ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k9_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: 0.6352
• Qwk: 0.4519
• Mse: 0.6352
• Rmse: 0.7970

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	0.0417	2	4.1346	-0.0290	4.1346	2.0334
No log	0.0833	4	2.0131	0.0856	2.0131	1.4188
No log	0.125	6	1.2942	0.0302	1.2942	1.1376
No log	0.1667	8	0.9353	-0.0346	0.9353	0.9671
No log	0.2083	10	0.8335	0.1686	0.8335	0.9130
No log	0.25	12	0.8265	0.1359	0.8265	0.9091
No log	0.2917	14	0.8349	0.1359	0.8349	0.9137
No log	0.3333	16	0.8561	0.1334	0.8561	0.9253
No log	0.375	18	0.8284	0.1396	0.8284	0.9102
No log	0.4167	20	0.8322	0.2152	0.8322	0.9123
No log	0.4583	22	0.8240	0.2068	0.8240	0.9077
No log	0.5	24	0.8417	0.0935	0.8417	0.9174
No log	0.5417	26	0.8830	0.0902	0.8830	0.9397
No log	0.5833	28	0.8761	0.1388	0.8761	0.9360
No log	0.625	30	0.8912	0.1114	0.8912	0.9440
No log	0.6667	32	0.9072	0.0734	0.9072	0.9525
No log	0.7083	34	1.1953	-0.0065	1.1953	1.0933
No log	0.75	36	1.3662	0.0	1.3662	1.1688
No log	0.7917	38	1.2875	0.0	1.2875	1.1347
No log	0.8333	40	1.2426	0.0312	1.2426	1.1147
No log	0.875	42	1.0248	0.1798	1.0248	1.0123
No log	0.9167	44	0.8101	0.1669	0.8101	0.9001
No log	0.9583	46	0.8313	0.1596	0.8313	0.9118
No log	1.0	48	0.9679	0.2122	0.9679	0.9838
No log	1.0417	50	1.2472	0.0309	1.2472	1.1168
No log	1.0833	52	1.3040	0.0	1.3040	1.1419
No log	1.125	54	1.2463	0.0	1.2463	1.1164
No log	1.1667	56	1.2368	0.0469	1.2368	1.1121
No log	1.2083	58	1.0839	0.0516	1.0839	1.0411
No log	1.25	60	0.8419	0.1353	0.8419	0.9175
No log	1.2917	62	0.8239	0.1647	0.8239	0.9077
No log	1.3333	64	0.9239	0.1181	0.9239	0.9612
No log	1.375	66	0.9546	0.1929	0.9546	0.9770
No log	1.4167	68	0.8939	0.2800	0.8939	0.9455
No log	1.4583	70	0.8471	0.1860	0.8471	0.9204
No log	1.5	72	0.8066	0.2040	0.8066	0.8981
No log	1.5417	74	0.7787	0.2175	0.7787	0.8824
No log	1.5833	76	0.7610	0.2500	0.7610	0.8724
No log	1.625	78	0.7432	0.2476	0.7432	0.8621
No log	1.6667	80	0.7846	0.1953	0.7846	0.8858
No log	1.7083	82	0.8342	0.2188	0.8342	0.9133
No log	1.75	84	0.8149	0.2673	0.8149	0.9027
No log	1.7917	86	0.8127	0.2898	0.8127	0.9015
No log	1.8333	88	0.8026	0.4147	0.8026	0.8959
No log	1.875	90	0.7585	0.3876	0.7585	0.8709
No log	1.9167	92	0.7385	0.3318	0.7385	0.8594
No log	1.9583	94	0.7329	0.2534	0.7329	0.8561
No log	2.0	96	0.7577	0.3114	0.7577	0.8705
No log	2.0417	98	0.8980	0.2643	0.8980	0.9476
No log	2.0833	100	0.8777	0.2571	0.8777	0.9369
No log	2.125	102	0.7560	0.3367	0.7560	0.8695
No log	2.1667	104	0.7627	0.2638	0.7627	0.8733
No log	2.2083	106	0.8853	0.2182	0.8853	0.9409
No log	2.25	108	0.8833	0.2182	0.8833	0.9398
No log	2.2917	110	0.7813	0.2086	0.7813	0.8839
No log	2.3333	112	0.7297	0.3406	0.7297	0.8542
No log	2.375	114	0.7444	0.3820	0.7444	0.8628
No log	2.4167	116	0.7889	0.4606	0.7889	0.8882
No log	2.4583	118	0.7940	0.4492	0.7940	0.8911
No log	2.5	120	0.7960	0.4184	0.7960	0.8922
No log	2.5417	122	0.8029	0.4418	0.8029	0.8960
No log	2.5833	124	0.7967	0.4439	0.7967	0.8926
No log	2.625	126	0.7795	0.4527	0.7795	0.8829
No log	2.6667	128	0.7469	0.4681	0.7469	0.8642
No log	2.7083	130	0.7077	0.4603	0.7077	0.8413
No log	2.75	132	0.6706	0.4405	0.6706	0.8189
No log	2.7917	134	0.6704	0.4332	0.6704	0.8188
No log	2.8333	136	0.6906	0.4215	0.6906	0.8311
No log	2.875	138	0.7164	0.3770	0.7164	0.8464
No log	2.9167	140	0.7112	0.4619	0.7112	0.8433
No log	2.9583	142	0.7555	0.4899	0.7555	0.8692
No log	3.0	144	0.7934	0.4344	0.7934	0.8907
No log	3.0417	146	0.7869	0.4962	0.7869	0.8871
No log	3.0833	148	0.7870	0.4747	0.7870	0.8871
No log	3.125	150	0.7586	0.4692	0.7586	0.8710
No log	3.1667	152	0.7309	0.4370	0.7309	0.8549
No log	3.2083	154	0.7339	0.4736	0.7339	0.8567
No log	3.25	156	0.7304	0.4820	0.7304	0.8547
No log	3.2917	158	0.7065	0.4243	0.7065	0.8405
No log	3.3333	160	0.7061	0.4725	0.7061	0.8403
No log	3.375	162	0.7154	0.4939	0.7154	0.8458
No log	3.4167	164	0.7031	0.5088	0.7031	0.8385
No log	3.4583	166	0.6753	0.4173	0.6753	0.8218
No log	3.5	168	0.6627	0.4450	0.6627	0.8141
No log	3.5417	170	0.6808	0.4113	0.6808	0.8251
No log	3.5833	172	0.7210	0.4698	0.7210	0.8491
No log	3.625	174	0.7614	0.4432	0.7614	0.8726
No log	3.6667	176	0.7774	0.4491	0.7774	0.8817
No log	3.7083	178	0.8701	0.4539	0.8701	0.9328
No log	3.75	180	1.0300	0.3715	1.0300	1.0149
No log	3.7917	182	0.9569	0.3777	0.9569	0.9782
No log	3.8333	184	0.9139	0.4211	0.9139	0.9560
No log	3.875	186	0.9610	0.4499	0.9610	0.9803
No log	3.9167	188	0.9939	0.4198	0.9939	0.9969
No log	3.9583	190	0.9533	0.4367	0.9533	0.9764
No log	4.0	192	0.8625	0.4297	0.8625	0.9287
No log	4.0417	194	0.8075	0.4145	0.8075	0.8986
No log	4.0833	196	0.7827	0.4394	0.7827	0.8847
No log	4.125	198	0.7466	0.4584	0.7466	0.8641
No log	4.1667	200	0.7209	0.4895	0.7209	0.8491
No log	4.2083	202	0.6622	0.4754	0.6622	0.8138
No log	4.25	204	0.6704	0.4891	0.6704	0.8188
No log	4.2917	206	0.6679	0.5018	0.6679	0.8173
No log	4.3333	208	0.6601	0.4894	0.6601	0.8125
No log	4.375	210	0.7024	0.5090	0.7024	0.8381
No log	4.4167	212	0.8773	0.4215	0.8773	0.9366
No log	4.4583	214	0.9480	0.3898	0.9480	0.9737
No log	4.5	216	0.8375	0.4358	0.8375	0.9152
No log	4.5417	218	0.7068	0.4418	0.7068	0.8407
No log	4.5833	220	0.9090	0.4098	0.9090	0.9534
No log	4.625	222	0.9374	0.4190	0.9374	0.9682
No log	4.6667	224	0.7636	0.4736	0.7636	0.8738
No log	4.7083	226	0.7465	0.5347	0.7465	0.8640
No log	4.75	228	0.7881	0.4866	0.7881	0.8878
No log	4.7917	230	0.7151	0.5548	0.7151	0.8456
No log	4.8333	232	0.6694	0.5625	0.6694	0.8182
No log	4.875	234	0.6434	0.4702	0.6434	0.8021
No log	4.9167	236	0.6354	0.4607	0.6354	0.7971
No log	4.9583	238	0.6306	0.4639	0.6306	0.7941
No log	5.0	240	0.6374	0.4680	0.6374	0.7984
No log	5.0417	242	0.6375	0.4426	0.6375	0.7984
No log	5.0833	244	0.6397	0.4535	0.6397	0.7998
No log	5.125	246	0.6632	0.4496	0.6632	0.8144
No log	5.1667	248	0.7080	0.3860	0.7080	0.8414
No log	5.2083	250	0.6839	0.3974	0.6839	0.8270
No log	5.25	252	0.6897	0.4179	0.6897	0.8305
No log	5.2917	254	0.6474	0.4397	0.6474	0.8046
No log	5.3333	256	0.6176	0.4601	0.6176	0.7859
No log	5.375	258	0.6012	0.4454	0.6012	0.7754
No log	5.4167	260	0.6005	0.4708	0.6005	0.7749
No log	5.4583	262	0.5960	0.4447	0.5960	0.7720
No log	5.5	264	0.5991	0.4220	0.5991	0.7740
No log	5.5417	266	0.6523	0.4552	0.6523	0.8077
No log	5.5833	268	0.6379	0.4552	0.6379	0.7987
No log	5.625	270	0.5780	0.4221	0.5780	0.7602
No log	5.6667	272	0.6704	0.5075	0.6704	0.8188
No log	5.7083	274	0.7610	0.4876	0.7610	0.8723
No log	5.75	276	0.7141	0.5161	0.7141	0.8451
No log	5.7917	278	0.6454	0.4753	0.6454	0.8034
No log	5.8333	280	0.6428	0.5034	0.6428	0.8018
No log	5.875	282	0.6417	0.4749	0.6417	0.8010
No log	5.9167	284	0.6509	0.5491	0.6509	0.8068
No log	5.9583	286	0.6642	0.5535	0.6642	0.8150
No log	6.0	288	0.6314	0.5186	0.6314	0.7946
No log	6.0417	290	0.6326	0.4152	0.6326	0.7954
No log	6.0833	292	0.6798	0.4474	0.6798	0.8245
No log	6.125	294	0.7680	0.4586	0.7680	0.8763
No log	6.1667	296	0.7793	0.4515	0.7793	0.8828
No log	6.2083	298	0.7573	0.4542	0.7573	0.8702
No log	6.25	300	0.7622	0.4451	0.7622	0.8730
No log	6.2917	302	0.6632	0.4465	0.6632	0.8144
No log	6.3333	304	0.6371	0.5319	0.6371	0.7982
No log	6.375	306	0.6558	0.5313	0.6558	0.8098
No log	6.4167	308	0.6968	0.5390	0.6968	0.8348
No log	6.4583	310	0.6833	0.5043	0.6833	0.8266
No log	6.5	312	0.6482	0.4607	0.6482	0.8051
No log	6.5417	314	0.6422	0.4073	0.6422	0.8014
No log	6.5833	316	0.6385	0.4305	0.6385	0.7990
No log	6.625	318	0.6392	0.5056	0.6392	0.7995
No log	6.6667	320	0.6447	0.5166	0.6447	0.8029
No log	6.7083	322	0.6421	0.4906	0.6421	0.8013
No log	6.75	324	0.6353	0.4676	0.6353	0.7971
No log	6.7917	326	0.6304	0.4772	0.6304	0.7940
No log	6.8333	328	0.6238	0.4276	0.6238	0.7898
No log	6.875	330	0.6379	0.3703	0.6379	0.7987
No log	6.9167	332	0.6416	0.3839	0.6416	0.8010
No log	6.9583	334	0.6256	0.4155	0.6256	0.7910
No log	7.0	336	0.6190	0.5248	0.6190	0.7868
No log	7.0417	338	0.6235	0.5231	0.6235	0.7896
No log	7.0833	340	0.6369	0.5037	0.6369	0.7980
No log	7.125	342	0.6735	0.4626	0.6735	0.8207
No log	7.1667	344	0.6357	0.5378	0.6357	0.7973
No log	7.2083	346	0.6054	0.4667	0.6054	0.7781
No log	7.25	348	0.5999	0.5363	0.5999	0.7745
No log	7.2917	350	0.6248	0.5276	0.6248	0.7905
No log	7.3333	352	0.6259	0.5391	0.6259	0.7911
No log	7.375	354	0.6164	0.5365	0.6164	0.7851
No log	7.4167	356	0.6415	0.4665	0.6415	0.8010
No log	7.4583	358	0.6701	0.4588	0.6701	0.8186
No log	7.5	360	0.6909	0.4496	0.6909	0.8312
No log	7.5417	362	0.6773	0.4746	0.6773	0.8230
No log	7.5833	364	0.6768	0.4207	0.6768	0.8227
No log	7.625	366	0.6937	0.3560	0.6937	0.8329
No log	7.6667	368	0.7172	0.3632	0.7172	0.8469
No log	7.7083	370	0.6537	0.4282	0.6537	0.8085
No log	7.75	372	0.6203	0.4913	0.6203	0.7876
No log	7.7917	374	0.6596	0.5458	0.6596	0.8122
No log	7.8333	376	0.6900	0.5549	0.6900	0.8307
No log	7.875	378	0.6959	0.4885	0.6959	0.8342
No log	7.9167	380	0.7595	0.4525	0.7595	0.8715
No log	7.9583	382	0.7566	0.4579	0.7566	0.8698
No log	8.0	384	0.7276	0.4756	0.7276	0.8530
No log	8.0417	386	0.7498	0.4748	0.7498	0.8659
No log	8.0833	388	0.7430	0.4828	0.7430	0.8620
No log	8.125	390	0.7639	0.4716	0.7639	0.8740
No log	8.1667	392	0.8148	0.4670	0.8148	0.9026
No log	8.2083	394	0.9008	0.4690	0.9008	0.9491
No log	8.25	396	0.8852	0.4530	0.8852	0.9408
No log	8.2917	398	0.7797	0.4745	0.7797	0.8830
No log	8.3333	400	0.6864	0.4930	0.6864	0.8285
No log	8.375	402	0.6459	0.5635	0.6459	0.8037
No log	8.4167	404	0.6522	0.4638	0.6522	0.8076
No log	8.4583	406	0.6405	0.4647	0.6405	0.8003
No log	8.5	408	0.6379	0.5204	0.6379	0.7987
No log	8.5417	410	0.6766	0.4980	0.6766	0.8225
No log	8.5833	412	0.7227	0.5278	0.7227	0.8501
No log	8.625	414	0.7411	0.5041	0.7411	0.8608
No log	8.6667	416	0.7127	0.5108	0.7127	0.8442
No log	8.7083	418	0.6874	0.4798	0.6874	0.8291
No log	8.75	420	0.6348	0.4910	0.6348	0.7967
No log	8.7917	422	0.6170	0.4895	0.6170	0.7855
No log	8.8333	424	0.5969	0.4648	0.5969	0.7726
No log	8.875	426	0.6017	0.5361	0.6017	0.7757
No log	8.9167	428	0.6021	0.5039	0.6021	0.7759
No log	8.9583	430	0.6100	0.4949	0.6100	0.7810
No log	9.0	432	0.6202	0.5290	0.6202	0.7875
No log	9.0417	434	0.6495	0.5900	0.6495	0.8059
No log	9.0833	436	0.6732	0.5682	0.6732	0.8205
No log	9.125	438	0.6281	0.5851	0.6281	0.7925
No log	9.1667	440	0.6022	0.5141	0.6022	0.7760
No log	9.2083	442	0.5986	0.4733	0.5986	0.7737
No log	9.25	444	0.6073	0.5156	0.6073	0.7793
No log	9.2917	446	0.6249	0.5137	0.6249	0.7905
No log	9.3333	448	0.6364	0.5282	0.6364	0.7978
No log	9.375	450	0.6520	0.5524	0.6520	0.8075
No log	9.4167	452	0.7365	0.4768	0.7365	0.8582
No log	9.4583	454	0.7614	0.4978	0.7614	0.8726
No log	9.5	456	0.6885	0.5280	0.6885	0.8298
No log	9.5417	458	0.6036	0.5380	0.6036	0.7769
No log	9.5833	460	0.5880	0.5083	0.5880	0.7668
No log	9.625	462	0.5980	0.4706	0.5980	0.7733
No log	9.6667	464	0.6059	0.5225	0.6059	0.7784
No log	9.7083	466	0.6603	0.5559	0.6603	0.8126
No log	9.75	468	0.7104	0.5416	0.7104	0.8428
No log	9.7917	470	0.6811	0.5469	0.6811	0.8253
No log	9.8333	472	0.6192	0.5641	0.6192	0.7869
No log	9.875	474	0.6120	0.5011	0.6120	0.7823
No log	9.9167	476	0.6013	0.5438	0.6013	0.7754
No log	9.9583	478	0.6053	0.5319	0.6053	0.7780
No log	10.0	480	0.6016	0.5260	0.6016	0.7756
No log	10.0417	482	0.6232	0.5687	0.6232	0.7894
No log	10.0833	484	0.6329	0.5456	0.6329	0.7956
No log	10.125	486	0.6351	0.5364	0.6351	0.7969
No log	10.1667	488	0.6474	0.5551	0.6474	0.8046
No log	10.2083	490	0.6531	0.5572	0.6531	0.8082
No log	10.25	492	0.6431	0.5536	0.6431	0.8019
No log	10.2917	494	0.6284	0.5605	0.6284	0.7927
No log	10.3333	496	0.6406	0.5722	0.6406	0.8004
No log	10.375	498	0.6632	0.5673	0.6632	0.8144
0.4548	10.4167	500	0.6370	0.5504	0.6370	0.7981
0.4548	10.4583	502	0.5898	0.4696	0.5898	0.7680
0.4548	10.5	504	0.5967	0.4560	0.5967	0.7725
0.4548	10.5417	506	0.6156	0.4794	0.6156	0.7846
0.4548	10.5833	508	0.6396	0.4776	0.6396	0.7997
0.4548	10.625	510	0.6839	0.5623	0.6839	0.8270
0.4548	10.6667	512	0.7493	0.5263	0.7493	0.8656
0.4548	10.7083	514	0.7586	0.5263	0.7586	0.8710
0.4548	10.75	516	0.7204	0.5520	0.7204	0.8488
0.4548	10.7917	518	0.6883	0.5518	0.6883	0.8296
0.4548	10.8333	520	0.6802	0.4997	0.6802	0.8247
0.4548	10.875	522	0.6659	0.4630	0.6659	0.8160
0.4548	10.9167	524	0.6719	0.5376	0.6719	0.8197
0.4548	10.9583	526	0.6882	0.5388	0.6882	0.8296
0.4548	11.0	528	0.6773	0.5600	0.6773	0.8230
0.4548	11.0417	530	0.6490	0.4940	0.6490	0.8056
0.4548	11.0833	532	0.6491	0.4891	0.6491	0.8057
0.4548	11.125	534	0.6445	0.4788	0.6445	0.8028
0.4548	11.1667	536	0.6523	0.5461	0.6523	0.8076
0.4548	11.2083	538	0.6629	0.5591	0.6629	0.8142
0.4548	11.25	540	0.6768	0.5816	0.6768	0.8227
0.4548	11.2917	542	0.6808	0.5542	0.6808	0.8251
0.4548	11.3333	544	0.6451	0.5391	0.6451	0.8032
0.4548	11.375	546	0.6183	0.4203	0.6183	0.7863
0.4548	11.4167	548	0.6299	0.4123	0.6299	0.7937
0.4548	11.4583	550	0.6385	0.4059	0.6385	0.7991
0.4548	11.5	552	0.6352	0.4519	0.6352	0.7970

Framework versions

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