Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask1_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: 0.5274
• Qwk: 0.5661
• Mse: 0.5274
• Rmse: 0.7262

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	0.0213	2	4.1570	0.0062	4.1570	2.0389
No log	0.0426	4	3.0412	0.0569	3.0412	1.7439
No log	0.0638	6	1.5052	0.0484	1.5052	1.2269
No log	0.0851	8	0.9490	0.0635	0.9490	0.9741
No log	0.1064	10	0.8485	-0.0531	0.8485	0.9211
No log	0.1277	12	0.8079	0.0428	0.8079	0.8988
No log	0.1489	14	0.8232	0.1046	0.8232	0.9073
No log	0.1702	16	0.6783	0.1773	0.6783	0.8236
No log	0.1915	18	0.5992	0.3810	0.5992	0.7741
No log	0.2128	20	0.5719	0.3971	0.5719	0.7563
No log	0.2340	22	0.5573	0.4182	0.5573	0.7465
No log	0.2553	24	0.5520	0.4522	0.5520	0.7430
No log	0.2766	26	0.5245	0.4732	0.5245	0.7242
No log	0.2979	28	0.5186	0.4861	0.5186	0.7202
No log	0.3191	30	0.5537	0.3462	0.5537	0.7441
No log	0.3404	32	0.5267	0.4769	0.5267	0.7258
No log	0.3617	34	0.5457	0.4942	0.5457	0.7387
No log	0.3830	36	0.6571	0.4994	0.6571	0.8106
No log	0.4043	38	0.5175	0.4843	0.5175	0.7193
No log	0.4255	40	0.5075	0.4987	0.5075	0.7124
No log	0.4468	42	0.6732	0.2381	0.6732	0.8205
No log	0.4681	44	0.7805	0.1625	0.7805	0.8835
No log	0.4894	46	0.7637	0.1298	0.7637	0.8739
No log	0.5106	48	0.6519	0.2204	0.6519	0.8074
No log	0.5319	50	0.5216	0.4499	0.5216	0.7223
No log	0.5532	52	0.5194	0.4844	0.5194	0.7207
No log	0.5745	54	0.5598	0.5072	0.5598	0.7482
No log	0.5957	56	0.5452	0.5186	0.5452	0.7384
No log	0.6170	58	0.5168	0.5452	0.5168	0.7189
No log	0.6383	60	0.4892	0.5408	0.4892	0.6994
No log	0.6596	62	0.5187	0.5015	0.5187	0.7202
No log	0.6809	64	0.5277	0.4747	0.5277	0.7265
No log	0.7021	66	0.5633	0.4785	0.5633	0.7505
No log	0.7234	68	0.5170	0.5582	0.5170	0.7190
No log	0.7447	70	0.5036	0.5782	0.5036	0.7097
No log	0.7660	72	0.5519	0.5765	0.5519	0.7429
No log	0.7872	74	0.5264	0.5612	0.5264	0.7255
No log	0.8085	76	0.4798	0.5508	0.4798	0.6926
No log	0.8298	78	0.4443	0.5326	0.4443	0.6665
No log	0.8511	80	0.4651	0.5066	0.4651	0.6820
No log	0.8723	82	0.4661	0.5223	0.4661	0.6827
No log	0.8936	84	0.4517	0.5465	0.4517	0.6721
No log	0.9149	86	0.4792	0.5160	0.4792	0.6923
No log	0.9362	88	0.5465	0.4305	0.5465	0.7393
No log	0.9574	90	0.5573	0.4272	0.5573	0.7465
No log	0.9787	92	0.5717	0.4128	0.5717	0.7561
No log	1.0	94	0.5082	0.5749	0.5082	0.7129
No log	1.0213	96	0.5163	0.5723	0.5163	0.7186
No log	1.0426	98	0.5538	0.5780	0.5538	0.7442
No log	1.0638	100	0.5070	0.5891	0.5070	0.7121
No log	1.0851	102	0.4661	0.6082	0.4661	0.6827
No log	1.1064	104	0.4772	0.5968	0.4772	0.6908
No log	1.1277	106	0.5048	0.5052	0.5048	0.7105
No log	1.1489	108	0.5362	0.4528	0.5362	0.7323
No log	1.1702	110	0.5384	0.4811	0.5384	0.7338
No log	1.1915	112	0.4743	0.6027	0.4743	0.6887
No log	1.2128	114	0.4891	0.6256	0.4891	0.6994
No log	1.2340	116	0.5151	0.6011	0.5151	0.7177
No log	1.2553	118	0.5462	0.5755	0.5462	0.7390
No log	1.2766	120	0.5263	0.5829	0.5263	0.7255
No log	1.2979	122	0.5510	0.5438	0.5510	0.7423
No log	1.3191	124	0.5436	0.5883	0.5436	0.7373
No log	1.3404	126	0.5137	0.6085	0.5137	0.7167
No log	1.3617	128	0.4834	0.6243	0.4834	0.6953
No log	1.3830	130	0.4673	0.6046	0.4673	0.6836
No log	1.4043	132	0.4821	0.6110	0.4821	0.6944
No log	1.4255	134	0.5447	0.4874	0.5447	0.7380
No log	1.4468	136	0.5302	0.4934	0.5302	0.7282
No log	1.4681	138	0.5457	0.4585	0.5457	0.7387
No log	1.4894	140	0.5586	0.4533	0.5586	0.7474
No log	1.5106	142	0.5354	0.5055	0.5354	0.7317
No log	1.5319	144	0.5272	0.5291	0.5272	0.7261
No log	1.5532	146	0.5379	0.4764	0.5379	0.7334
No log	1.5745	148	0.5288	0.4913	0.5288	0.7272
No log	1.5957	150	0.5327	0.5760	0.5327	0.7299
No log	1.6170	152	0.5967	0.5567	0.5967	0.7724
No log	1.6383	154	0.6085	0.5521	0.6085	0.7801
No log	1.6596	156	0.5926	0.5517	0.5926	0.7698
No log	1.6809	158	0.6374	0.5800	0.6374	0.7984
No log	1.7021	160	0.7886	0.5294	0.7886	0.8880
No log	1.7234	162	0.9284	0.4854	0.9284	0.9635
No log	1.7447	164	0.7619	0.4989	0.7619	0.8728
No log	1.7660	166	0.5230	0.5294	0.5230	0.7232
No log	1.7872	168	0.4656	0.5490	0.4656	0.6823
No log	1.8085	170	0.4778	0.4846	0.4778	0.6912
No log	1.8298	172	0.5005	0.4198	0.5005	0.7074
No log	1.8511	174	0.4891	0.4374	0.4891	0.6993
No log	1.8723	176	0.4630	0.4928	0.4630	0.6805
No log	1.8936	178	0.4635	0.4765	0.4635	0.6808
No log	1.9149	180	0.4697	0.4772	0.4697	0.6854
No log	1.9362	182	0.4663	0.4869	0.4663	0.6829
No log	1.9574	184	0.4474	0.5148	0.4474	0.6689
No log	1.9787	186	0.4545	0.5929	0.4545	0.6742
No log	2.0	188	0.4620	0.5892	0.4620	0.6797
No log	2.0213	190	0.4737	0.6127	0.4737	0.6883
No log	2.0426	192	0.5642	0.4721	0.5642	0.7511
No log	2.0638	194	0.5924	0.4422	0.5924	0.7697
No log	2.0851	196	0.5725	0.4549	0.5725	0.7566
No log	2.1064	198	0.5178	0.5035	0.5178	0.7196
No log	2.1277	200	0.4856	0.5461	0.4856	0.6968
No log	2.1489	202	0.4960	0.5400	0.4960	0.7043
No log	2.1702	204	0.4993	0.5412	0.4993	0.7066
No log	2.1915	206	0.4998	0.5368	0.4998	0.7069
No log	2.2128	208	0.5087	0.5172	0.5087	0.7133
No log	2.2340	210	0.5106	0.5005	0.5106	0.7146
No log	2.2553	212	0.5308	0.4595	0.5308	0.7285
No log	2.2766	214	0.5540	0.5126	0.5540	0.7443
No log	2.2979	216	0.5418	0.5342	0.5418	0.7361
No log	2.3191	218	0.5301	0.5260	0.5301	0.7281
No log	2.3404	220	0.4923	0.5429	0.4923	0.7017
No log	2.3617	222	0.4543	0.5897	0.4543	0.6740
No log	2.3830	224	0.4965	0.6055	0.4965	0.7046
No log	2.4043	226	0.6020	0.5999	0.6020	0.7759
No log	2.4255	228	0.6294	0.5644	0.6294	0.7933
No log	2.4468	230	0.6132	0.5671	0.6132	0.7831
No log	2.4681	232	0.6374	0.5495	0.6374	0.7984
No log	2.4894	234	0.6110	0.5560	0.6110	0.7817
No log	2.5106	236	0.5498	0.5730	0.5498	0.7415
No log	2.5319	238	0.4913	0.6078	0.4913	0.7009
No log	2.5532	240	0.4748	0.6354	0.4748	0.6890
No log	2.5745	242	0.4659	0.6515	0.4659	0.6826
No log	2.5957	244	0.4714	0.6341	0.4714	0.6866
No log	2.6170	246	0.5188	0.5720	0.5188	0.7203
No log	2.6383	248	0.5001	0.5666	0.5001	0.7072
No log	2.6596	250	0.4483	0.6007	0.4483	0.6695
No log	2.6809	252	0.4475	0.5932	0.4475	0.6689
No log	2.7021	254	0.4557	0.5495	0.4557	0.6750
No log	2.7234	256	0.4414	0.6014	0.4414	0.6644
No log	2.7447	258	0.4311	0.6029	0.4311	0.6566
No log	2.7660	260	0.4511	0.5956	0.4511	0.6717
No log	2.7872	262	0.4700	0.5768	0.4700	0.6855
No log	2.8085	264	0.4788	0.5873	0.4788	0.6919
No log	2.8298	266	0.5112	0.5854	0.5112	0.7150
No log	2.8511	268	0.5085	0.6202	0.5085	0.7131
No log	2.8723	270	0.5342	0.6087	0.5342	0.7309
No log	2.8936	272	0.5446	0.6253	0.5446	0.7380
No log	2.9149	274	0.5907	0.6028	0.5907	0.7685
No log	2.9362	276	0.6219	0.5028	0.6219	0.7886
No log	2.9574	278	0.6360	0.4579	0.6360	0.7975
No log	2.9787	280	0.6147	0.4297	0.6147	0.7840
No log	3.0	282	0.5556	0.4841	0.5556	0.7454
No log	3.0213	284	0.5164	0.4989	0.5164	0.7186
No log	3.0426	286	0.5023	0.5399	0.5023	0.7087
No log	3.0638	288	0.5040	0.5872	0.5040	0.7099
No log	3.0851	290	0.4883	0.6298	0.4883	0.6988
No log	3.1064	292	0.4837	0.6046	0.4837	0.6955
No log	3.1277	294	0.5245	0.5548	0.5245	0.7242
No log	3.1489	296	0.6011	0.5110	0.6011	0.7753
No log	3.1702	298	0.6217	0.5257	0.6217	0.7885
No log	3.1915	300	0.6184	0.5598	0.6184	0.7864
No log	3.2128	302	0.5968	0.5714	0.5968	0.7725
No log	3.2340	304	0.5233	0.5639	0.5233	0.7234
No log	3.2553	306	0.5073	0.5612	0.5073	0.7123
No log	3.2766	308	0.4940	0.5839	0.4940	0.7028
No log	3.2979	310	0.4580	0.6159	0.4580	0.6768
No log	3.3191	312	0.4488	0.5761	0.4488	0.6699
No log	3.3404	314	0.4735	0.4742	0.4735	0.6881
No log	3.3617	316	0.5284	0.4745	0.5284	0.7269
No log	3.3830	318	0.5257	0.4698	0.5257	0.7250
No log	3.4043	320	0.4661	0.5881	0.4661	0.6827
No log	3.4255	322	0.4627	0.5993	0.4627	0.6802
No log	3.4468	324	0.4772	0.6256	0.4772	0.6908
No log	3.4681	326	0.5222	0.5686	0.5222	0.7227
No log	3.4894	328	0.5624	0.4827	0.5624	0.7499
No log	3.5106	330	0.5424	0.4675	0.5424	0.7365
No log	3.5319	332	0.4859	0.5026	0.4859	0.6971
No log	3.5532	334	0.4671	0.5782	0.4671	0.6835
No log	3.5745	336	0.4867	0.5983	0.4867	0.6977
No log	3.5957	338	0.5110	0.5665	0.5110	0.7149
No log	3.6170	340	0.5796	0.5804	0.5796	0.7613
No log	3.6383	342	0.6230	0.5837	0.6230	0.7893
No log	3.6596	344	0.6171	0.5945	0.6171	0.7856
No log	3.6809	346	0.5571	0.5826	0.5571	0.7464
No log	3.7021	348	0.5271	0.5929	0.5271	0.7260
No log	3.7234	350	0.5281	0.5989	0.5281	0.7267
No log	3.7447	352	0.5229	0.6093	0.5229	0.7231
No log	3.7660	354	0.6081	0.5818	0.6081	0.7798
No log	3.7872	356	0.6007	0.5637	0.6007	0.7751
No log	3.8085	358	0.5139	0.6131	0.5139	0.7169
No log	3.8298	360	0.5687	0.5703	0.5687	0.7541
No log	3.8511	362	0.7703	0.4651	0.7703	0.8776
No log	3.8723	364	0.7276	0.4624	0.7276	0.8530
No log	3.8936	366	0.5263	0.5879	0.5263	0.7255
No log	3.9149	368	0.4873	0.6163	0.4873	0.6980
No log	3.9362	370	0.6625	0.4343	0.6625	0.8140
No log	3.9574	372	0.7137	0.3871	0.7137	0.8448
No log	3.9787	374	0.6629	0.3695	0.6629	0.8142
No log	4.0	376	0.5356	0.4970	0.5356	0.7319
No log	4.0213	378	0.4238	0.6166	0.4238	0.6510
No log	4.0426	380	0.4476	0.5938	0.4476	0.6691
No log	4.0638	382	0.5058	0.5898	0.5058	0.7112
No log	4.0851	384	0.5149	0.5722	0.5149	0.7175
No log	4.1064	386	0.4923	0.6289	0.4923	0.7016
No log	4.1277	388	0.5911	0.5738	0.5911	0.7688
No log	4.1489	390	0.6332	0.5628	0.6332	0.7957
No log	4.1702	392	0.6267	0.5412	0.6267	0.7917
No log	4.1915	394	0.5485	0.5146	0.5485	0.7406
No log	4.2128	396	0.4796	0.5358	0.4796	0.6925
No log	4.2340	398	0.4605	0.5826	0.4605	0.6786
No log	4.2553	400	0.4627	0.5774	0.4627	0.6802
No log	4.2766	402	0.4682	0.5931	0.4682	0.6843
No log	4.2979	404	0.5080	0.5873	0.5080	0.7128
No log	4.3191	406	0.5571	0.5806	0.5571	0.7464
No log	4.3404	408	0.5474	0.6000	0.5474	0.7399
No log	4.3617	410	0.5568	0.5805	0.5568	0.7462
No log	4.3830	412	0.5448	0.5925	0.5448	0.7381
No log	4.4043	414	0.5437	0.5906	0.5437	0.7374
No log	4.4255	416	0.5420	0.6083	0.5420	0.7362
No log	4.4468	418	0.5076	0.6318	0.5076	0.7125
No log	4.4681	420	0.4739	0.6384	0.4739	0.6884
No log	4.4894	422	0.4616	0.6460	0.4616	0.6794
No log	4.5106	424	0.4319	0.5970	0.4319	0.6572
No log	4.5319	426	0.4296	0.5399	0.4296	0.6554
No log	4.5532	428	0.4408	0.5711	0.4408	0.6639
No log	4.5745	430	0.4437	0.5662	0.4437	0.6661
No log	4.5957	432	0.4663	0.5712	0.4663	0.6829
No log	4.6170	434	0.6000	0.4536	0.6000	0.7746
No log	4.6383	436	0.7025	0.4412	0.7025	0.8382
No log	4.6596	438	0.6640	0.4932	0.6640	0.8148
No log	4.6809	440	0.5988	0.5445	0.5988	0.7738
No log	4.7021	442	0.5320	0.5831	0.5320	0.7294
No log	4.7234	444	0.5366	0.6061	0.5366	0.7325
No log	4.7447	446	0.5268	0.5943	0.5268	0.7258
No log	4.7660	448	0.4916	0.5654	0.4916	0.7011
No log	4.7872	450	0.5166	0.5468	0.5166	0.7187
No log	4.8085	452	0.5258	0.4739	0.5258	0.7251
No log	4.8298	454	0.4780	0.5585	0.4780	0.6914
No log	4.8511	456	0.4484	0.5945	0.4484	0.6696
No log	4.8723	458	0.4498	0.6016	0.4498	0.6706
No log	4.8936	460	0.4779	0.5871	0.4779	0.6913
No log	4.9149	462	0.4705	0.6040	0.4705	0.6859
No log	4.9362	464	0.4848	0.6213	0.4848	0.6963
No log	4.9574	466	0.5564	0.5978	0.5564	0.7459
No log	4.9787	468	0.5640	0.5897	0.5640	0.7510
No log	5.0	470	0.5145	0.6273	0.5145	0.7173
No log	5.0213	472	0.5034	0.6247	0.5034	0.7095
No log	5.0426	474	0.5160	0.6336	0.5160	0.7183
No log	5.0638	476	0.5397	0.6019	0.5397	0.7347
No log	5.0851	478	0.5499	0.5674	0.5499	0.7415
No log	5.1064	480	0.4940	0.6336	0.4940	0.7028
No log	5.1277	482	0.4634	0.6266	0.4634	0.6807
No log	5.1489	484	0.4504	0.6109	0.4504	0.6711
No log	5.1702	486	0.4472	0.6167	0.4472	0.6687
No log	5.1915	488	0.4768	0.5973	0.4768	0.6905
No log	5.2128	490	0.4885	0.6054	0.4885	0.6989
No log	5.2340	492	0.4607	0.6055	0.4607	0.6787
No log	5.2553	494	0.4848	0.5690	0.4848	0.6963
No log	5.2766	496	0.5042	0.5817	0.5042	0.7101
No log	5.2979	498	0.5107	0.5889	0.5107	0.7147
0.5018	5.3191	500	0.5829	0.5899	0.5829	0.7635
0.5018	5.3404	502	0.6517	0.5201	0.6517	0.8073
0.5018	5.3617	504	0.5851	0.5612	0.5851	0.7649
0.5018	5.3830	506	0.5076	0.5738	0.5076	0.7125
0.5018	5.4043	508	0.4688	0.5912	0.4688	0.6847
0.5018	5.4255	510	0.4580	0.5795	0.4580	0.6768
0.5018	5.4468	512	0.4422	0.5968	0.4422	0.6650
0.5018	5.4681	514	0.4394	0.6115	0.4394	0.6629
0.5018	5.4894	516	0.5108	0.6360	0.5108	0.7147
0.5018	5.5106	518	0.6011	0.5937	0.6011	0.7753
0.5018	5.5319	520	0.5667	0.5927	0.5667	0.7528
0.5018	5.5532	522	0.4852	0.6446	0.4852	0.6965
0.5018	5.5745	524	0.4709	0.6081	0.4709	0.6862
0.5018	5.5957	526	0.4704	0.5964	0.4704	0.6859
0.5018	5.6170	528	0.4563	0.6114	0.4563	0.6755
0.5018	5.6383	530	0.4487	0.5932	0.4487	0.6699
0.5018	5.6596	532	0.4653	0.5973	0.4653	0.6821
0.5018	5.6809	534	0.5282	0.5564	0.5282	0.7268
0.5018	5.7021	536	0.6115	0.4904	0.6115	0.7820
0.5018	5.7234	538	0.6489	0.4966	0.6489	0.8055
0.5018	5.7447	540	0.5662	0.5511	0.5662	0.7524
0.5018	5.7660	542	0.4932	0.6087	0.4932	0.7023
0.5018	5.7872	544	0.5044	0.6244	0.5044	0.7102
0.5018	5.8085	546	0.4846	0.6482	0.4846	0.6961
0.5018	5.8298	548	0.4979	0.6382	0.4979	0.7056
0.5018	5.8511	550	0.5248	0.6293	0.5248	0.7244
0.5018	5.8723	552	0.6130	0.5668	0.6130	0.7829
0.5018	5.8936	554	0.7326	0.5370	0.7326	0.8559
0.5018	5.9149	556	0.6693	0.5719	0.6693	0.8181
0.5018	5.9362	558	0.5443	0.6033	0.5443	0.7378
0.5018	5.9574	560	0.5230	0.6091	0.5230	0.7232
0.5018	5.9787	562	0.5291	0.5794	0.5291	0.7274
0.5018	6.0	564	0.5529	0.5504	0.5529	0.7436
0.5018	6.0213	566	0.6011	0.5209	0.6011	0.7753
0.5018	6.0426	568	0.5883	0.5402	0.5883	0.7670
0.5018	6.0638	570	0.5274	0.5661	0.5274	0.7262

Framework versions

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