Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask8_grammar

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: 1.1541
• Qwk: 0.4137
• Mse: 1.1541
• Rmse: 1.0743

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	0.0196	2	4.6665	0.0108	4.6665	2.1602
No log	0.0392	4	3.6593	0.0367	3.6593	1.9129
No log	0.0588	6	2.0428	0.0808	2.0428	1.4293
No log	0.0784	8	0.9602	0.1798	0.9602	0.9799
No log	0.0980	10	0.7992	0.1622	0.7992	0.8940
No log	0.1176	12	0.8159	0.1181	0.8159	0.9033
No log	0.1373	14	0.7635	0.3098	0.7635	0.8738
No log	0.1569	16	0.8561	0.3451	0.8561	0.9253
No log	0.1765	18	0.6892	0.3942	0.6892	0.8302
No log	0.1961	20	0.7363	0.4052	0.7363	0.8581
No log	0.2157	22	0.7910	0.2309	0.7910	0.8894
No log	0.2353	24	0.9228	0.0177	0.9228	0.9606
No log	0.2549	26	0.8609	0.0740	0.8609	0.9279
No log	0.2745	28	0.6962	0.2557	0.6962	0.8344
No log	0.2941	30	0.5877	0.4365	0.5877	0.7666
No log	0.3137	32	0.6307	0.4433	0.6307	0.7942
No log	0.3333	34	0.5963	0.4920	0.5963	0.7722
No log	0.3529	36	0.5625	0.5120	0.5625	0.7500
No log	0.3725	38	0.6726	0.4113	0.6726	0.8201
No log	0.3922	40	0.7038	0.3033	0.7038	0.8389
No log	0.4118	42	0.6342	0.3713	0.6342	0.7963
No log	0.4314	44	0.5829	0.4489	0.5829	0.7635
No log	0.4510	46	0.5868	0.4642	0.5868	0.7660
No log	0.4706	48	0.5946	0.4678	0.5946	0.7711
No log	0.4902	50	0.5810	0.4294	0.5810	0.7622
No log	0.5098	52	0.5345	0.4221	0.5345	0.7311
No log	0.5294	54	0.5094	0.4302	0.5094	0.7137
No log	0.5490	56	0.5386	0.4316	0.5386	0.7339
No log	0.5686	58	0.5933	0.4128	0.5933	0.7703
No log	0.5882	60	0.6873	0.3909	0.6873	0.8291
No log	0.6078	62	0.6825	0.4340	0.6825	0.8261
No log	0.6275	64	0.6071	0.5436	0.6071	0.7792
No log	0.6471	66	0.5447	0.6146	0.5447	0.7381
No log	0.6667	68	0.4726	0.6243	0.4726	0.6875
No log	0.6863	70	0.4617	0.6475	0.4617	0.6795
No log	0.7059	72	0.5190	0.6321	0.5190	0.7204
No log	0.7255	74	0.4766	0.6629	0.4766	0.6904
No log	0.7451	76	0.5066	0.6681	0.5066	0.7118
No log	0.7647	78	0.6468	0.5397	0.6468	0.8043
No log	0.7843	80	0.6336	0.5465	0.6336	0.7960
No log	0.8039	82	0.5293	0.4872	0.5293	0.7276
No log	0.8235	84	0.5339	0.5680	0.5339	0.7307
No log	0.8431	86	0.6458	0.5156	0.6458	0.8036
No log	0.8627	88	0.6336	0.5204	0.6336	0.7960
No log	0.8824	90	0.5097	0.5856	0.5097	0.7139
No log	0.9020	92	0.4953	0.4911	0.4953	0.7038
No log	0.9216	94	0.5481	0.4987	0.5481	0.7403
No log	0.9412	96	0.6404	0.4835	0.6404	0.8003
No log	0.9608	98	0.6058	0.4651	0.6058	0.7783
No log	0.9804	100	0.5402	0.4272	0.5402	0.7350
No log	1.0	102	0.5149	0.4887	0.5149	0.7175
No log	1.0196	104	0.4928	0.5260	0.4928	0.7020
No log	1.0392	106	0.4908	0.5549	0.4908	0.7006
No log	1.0588	108	0.5213	0.5391	0.5213	0.7220
No log	1.0784	110	0.5177	0.5567	0.5177	0.7195
No log	1.0980	112	0.4785	0.6352	0.4785	0.6917
No log	1.1176	114	0.4813	0.6326	0.4813	0.6938
No log	1.1373	116	0.4926	0.6358	0.4926	0.7018
No log	1.1569	118	0.5730	0.5368	0.5730	0.7570
No log	1.1765	120	0.5955	0.4977	0.5955	0.7717
No log	1.1961	122	0.5461	0.5295	0.5461	0.7390
No log	1.2157	124	0.4687	0.6080	0.4687	0.6846
No log	1.2353	126	0.4648	0.6402	0.4648	0.6817
No log	1.2549	128	0.4722	0.6382	0.4722	0.6872
No log	1.2745	130	0.4883	0.6479	0.4883	0.6988
No log	1.2941	132	0.5171	0.6730	0.5171	0.7191
No log	1.3137	134	0.5949	0.6131	0.5949	0.7713
No log	1.3333	136	0.6381	0.6094	0.6381	0.7988
No log	1.3529	138	0.5281	0.6637	0.5281	0.7267
No log	1.3725	140	0.4765	0.6983	0.4765	0.6903
No log	1.3922	142	0.5037	0.6542	0.5037	0.7097
No log	1.4118	144	0.5388	0.6385	0.5388	0.7341
No log	1.4314	146	0.5120	0.6027	0.5120	0.7155
No log	1.4510	148	0.4459	0.6334	0.4459	0.6677
No log	1.4706	150	0.4478	0.5996	0.4478	0.6692
No log	1.4902	152	0.4943	0.5984	0.4943	0.7030
No log	1.5098	154	0.5852	0.5646	0.5852	0.7650
No log	1.5294	156	0.6282	0.5216	0.6282	0.7926
No log	1.5490	158	0.6769	0.5158	0.6769	0.8227
No log	1.5686	160	0.5846	0.5780	0.5846	0.7646
No log	1.5882	162	0.4731	0.6097	0.4731	0.6878
No log	1.6078	164	0.4387	0.6364	0.4387	0.6623
No log	1.6275	166	0.4226	0.6399	0.4226	0.6501
No log	1.6471	168	0.4096	0.6776	0.4096	0.6400
No log	1.6667	170	0.5214	0.6180	0.5214	0.7221
No log	1.6863	172	0.7892	0.4572	0.7892	0.8884
No log	1.7059	174	0.8675	0.4051	0.8675	0.9314
No log	1.7255	176	0.8054	0.4451	0.8054	0.8975
No log	1.7451	178	0.7479	0.3709	0.7479	0.8648
No log	1.7647	180	0.6472	0.3935	0.6472	0.8045
No log	1.7843	182	0.6338	0.4099	0.6338	0.7961
No log	1.8039	184	0.6872	0.4359	0.6872	0.8290
No log	1.8235	186	0.6785	0.4427	0.6785	0.8237
No log	1.8431	188	0.6442	0.4487	0.6442	0.8026
No log	1.8627	190	0.5911	0.4535	0.5911	0.7688
No log	1.8824	192	0.5084	0.5201	0.5084	0.7130
No log	1.9020	194	0.4296	0.6170	0.4296	0.6555
No log	1.9216	196	0.4087	0.6970	0.4087	0.6393
No log	1.9412	198	0.4103	0.7251	0.4103	0.6406
No log	1.9608	200	0.4104	0.7009	0.4104	0.6406
No log	1.9804	202	0.4596	0.6691	0.4596	0.6780
No log	2.0	204	0.4952	0.6559	0.4952	0.7037
No log	2.0196	206	0.4846	0.6652	0.4846	0.6961
No log	2.0392	208	0.4455	0.6767	0.4455	0.6675
No log	2.0588	210	0.4160	0.6898	0.4160	0.6450
No log	2.0784	212	0.4571	0.6640	0.4571	0.6761
No log	2.0980	214	0.5360	0.6358	0.5360	0.7321
No log	2.1176	216	0.5001	0.6520	0.5001	0.7072
No log	2.1373	218	0.4078	0.6697	0.4078	0.6386
No log	2.1569	220	0.4165	0.6410	0.4165	0.6454
No log	2.1765	222	0.4463	0.6157	0.4463	0.6681
No log	2.1961	224	0.4716	0.6056	0.4716	0.6867
No log	2.2157	226	0.4912	0.6084	0.4912	0.7009
No log	2.2353	228	0.4759	0.6127	0.4759	0.6899
No log	2.2549	230	0.4367	0.6317	0.4367	0.6608
No log	2.2745	232	0.4361	0.6747	0.4361	0.6604
No log	2.2941	234	0.5510	0.6428	0.5510	0.7423
No log	2.3137	236	0.6165	0.5801	0.6165	0.7852
No log	2.3333	238	0.5309	0.6651	0.5309	0.7286
No log	2.3529	240	0.4283	0.7254	0.4283	0.6544
No log	2.3725	242	0.3972	0.7336	0.3972	0.6303
No log	2.3922	244	0.3931	0.7157	0.3931	0.6270
No log	2.4118	246	0.3958	0.7307	0.3958	0.6291
No log	2.4314	248	0.4252	0.7417	0.4252	0.6521
No log	2.4510	250	0.4369	0.7405	0.4369	0.6610
No log	2.4706	252	0.4154	0.6969	0.4154	0.6445
No log	2.4902	254	0.4035	0.6824	0.4035	0.6352
No log	2.5098	256	0.4216	0.6594	0.4216	0.6493
No log	2.5294	258	0.4781	0.6175	0.4781	0.6915
No log	2.5490	260	0.6034	0.5766	0.6034	0.7768
No log	2.5686	262	0.6523	0.5303	0.6523	0.8077
No log	2.5882	264	0.5875	0.6323	0.5875	0.7665
No log	2.6078	266	0.5240	0.6382	0.5240	0.7239
No log	2.6275	268	0.5511	0.6434	0.5511	0.7424
No log	2.6471	270	0.5077	0.6356	0.5077	0.7126
No log	2.6667	272	0.4701	0.6288	0.4701	0.6856
No log	2.6863	274	0.5019	0.6250	0.5019	0.7084
No log	2.7059	276	0.5210	0.6129	0.5210	0.7218
No log	2.7255	278	0.4912	0.6352	0.4912	0.7008
No log	2.7451	280	0.4607	0.6381	0.4607	0.6787
No log	2.7647	282	0.4367	0.6455	0.4367	0.6609
No log	2.7843	284	0.4137	0.6385	0.4137	0.6432
No log	2.8039	286	0.4050	0.6669	0.4050	0.6364
No log	2.8235	288	0.4054	0.6565	0.4054	0.6367
No log	2.8431	290	0.4656	0.6768	0.4656	0.6823
No log	2.8627	292	0.6891	0.5419	0.6891	0.8301
No log	2.8824	294	0.8701	0.4711	0.8701	0.9328
No log	2.9020	296	0.8427	0.4836	0.8427	0.9180
No log	2.9216	298	0.6257	0.6071	0.6257	0.7910
No log	2.9412	300	0.4503	0.6795	0.4503	0.6711
No log	2.9608	302	0.4708	0.6801	0.4708	0.6861
No log	2.9804	304	0.4785	0.6750	0.4785	0.6917
No log	3.0	306	0.4060	0.6479	0.4060	0.6372
No log	3.0196	308	0.4294	0.6488	0.4294	0.6553
No log	3.0392	310	0.5220	0.5757	0.5220	0.7225
No log	3.0588	312	0.6074	0.4948	0.6074	0.7794
No log	3.0784	314	0.5872	0.4947	0.5872	0.7663
No log	3.0980	316	0.5101	0.5969	0.5101	0.7142
No log	3.1176	318	0.4545	0.6390	0.4545	0.6741
No log	3.1373	320	0.4097	0.6949	0.4097	0.6400
No log	3.1569	322	0.4174	0.7326	0.4174	0.6460
No log	3.1765	324	0.4067	0.7318	0.4067	0.6377
No log	3.1961	326	0.4165	0.7270	0.4165	0.6454
No log	3.2157	328	0.4501	0.7125	0.4501	0.6709
No log	3.2353	330	0.4437	0.7116	0.4437	0.6661
No log	3.2549	332	0.4234	0.7192	0.4234	0.6507
No log	3.2745	334	0.4619	0.6944	0.4619	0.6797
No log	3.2941	336	0.5880	0.6181	0.5880	0.7668
No log	3.3137	338	0.7674	0.5219	0.7674	0.8760
No log	3.3333	340	0.7755	0.5307	0.7755	0.8806
No log	3.3529	342	0.5740	0.6826	0.5740	0.7576
No log	3.3725	344	0.4168	0.7197	0.4168	0.6456
No log	3.3922	346	0.4122	0.7047	0.4122	0.6420
No log	3.4118	348	0.4041	0.7148	0.4041	0.6357
No log	3.4314	350	0.4547	0.7029	0.4547	0.6743
No log	3.4510	352	0.7426	0.5516	0.7426	0.8617
No log	3.4706	354	0.8988	0.4434	0.8988	0.9480
No log	3.4902	356	0.8012	0.4653	0.8012	0.8951
No log	3.5098	358	0.6497	0.5098	0.6497	0.8061
No log	3.5294	360	0.5067	0.5717	0.5067	0.7119
No log	3.5490	362	0.4191	0.6337	0.4191	0.6474
No log	3.5686	364	0.3769	0.6874	0.3769	0.6139
No log	3.5882	366	0.4186	0.7377	0.4186	0.6470
No log	3.6078	368	0.4372	0.7375	0.4372	0.6612
No log	3.6275	370	0.4703	0.7065	0.4703	0.6858
No log	3.6471	372	0.5848	0.6301	0.5848	0.7647
No log	3.6667	374	0.6585	0.5570	0.6585	0.8115
No log	3.6863	376	0.6498	0.5366	0.6498	0.8061
No log	3.7059	378	0.5813	0.5361	0.5813	0.7624
No log	3.7255	380	0.5038	0.6183	0.5038	0.7098
No log	3.7451	382	0.4479	0.6634	0.4479	0.6692
No log	3.7647	384	0.4120	0.7157	0.4120	0.6419
No log	3.7843	386	0.4097	0.7078	0.4097	0.6401
No log	3.8039	388	0.4032	0.7149	0.4032	0.6350
No log	3.8235	390	0.4106	0.7075	0.4106	0.6408
No log	3.8431	392	0.4225	0.6922	0.4225	0.6500
No log	3.8627	394	0.4001	0.6806	0.4001	0.6325
No log	3.8824	396	0.4227	0.6597	0.4227	0.6501
No log	3.9020	398	0.4176	0.6684	0.4176	0.6462
No log	3.9216	400	0.4039	0.6408	0.4039	0.6355
No log	3.9412	402	0.4125	0.6865	0.4125	0.6422
No log	3.9608	404	0.4811	0.6565	0.4811	0.6936
No log	3.9804	406	0.4876	0.6609	0.4876	0.6983
No log	4.0	408	0.5054	0.6407	0.5054	0.7109
No log	4.0196	410	0.6054	0.6025	0.6054	0.7781
No log	4.0392	412	0.7235	0.5638	0.7235	0.8506
No log	4.0588	414	0.6509	0.5759	0.6509	0.8068
No log	4.0784	416	0.4875	0.6375	0.4875	0.6982
No log	4.0980	418	0.4572	0.5912	0.4572	0.6761
No log	4.1176	420	0.4301	0.6375	0.4301	0.6558
No log	4.1373	422	0.4545	0.6781	0.4545	0.6741
No log	4.1569	424	0.6376	0.6241	0.6376	0.7985
No log	4.1765	426	0.6940	0.5995	0.6940	0.8331
No log	4.1961	428	0.5903	0.6331	0.5903	0.7683
No log	4.2157	430	0.4306	0.7018	0.4306	0.6562
No log	4.2353	432	0.4065	0.7273	0.4065	0.6376
No log	4.2549	434	0.4378	0.6886	0.4378	0.6617
No log	4.2745	436	0.4704	0.6384	0.4704	0.6859
No log	4.2941	438	0.4140	0.6299	0.4140	0.6435
No log	4.3137	440	0.4161	0.6109	0.4161	0.6450
No log	4.3333	442	0.4137	0.6108	0.4137	0.6432
No log	4.3529	444	0.4340	0.6292	0.4340	0.6588
No log	4.3725	446	0.4270	0.6492	0.4270	0.6534
No log	4.3922	448	0.4554	0.6702	0.4554	0.6749
No log	4.4118	450	0.4837	0.6932	0.4837	0.6955
No log	4.4314	452	0.4349	0.6984	0.4349	0.6594
No log	4.4510	454	0.4324	0.7469	0.4324	0.6575
No log	4.4706	456	0.5200	0.6761	0.5200	0.7211
No log	4.4902	458	0.6330	0.6053	0.6330	0.7956
No log	4.5098	460	0.5442	0.6572	0.5442	0.7377
No log	4.5294	462	0.4984	0.6777	0.4984	0.7060
No log	4.5490	464	0.4089	0.7200	0.4089	0.6394
No log	4.5686	466	0.3918	0.6788	0.3918	0.6260
No log	4.5882	468	0.4436	0.6895	0.4436	0.6660
No log	4.6078	470	0.4651	0.6849	0.4651	0.6820
No log	4.6275	472	0.4733	0.6846	0.4733	0.6880
No log	4.6471	474	0.4265	0.6936	0.4265	0.6531
No log	4.6667	476	0.4392	0.6880	0.4392	0.6627
No log	4.6863	478	0.4242	0.6985	0.4242	0.6513
No log	4.7059	480	0.3954	0.7178	0.3954	0.6288
No log	4.7255	482	0.4074	0.6795	0.4074	0.6383
No log	4.7451	484	0.4319	0.6026	0.4319	0.6572
No log	4.7647	486	0.4385	0.6151	0.4385	0.6622
No log	4.7843	488	0.4686	0.6215	0.4686	0.6845
No log	4.8039	490	0.4545	0.6573	0.4545	0.6742
No log	4.8235	492	0.4573	0.6754	0.4573	0.6763
No log	4.8431	494	0.5645	0.6575	0.5645	0.7514
No log	4.8627	496	0.6008	0.6470	0.6008	0.7751
No log	4.8824	498	0.5220	0.6913	0.5220	0.7225
0.5195	4.9020	500	0.4284	0.7482	0.4284	0.6545
0.5195	4.9216	502	0.4141	0.7477	0.4141	0.6435
0.5195	4.9412	504	0.4159	0.7254	0.4159	0.6449
0.5195	4.9608	506	0.6276	0.6328	0.6276	0.7922
0.5195	4.9804	508	1.0729	0.4353	1.0729	1.0358
0.5195	5.0	510	1.1541	0.4137	1.1541	1.0743

Framework versions

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