Modelpublic

MayBashendy/Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask7_grammar

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes3downloads

Model Card

ArabicCrossPromptFineTuningAraBERTnoAugTestTask7_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: 0.7020
—Qwk: 0.5776
—Mse: 0.7020
—Rmse: 0.8379

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
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0202	2	4.2066	0.0038	4.2066	2.0510
No log	0.0404	4	3.2857	0.0288	3.2857	1.8126
No log	0.0606	6	2.0350	0.0648	2.0350	1.4265
No log	0.0808	8	0.9950	0.1410	0.9950	0.9975
No log	0.1010	10	0.9184	0.0766	0.9184	0.9583
No log	0.1212	12	0.9905	0.0522	0.9905	0.9952
No log	0.1414	14	0.9266	0.0275	0.9266	0.9626
No log	0.1616	16	0.8571	0.0562	0.8571	0.9258
No log	0.1818	18	0.7856	0.2371	0.7856	0.8863
No log	0.2020	20	0.7807	0.4035	0.7807	0.8836
No log	0.2222	22	0.7716	0.4214	0.7716	0.8784
No log	0.2424	24	0.7313	0.4080	0.7313	0.8551
No log	0.2626	26	0.7380	0.2240	0.7380	0.8591
No log	0.2828	28	0.7991	0.1854	0.7991	0.8939
No log	0.3030	30	0.7612	0.2355	0.7612	0.8725
No log	0.3232	32	0.6563	0.3694	0.6563	0.8101
No log	0.3434	34	0.6203	0.4564	0.6203	0.7876
No log	0.3636	36	0.6120	0.4261	0.6120	0.7823
No log	0.3838	38	0.6648	0.3893	0.6648	0.8154
No log	0.4040	40	0.7147	0.3300	0.7147	0.8454
No log	0.4242	42	0.7589	0.3849	0.7589	0.8712
No log	0.4444	44	0.7400	0.4386	0.7400	0.8603
No log	0.4646	46	0.7547	0.4505	0.7547	0.8687
No log	0.4848	48	0.6243	0.4781	0.6243	0.7901
No log	0.5051	50	0.5571	0.5465	0.5571	0.7464
No log	0.5253	52	0.5483	0.5050	0.5483	0.7404
No log	0.5455	54	0.5732	0.4436	0.5732	0.7571
No log	0.5657	56	0.6846	0.3726	0.6846	0.8274
No log	0.5859	58	0.7354	0.2884	0.7354	0.8576
No log	0.6061	60	0.7393	0.2819	0.7393	0.8598
No log	0.6263	62	0.7009	0.2671	0.7009	0.8372
No log	0.6465	64	0.6829	0.2664	0.6829	0.8264
No log	0.6667	66	0.6413	0.3386	0.6413	0.8008
No log	0.6869	68	0.6192	0.3976	0.6192	0.7869
No log	0.7071	70	0.6957	0.4284	0.6957	0.8341
No log	0.7273	72	0.7624	0.4444	0.7624	0.8732
No log	0.7475	74	0.7196	0.4976	0.7196	0.8483
No log	0.7677	76	0.6587	0.5412	0.6587	0.8116
No log	0.7879	78	0.5828	0.5778	0.5828	0.7634
No log	0.8081	80	0.5187	0.5728	0.5187	0.7202
No log	0.8283	82	0.4990	0.5873	0.4990	0.7064
No log	0.8485	84	0.5424	0.5804	0.5424	0.7365
No log	0.8687	86	0.5306	0.6152	0.5306	0.7284
No log	0.8889	88	0.5059	0.6329	0.5059	0.7113
No log	0.9091	90	0.5636	0.5765	0.5636	0.7508
No log	0.9293	92	0.6334	0.4352	0.6334	0.7959
No log	0.9495	94	0.6473	0.4051	0.6473	0.8045
No log	0.9697	96	0.6179	0.4591	0.6179	0.7861
No log	0.9899	98	0.6062	0.5154	0.6062	0.7786
No log	1.0101	100	0.5195	0.5603	0.5195	0.7208
No log	1.0303	102	0.5444	0.6026	0.5444	0.7378
No log	1.0505	104	0.6167	0.5782	0.6167	0.7853
No log	1.0707	106	0.6387	0.5454	0.6387	0.7992
No log	1.0909	108	0.6018	0.5139	0.6018	0.7758
No log	1.1111	110	0.6058	0.5100	0.6058	0.7783
No log	1.1313	112	0.6145	0.5171	0.6145	0.7839
No log	1.1515	114	0.5663	0.5897	0.5663	0.7525
No log	1.1717	116	0.5918	0.6043	0.5918	0.7693
No log	1.1919	118	0.5579	0.6265	0.5579	0.7469
No log	1.2121	120	0.5488	0.6271	0.5488	0.7408
No log	1.2323	122	0.5306	0.5846	0.5306	0.7284
No log	1.2525	124	0.5882	0.5149	0.5882	0.7669
No log	1.2727	126	0.6887	0.3758	0.6887	0.8299
No log	1.2929	128	0.7031	0.3342	0.7031	0.8385
No log	1.3131	130	0.6847	0.3359	0.6847	0.8275
No log	1.3333	132	0.6488	0.4184	0.6488	0.8055
No log	1.3535	134	0.6094	0.4793	0.6094	0.7807
No log	1.3737	136	0.6229	0.5115	0.6229	0.7893
No log	1.3939	138	0.5725	0.5374	0.5725	0.7566
No log	1.4141	140	0.5884	0.5436	0.5884	0.7671
No log	1.4343	142	0.5793	0.5602	0.5793	0.7611
No log	1.4545	144	0.6110	0.5772	0.6110	0.7817
No log	1.4747	146	0.6035	0.5849	0.6035	0.7769
No log	1.4949	148	0.5221	0.5972	0.5221	0.7226
No log	1.5152	150	0.5574	0.5888	0.5574	0.7466
No log	1.5354	152	0.6931	0.4962	0.6931	0.8325
No log	1.5556	154	0.8766	0.3737	0.8766	0.9363
No log	1.5758	156	0.9278	0.3457	0.9278	0.9632
No log	1.5960	158	0.8315	0.4112	0.8315	0.9119
No log	1.6162	160	0.6595	0.5450	0.6595	0.8121
No log	1.6364	162	0.5592	0.5899	0.5592	0.7478
No log	1.6566	164	0.5162	0.6132	0.5162	0.7185
No log	1.6768	166	0.4919	0.6083	0.4919	0.7013
No log	1.6970	168	0.4874	0.6210	0.4874	0.6982
No log	1.7172	170	0.5376	0.6129	0.5376	0.7332
No log	1.7374	172	0.5294	0.6173	0.5294	0.7276
No log	1.7576	174	0.5825	0.5844	0.5825	0.7632
No log	1.7778	176	0.6408	0.5601	0.6408	0.8005
No log	1.7980	178	0.6486	0.5541	0.6486	0.8054
No log	1.8182	180	0.5467	0.6066	0.5467	0.7394
No log	1.8384	182	0.4932	0.5659	0.4932	0.7023
No log	1.8586	184	0.5009	0.5497	0.5009	0.7077
No log	1.8788	186	0.5570	0.5711	0.5570	0.7463
No log	1.8990	188	0.5645	0.5529	0.5645	0.7513
No log	1.9192	190	0.5285	0.6103	0.5285	0.7270
No log	1.9394	192	0.5198	0.6293	0.5198	0.7210
No log	1.9596	194	0.4829	0.6476	0.4829	0.6949
No log	1.9798	196	0.4656	0.6819	0.4656	0.6824
No log	2.0	198	0.4903	0.6451	0.4903	0.7002
No log	2.0202	200	0.6542	0.5854	0.6542	0.8088
No log	2.0404	202	0.9370	0.4282	0.9370	0.9680
No log	2.0606	204	0.9795	0.3803	0.9795	0.9897
No log	2.0808	206	0.8086	0.4539	0.8086	0.8992
No log	2.1010	208	0.6387	0.4980	0.6387	0.7992
No log	2.1212	210	0.6249	0.3747	0.6249	0.7905
No log	2.1414	212	0.6017	0.4178	0.6017	0.7757
No log	2.1616	214	0.5658	0.5272	0.5658	0.7522
No log	2.1818	216	0.5495	0.5450	0.5495	0.7413
No log	2.2020	218	0.6072	0.5463	0.6072	0.7792
No log	2.2222	220	0.7074	0.5095	0.7074	0.8411
No log	2.2424	222	0.7652	0.5510	0.7652	0.8748
No log	2.2626	224	0.6011	0.6199	0.6011	0.7753
No log	2.2828	226	0.4625	0.6990	0.4625	0.6801
No log	2.3030	228	0.4502	0.7017	0.4502	0.6709
No log	2.3232	230	0.4626	0.6927	0.4626	0.6802
No log	2.3434	232	0.5433	0.6160	0.5433	0.7371
No log	2.3636	234	0.6130	0.6334	0.6130	0.7829
No log	2.3838	236	0.5587	0.6341	0.5587	0.7475
No log	2.4040	238	0.5849	0.5685	0.5849	0.7648
No log	2.4242	240	0.6319	0.5214	0.6319	0.7949
No log	2.4444	242	0.5846	0.5527	0.5846	0.7646
No log	2.4646	244	0.5707	0.5550	0.5707	0.7555
No log	2.4848	246	0.6578	0.5161	0.6578	0.8111
No log	2.5051	248	0.6705	0.5192	0.6705	0.8188
No log	2.5253	250	0.6691	0.5263	0.6691	0.8180
No log	2.5455	252	0.5750	0.6165	0.5750	0.7583
No log	2.5657	254	0.5381	0.6535	0.5381	0.7336
No log	2.5859	256	0.5521	0.6378	0.5521	0.7430
No log	2.6061	258	0.5875	0.6426	0.5875	0.7665
No log	2.6263	260	0.5384	0.6689	0.5384	0.7338
No log	2.6465	262	0.5567	0.6528	0.5567	0.7461
No log	2.6667	264	0.6365	0.6244	0.6365	0.7978
No log	2.6869	266	0.6049	0.6395	0.6049	0.7777
No log	2.7071	268	0.5318	0.6332	0.5318	0.7292
No log	2.7273	270	0.5009	0.6499	0.5009	0.7077
No log	2.7475	272	0.4521	0.6789	0.4521	0.6724
No log	2.7677	274	0.4517	0.6767	0.4517	0.6721
No log	2.7879	276	0.4567	0.6305	0.4567	0.6758
No log	2.8081	278	0.5514	0.5972	0.5514	0.7425
No log	2.8283	280	0.5712	0.5554	0.5712	0.7558
No log	2.8485	282	0.6003	0.5204	0.6003	0.7748
No log	2.8687	284	0.5597	0.5314	0.5597	0.7481
No log	2.8889	286	0.4874	0.5603	0.4874	0.6981
No log	2.9091	288	0.4776	0.5872	0.4776	0.6911
No log	2.9293	290	0.5148	0.5877	0.5148	0.7175
No log	2.9495	292	0.5315	0.6353	0.5315	0.7291
No log	2.9697	294	0.5408	0.6570	0.5408	0.7354
No log	2.9899	296	0.5767	0.6181	0.5767	0.7594
No log	3.0101	298	0.5392	0.6491	0.5392	0.7343
No log	3.0303	300	0.5811	0.6222	0.5811	0.7623
No log	3.0505	302	0.6494	0.6149	0.6494	0.8058
No log	3.0707	304	0.7728	0.5570	0.7728	0.8791
No log	3.0909	306	0.6290	0.6177	0.6290	0.7931
No log	3.1111	308	0.4726	0.6381	0.4726	0.6874
No log	3.1313	310	0.4705	0.6312	0.4705	0.6859
No log	3.1515	312	0.5633	0.6059	0.5633	0.7505
No log	3.1717	314	0.7147	0.5681	0.7147	0.8454
No log	3.1919	316	0.6940	0.5653	0.6940	0.8330
No log	3.2121	318	0.5949	0.6013	0.5949	0.7713
No log	3.2323	320	0.6116	0.6103	0.6116	0.7821
No log	3.2525	322	0.5518	0.6217	0.5518	0.7428
No log	3.2727	324	0.6266	0.6149	0.6266	0.7916
No log	3.2929	326	0.6321	0.6090	0.6321	0.7950
No log	3.3131	328	0.4804	0.6478	0.4804	0.6931
No log	3.3333	330	0.4556	0.6723	0.4556	0.6750
No log	3.3535	332	0.4632	0.6821	0.4632	0.6806
No log	3.3737	334	0.5296	0.6356	0.5296	0.7277
No log	3.3939	336	0.7352	0.5966	0.7352	0.8574
No log	3.4141	338	0.8905	0.5470	0.8905	0.9437
No log	3.4343	340	0.7908	0.5789	0.7908	0.8893
No log	3.4545	342	0.5379	0.6503	0.5379	0.7334
No log	3.4747	344	0.4489	0.6784	0.4489	0.6700
No log	3.4949	346	0.4371	0.6873	0.4371	0.6611
No log	3.5152	348	0.4566	0.6300	0.4566	0.6757
No log	3.5354	350	0.6308	0.5805	0.6308	0.7942
No log	3.5556	352	0.7288	0.5195	0.7288	0.8537
No log	3.5758	354	0.6718	0.5069	0.6718	0.8196
No log	3.5960	356	0.6201	0.5429	0.6201	0.7875
No log	3.6162	358	0.6016	0.5482	0.6016	0.7756
No log	3.6364	360	0.5238	0.5826	0.5238	0.7237
No log	3.6566	362	0.5146	0.6072	0.5146	0.7173
No log	3.6768	364	0.5746	0.5899	0.5746	0.7580
No log	3.6970	366	0.5142	0.6444	0.5142	0.7171
No log	3.7172	368	0.5550	0.5994	0.5550	0.7450
No log	3.7374	370	0.5792	0.6170	0.5792	0.7611
No log	3.7576	372	0.5286	0.6537	0.5286	0.7271
No log	3.7778	374	0.6107	0.6087	0.6107	0.7815
No log	3.7980	376	0.5670	0.6538	0.5670	0.7530
No log	3.8182	378	0.4911	0.6540	0.4911	0.7008
No log	3.8384	380	0.5064	0.6157	0.5064	0.7116
No log	3.8586	382	0.5421	0.6426	0.5421	0.7363
No log	3.8788	384	0.8343	0.5155	0.8343	0.9134
No log	3.8990	386	0.9728	0.4728	0.9728	0.9863
No log	3.9192	388	0.8744	0.5059	0.8744	0.9351
No log	3.9394	390	0.6642	0.5804	0.6642	0.8150
No log	3.9596	392	0.4827	0.6463	0.4827	0.6948
No log	3.9798	394	0.4235	0.6538	0.4235	0.6507
No log	4.0	396	0.4296	0.6585	0.4296	0.6554
No log	4.0202	398	0.5509	0.6652	0.5509	0.7422
No log	4.0404	400	0.7656	0.5426	0.7656	0.8750
No log	4.0606	402	0.7309	0.5628	0.7309	0.8550
No log	4.0808	404	0.5898	0.6501	0.5898	0.7680
No log	4.1010	406	0.4672	0.6852	0.4672	0.6835
No log	4.1212	408	0.4301	0.6559	0.4301	0.6558
No log	4.1414	410	0.4217	0.6511	0.4217	0.6494
No log	4.1616	412	0.4331	0.6558	0.4331	0.6581
No log	4.1818	414	0.4998	0.6675	0.4998	0.7070
No log	4.2020	416	0.5652	0.6198	0.5652	0.7518
No log	4.2222	418	0.5533	0.6238	0.5533	0.7439
No log	4.2424	420	0.5296	0.6398	0.5296	0.7278
No log	4.2626	422	0.5728	0.6058	0.5728	0.7568
No log	4.2828	424	0.5494	0.6564	0.5494	0.7412
No log	4.3030	426	0.5678	0.6702	0.5678	0.7535
No log	4.3232	428	0.5620	0.6625	0.5620	0.7497
No log	4.3434	430	0.5900	0.6660	0.5900	0.7681
No log	4.3636	432	0.5394	0.6861	0.5394	0.7345
No log	4.3838	434	0.6717	0.6214	0.6717	0.8196
No log	4.4040	436	0.6642	0.6046	0.6642	0.8150
No log	4.4242	438	0.6688	0.5791	0.6688	0.8178
No log	4.4444	440	0.5311	0.6257	0.5311	0.7287
No log	4.4646	442	0.5138	0.6227	0.5138	0.7168
No log	4.4848	444	0.5267	0.6122	0.5267	0.7257
No log	4.5051	446	0.4676	0.6500	0.4676	0.6838
No log	4.5253	448	0.4944	0.6452	0.4944	0.7031
No log	4.5455	450	0.5701	0.6263	0.5701	0.7551
No log	4.5657	452	0.6354	0.6357	0.6354	0.7971
No log	4.5859	454	0.5396	0.6652	0.5396	0.7346
No log	4.6061	456	0.4810	0.6748	0.4810	0.6935
No log	4.6263	458	0.4722	0.6822	0.4722	0.6871
No log	4.6465	460	0.5397	0.6720	0.5397	0.7346
No log	4.6667	462	0.7453	0.6161	0.7453	0.8633
No log	4.6869	464	0.6480	0.6782	0.6480	0.8050
No log	4.7071	466	0.5671	0.6811	0.5671	0.7531
No log	4.7273	468	0.4734	0.6839	0.4734	0.6880
No log	4.7475	470	0.4815	0.6809	0.4815	0.6939
No log	4.7677	472	0.6504	0.6285	0.6504	0.8065
No log	4.7879	474	1.0527	0.4400	1.0527	1.0260
No log	4.8081	476	1.1043	0.4269	1.1043	1.0509
No log	4.8283	478	0.8676	0.5068	0.8676	0.9314
No log	4.8485	480	0.6248	0.6051	0.6248	0.7904
No log	4.8687	482	0.4809	0.6318	0.4809	0.6935
No log	4.8889	484	0.4613	0.6299	0.4613	0.6792
No log	4.9091	486	0.4615	0.6418	0.4615	0.6793
No log	4.9293	488	0.5440	0.6771	0.5440	0.7376
No log	4.9495	490	0.7241	0.5682	0.7241	0.8509
No log	4.9697	492	0.7479	0.5578	0.7479	0.8648
No log	4.9899	494	0.6394	0.6305	0.6394	0.7996
No log	5.0101	496	0.5398	0.6820	0.5398	0.7347
No log	5.0303	498	0.4562	0.6784	0.4562	0.6754
0.516	5.0505	500	0.5035	0.6809	0.5035	0.7096
0.516	5.0707	502	0.6625	0.6183	0.6625	0.8140
0.516	5.0909	504	0.6130	0.6255	0.6130	0.7829
0.516	5.1111	506	0.5895	0.6355	0.5895	0.7678
0.516	5.1313	508	0.5015	0.6608	0.5015	0.7082
0.516	5.1515	510	0.5201	0.6833	0.5201	0.7212
0.516	5.1717	512	0.5335	0.6565	0.5335	0.7304
0.516	5.1919	514	0.6211	0.6531	0.6211	0.7881
0.516	5.2121	516	0.5957	0.6673	0.5957	0.7718
0.516	5.2323	518	0.5805	0.6872	0.5805	0.7619
0.516	5.2525	520	0.6756	0.6723	0.6756	0.8219
0.516	5.2727	522	0.5668	0.6843	0.5668	0.7529
0.516	5.2929	524	0.4896	0.6958	0.4896	0.6997
0.516	5.3131	526	0.4672	0.6915	0.4672	0.6835
0.516	5.3333	528	0.4374	0.6900	0.4374	0.6613
0.516	5.3535	530	0.4624	0.6725	0.4624	0.6800
0.516	5.3737	532	0.5545	0.6402	0.5545	0.7447
0.516	5.3939	534	0.6613	0.5787	0.6613	0.8132
0.516	5.4141	536	0.8373	0.5098	0.8373	0.9151
0.516	5.4343	538	0.7020	0.5776	0.7020	0.8379

Framework versions

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