Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask6_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: 0.5716
• Qwk: 0.5757
• Mse: 0.5716
• Rmse: 0.7560

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	0.0194	2	4.6545	-0.0214	4.6545	2.1574
No log	0.0388	4	2.7259	0.0440	2.7259	1.6510
No log	0.0583	6	1.4363	0.0351	1.4363	1.1984
No log	0.0777	8	0.8380	0.1736	0.8380	0.9154
No log	0.0971	10	0.7015	0.2479	0.7015	0.8375
No log	0.1165	12	0.7047	0.1433	0.7047	0.8395
No log	0.1359	14	0.7369	0.1669	0.7369	0.8584
No log	0.1553	16	0.7415	0.1648	0.7415	0.8611
No log	0.1748	18	0.8791	0.1936	0.8791	0.9376
No log	0.1942	20	1.5824	0.0677	1.5824	1.2579
No log	0.2136	22	1.4080	0.1148	1.4080	1.1866
No log	0.2330	24	0.8231	0.2773	0.8231	0.9073
No log	0.2524	26	0.5790	0.3206	0.5790	0.7609
No log	0.2718	28	0.6999	0.1758	0.6999	0.8366
No log	0.2913	30	0.6414	0.2109	0.6414	0.8009
No log	0.3107	32	0.5569	0.3844	0.5569	0.7462
No log	0.3301	34	0.5638	0.4470	0.5638	0.7509
No log	0.3495	36	0.5842	0.3854	0.5842	0.7644
No log	0.3689	38	0.5960	0.3821	0.5960	0.7720
No log	0.3883	40	0.5704	0.4008	0.5704	0.7553
No log	0.4078	42	0.5522	0.4577	0.5522	0.7431
No log	0.4272	44	0.5444	0.5145	0.5444	0.7378
No log	0.4466	46	0.5460	0.5089	0.5460	0.7389
No log	0.4660	48	0.5958	0.5061	0.5958	0.7719
No log	0.4854	50	0.6412	0.5038	0.6412	0.8007
No log	0.5049	52	0.7626	0.4769	0.7626	0.8733
No log	0.5243	54	0.6720	0.4852	0.6720	0.8197
No log	0.5437	56	0.6008	0.5456	0.6008	0.7751
No log	0.5631	58	0.5317	0.5351	0.5317	0.7292
No log	0.5825	60	0.5529	0.3992	0.5529	0.7435
No log	0.6019	62	0.6467	0.2379	0.6467	0.8042
No log	0.6214	64	0.6519	0.2038	0.6519	0.8074
No log	0.6408	66	0.5984	0.2281	0.5984	0.7736
No log	0.6602	68	0.5865	0.2393	0.5865	0.7658
No log	0.6796	70	0.5819	0.2638	0.5819	0.7628
No log	0.6990	72	0.6064	0.2852	0.6064	0.7787
No log	0.7184	74	0.6024	0.3006	0.6024	0.7761
No log	0.7379	76	0.5880	0.3303	0.5880	0.7668
No log	0.7573	78	0.5543	0.4014	0.5543	0.7445
No log	0.7767	80	0.6039	0.4303	0.6039	0.7771
No log	0.7961	82	0.6884	0.3854	0.6884	0.8297
No log	0.8155	84	0.6038	0.4916	0.6038	0.7770
No log	0.8350	86	0.5193	0.4737	0.5193	0.7206
No log	0.8544	88	0.5262	0.4757	0.5262	0.7254
No log	0.8738	90	0.5654	0.4787	0.5654	0.7519
No log	0.8932	92	0.5377	0.5137	0.5377	0.7333
No log	0.9126	94	0.4853	0.5394	0.4853	0.6966
No log	0.9320	96	0.4972	0.5742	0.4972	0.7051
No log	0.9515	98	0.5283	0.5720	0.5283	0.7269
No log	0.9709	100	0.5336	0.5732	0.5336	0.7305
No log	0.9903	102	0.5841	0.5644	0.5841	0.7643
No log	1.0097	104	0.6572	0.5391	0.6572	0.8107
No log	1.0291	106	0.7438	0.3423	0.7438	0.8625
No log	1.0485	108	0.8559	0.2858	0.8559	0.9252
No log	1.0680	110	0.7397	0.3083	0.7397	0.8600
No log	1.0874	112	0.5669	0.4512	0.5669	0.7529
No log	1.1068	114	0.5004	0.5715	0.5004	0.7074
No log	1.1262	116	0.4792	0.5518	0.4792	0.6922
No log	1.1456	118	0.5171	0.5388	0.5171	0.7191
No log	1.1650	120	0.5677	0.4987	0.5677	0.7534
No log	1.1845	122	0.5123	0.4961	0.5123	0.7157
No log	1.2039	124	0.6051	0.4994	0.6051	0.7779
No log	1.2233	126	0.5715	0.5299	0.5715	0.7560
No log	1.2427	128	0.5504	0.5049	0.5504	0.7419
No log	1.2621	130	0.4478	0.5278	0.4478	0.6692
No log	1.2816	132	0.4424	0.5410	0.4424	0.6651
No log	1.3010	134	0.5270	0.5637	0.5270	0.7260
No log	1.3204	136	0.5390	0.5421	0.5390	0.7342
No log	1.3398	138	0.4542	0.5339	0.4542	0.6739
No log	1.3592	140	0.4411	0.5432	0.4411	0.6642
No log	1.3786	142	0.4980	0.5417	0.4980	0.7057
No log	1.3981	144	0.6240	0.5235	0.6240	0.7900
No log	1.4175	146	0.6735	0.5291	0.6735	0.8207
No log	1.4369	148	0.5989	0.5301	0.5989	0.7739
No log	1.4563	150	0.5410	0.5244	0.5410	0.7355
No log	1.4757	152	0.6051	0.5085	0.6051	0.7779
No log	1.4951	154	0.6147	0.5084	0.6147	0.7840
No log	1.5146	156	0.6051	0.4768	0.6051	0.7779
No log	1.5340	158	0.6878	0.4858	0.6878	0.8293
No log	1.5534	160	0.8004	0.4865	0.8004	0.8946
No log	1.5728	162	0.7777	0.5131	0.7777	0.8819
No log	1.5922	164	0.6453	0.5721	0.6453	0.8033
No log	1.6117	166	0.6097	0.5718	0.6097	0.7809
No log	1.6311	168	0.5600	0.5813	0.5600	0.7484
No log	1.6505	170	0.5061	0.5766	0.5061	0.7114
No log	1.6699	172	0.4845	0.5491	0.4845	0.6960
No log	1.6893	174	0.4818	0.5497	0.4818	0.6942
No log	1.7087	176	0.4678	0.5319	0.4678	0.6840
No log	1.7282	178	0.4889	0.5356	0.4889	0.6992
No log	1.7476	180	0.5018	0.5429	0.5018	0.7083
No log	1.7670	182	0.5020	0.5682	0.5020	0.7085
No log	1.7864	184	0.4740	0.5979	0.4740	0.6885
No log	1.8058	186	0.5502	0.5223	0.5502	0.7417
No log	1.8252	188	0.5452	0.5580	0.5452	0.7384
No log	1.8447	190	0.5029	0.5953	0.5029	0.7092
No log	1.8641	192	0.4626	0.5878	0.4626	0.6801
No log	1.8835	194	0.4846	0.5286	0.4846	0.6961
No log	1.9029	196	0.5039	0.4473	0.5039	0.7098
No log	1.9223	198	0.5397	0.5014	0.5397	0.7347
No log	1.9417	200	0.5410	0.5068	0.5410	0.7355
No log	1.9612	202	0.4834	0.5456	0.4834	0.6952
No log	1.9806	204	0.4564	0.5993	0.4564	0.6756
No log	2.0	206	0.5032	0.6130	0.5032	0.7094
No log	2.0194	208	0.5107	0.6141	0.5107	0.7146
No log	2.0388	210	0.5354	0.5934	0.5354	0.7317
No log	2.0583	212	0.6298	0.5544	0.6298	0.7936
No log	2.0777	214	0.6518	0.5299	0.6518	0.8073
No log	2.0971	216	0.5772	0.5484	0.5772	0.7597
No log	2.1165	218	0.4868	0.6097	0.4868	0.6977
No log	2.1359	220	0.4603	0.5497	0.4603	0.6784
No log	2.1553	222	0.4669	0.5136	0.4669	0.6833
No log	2.1748	224	0.4767	0.5825	0.4767	0.6905
No log	2.1942	226	0.5362	0.5868	0.5362	0.7322
No log	2.2136	228	0.5987	0.5293	0.5987	0.7738
No log	2.2330	230	0.6892	0.5273	0.6892	0.8302
No log	2.2524	232	0.7109	0.5452	0.7109	0.8431
No log	2.2718	234	0.6664	0.5634	0.6664	0.8163
No log	2.2913	236	0.7045	0.5180	0.7045	0.8393
No log	2.3107	238	0.7991	0.5335	0.7991	0.8939
No log	2.3301	240	0.7188	0.5624	0.7188	0.8478
No log	2.3495	242	0.5465	0.5943	0.5465	0.7393
No log	2.3689	244	0.4863	0.5975	0.4863	0.6974
No log	2.3883	246	0.4878	0.5633	0.4878	0.6984
No log	2.4078	248	0.4951	0.5247	0.4951	0.7037
No log	2.4272	250	0.5445	0.5491	0.5445	0.7379
No log	2.4466	252	0.5991	0.4937	0.5991	0.7740
No log	2.4660	254	0.5941	0.5084	0.5941	0.7708
No log	2.4854	256	0.5324	0.5057	0.5324	0.7296
No log	2.5049	258	0.4877	0.5353	0.4877	0.6983
No log	2.5243	260	0.4715	0.5469	0.4715	0.6866
No log	2.5437	262	0.4589	0.5627	0.4589	0.6774
No log	2.5631	264	0.5118	0.5565	0.5118	0.7154
No log	2.5825	266	0.5824	0.5223	0.5824	0.7632
No log	2.6019	268	0.5401	0.5565	0.5401	0.7349
No log	2.6214	270	0.4580	0.5610	0.4580	0.6768
No log	2.6408	272	0.4690	0.5792	0.4690	0.6849
No log	2.6602	274	0.4957	0.5878	0.4957	0.7041
No log	2.6796	276	0.5316	0.5752	0.5316	0.7291
No log	2.6990	278	0.5905	0.5645	0.5905	0.7684
No log	2.7184	280	0.6116	0.5303	0.6116	0.7820
No log	2.7379	282	0.5301	0.5694	0.5301	0.7281
No log	2.7573	284	0.4703	0.6349	0.4703	0.6858
No log	2.7767	286	0.4633	0.6324	0.4633	0.6806
No log	2.7961	288	0.4918	0.6007	0.4918	0.7013
No log	2.8155	290	0.5483	0.5627	0.5483	0.7405
No log	2.8350	292	0.6367	0.5160	0.6367	0.7979
No log	2.8544	294	0.6195	0.5578	0.6195	0.7871
No log	2.8738	296	0.5627	0.5896	0.5627	0.7502
No log	2.8932	298	0.5472	0.5927	0.5472	0.7398
No log	2.9126	300	0.5601	0.5869	0.5601	0.7484
No log	2.9320	302	0.5745	0.5934	0.5745	0.7580
No log	2.9515	304	0.5770	0.5821	0.5770	0.7596
No log	2.9709	306	0.4609	0.6320	0.4609	0.6789
No log	2.9903	308	0.4359	0.5807	0.4359	0.6602
No log	3.0097	310	0.4531	0.5308	0.4531	0.6731
No log	3.0291	312	0.4365	0.5746	0.4365	0.6607
No log	3.0485	314	0.5167	0.5513	0.5167	0.7188
No log	3.0680	316	0.6775	0.4924	0.6775	0.8231
No log	3.0874	318	0.7080	0.4916	0.7080	0.8414
No log	3.1068	320	0.5510	0.5634	0.5510	0.7423
No log	3.1262	322	0.4830	0.6149	0.4830	0.6950
No log	3.1456	324	0.4578	0.6345	0.4578	0.6766
No log	3.1650	326	0.4658	0.6258	0.4658	0.6825
No log	3.1845	328	0.4954	0.6346	0.4954	0.7038
No log	3.2039	330	0.4748	0.6427	0.4748	0.6891
No log	3.2233	332	0.4469	0.6646	0.4469	0.6685
No log	3.2427	334	0.4544	0.6455	0.4544	0.6741
No log	3.2621	336	0.4646	0.6187	0.4646	0.6816
No log	3.2816	338	0.5084	0.5853	0.5084	0.7130
No log	3.3010	340	0.5481	0.5621	0.5481	0.7403
No log	3.3204	342	0.5867	0.5422	0.5867	0.7660
No log	3.3398	344	0.5339	0.5650	0.5339	0.7307
No log	3.3592	346	0.4708	0.6416	0.4708	0.6861
No log	3.3786	348	0.4752	0.6357	0.4752	0.6894
No log	3.3981	350	0.4780	0.6276	0.4780	0.6913
No log	3.4175	352	0.5024	0.6132	0.5024	0.7088
No log	3.4369	354	0.5332	0.5940	0.5332	0.7302
No log	3.4563	356	0.5591	0.5682	0.5591	0.7477
No log	3.4757	358	0.5566	0.5704	0.5566	0.7461
No log	3.4951	360	0.5596	0.5456	0.5596	0.7480
No log	3.5146	362	0.5304	0.5464	0.5304	0.7283
No log	3.5340	364	0.5426	0.5552	0.5426	0.7366
No log	3.5534	366	0.5885	0.5402	0.5885	0.7672
No log	3.5728	368	0.6248	0.5048	0.6248	0.7904
No log	3.5922	370	0.5326	0.5680	0.5326	0.7298
No log	3.6117	372	0.4745	0.5689	0.4745	0.6889
No log	3.6311	374	0.4612	0.5776	0.4612	0.6791
No log	3.6505	376	0.4595	0.5968	0.4595	0.6779
No log	3.6699	378	0.5115	0.5590	0.5115	0.7152
No log	3.6893	380	0.5568	0.5329	0.5568	0.7462
No log	3.7087	382	0.5341	0.5713	0.5341	0.7308
No log	3.7282	384	0.4777	0.5978	0.4777	0.6912
No log	3.7476	386	0.4856	0.6393	0.4856	0.6969
No log	3.7670	388	0.4701	0.6397	0.4701	0.6856
No log	3.7864	390	0.4745	0.6210	0.4745	0.6889
No log	3.8058	392	0.5133	0.5870	0.5133	0.7164
No log	3.8252	394	0.5393	0.5845	0.5393	0.7344
No log	3.8447	396	0.5209	0.5874	0.5209	0.7218
No log	3.8641	398	0.4869	0.6136	0.4869	0.6978
No log	3.8835	400	0.5143	0.6148	0.5143	0.7171
No log	3.9029	402	0.5088	0.6156	0.5088	0.7133
No log	3.9223	404	0.5327	0.5760	0.5327	0.7299
No log	3.9417	406	0.6752	0.5536	0.6752	0.8217
No log	3.9612	408	0.6384	0.5615	0.6384	0.7990
No log	3.9806	410	0.5492	0.5368	0.5492	0.7411
No log	4.0	412	0.5137	0.5769	0.5137	0.7167
No log	4.0194	414	0.4946	0.5898	0.4946	0.7033
No log	4.0388	416	0.5414	0.5737	0.5414	0.7358
No log	4.0583	418	0.7217	0.5596	0.7217	0.8496
No log	4.0777	420	0.7358	0.5580	0.7358	0.8578
No log	4.0971	422	0.6055	0.5672	0.6055	0.7781
No log	4.1165	424	0.5514	0.5833	0.5514	0.7426
No log	4.1359	426	0.5632	0.5857	0.5632	0.7505
No log	4.1553	428	0.5653	0.5728	0.5653	0.7519
No log	4.1748	430	0.7886	0.5806	0.7886	0.8880
No log	4.1942	432	0.9425	0.5621	0.9425	0.9708
No log	4.2136	434	0.7834	0.5612	0.7834	0.8851
No log	4.2330	436	0.5045	0.5930	0.5045	0.7103
No log	4.2524	438	0.4787	0.6151	0.4787	0.6919
No log	4.2718	440	0.4525	0.6314	0.4525	0.6727
No log	4.2913	442	0.5405	0.5804	0.5405	0.7352
No log	4.3107	444	0.7829	0.5530	0.7829	0.8848
No log	4.3301	446	0.7624	0.5382	0.7624	0.8731
No log	4.3495	448	0.5518	0.5940	0.5518	0.7428
No log	4.3689	450	0.4466	0.6150	0.4466	0.6683
No log	4.3883	452	0.4626	0.5760	0.4626	0.6801
No log	4.4078	454	0.4597	0.5911	0.4597	0.6780
No log	4.4272	456	0.4537	0.5898	0.4537	0.6736
No log	4.4466	458	0.4605	0.6325	0.4605	0.6786
No log	4.4660	460	0.4995	0.6250	0.4995	0.7067
No log	4.4854	462	0.4679	0.6342	0.4679	0.6840
No log	4.5049	464	0.4824	0.6461	0.4824	0.6945
No log	4.5243	466	0.5036	0.6415	0.5036	0.7097
No log	4.5437	468	0.4977	0.6382	0.4977	0.7055
No log	4.5631	470	0.5532	0.6175	0.5532	0.7438
No log	4.5825	472	0.5259	0.5839	0.5259	0.7252
No log	4.6019	474	0.5735	0.5797	0.5735	0.7573
No log	4.6214	476	0.6616	0.5669	0.6616	0.8134
No log	4.6408	478	0.7244	0.5504	0.7244	0.8511
No log	4.6602	480	0.6635	0.5653	0.6635	0.8145
No log	4.6796	482	0.5177	0.5902	0.5177	0.7195
No log	4.6990	484	0.4558	0.5988	0.4558	0.6751
No log	4.7184	486	0.4547	0.5895	0.4547	0.6743
No log	4.7379	488	0.4688	0.5756	0.4688	0.6847
No log	4.7573	490	0.5761	0.5615	0.5761	0.7590
No log	4.7767	492	0.6651	0.5222	0.6651	0.8156
No log	4.7961	494	0.6016	0.5245	0.6016	0.7756
No log	4.8155	496	0.5011	0.5653	0.5011	0.7079
No log	4.8350	498	0.4574	0.5667	0.4574	0.6763
0.53	4.8544	500	0.4520	0.5761	0.4520	0.6723
0.53	4.8738	502	0.4726	0.5993	0.4726	0.6874
0.53	4.8932	504	0.5501	0.5582	0.5501	0.7417
0.53	4.9126	506	0.5831	0.5671	0.5831	0.7636
0.53	4.9320	508	0.5097	0.5817	0.5097	0.7139
0.53	4.9515	510	0.5021	0.6048	0.5021	0.7086
0.53	4.9709	512	0.5653	0.5900	0.5653	0.7519
0.53	4.9903	514	0.6278	0.5830	0.6278	0.7924
0.53	5.0097	516	0.6706	0.5531	0.6706	0.8189
0.53	5.0291	518	0.5891	0.5773	0.5891	0.7676
0.53	5.0485	520	0.4875	0.6380	0.4875	0.6982
0.53	5.0680	522	0.4882	0.6250	0.4882	0.6987
0.53	5.0874	524	0.5620	0.5813	0.5620	0.7497
0.53	5.1068	526	0.6514	0.5633	0.6514	0.8071
0.53	5.1262	528	0.6162	0.5737	0.6162	0.7850
0.53	5.1456	530	0.5488	0.5685	0.5488	0.7408
0.53	5.1650	532	0.5820	0.5751	0.5820	0.7629
0.53	5.1845	534	0.5716	0.5757	0.5716	0.7560

Framework versions

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