ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k3_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: 0.6071
• Qwk: 0.4662
• Mse: 0.6071
• Rmse: 0.7791

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	0.1111	2	4.4528	-0.0243	4.4528	2.1102
No log	0.2222	4	2.5188	0.0059	2.5188	1.5871
No log	0.3333	6	1.3962	0.0356	1.3962	1.1816
No log	0.4444	8	1.1928	-0.0154	1.1928	1.0921
No log	0.5556	10	1.0809	-0.0181	1.0809	1.0397
No log	0.6667	12	0.8134	0.2704	0.8134	0.9019
No log	0.7778	14	0.8645	0.1697	0.8645	0.9298
No log	0.8889	16	1.1460	-0.0058	1.1460	1.0705
No log	1.0	18	1.3752	0.0205	1.3752	1.1727
No log	1.1111	20	1.3034	0.0043	1.3034	1.1417
No log	1.2222	22	1.0221	0.0562	1.0221	1.0110
No log	1.3333	24	0.8078	0.1696	0.8078	0.8988
No log	1.4444	26	0.8235	0.1080	0.8235	0.9075
No log	1.5556	28	0.8397	0.0869	0.8397	0.9163
No log	1.6667	30	0.8413	0.1987	0.8413	0.9172
No log	1.7778	32	0.7575	0.2736	0.7575	0.8703
No log	1.8889	34	0.7765	0.1047	0.7765	0.8812
No log	2.0	36	0.9253	0.1926	0.9253	0.9619
No log	2.1111	38	0.8901	0.1987	0.8901	0.9434
No log	2.2222	40	0.8002	0.1239	0.8002	0.8945
No log	2.3333	42	0.7706	0.1588	0.7706	0.8778
No log	2.4444	44	0.7951	0.1736	0.7951	0.8917
No log	2.5556	46	0.8693	0.1686	0.8693	0.9323
No log	2.6667	48	1.1263	0.3092	1.1263	1.0613
No log	2.7778	50	1.1225	0.3135	1.1225	1.0595
No log	2.8889	52	0.8842	0.2706	0.8842	0.9403
No log	3.0	54	0.8131	0.2346	0.8131	0.9017
No log	3.1111	56	0.7975	0.2705	0.7975	0.8930
No log	3.2222	58	0.8570	0.2898	0.8570	0.9258
No log	3.3333	60	0.9900	0.3113	0.9900	0.9950
No log	3.4444	62	1.1402	0.3477	1.1402	1.0678
No log	3.5556	64	1.1837	0.3596	1.1837	1.0880
No log	3.6667	66	1.0669	0.3161	1.0669	1.0329
No log	3.7778	68	0.9023	0.3480	0.9023	0.9499
No log	3.8889	70	0.9465	0.3246	0.9465	0.9729
No log	4.0	72	0.9946	0.3545	0.9946	0.9973
No log	4.1111	74	0.8648	0.4022	0.8648	0.9300
No log	4.2222	76	0.8070	0.3574	0.8070	0.8984
No log	4.3333	78	0.8336	0.2764	0.8336	0.9130
No log	4.4444	80	0.7912	0.4185	0.7912	0.8895
No log	4.5556	82	0.8126	0.4410	0.8126	0.9014
No log	4.6667	84	0.8249	0.3830	0.8249	0.9083
No log	4.7778	86	0.7892	0.4019	0.7892	0.8884
No log	4.8889	88	0.8026	0.4637	0.8026	0.8959
No log	5.0	90	0.9607	0.4248	0.9607	0.9801
No log	5.1111	92	1.0243	0.4198	1.0243	1.0121
No log	5.2222	94	1.1555	0.3807	1.1555	1.0750
No log	5.3333	96	1.0519	0.3848	1.0519	1.0256
No log	5.4444	98	0.9274	0.4357	0.9274	0.9630
No log	5.5556	100	0.8613	0.4014	0.8613	0.9281
No log	5.6667	102	0.8636	0.3670	0.8636	0.9293
No log	5.7778	104	0.8862	0.3826	0.8862	0.9414
No log	5.8889	106	0.8724	0.3683	0.8724	0.9340
No log	6.0	108	0.9734	0.3384	0.9734	0.9866
No log	6.1111	110	0.9271	0.3222	0.9271	0.9628
No log	6.2222	112	0.9096	0.3222	0.9096	0.9538
No log	6.3333	114	0.8471	0.3852	0.8471	0.9204
No log	6.4444	116	0.9654	0.3020	0.9654	0.9825
No log	6.5556	118	1.2460	0.2667	1.2460	1.1162
No log	6.6667	120	1.2332	0.2758	1.2332	1.1105
No log	6.7778	122	1.2441	0.2758	1.2441	1.1154
No log	6.8889	124	0.9573	0.4745	0.9573	0.9784
No log	7.0	126	0.8738	0.4838	0.8738	0.9348
No log	7.1111	128	0.9329	0.4868	0.9329	0.9659
No log	7.2222	130	1.2320	0.3274	1.2320	1.1100
No log	7.3333	132	1.5470	0.2497	1.5470	1.2438
No log	7.4444	134	1.4099	0.2834	1.4099	1.1874
No log	7.5556	136	0.9812	0.3797	0.9812	0.9906
No log	7.6667	138	0.6703	0.5598	0.6703	0.8187
No log	7.7778	140	0.7277	0.4881	0.7277	0.8531
No log	7.8889	142	0.7069	0.4939	0.7069	0.8407
No log	8.0	144	0.6252	0.5341	0.6252	0.7907
No log	8.1111	146	0.6304	0.4969	0.6304	0.7940
No log	8.2222	148	0.7218	0.4105	0.7218	0.8496
No log	8.3333	150	0.7601	0.3853	0.7601	0.8718
No log	8.4444	152	0.7339	0.4250	0.7339	0.8567
No log	8.5556	154	0.6855	0.4814	0.6855	0.8280
No log	8.6667	156	0.7243	0.5352	0.7243	0.8511
No log	8.7778	158	0.7494	0.5336	0.7494	0.8657
No log	8.8889	160	0.7667	0.5331	0.7667	0.8756
No log	9.0	162	0.8049	0.5168	0.8049	0.8972
No log	9.1111	164	0.8836	0.4261	0.8836	0.9400
No log	9.2222	166	0.9374	0.3740	0.9374	0.9682
No log	9.3333	168	0.8149	0.4141	0.8149	0.9027
No log	9.4444	170	0.7478	0.4364	0.7478	0.8647
No log	9.5556	172	0.6956	0.4546	0.6956	0.8340
No log	9.6667	174	0.6968	0.4257	0.6968	0.8347
No log	9.7778	176	0.6765	0.4483	0.6765	0.8225
No log	9.8889	178	0.7046	0.4390	0.7046	0.8394
No log	10.0	180	0.7274	0.4334	0.7274	0.8529
No log	10.1111	182	0.8045	0.4166	0.8045	0.8970
No log	10.2222	184	0.7967	0.3958	0.7967	0.8926
No log	10.3333	186	0.7031	0.4863	0.7031	0.8385
No log	10.4444	188	0.6651	0.5465	0.6651	0.8155
No log	10.5556	190	0.6648	0.4968	0.6648	0.8154
No log	10.6667	192	0.6110	0.5453	0.6110	0.7816
No log	10.7778	194	0.6563	0.4642	0.6563	0.8101
No log	10.8889	196	0.9737	0.3833	0.9737	0.9868
No log	11.0	198	1.2659	0.2907	1.2659	1.1251
No log	11.1111	200	1.2782	0.2883	1.2782	1.1306
No log	11.2222	202	0.9922	0.3452	0.9922	0.9961
No log	11.3333	204	0.7998	0.4789	0.7998	0.8943
No log	11.4444	206	0.6719	0.5546	0.6719	0.8197
No log	11.5556	208	0.7434	0.4636	0.7434	0.8622
No log	11.6667	210	0.7573	0.4329	0.7573	0.8702
No log	11.7778	212	0.6780	0.5365	0.6780	0.8234
No log	11.8889	214	0.6040	0.5403	0.6040	0.7772
No log	12.0	216	0.6024	0.4229	0.6024	0.7762
No log	12.1111	218	0.6194	0.4	0.6194	0.7870
No log	12.2222	220	0.6005	0.4024	0.6005	0.7749
No log	12.3333	222	0.6262	0.4627	0.6262	0.7913
No log	12.4444	224	0.7301	0.4680	0.7301	0.8545
No log	12.5556	226	0.7761	0.4211	0.7761	0.8810
No log	12.6667	228	0.7048	0.4987	0.7048	0.8395
No log	12.7778	230	0.6509	0.4096	0.6509	0.8068
No log	12.8889	232	0.6462	0.4001	0.6462	0.8038
No log	13.0	234	0.6487	0.3998	0.6487	0.8054
No log	13.1111	236	0.6554	0.4281	0.6554	0.8096
No log	13.2222	238	0.6759	0.4845	0.6759	0.8221
No log	13.3333	240	0.6876	0.5046	0.6876	0.8292
No log	13.4444	242	0.7477	0.4762	0.7477	0.8647
No log	13.5556	244	0.9190	0.3582	0.9190	0.9586
No log	13.6667	246	0.9477	0.3412	0.9477	0.9735
No log	13.7778	248	0.9700	0.3665	0.9700	0.9849
No log	13.8889	250	0.8409	0.4497	0.8409	0.9170
No log	14.0	252	0.7642	0.4523	0.7642	0.8742
No log	14.1111	254	0.7286	0.4477	0.7286	0.8536
No log	14.2222	256	0.6956	0.4308	0.6956	0.8340
No log	14.3333	258	0.6873	0.4313	0.6873	0.8290
No log	14.4444	260	0.6728	0.3964	0.6728	0.8203
No log	14.5556	262	0.6783	0.4084	0.6783	0.8236
No log	14.6667	264	0.7164	0.4177	0.7164	0.8464
No log	14.7778	266	0.7665	0.4177	0.7665	0.8755
No log	14.8889	268	0.7710	0.4012	0.7710	0.8781
No log	15.0	270	0.7606	0.4005	0.7606	0.8721
No log	15.1111	272	0.7379	0.3943	0.7379	0.8590
No log	15.2222	274	0.7141	0.4669	0.7141	0.8450
No log	15.3333	276	0.7241	0.4627	0.7241	0.8509
No log	15.4444	278	0.7263	0.5025	0.7263	0.8522
No log	15.5556	280	0.6922	0.4757	0.6922	0.8320
No log	15.6667	282	0.7098	0.4555	0.7098	0.8425
No log	15.7778	284	0.7906	0.4007	0.7906	0.8891
No log	15.8889	286	0.8868	0.3972	0.8868	0.9417
No log	16.0	288	0.8544	0.3831	0.8544	0.9243
No log	16.1111	290	0.7201	0.4663	0.7201	0.8486
No log	16.2222	292	0.6829	0.5054	0.6829	0.8264
No log	16.3333	294	0.7054	0.5220	0.7054	0.8399
No log	16.4444	296	0.6889	0.5243	0.6889	0.8300
No log	16.5556	298	0.6882	0.5175	0.6882	0.8296
No log	16.6667	300	0.6963	0.4992	0.6963	0.8344
No log	16.7778	302	0.7491	0.4568	0.7491	0.8655
No log	16.8889	304	0.7581	0.4603	0.7581	0.8707
No log	17.0	306	0.7235	0.4864	0.7235	0.8506
No log	17.1111	308	0.7031	0.5279	0.7031	0.8385
No log	17.2222	310	0.6963	0.5065	0.6963	0.8345
No log	17.3333	312	0.6933	0.5345	0.6933	0.8327
No log	17.4444	314	0.6553	0.5198	0.6553	0.8095
No log	17.5556	316	0.6443	0.4897	0.6443	0.8027
No log	17.6667	318	0.7030	0.4157	0.7030	0.8384
No log	17.7778	320	0.7196	0.4244	0.7196	0.8483
No log	17.8889	322	0.6707	0.4451	0.6707	0.8190
No log	18.0	324	0.6232	0.4991	0.6232	0.7895
No log	18.1111	326	0.6415	0.5170	0.6415	0.8009
No log	18.2222	328	0.6562	0.5267	0.6562	0.8101
No log	18.3333	330	0.6262	0.5227	0.6262	0.7913
No log	18.4444	332	0.5837	0.4867	0.5837	0.7640
No log	18.5556	334	0.5805	0.4089	0.5805	0.7619
No log	18.6667	336	0.5924	0.4159	0.5924	0.7696
No log	18.7778	338	0.6022	0.4092	0.6022	0.7760
No log	18.8889	340	0.5985	0.4598	0.5985	0.7737
No log	19.0	342	0.6383	0.5195	0.6383	0.7989
No log	19.1111	344	0.6898	0.5546	0.6898	0.8305
No log	19.2222	346	0.6877	0.5377	0.6877	0.8293
No log	19.3333	348	0.6535	0.5152	0.6535	0.8084
No log	19.4444	350	0.6477	0.5004	0.6477	0.8048
No log	19.5556	352	0.6603	0.4158	0.6603	0.8126
No log	19.6667	354	0.6516	0.4123	0.6516	0.8072
No log	19.7778	356	0.6435	0.4512	0.6435	0.8022
No log	19.8889	358	0.6443	0.5114	0.6443	0.8027
No log	20.0	360	0.6629	0.5524	0.6629	0.8142
No log	20.1111	362	0.6925	0.5255	0.6925	0.8321
No log	20.2222	364	0.7097	0.5255	0.7097	0.8425
No log	20.3333	366	0.7105	0.4569	0.7105	0.8429
No log	20.4444	368	0.7379	0.4558	0.7379	0.8590
No log	20.5556	370	0.7737	0.4133	0.7737	0.8796
No log	20.6667	372	0.7819	0.4183	0.7819	0.8842
No log	20.7778	374	0.8151	0.4072	0.8151	0.9028
No log	20.8889	376	0.8754	0.3958	0.8754	0.9356
No log	21.0	378	0.9121	0.4009	0.9121	0.9550
No log	21.1111	380	0.9036	0.3772	0.9036	0.9506
No log	21.2222	382	0.8795	0.4108	0.8795	0.9378
No log	21.3333	384	0.8454	0.4154	0.8454	0.9194
No log	21.4444	386	0.8167	0.4263	0.8167	0.9037
No log	21.5556	388	0.8225	0.4555	0.8225	0.9069
No log	21.6667	390	0.8987	0.4072	0.8987	0.9480
No log	21.7778	392	0.9404	0.4164	0.9404	0.9698
No log	21.8889	394	0.8889	0.4237	0.8889	0.9428
No log	22.0	396	0.7935	0.4283	0.7935	0.8908
No log	22.1111	398	0.7042	0.3932	0.7042	0.8391
No log	22.2222	400	0.6552	0.4711	0.6552	0.8094
No log	22.3333	402	0.6532	0.5126	0.6532	0.8082
No log	22.4444	404	0.6546	0.4930	0.6546	0.8091
No log	22.5556	406	0.6868	0.3927	0.6868	0.8288
No log	22.6667	408	0.7177	0.4236	0.7177	0.8472
No log	22.7778	410	0.7255	0.4411	0.7255	0.8517
No log	22.8889	412	0.7083	0.5073	0.7083	0.8416
No log	23.0	414	0.6974	0.5115	0.6974	0.8351
No log	23.1111	416	0.6869	0.5176	0.6869	0.8288
No log	23.2222	418	0.6574	0.5276	0.6574	0.8108
No log	23.3333	420	0.6433	0.5336	0.6433	0.8021
No log	23.4444	422	0.6478	0.5295	0.6478	0.8049
No log	23.5556	424	0.6655	0.5319	0.6655	0.8158
No log	23.6667	426	0.6734	0.5415	0.6734	0.8206
No log	23.7778	428	0.7041	0.4835	0.7041	0.8391
No log	23.8889	430	0.7350	0.4307	0.7350	0.8573
No log	24.0	432	0.7351	0.4051	0.7351	0.8574
No log	24.1111	434	0.7281	0.4051	0.7281	0.8533
No log	24.2222	436	0.6821	0.4295	0.6821	0.8259
No log	24.3333	438	0.6220	0.5192	0.6220	0.7887
No log	24.4444	440	0.5988	0.4984	0.5988	0.7738
No log	24.5556	442	0.5955	0.4860	0.5955	0.7717
No log	24.6667	444	0.6012	0.4847	0.6012	0.7754
No log	24.7778	446	0.6157	0.5249	0.6157	0.7847
No log	24.8889	448	0.6275	0.5434	0.6275	0.7921
No log	25.0	450	0.6268	0.5434	0.6268	0.7917
No log	25.1111	452	0.6164	0.5453	0.6164	0.7851
No log	25.2222	454	0.6072	0.5472	0.6072	0.7792
No log	25.3333	456	0.6050	0.5269	0.6050	0.7778
No log	25.4444	458	0.6084	0.5269	0.6084	0.7800
No log	25.5556	460	0.5982	0.5497	0.5982	0.7734
No log	25.6667	462	0.6062	0.5325	0.6062	0.7786
No log	25.7778	464	0.6134	0.5590	0.6134	0.7832
No log	25.8889	466	0.6292	0.5513	0.6292	0.7932
No log	26.0	468	0.6238	0.5450	0.6238	0.7898
No log	26.1111	470	0.6125	0.5528	0.6125	0.7827
No log	26.2222	472	0.5902	0.4978	0.5902	0.7683
No log	26.3333	474	0.5836	0.5039	0.5836	0.7639
No log	26.4444	476	0.5909	0.5321	0.5909	0.7687
No log	26.5556	478	0.6187	0.5261	0.6187	0.7866
No log	26.6667	480	0.6272	0.5329	0.6272	0.7919
No log	26.7778	482	0.6275	0.53	0.6275	0.7921
No log	26.8889	484	0.6342	0.5524	0.6342	0.7964
No log	27.0	486	0.6480	0.4984	0.6480	0.8050
No log	27.1111	488	0.6303	0.5304	0.6303	0.7939
No log	27.2222	490	0.6117	0.5197	0.6117	0.7821
No log	27.3333	492	0.6047	0.5329	0.6047	0.7776
No log	27.4444	494	0.6018	0.5249	0.6018	0.7757
No log	27.5556	496	0.6172	0.5333	0.6172	0.7857
No log	27.6667	498	0.6179	0.5260	0.6179	0.7860
0.3462	27.7778	500	0.6074	0.5305	0.6074	0.7794
0.3462	27.8889	502	0.5937	0.4741	0.5937	0.7705
0.3462	28.0	504	0.6086	0.4081	0.6086	0.7802
0.3462	28.1111	506	0.6347	0.4294	0.6347	0.7967
0.3462	28.2222	508	0.6363	0.4401	0.6363	0.7977
0.3462	28.3333	510	0.6209	0.5421	0.6209	0.7880
0.3462	28.4444	512	0.6144	0.5170	0.6144	0.7838
0.3462	28.5556	514	0.6013	0.4465	0.6013	0.7754
0.3462	28.6667	516	0.6074	0.4325	0.6074	0.7793
0.3462	28.7778	518	0.6066	0.4085	0.6066	0.7788
0.3462	28.8889	520	0.6071	0.4662	0.6071	0.7791

Framework versions

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