Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask4_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: 0.4946
• Qwk: 0.5245
• Mse: 0.4946
• Rmse: 0.7033

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	0.0187	2	4.6909	0.0067	4.6909	2.1658
No log	0.0374	4	3.3550	0.0504	3.3550	1.8317
No log	0.0561	6	1.8060	0.1151	1.8060	1.3439
No log	0.0748	8	0.9222	0.1800	0.9222	0.9603
No log	0.0935	10	0.8426	0.1258	0.8426	0.9180
No log	0.1121	12	0.8917	0.1169	0.8917	0.9443
No log	0.1308	14	1.0185	0.0879	1.0185	1.0092
No log	0.1495	16	1.0964	0.0863	1.0964	1.0471
No log	0.1682	18	0.9224	0.2409	0.9224	0.9604
No log	0.1869	20	0.8513	0.1995	0.8513	0.9227
No log	0.2056	22	0.7326	0.2205	0.7326	0.8559
No log	0.2243	24	0.6936	0.2493	0.6936	0.8328
No log	0.2430	26	0.6989	0.3637	0.6989	0.8360
No log	0.2617	28	0.7834	0.3652	0.7834	0.8851
No log	0.2804	30	0.6835	0.3956	0.6835	0.8267
No log	0.2991	32	0.6387	0.3739	0.6387	0.7992
No log	0.3178	34	0.7230	0.3301	0.7230	0.8503
No log	0.3364	36	0.7429	0.3196	0.7429	0.8619
No log	0.3551	38	0.6954	0.3338	0.6954	0.8339
No log	0.3738	40	0.6865	0.3419	0.6865	0.8286
No log	0.3925	42	0.6636	0.3361	0.6636	0.8146
No log	0.4112	44	0.6712	0.3367	0.6712	0.8193
No log	0.4299	46	0.7001	0.3346	0.7001	0.8367
No log	0.4486	48	0.7158	0.3153	0.7158	0.8461
No log	0.4673	50	0.6919	0.3314	0.6919	0.8318
No log	0.4860	52	0.6841	0.3344	0.6841	0.8271
No log	0.5047	54	0.6269	0.3067	0.6269	0.7917
No log	0.5234	56	0.6212	0.3513	0.6212	0.7881
No log	0.5421	58	0.6123	0.3793	0.6123	0.7825
No log	0.5607	60	0.5916	0.3094	0.5916	0.7692
No log	0.5794	62	0.6205	0.2840	0.6205	0.7877
No log	0.5981	64	0.5838	0.3333	0.5838	0.7641
No log	0.6168	66	0.5679	0.4087	0.5679	0.7536
No log	0.6355	68	0.5330	0.4381	0.5330	0.7301
No log	0.6542	70	0.5568	0.4050	0.5568	0.7462
No log	0.6729	72	0.5778	0.4466	0.5778	0.7601
No log	0.6916	74	0.7796	0.3016	0.7796	0.8830
No log	0.7103	76	0.8055	0.2610	0.8055	0.8975
No log	0.7290	78	0.8392	0.1976	0.8392	0.9161
No log	0.7477	80	0.8873	0.1131	0.8873	0.9419
No log	0.7664	82	0.9376	0.1404	0.9376	0.9683
No log	0.7850	84	1.0218	0.1780	1.0218	1.0109
No log	0.8037	86	0.9614	0.1926	0.9614	0.9805
No log	0.8224	88	0.7407	0.4210	0.7407	0.8606
No log	0.8411	90	0.5650	0.4620	0.5650	0.7516
No log	0.8598	92	0.5112	0.4219	0.5112	0.7150
No log	0.8785	94	0.5244	0.3832	0.5244	0.7241
No log	0.8972	96	0.5448	0.3759	0.5448	0.7381
No log	0.9159	98	0.5472	0.3533	0.5472	0.7397
No log	0.9346	100	0.5826	0.3699	0.5826	0.7633
No log	0.9533	102	0.6793	0.4322	0.6793	0.8242
No log	0.9720	104	0.7808	0.4309	0.7808	0.8836
No log	0.9907	106	0.7082	0.4691	0.7082	0.8415
No log	1.0093	108	0.6321	0.4551	0.6321	0.7950
No log	1.0280	110	0.5119	0.4712	0.5119	0.7154
No log	1.0467	112	0.4803	0.4973	0.4803	0.6931
No log	1.0654	114	0.4714	0.5047	0.4714	0.6866
No log	1.0841	116	0.4958	0.5252	0.4958	0.7042
No log	1.1028	118	0.6300	0.5123	0.6300	0.7937
No log	1.1215	120	0.6902	0.5153	0.6902	0.8308
No log	1.1402	122	0.6344	0.5549	0.6344	0.7965
No log	1.1589	124	0.5181	0.6337	0.5181	0.7198
No log	1.1776	126	0.5060	0.6224	0.5060	0.7113
No log	1.1963	128	0.5268	0.6368	0.5268	0.7258
No log	1.2150	130	0.5112	0.6431	0.5112	0.7150
No log	1.2336	132	0.4970	0.6516	0.4970	0.7049
No log	1.2523	134	0.4880	0.6287	0.4880	0.6986
No log	1.2710	136	0.5088	0.6221	0.5088	0.7133
No log	1.2897	138	0.5693	0.5806	0.5693	0.7545
No log	1.3084	140	0.6024	0.5615	0.6024	0.7762
No log	1.3271	142	0.6086	0.5236	0.6086	0.7801
No log	1.3458	144	0.4797	0.5731	0.4797	0.6926
No log	1.3645	146	0.4482	0.5821	0.4482	0.6695
No log	1.3832	148	0.4818	0.5926	0.4818	0.6941
No log	1.4019	150	0.4787	0.5917	0.4787	0.6918
No log	1.4206	152	0.4551	0.5398	0.4551	0.6746
No log	1.4393	154	0.5331	0.4403	0.5331	0.7301
No log	1.4579	156	0.6580	0.4073	0.6580	0.8112
No log	1.4766	158	0.7586	0.3895	0.7586	0.8710
No log	1.4953	160	0.7507	0.4276	0.7507	0.8664
No log	1.5140	162	0.6379	0.4460	0.6379	0.7987
No log	1.5327	164	0.5549	0.4837	0.5549	0.7449
No log	1.5514	166	0.4786	0.6031	0.4786	0.6918
No log	1.5701	168	0.4632	0.6238	0.4632	0.6806
No log	1.5888	170	0.4807	0.6470	0.4807	0.6933
No log	1.6075	172	0.4879	0.6186	0.4879	0.6985
No log	1.6262	174	0.6092	0.5360	0.6092	0.7805
No log	1.6449	176	0.7225	0.3810	0.7225	0.8500
No log	1.6636	178	0.7457	0.3395	0.7457	0.8635
No log	1.6822	180	0.6915	0.4367	0.6915	0.8316
No log	1.7009	182	0.5971	0.5079	0.5971	0.7727
No log	1.7196	184	0.4874	0.5671	0.4874	0.6981
No log	1.7383	186	0.4545	0.5565	0.4545	0.6742
No log	1.7570	188	0.4996	0.5464	0.4996	0.7068
No log	1.7757	190	0.4844	0.5489	0.4844	0.6960
No log	1.7944	192	0.4610	0.5210	0.4610	0.6789
No log	1.8131	194	0.4881	0.5564	0.4881	0.6986
No log	1.8318	196	0.5238	0.5738	0.5238	0.7238
No log	1.8505	198	0.5021	0.5872	0.5021	0.7086
No log	1.8692	200	0.4610	0.5851	0.4610	0.6790
No log	1.8879	202	0.5161	0.5477	0.5161	0.7184
No log	1.9065	204	0.4841	0.5699	0.4841	0.6958
No log	1.9252	206	0.4415	0.6101	0.4415	0.6644
No log	1.9439	208	0.5044	0.5768	0.5044	0.7102
No log	1.9626	210	0.5646	0.5234	0.5646	0.7514
No log	1.9813	212	0.5393	0.5046	0.5393	0.7344
No log	2.0	214	0.4874	0.4772	0.4874	0.6982
No log	2.0187	216	0.4948	0.4653	0.4948	0.7034
No log	2.0374	218	0.5073	0.4489	0.5073	0.7122
No log	2.0561	220	0.5328	0.3936	0.5328	0.7299
No log	2.0748	222	0.5639	0.3794	0.5639	0.7509
No log	2.0935	224	0.5730	0.3673	0.5730	0.7570
No log	2.1121	226	0.5888	0.3276	0.5888	0.7673
No log	2.1308	228	0.5698	0.3870	0.5698	0.7548
No log	2.1495	230	0.5221	0.4694	0.5221	0.7226
No log	2.1682	232	0.4869	0.5875	0.4869	0.6978
No log	2.1869	234	0.4779	0.6017	0.4779	0.6913
No log	2.2056	236	0.4587	0.6373	0.4587	0.6773
No log	2.2243	238	0.4770	0.6463	0.4770	0.6906
No log	2.2430	240	0.5380	0.5828	0.5380	0.7335
No log	2.2617	242	0.5793	0.5720	0.5793	0.7611
No log	2.2804	244	0.5067	0.5982	0.5067	0.7118
No log	2.2991	246	0.4665	0.5676	0.4665	0.6830
No log	2.3178	248	0.4592	0.5578	0.4592	0.6777
No log	2.3364	250	0.4638	0.5404	0.4638	0.6810
No log	2.3551	252	0.5172	0.5472	0.5172	0.7191
No log	2.3738	254	0.6020	0.4921	0.6020	0.7759
No log	2.3925	256	0.6448	0.4939	0.6448	0.8030
No log	2.4112	258	0.5623	0.5591	0.5623	0.7499
No log	2.4299	260	0.4486	0.6020	0.4486	0.6698
No log	2.4486	262	0.4297	0.5698	0.4297	0.6555
No log	2.4673	264	0.4221	0.6116	0.4221	0.6497
No log	2.4860	266	0.4321	0.6420	0.4321	0.6573
No log	2.5047	268	0.5164	0.6357	0.5164	0.7186
No log	2.5234	270	0.5749	0.5900	0.5749	0.7582
No log	2.5421	272	0.4987	0.6262	0.4987	0.7062
No log	2.5607	274	0.4699	0.6288	0.4699	0.6855
No log	2.5794	276	0.5253	0.6040	0.5253	0.7248
No log	2.5981	278	0.5125	0.5980	0.5125	0.7159
No log	2.6168	280	0.4667	0.6513	0.4667	0.6832
No log	2.6355	282	0.4391	0.6185	0.4391	0.6627
No log	2.6542	284	0.4485	0.6706	0.4485	0.6697
No log	2.6729	286	0.5413	0.6169	0.5413	0.7358
No log	2.6916	288	0.7172	0.5152	0.7172	0.8469
No log	2.7103	290	0.7016	0.5329	0.7016	0.8376
No log	2.7290	292	0.5335	0.6034	0.5335	0.7304
No log	2.7477	294	0.4575	0.6415	0.4575	0.6764
No log	2.7664	296	0.4277	0.6038	0.4277	0.6540
No log	2.7850	298	0.4262	0.6193	0.4262	0.6528
No log	2.8037	300	0.4214	0.6108	0.4214	0.6492
No log	2.8224	302	0.4229	0.6507	0.4229	0.6503
No log	2.8411	304	0.4155	0.6093	0.4155	0.6446
No log	2.8598	306	0.4679	0.6349	0.4679	0.6840
No log	2.8785	308	0.4657	0.6356	0.4657	0.6824
No log	2.8972	310	0.4787	0.6208	0.4787	0.6919
No log	2.9159	312	0.5411	0.6151	0.5411	0.7356
No log	2.9346	314	0.4876	0.6108	0.4876	0.6983
No log	2.9533	316	0.4206	0.6204	0.4206	0.6485
No log	2.9720	318	0.4224	0.6200	0.4224	0.6499
No log	2.9907	320	0.4367	0.6026	0.4367	0.6608
No log	3.0093	322	0.5085	0.5390	0.5085	0.7131
No log	3.0280	324	0.5996	0.5456	0.5996	0.7743
No log	3.0467	326	0.5840	0.5655	0.5840	0.7642
No log	3.0654	328	0.5168	0.6144	0.5168	0.7189
No log	3.0841	330	0.4641	0.6322	0.4641	0.6813
No log	3.1028	332	0.4594	0.6770	0.4594	0.6778
No log	3.1215	334	0.4794	0.6916	0.4794	0.6924
No log	3.1402	336	0.5288	0.6577	0.5288	0.7272
No log	3.1589	338	0.5831	0.6389	0.5831	0.7636
No log	3.1776	340	0.5270	0.6524	0.5270	0.7260
No log	3.1963	342	0.4278	0.6609	0.4278	0.6541
No log	3.2150	344	0.4226	0.6493	0.4226	0.6501
No log	3.2336	346	0.4175	0.6672	0.4175	0.6461
No log	3.2523	348	0.4628	0.6565	0.4628	0.6803
No log	3.2710	350	0.4828	0.6549	0.4828	0.6948
No log	3.2897	352	0.4547	0.6548	0.4547	0.6743
No log	3.3084	354	0.4429	0.6153	0.4429	0.6655
No log	3.3271	356	0.4685	0.5639	0.4685	0.6845
No log	3.3458	358	0.4661	0.5507	0.4661	0.6827
No log	3.3645	360	0.4614	0.5829	0.4614	0.6792
No log	3.3832	362	0.4663	0.5402	0.4663	0.6829
No log	3.4019	364	0.4685	0.5632	0.4685	0.6844
No log	3.4206	366	0.4967	0.6130	0.4967	0.7048
No log	3.4393	368	0.5437	0.6385	0.5437	0.7373
No log	3.4579	370	0.6294	0.5986	0.6294	0.7934
No log	3.4766	372	0.6688	0.5647	0.6688	0.8178
No log	3.4953	374	0.5939	0.6051	0.5939	0.7706
No log	3.5140	376	0.5189	0.6785	0.5189	0.7204
No log	3.5327	378	0.4826	0.6946	0.4826	0.6947
No log	3.5514	380	0.5590	0.6266	0.5590	0.7476
No log	3.5701	382	0.6080	0.6000	0.6080	0.7797
No log	3.5888	384	0.4495	0.6764	0.4495	0.6705
No log	3.6075	386	0.4134	0.6896	0.4134	0.6430
No log	3.6262	388	0.4689	0.6340	0.4689	0.6847
No log	3.6449	390	0.4628	0.6472	0.4628	0.6803
No log	3.6636	392	0.4298	0.6543	0.4298	0.6556
No log	3.6822	394	0.4038	0.6282	0.4038	0.6355
No log	3.7009	396	0.4084	0.6316	0.4084	0.6390
No log	3.7196	398	0.4341	0.6564	0.4341	0.6589
No log	3.7383	400	0.4665	0.6413	0.4665	0.6830
No log	3.7570	402	0.5091	0.6188	0.5091	0.7135
No log	3.7757	404	0.5099	0.6542	0.5099	0.7141
No log	3.7944	406	0.5958	0.6279	0.5958	0.7719
No log	3.8131	408	0.6455	0.6095	0.6455	0.8034
No log	3.8318	410	0.5262	0.6232	0.5262	0.7254
No log	3.8505	412	0.4311	0.6495	0.4311	0.6566
No log	3.8692	414	0.4412	0.6336	0.4412	0.6642
No log	3.8879	416	0.4283	0.6049	0.4283	0.6544
No log	3.9065	418	0.4452	0.5769	0.4452	0.6672
No log	3.9252	420	0.4954	0.5872	0.4954	0.7039
No log	3.9439	422	0.5485	0.5954	0.5485	0.7406
No log	3.9626	424	0.5847	0.6058	0.5847	0.7646
No log	3.9813	426	0.4560	0.6836	0.4560	0.6753
No log	4.0	428	0.4409	0.6695	0.4409	0.6640
No log	4.0187	430	0.5017	0.6337	0.5017	0.7083
No log	4.0374	432	0.5970	0.6133	0.5970	0.7726
No log	4.0561	434	0.6838	0.5644	0.6838	0.8269
No log	4.0748	436	0.6351	0.5812	0.6351	0.7969
No log	4.0935	438	0.4993	0.6536	0.4993	0.7066
No log	4.1121	440	0.4587	0.6345	0.4587	0.6773
No log	4.1308	442	0.4994	0.6431	0.4994	0.7067
No log	4.1495	444	0.6705	0.6142	0.6705	0.8188
No log	4.1682	446	0.7197	0.6162	0.7197	0.8484
No log	4.1869	448	0.5529	0.6450	0.5529	0.7435
No log	4.2056	450	0.4448	0.6703	0.4448	0.6669
No log	4.2243	452	0.4174	0.6355	0.4174	0.6461
No log	4.2430	454	0.4297	0.6438	0.4297	0.6555
No log	4.2617	456	0.5314	0.6442	0.5314	0.7290
No log	4.2804	458	0.5980	0.5995	0.5980	0.7733
No log	4.2991	460	0.5239	0.6088	0.5239	0.7238
No log	4.3178	462	0.4698	0.6219	0.4698	0.6854
No log	4.3364	464	0.4848	0.6170	0.4848	0.6963
No log	4.3551	466	0.4880	0.5750	0.4880	0.6986
No log	4.3738	468	0.5079	0.6204	0.5079	0.7127
No log	4.3925	470	0.5434	0.5999	0.5434	0.7371
No log	4.4112	472	0.4981	0.6239	0.4981	0.7058
No log	4.4299	474	0.4921	0.6309	0.4921	0.7015
No log	4.4486	476	0.4660	0.6424	0.4660	0.6826
No log	4.4673	478	0.4366	0.6050	0.4366	0.6607
No log	4.4860	480	0.4717	0.6322	0.4717	0.6868
No log	4.5047	482	0.5668	0.6115	0.5668	0.7529
No log	4.5234	484	0.5440	0.6297	0.5440	0.7376
No log	4.5421	486	0.4823	0.5895	0.4823	0.6945
No log	4.5607	488	0.4709	0.6113	0.4709	0.6862
No log	4.5794	490	0.4921	0.6169	0.4921	0.7015
No log	4.5981	492	0.5569	0.6156	0.5569	0.7462
No log	4.6168	494	0.5460	0.6325	0.5460	0.7389
No log	4.6355	496	0.5375	0.6419	0.5375	0.7332
No log	4.6542	498	0.4752	0.6239	0.4752	0.6893
0.5152	4.6729	500	0.4713	0.6180	0.4713	0.6865
0.5152	4.6916	502	0.5551	0.6099	0.5551	0.7450
0.5152	4.7103	504	0.6524	0.6019	0.6524	0.8077
0.5152	4.7290	506	0.5678	0.6216	0.5678	0.7535
0.5152	4.7477	508	0.4535	0.6230	0.4535	0.6734
0.5152	4.7664	510	0.4542	0.6517	0.4542	0.6739
0.5152	4.7850	512	0.5111	0.6368	0.5111	0.7149
0.5152	4.8037	514	0.4801	0.6459	0.4801	0.6929
0.5152	4.8224	516	0.4818	0.6476	0.4818	0.6941
0.5152	4.8411	518	0.5343	0.6469	0.5343	0.7309
0.5152	4.8598	520	0.4977	0.6306	0.4977	0.7055
0.5152	4.8785	522	0.5100	0.6358	0.5100	0.7141
0.5152	4.8972	524	0.6145	0.6005	0.6145	0.7839
0.5152	4.9159	526	0.6761	0.5857	0.6761	0.8222
0.5152	4.9346	528	0.5247	0.6878	0.5247	0.7243
0.5152	4.9533	530	0.4911	0.6990	0.4911	0.7008
0.5152	4.9720	532	0.4745	0.6669	0.4745	0.6888
0.5152	4.9907	534	0.4599	0.6855	0.4599	0.6781
0.5152	5.0093	536	0.6473	0.6019	0.6473	0.8046
0.5152	5.0280	538	0.7257	0.5849	0.7257	0.8519
0.5152	5.0467	540	0.5479	0.6201	0.5479	0.7402
0.5152	5.0654	542	0.4119	0.6353	0.4119	0.6418
0.5152	5.0841	544	0.4255	0.6308	0.4255	0.6523
0.5152	5.1028	546	0.4255	0.6243	0.4255	0.6523
0.5152	5.1215	548	0.4230	0.6337	0.4230	0.6504
0.5152	5.1402	550	0.4778	0.6636	0.4778	0.6912
0.5152	5.1589	552	0.5074	0.6614	0.5074	0.7123
0.5152	5.1776	554	0.5727	0.6121	0.5727	0.7568
0.5152	5.1963	556	0.6526	0.5814	0.6526	0.8078
0.5152	5.2150	558	0.6055	0.6377	0.6055	0.7781
0.5152	5.2336	560	0.6056	0.6369	0.6056	0.7782
0.5152	5.2523	562	0.7271	0.6123	0.7271	0.8527
0.5152	5.2710	564	0.7510	0.5707	0.7510	0.8666
0.5152	5.2897	566	0.6316	0.5895	0.6316	0.7947
0.5152	5.3084	568	0.4594	0.6470	0.4594	0.6778
0.5152	5.3271	570	0.4248	0.6600	0.4248	0.6518
0.5152	5.3458	572	0.4238	0.6409	0.4238	0.6510
0.5152	5.3645	574	0.4787	0.6259	0.4787	0.6919
0.5152	5.3832	576	0.5882	0.5796	0.5882	0.7669
0.5152	5.4019	578	0.5628	0.5983	0.5628	0.7502
0.5152	5.4206	580	0.4385	0.6573	0.4385	0.6622
0.5152	5.4393	582	0.4253	0.6364	0.4253	0.6521
0.5152	5.4579	584	0.4358	0.6150	0.4358	0.6602
0.5152	5.4766	586	0.4464	0.6277	0.4464	0.6682
0.5152	5.4953	588	0.4953	0.6450	0.4953	0.7037
0.5152	5.5140	590	0.6014	0.6147	0.6014	0.7755
0.5152	5.5327	592	0.6139	0.6052	0.6139	0.7835
0.5152	5.5514	594	0.5179	0.6410	0.5179	0.7196
0.5152	5.5701	596	0.4847	0.6447	0.4847	0.6962
0.5152	5.5888	598	0.5227	0.6324	0.5227	0.7230
0.5152	5.6075	600	0.6672	0.5594	0.6672	0.8168
0.5152	5.6262	602	0.6386	0.5335	0.6386	0.7991
0.5152	5.6449	604	0.5325	0.5382	0.5325	0.7297
0.5152	5.6636	606	0.5288	0.5100	0.5288	0.7272
0.5152	5.6822	608	0.4946	0.5245	0.4946	0.7033

Framework versions

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