ArabicNewSplits6_FineTuningAraBERTFreeze_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: 0.7392
• Qwk: 0.5546
• Mse: 0.7392
• Rmse: 0.8598

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: 16
• eval_batch_size: 16
• 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	0.0952	2	6.3823	-0.0278	6.3823	2.5263
No log	0.1905	4	4.2905	-0.0269	4.2905	2.0713
No log	0.2857	6	2.9754	0.0179	2.9754	1.7249
No log	0.3810	8	2.1280	0.0168	2.1280	1.4588
No log	0.4762	10	1.5407	0.0602	1.5407	1.2412
No log	0.5714	12	1.1863	0.0417	1.1863	1.0892
No log	0.6667	14	1.1069	-0.0132	1.1069	1.0521
No log	0.7619	16	1.2557	0.0292	1.2557	1.1206
No log	0.8571	18	1.3092	0.0351	1.3092	1.1442
No log	0.9524	20	1.0609	0.0438	1.0609	1.0300
No log	1.0476	22	0.9162	0.0280	0.9162	0.9572
No log	1.1429	24	0.7561	0.2166	0.7561	0.8696
No log	1.2381	26	0.6744	0.3098	0.6744	0.8212
No log	1.3333	28	0.6397	0.2806	0.6397	0.7998
No log	1.4286	30	0.6387	0.2886	0.6387	0.7992
No log	1.5238	32	0.6678	0.2171	0.6678	0.8172
No log	1.6190	34	0.7234	0.2404	0.7234	0.8505
No log	1.7143	36	0.8149	0.1914	0.8149	0.9027
No log	1.8095	38	0.8723	0.2691	0.8723	0.9340
No log	1.9048	40	0.8933	0.2953	0.8933	0.9451
No log	2.0	42	0.8633	0.3157	0.8633	0.9291
No log	2.0952	44	0.7725	0.2839	0.7725	0.8789
No log	2.1905	46	0.6663	0.3575	0.6663	0.8163
No log	2.2857	48	0.6106	0.4371	0.6106	0.7814
No log	2.3810	50	0.5919	0.4068	0.5919	0.7694
No log	2.4762	52	0.5872	0.4151	0.5872	0.7663
No log	2.5714	54	0.5996	0.4313	0.5996	0.7743
No log	2.6667	56	0.6340	0.4433	0.6340	0.7963
No log	2.7619	58	0.6586	0.4649	0.6586	0.8115
No log	2.8571	60	0.7269	0.3795	0.7269	0.8526
No log	2.9524	62	0.8532	0.3544	0.8532	0.9237
No log	3.0476	64	0.8770	0.3316	0.8770	0.9365
No log	3.1429	66	0.8051	0.4098	0.8051	0.8973
No log	3.2381	68	0.7222	0.4551	0.7222	0.8498
No log	3.3333	70	0.7405	0.4688	0.7405	0.8605
No log	3.4286	72	0.7901	0.4608	0.7901	0.8889
No log	3.5238	74	0.7377	0.4293	0.7377	0.8589
No log	3.6190	76	0.6380	0.4936	0.6380	0.7987
No log	3.7143	78	0.5633	0.5128	0.5633	0.7505
No log	3.8095	80	0.5539	0.5403	0.5539	0.7443
No log	3.9048	82	0.5675	0.5085	0.5675	0.7533
No log	4.0	84	0.5900	0.4945	0.5900	0.7681
No log	4.0952	86	0.6390	0.5103	0.6390	0.7994
No log	4.1905	88	0.6814	0.4990	0.6814	0.8255
No log	4.2857	90	0.7045	0.4653	0.7045	0.8393
No log	4.3810	92	0.6778	0.5056	0.6778	0.8233
No log	4.4762	94	0.5901	0.5239	0.5901	0.7682
No log	4.5714	96	0.5171	0.4912	0.5171	0.7191
No log	4.6667	98	0.5045	0.4813	0.5045	0.7103
No log	4.7619	100	0.5059	0.4813	0.5059	0.7113
No log	4.8571	102	0.5033	0.4744	0.5033	0.7094
No log	4.9524	104	0.5063	0.4757	0.5063	0.7115
No log	5.0476	106	0.5249	0.5254	0.5249	0.7245
No log	5.1429	108	0.5866	0.5646	0.5866	0.7659
No log	5.2381	110	0.6912	0.4836	0.6912	0.8314
No log	5.3333	112	0.7357	0.4848	0.7357	0.8577
No log	5.4286	114	0.6889	0.5018	0.6889	0.8300
No log	5.5238	116	0.6115	0.5643	0.6115	0.7820
No log	5.6190	118	0.5688	0.5722	0.5688	0.7542
No log	5.7143	120	0.5543	0.5504	0.5543	0.7445
No log	5.8095	122	0.5349	0.5246	0.5349	0.7314
No log	5.9048	124	0.5298	0.4928	0.5298	0.7278
No log	6.0	126	0.5245	0.4918	0.5245	0.7242
No log	6.0952	128	0.5161	0.5367	0.5161	0.7184
No log	6.1905	130	0.5406	0.5700	0.5406	0.7353
No log	6.2857	132	0.5754	0.5985	0.5754	0.7586
No log	6.3810	134	0.6277	0.5310	0.6277	0.7923
No log	6.4762	136	0.6598	0.5590	0.6598	0.8123
No log	6.5714	138	0.6582	0.5371	0.6582	0.8113
No log	6.6667	140	0.6235	0.5885	0.6235	0.7896
No log	6.7619	142	0.5936	0.5527	0.5936	0.7704
No log	6.8571	144	0.6013	0.6136	0.6013	0.7755
No log	6.9524	146	0.5985	0.5682	0.5985	0.7736
No log	7.0476	148	0.5683	0.5939	0.5683	0.7539
No log	7.1429	150	0.5367	0.5178	0.5367	0.7326
No log	7.2381	152	0.5577	0.54	0.5577	0.7468
No log	7.3333	154	0.5772	0.4983	0.5772	0.7597
No log	7.4286	156	0.5667	0.5403	0.5667	0.7528
No log	7.5238	158	0.5645	0.5552	0.5645	0.7514
No log	7.6190	160	0.6085	0.5820	0.6085	0.7801
No log	7.7143	162	0.6524	0.5557	0.6524	0.8077
No log	7.8095	164	0.6701	0.5474	0.6701	0.8186
No log	7.9048	166	0.6417	0.5543	0.6417	0.8010
No log	8.0	168	0.6227	0.5350	0.6227	0.7891
No log	8.0952	170	0.6039	0.5585	0.6039	0.7771
No log	8.1905	172	0.5959	0.5688	0.5959	0.7720
No log	8.2857	174	0.5973	0.5302	0.5973	0.7728
No log	8.3810	176	0.5970	0.5320	0.5970	0.7727
No log	8.4762	178	0.6103	0.5441	0.6103	0.7812
No log	8.5714	180	0.6350	0.5861	0.6350	0.7969
No log	8.6667	182	0.6503	0.5888	0.6503	0.8064
No log	8.7619	184	0.6679	0.5787	0.6679	0.8172
No log	8.8571	186	0.7047	0.5267	0.7047	0.8395
No log	8.9524	188	0.6992	0.5430	0.6992	0.8362
No log	9.0476	190	0.6849	0.5536	0.6849	0.8276
No log	9.1429	192	0.7055	0.54	0.7055	0.8399
No log	9.2381	194	0.7023	0.5246	0.7023	0.8380
No log	9.3333	196	0.6690	0.5519	0.6690	0.8179
No log	9.4286	198	0.6583	0.5405	0.6583	0.8114
No log	9.5238	200	0.6982	0.5234	0.6982	0.8356
No log	9.6190	202	0.7263	0.5248	0.7263	0.8522
No log	9.7143	204	0.7260	0.5248	0.7260	0.8520
No log	9.8095	206	0.7074	0.5413	0.7074	0.8411
No log	9.9048	208	0.6811	0.5272	0.6811	0.8253
No log	10.0	210	0.6760	0.5354	0.6760	0.8222
No log	10.0952	212	0.6828	0.5363	0.6828	0.8263
No log	10.1905	214	0.7025	0.5135	0.7025	0.8382
No log	10.2857	216	0.7021	0.5170	0.7021	0.8379
No log	10.3810	218	0.6957	0.5673	0.6957	0.8341
No log	10.4762	220	0.6908	0.5264	0.6908	0.8312
No log	10.5714	222	0.6835	0.5315	0.6835	0.8268
No log	10.6667	224	0.7029	0.5214	0.7029	0.8384
No log	10.7619	226	0.7081	0.5091	0.7081	0.8415
No log	10.8571	228	0.6950	0.5192	0.6950	0.8337
No log	10.9524	230	0.6985	0.5187	0.6985	0.8357
No log	11.0476	232	0.6983	0.5287	0.6983	0.8356
No log	11.1429	234	0.7049	0.5302	0.7049	0.8396
No log	11.2381	236	0.7168	0.5233	0.7168	0.8466
No log	11.3333	238	0.6974	0.5186	0.6974	0.8351
No log	11.4286	240	0.6860	0.5579	0.6860	0.8283
No log	11.5238	242	0.7026	0.5405	0.7026	0.8382
No log	11.6190	244	0.7156	0.5356	0.7156	0.8459
No log	11.7143	246	0.7102	0.5534	0.7102	0.8428
No log	11.8095	248	0.7114	0.5861	0.7114	0.8434
No log	11.9048	250	0.7415	0.5419	0.7415	0.8611
No log	12.0	252	0.7476	0.5554	0.7476	0.8647
No log	12.0952	254	0.7332	0.5419	0.7332	0.8563
No log	12.1905	256	0.7368	0.5421	0.7368	0.8584
No log	12.2857	258	0.7496	0.5889	0.7496	0.8658
No log	12.3810	260	0.7682	0.5550	0.7682	0.8765
No log	12.4762	262	0.7850	0.5271	0.7850	0.8860
No log	12.5714	264	0.7740	0.5425	0.7740	0.8798
No log	12.6667	266	0.7405	0.5257	0.7405	0.8605
No log	12.7619	268	0.7147	0.5113	0.7147	0.8454
No log	12.8571	270	0.7161	0.5087	0.7161	0.8462
No log	12.9524	272	0.7252	0.4773	0.7252	0.8516
No log	13.0476	274	0.7432	0.5006	0.7432	0.8621
No log	13.1429	276	0.7506	0.5589	0.7506	0.8664
No log	13.2381	278	0.7540	0.5591	0.7540	0.8683
No log	13.3333	280	0.7802	0.5643	0.7802	0.8833
No log	13.4286	282	0.8127	0.5263	0.8127	0.9015
No log	13.5238	284	0.8167	0.5654	0.8167	0.9037
No log	13.6190	286	0.8284	0.5865	0.8284	0.9102
No log	13.7143	288	0.8305	0.5714	0.8305	0.9113
No log	13.8095	290	0.8217	0.5265	0.8217	0.9065
No log	13.9048	292	0.8017	0.5189	0.8017	0.8954
No log	14.0	294	0.7896	0.5180	0.7896	0.8886
No log	14.0952	296	0.8009	0.5306	0.8009	0.8949
No log	14.1905	298	0.8387	0.5228	0.8387	0.9158
No log	14.2857	300	0.8306	0.5395	0.8306	0.9114
No log	14.3810	302	0.7899	0.5654	0.7899	0.8887
No log	14.4762	304	0.7734	0.5105	0.7734	0.8794
No log	14.5714	306	0.8229	0.4767	0.8229	0.9072
No log	14.6667	308	0.8724	0.4785	0.8724	0.9340
No log	14.7619	310	0.8609	0.4812	0.8609	0.9278
No log	14.8571	312	0.8121	0.5175	0.8121	0.9012
No log	14.9524	314	0.7948	0.5527	0.7948	0.8915
No log	15.0476	316	0.7959	0.54	0.7959	0.8922
No log	15.1429	318	0.7769	0.5411	0.7769	0.8814
No log	15.2381	320	0.7637	0.5040	0.7637	0.8739
No log	15.3333	322	0.7606	0.5292	0.7606	0.8721
No log	15.4286	324	0.7691	0.5105	0.7691	0.8770
No log	15.5238	326	0.7944	0.5540	0.7944	0.8913
No log	15.6190	328	0.8170	0.5668	0.8170	0.9039
No log	15.7143	330	0.8292	0.5548	0.8292	0.9106
No log	15.8095	332	0.8312	0.5623	0.8312	0.9117
No log	15.9048	334	0.8097	0.5407	0.8097	0.8999
No log	16.0	336	0.8006	0.5040	0.8005	0.8947
No log	16.0952	338	0.8129	0.5105	0.8129	0.9016
No log	16.1905	340	0.8228	0.5331	0.8228	0.9071
No log	16.2857	342	0.8206	0.5515	0.8206	0.9059
No log	16.3810	344	0.8130	0.5477	0.8130	0.9017
No log	16.4762	346	0.8020	0.5477	0.8020	0.8955
No log	16.5714	348	0.7853	0.5489	0.7853	0.8862
No log	16.6667	350	0.7577	0.5347	0.7577	0.8704
No log	16.7619	352	0.7347	0.5289	0.7347	0.8572
No log	16.8571	354	0.7257	0.5049	0.7257	0.8519
No log	16.9524	356	0.7229	0.5008	0.7229	0.8503
No log	17.0476	358	0.7199	0.5166	0.7199	0.8485
No log	17.1429	360	0.7249	0.5390	0.7249	0.8514
No log	17.2381	362	0.7295	0.5458	0.7295	0.8541
No log	17.3333	364	0.7426	0.5494	0.7426	0.8618
No log	17.4286	366	0.7751	0.5338	0.7751	0.8804
No log	17.5238	368	0.8010	0.5435	0.8010	0.8950
No log	17.6190	370	0.7867	0.5344	0.7867	0.8869
No log	17.7143	372	0.7710	0.5188	0.7710	0.8780
No log	17.8095	374	0.7734	0.5508	0.7734	0.8794
No log	17.9048	376	0.7780	0.5719	0.7780	0.8820
No log	18.0	378	0.7727	0.5499	0.7727	0.8790
No log	18.0952	380	0.7769	0.5691	0.7769	0.8814
No log	18.1905	382	0.7686	0.5575	0.7686	0.8767
No log	18.2857	384	0.7585	0.5590	0.7585	0.8709
No log	18.3810	386	0.7553	0.5797	0.7553	0.8691
No log	18.4762	388	0.7592	0.5803	0.7592	0.8713
No log	18.5714	390	0.7587	0.5672	0.7587	0.8711
No log	18.6667	392	0.7592	0.5519	0.7592	0.8713
No log	18.7619	394	0.7505	0.5776	0.7505	0.8663
No log	18.8571	396	0.7432	0.5590	0.7432	0.8621
No log	18.9524	398	0.7522	0.5667	0.7522	0.8673
No log	19.0476	400	0.7618	0.5703	0.7618	0.8728
No log	19.1429	402	0.7708	0.5575	0.7708	0.8780
No log	19.2381	404	0.7873	0.5812	0.7873	0.8873
No log	19.3333	406	0.8064	0.5784	0.8064	0.8980
No log	19.4286	408	0.7943	0.5787	0.7943	0.8912
No log	19.5238	410	0.7795	0.5849	0.7795	0.8829
No log	19.6190	412	0.7626	0.5577	0.7626	0.8733
No log	19.7143	414	0.7659	0.5666	0.7659	0.8751
No log	19.8095	416	0.7762	0.5598	0.7762	0.8810
No log	19.9048	418	0.7655	0.5696	0.7655	0.8749
No log	20.0	420	0.7479	0.5515	0.7479	0.8648
No log	20.0952	422	0.7391	0.5324	0.7391	0.8597
No log	20.1905	424	0.7266	0.5658	0.7266	0.8524
No log	20.2857	426	0.7138	0.5838	0.7138	0.8449
No log	20.3810	428	0.7202	0.6037	0.7202	0.8487
No log	20.4762	430	0.7237	0.5916	0.7237	0.8507
No log	20.5714	432	0.7025	0.6072	0.7025	0.8381
No log	20.6667	434	0.6979	0.5882	0.6979	0.8354
No log	20.7619	436	0.7044	0.5541	0.7044	0.8393
No log	20.8571	438	0.7343	0.5595	0.7343	0.8569
No log	20.9524	440	0.7675	0.5148	0.7675	0.8761
No log	21.0476	442	0.7886	0.5063	0.7886	0.8880
No log	21.1429	444	0.7982	0.5602	0.7982	0.8934
No log	21.2381	446	0.8085	0.5701	0.8085	0.8992
No log	21.3333	448	0.8160	0.5650	0.8160	0.9033
No log	21.4286	450	0.8132	0.5324	0.8132	0.9018
No log	21.5238	452	0.7877	0.5375	0.7877	0.8875
No log	21.6190	454	0.7508	0.5254	0.7508	0.8665
No log	21.7143	456	0.7270	0.5133	0.7270	0.8526
No log	21.8095	458	0.7169	0.5274	0.7169	0.8467
No log	21.9048	460	0.7186	0.5251	0.7186	0.8477
No log	22.0	462	0.7353	0.5327	0.7353	0.8575
No log	22.0952	464	0.7596	0.5615	0.7596	0.8715
No log	22.1905	466	0.7517	0.5926	0.7517	0.8670
No log	22.2857	468	0.7420	0.5868	0.7420	0.8614
No log	22.3810	470	0.7405	0.5710	0.7405	0.8605
No log	22.4762	472	0.7454	0.5398	0.7454	0.8634
No log	22.5714	474	0.7527	0.5020	0.7527	0.8676
No log	22.6667	476	0.7459	0.5272	0.7459	0.8637
No log	22.7619	478	0.7478	0.5037	0.7478	0.8647
No log	22.8571	480	0.7586	0.4922	0.7586	0.8710
No log	22.9524	482	0.7715	0.4770	0.7715	0.8784
No log	23.0476	484	0.7607	0.5127	0.7607	0.8722
No log	23.1429	486	0.7412	0.5152	0.7412	0.8609
No log	23.2381	488	0.7342	0.5471	0.7342	0.8569
No log	23.3333	490	0.7449	0.5325	0.7449	0.8631
No log	23.4286	492	0.7636	0.5154	0.7636	0.8738
No log	23.5238	494	0.7518	0.5275	0.7518	0.8670
No log	23.6190	496	0.7302	0.5511	0.7302	0.8545
No log	23.7143	498	0.7355	0.5743	0.7355	0.8576
0.539	23.8095	500	0.7394	0.5561	0.7394	0.8599
0.539	23.9048	502	0.7242	0.5694	0.7242	0.8510
0.539	24.0	504	0.7105	0.5603	0.7105	0.8429
0.539	24.0952	506	0.7102	0.5491	0.7102	0.8428
0.539	24.1905	508	0.7265	0.5291	0.7265	0.8523
0.539	24.2857	510	0.7605	0.5368	0.7605	0.8721
0.539	24.3810	512	0.7777	0.5505	0.7777	0.8819
0.539	24.4762	514	0.7653	0.5575	0.7653	0.8748
0.539	24.5714	516	0.7648	0.5564	0.7648	0.8746
0.539	24.6667	518	0.7684	0.5615	0.7684	0.8766
0.539	24.7619	520	0.7920	0.5623	0.7920	0.8899
0.539	24.8571	522	0.8379	0.5388	0.8379	0.9154
0.539	24.9524	524	0.8389	0.5345	0.8389	0.9159
0.539	25.0476	526	0.8114	0.5479	0.8114	0.9008
0.539	25.1429	528	0.7869	0.5640	0.7869	0.8871
0.539	25.2381	530	0.7722	0.5324	0.7722	0.8787
0.539	25.3333	532	0.7719	0.5548	0.7719	0.8786
0.539	25.4286	534	0.7588	0.5550	0.7588	0.8711
0.539	25.5238	536	0.7553	0.5734	0.7553	0.8691
0.539	25.6190	538	0.7529	0.5800	0.7529	0.8677
0.539	25.7143	540	0.7545	0.5800	0.7545	0.8686
0.539	25.8095	542	0.7542	0.5476	0.7542	0.8685
0.539	25.9048	544	0.7464	0.5604	0.7464	0.8639
0.539	26.0	546	0.7325	0.5437	0.7325	0.8558
0.539	26.0952	548	0.7215	0.5433	0.7215	0.8494
0.539	26.1905	550	0.7169	0.5376	0.7169	0.8467
0.539	26.2857	552	0.7312	0.5546	0.7312	0.8551
0.539	26.3810	554	0.7392	0.5546	0.7392	0.8598

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1