log	65.6	328	0.4102	0.6761	0.4102	0.6404
No log	66.0	330	0.4041	0.6939	0.4041	0.6357
No log	66.4	332	0.4003	0.6828	0.4003	0.6327
No log	66.8	334	0.4006	0.7012	0.4006	0.6329
No log	67.2	336	0.4028	0.7012	0.4028	0.6347
No log	67.6	338	0.4063	0.6852	0.4063	0.6374
No log	68.0	340	0.4075	0.6650	0.4075	0.6384
No log	68.4	342	0.4083	0.6839	0.4083	0.6390
No log	68.8	344	0.4084	0.6650	0.4084	0.6391
No log	69.2	346	0.4104	0.6908	0.4104	0.6406
No log	69.6	348	0.4144	0.6908	0.4144	0.6438
No log	70.0	350	0.4167	0.6894	0.4167	0.6455
No log	70.4	352	0.4168	0.6908	0.4168	0.6456
No log	70.8	354	0.4163	0.6727	0.4163	0.6452
No log	71.2	356	0.4152	0.6736	0.4152	0.6443
No log	71.6	358	0.4117	0.6736	0.4117	0.6416
No log	72.0	360	0.4071	0.6736	0.4071	0.6381
No log	72.4	362	0.4045	0.6841	0.4045	0.6360
No log	72.8	364	0.4045	0.7032	0.4045	0.6360
No log	73.2	366	0.4092	0.6761	0.4092	0.6397
No log	73.6	368	0.4168	0.6761	0.4168	0.6456
No log	74.0	370	0.4189	0.6770	0.4189	0.6472
No log	74.4	372	0.4183	0.6866	0.4183	0.6468
No log	74.8	374	0.4154	0.6852	0.4154	0.6445
No log	75.2	376	0.4134	0.6839	0.4134	0.6430
No log	75.6	378	0.4120	0.7229	0.4120	0.6419
No log	76.0	380	0.4120	0.7221	0.4120	0.6418
No log	76.4	382	0.4115	0.7221	0.4115	0.6415
No log	76.8	384	0.4109	0.7221	0.4109	0.6410
No log	77.2	386	0.4113	0.7062	0.4113	0.6413
No log	77.6	388	0.4127	0.7140	0.4127	0.6424
No log	78.0	390	0.4148	0.6966	0.4148	0.6440
No log	78.4	392	0.4173	0.6966	0.4173	0.6460
No log	78.8	394	0.4178	0.6966	0.4178	0.6464
No log	79.2	396	0.4184	0.6966	0.4184	0.6468
No log	79.6	398	0.4185	0.6983	0.4185	0.6469
No log	80.0	400	0.4165	0.6983	0.4165	0.6454
No log	80.4	402	0.4129	0.6983	0.4129	0.6425
No log	80.8	404	0.4112	0.6993	0.4112	0.6413
No log	81.2	406	0.4119	0.6818	0.4119	0.6418
No log	81.6	408	0.4125	0.6807	0.4125	0.6422
No log	82.0	410	0.4127	0.6627	0.4127	0.6424
No log	82.4	412	0.4117	0.6730	0.4117	0.6416
No log	82.8	414	0.4103	0.6730	0.4103	0.6405
No log	83.2	416	0.4100	0.6730	0.4100	0.6403
No log	83.6	418	0.4110	0.6929	0.4110	0.6411
No log	84.0	420	0.4117	0.6929	0.4117	0.6416
No log	84.4	422	0.4115	0.6929	0.4115	0.6415
No log	84.8	424	0.4115	0.6739	0.4115	0.6414
No log	85.2	426	0.4107	0.6739	0.4107	0.6409
No log	85.6	428	0.4101	0.6542	0.4101	0.6404
No log	86.0	430	0.4103	0.6730	0.4103	0.6406
No log	86.4	432	0.4105	0.6730	0.4105	0.6407
No log	86.8	434	0.4106	0.6730	0.4106	0.6408
No log	87.2	436	0.4113	0.6730	0.4113	0.6413
No log	87.6	438	0.4120	0.6730	0.4120	0.6419
No log	88.0	440	0.4133	0.6730	0.4133	0.6429
No log	88.4	442	0.4148	0.6914	0.4148	0.6440
No log	88.8	444	0.4171	0.6914	0.4171	0.6459
No log	89.2	446	0.4185	0.6929	0.4185	0.6469
No log	89.6	448	0.4180	0.6929	0.4180	0.6465
No log	90.0	450	0.4173	0.6929	0.4173	0.6460
No log	90.4	452	0.4174	0.6929	0.4174	0.6460
No log	90.8	454	0.4175	0.6946	0.4175	0.6461
No log	91.2	456	0.4166	0.6929	0.4166	0.6454
No log	91.6	458	0.4158	0.6946	0.4158	0.6449
No log	92.0	460	0.4155	0.6946	0.4155	0.6446
No log	92.4	462	0.4145	0.6747	0.4145	0.6438
No log	92.8	464	0.4139	0.6747	0.4139	0.6433
No log	93.2	466	0.4138	0.6636	0.4138	0.6432
No log	93.6	468	0.4135	0.6422	0.4135	0.6430
No log	94.0	470	0.4133	0.6422	0.4133	0.6429
No log	94.4	472	0.4133	0.6422	0.4133	0.6429
No log	94.8	474	0.4132	0.6422	0.4132	0.6428
No log	95.2	476	0.4129	0.6422	0.4129	0.6426
No log	95.6	478	0.4127	0.6422	0.4127	0.6424
No log	96.0	480	0.4127	0.6422	0.4127	0.6425
No log	96.4	482	0.4128	0.6422	0.4128	0.6425
No log	96.8	484	0.4125	0.6422	0.4125	0.6423
No log	97.2	486	0.4124	0.6422	0.4124	0.6421
No log	97.6	488	0.4123	0.6422	0.4123	0.6421
No log	98.0	490	0.4122	0.6422	0.4122	0.6420
No log	98.4	492	0.4120	0.6422	0.4120	0.6419
No log	98.8	494	0.4119	0.6422	0.4119	0.6418
No log	99.2	496	0.4117	0.6422	0.4117	0.6416
No log	99.6	498	0.4116	0.6422	0.4116	0.6416
0.1653	100.0	500	0.4116	0.6422	0.4116	0.6416

Framework versions

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