README.md

metadata

library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k3_task1_organization
    results: []

ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k3_task1_organization

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: 1.1391
• Qwk: 0.6047
• Mse: 1.1391
• Rmse: 1.0673

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	0.1429	2	7.0888	0.0	7.0888	2.6625
No log	0.2857	4	4.6085	0.0465	4.6085	2.1467
No log	0.4286	6	3.1630	0.0833	3.1630	1.7785
No log	0.5714	8	2.9042	0.0387	2.9042	1.7042
No log	0.7143	10	2.1985	0.1538	2.1985	1.4827
No log	0.8571	12	1.8597	0.1284	1.8597	1.3637
No log	1.0	14	1.9150	0.1964	1.9150	1.3838
No log	1.1429	16	2.1047	0.1513	2.1047	1.4508
No log	1.2857	18	2.1554	0.0984	2.1554	1.4681
No log	1.4286	20	2.4395	-0.0155	2.4395	1.5619
No log	1.5714	22	2.1311	0.1322	2.1311	1.4598
No log	1.7143	24	1.9880	0.2051	1.9880	1.4100
No log	1.8571	26	1.7429	0.1897	1.7429	1.3202
No log	2.0	28	1.6455	0.2087	1.6455	1.2828
No log	2.1429	30	1.8338	0.3279	1.8338	1.3542
No log	2.2857	32	1.7839	0.3415	1.7839	1.3356
No log	2.4286	34	1.4674	0.3077	1.4674	1.2114
No log	2.5714	36	1.3577	0.3529	1.3578	1.1652
No log	2.7143	38	1.2997	0.4167	1.2997	1.1400
No log	2.8571	40	1.2729	0.4553	1.2729	1.1282
No log	3.0	42	1.5532	0.3009	1.5532	1.2463
No log	3.1429	44	1.8502	0.1897	1.8502	1.3602
No log	3.2857	46	1.3977	0.4320	1.3977	1.1823
No log	3.4286	48	1.2744	0.5248	1.2744	1.1289
No log	3.5714	50	1.2519	0.5441	1.2519	1.1189
No log	3.7143	52	1.4371	0.3824	1.4371	1.1988
No log	3.8571	54	1.5049	0.3650	1.5049	1.2267
No log	4.0	56	1.7120	0.3333	1.7120	1.3084
No log	4.1429	58	1.5715	0.4030	1.5715	1.2536
No log	4.2857	60	1.1796	0.5224	1.1796	1.0861
No log	4.4286	62	1.1648	0.3710	1.1648	1.0793
No log	4.5714	64	1.1835	0.4132	1.1835	1.0879
No log	4.7143	66	1.2012	0.3826	1.2012	1.0960
No log	4.8571	68	1.3653	0.4320	1.3653	1.1685
No log	5.0	70	1.5138	0.4219	1.5138	1.2304
No log	5.1429	72	1.3110	0.4640	1.3110	1.1450
No log	5.2857	74	1.1618	0.3419	1.1618	1.0779
No log	5.4286	76	1.2189	0.4844	1.2189	1.1040
No log	5.5714	78	1.0765	0.4923	1.0765	1.0376
No log	5.7143	80	1.1995	0.4960	1.1995	1.0952
No log	5.8571	82	1.4532	0.4341	1.4532	1.2055
No log	6.0	84	1.3306	0.4252	1.3306	1.1535
No log	6.1429	86	1.1643	0.4754	1.1643	1.0790
No log	6.2857	88	1.0378	0.4754	1.0378	1.0187
No log	6.4286	90	1.0622	0.4746	1.0622	1.0306
No log	6.5714	92	1.1201	0.4522	1.1201	1.0583
No log	6.7143	94	1.1126	0.4035	1.1126	1.0548
No log	6.8571	96	1.1025	0.4754	1.1025	1.0500
No log	7.0	98	1.0517	0.5203	1.0517	1.0255
No log	7.1429	100	1.0080	0.5082	1.0080	1.0040
No log	7.2857	102	1.1229	0.5354	1.1229	1.0597
No log	7.4286	104	1.1739	0.5	1.1739	1.0835
No log	7.5714	106	1.0341	0.4754	1.0341	1.0169
No log	7.7143	108	1.0425	0.4918	1.0425	1.0210
No log	7.8571	110	1.1496	0.5041	1.1496	1.0722
No log	8.0	112	1.2833	0.5079	1.2833	1.1328
No log	8.1429	114	1.2984	0.5079	1.2984	1.1395
No log	8.2857	116	1.1003	0.4918	1.1003	1.0490
No log	8.4286	118	1.0470	0.4959	1.0470	1.0232
No log	8.5714	120	1.0254	0.4959	1.0254	1.0126
No log	8.7143	122	1.0387	0.4918	1.0387	1.0192
No log	8.8571	124	1.2795	0.4688	1.2795	1.1311
No log	9.0	126	1.1934	0.4882	1.1934	1.0924
No log	9.1429	128	1.0214	0.5556	1.0214	1.0106
No log	9.2857	130	0.9842	0.5556	0.9842	0.9921
No log	9.4286	132	0.9731	0.544	0.9731	0.9865
No log	9.5714	134	0.9452	0.5714	0.9452	0.9722
No log	9.7143	136	0.9153	0.6107	0.9153	0.9567
No log	9.8571	138	0.9298	0.6202	0.9298	0.9643
No log	10.0	140	0.9676	0.6308	0.9676	0.9837
No log	10.1429	142	1.0704	0.5	1.0704	1.0346
No log	10.2857	144	1.1087	0.4923	1.1087	1.0529
No log	10.4286	146	1.0185	0.5649	1.0185	1.0092
No log	10.5714	148	0.8184	0.6667	0.8184	0.9046
No log	10.7143	150	0.7754	0.6714	0.7754	0.8806
No log	10.8571	152	0.9293	0.5758	0.9293	0.9640
No log	11.0	154	1.4100	0.4776	1.4100	1.1874
No log	11.1429	156	1.6137	0.4593	1.6137	1.2703
No log	11.2857	158	1.3696	0.4776	1.3696	1.1703
No log	11.4286	160	0.9863	0.6061	0.9863	0.9931
No log	11.5714	162	0.8539	0.6154	0.8539	0.9241
No log	11.7143	164	0.8933	0.5714	0.8933	0.9451
No log	11.8571	166	1.0152	0.5714	1.0152	1.0076
No log	12.0	168	1.0850	0.5938	1.0850	1.0416
No log	12.1429	170	1.2002	0.5758	1.2002	1.0955
No log	12.2857	172	1.1434	0.5758	1.1434	1.0693
No log	12.4286	174	0.9069	0.5781	0.9069	0.9523
No log	12.5714	176	0.8613	0.5891	0.8613	0.9281
No log	12.7143	178	0.9513	0.5781	0.9513	0.9753
No log	12.8571	180	0.9912	0.5781	0.9912	0.9956
No log	13.0	182	1.0692	0.5846	1.0692	1.0340
No log	13.1429	184	0.9828	0.5846	0.9828	0.9913
No log	13.2857	186	0.8543	0.5938	0.8543	0.9243
No log	13.4286	188	0.7508	0.6316	0.7508	0.8665
No log	13.5714	190	0.7654	0.6716	0.7654	0.8749
No log	13.7143	192	0.8496	0.6	0.8496	0.9218
No log	13.8571	194	1.0755	0.5954	1.0755	1.0371
No log	14.0	196	1.2106	0.5038	1.2106	1.1003
No log	14.1429	198	1.0480	0.5692	1.0480	1.0237
No log	14.2857	200	0.8811	0.5714	0.8811	0.9387
No log	14.4286	202	0.8732	0.56	0.8732	0.9345
No log	14.5714	204	0.9449	0.5846	0.9449	0.9721
No log	14.7143	206	1.0372	0.5954	1.0372	1.0184
No log	14.8571	208	1.1288	0.5758	1.1288	1.0625
No log	15.0	210	1.3459	0.4697	1.3459	1.1601
No log	15.1429	212	1.2832	0.5038	1.2832	1.1328
No log	15.2857	214	1.1356	0.5846	1.1356	1.0656
No log	15.4286	216	1.0395	0.608	1.0395	1.0196
No log	15.5714	218	0.9942	0.6142	0.9942	0.9971
No log	15.7143	220	0.9606	0.6094	0.9606	0.9801
No log	15.8571	222	1.1280	0.5758	1.1280	1.0621
No log	16.0	224	1.5268	0.4122	1.5268	1.2356
No log	16.1429	226	1.6402	0.4776	1.6402	1.2807
No log	16.2857	228	1.2419	0.5522	1.2419	1.1144
No log	16.4286	230	0.8077	0.6316	0.8077	0.8987
No log	16.5714	232	0.7854	0.6324	0.7854	0.8862
No log	16.7143	234	0.8103	0.6370	0.8103	0.9001
No log	16.8571	236	0.8716	0.6154	0.8716	0.9336
No log	17.0	238	0.9673	0.5984	0.9673	0.9835
No log	17.1429	240	0.9582	0.6047	0.9582	0.9789
No log	17.2857	242	0.9599	0.5827	0.9599	0.9797
No log	17.4286	244	1.0056	0.5669	1.0056	1.0028
No log	17.5714	246	1.0964	0.5669	1.0964	1.0471
No log	17.7143	248	1.2196	0.5736	1.2196	1.1044
No log	17.8571	250	1.1812	0.5781	1.1812	1.0868
No log	18.0	252	1.2103	0.5846	1.2103	1.1001
No log	18.1429	254	1.2053	0.5891	1.2053	1.0979
No log	18.2857	256	1.1215	0.544	1.1215	1.0590
No log	18.4286	258	1.0931	0.5691	1.0931	1.0455
No log	18.5714	260	1.0398	0.5691	1.0398	1.0197
No log	18.7143	262	1.0473	0.544	1.0473	1.0234
No log	18.8571	264	1.0691	0.5938	1.0691	1.0340
No log	19.0	266	1.0749	0.6	1.0749	1.0368
No log	19.1429	268	1.0092	0.5827	1.0092	1.0046
No log	19.2857	270	0.9449	0.5484	0.9449	0.9721
No log	19.4286	272	0.9479	0.5528	0.9479	0.9736
No log	19.5714	274	0.9576	0.5410	0.9576	0.9786
No log	19.7143	276	1.0133	0.5873	1.0133	1.0066
No log	19.8571	278	1.2346	0.4961	1.2346	1.1111
No log	20.0	280	1.3634	0.4462	1.3634	1.1677
No log	20.1429	282	1.2573	0.5758	1.2573	1.1213
No log	20.2857	284	1.0114	0.5846	1.0114	1.0057
No log	20.4286	286	0.9077	0.5984	0.9077	0.9527
No log	20.5714	288	0.9457	0.5984	0.9457	0.9725
No log	20.7143	290	1.0062	0.5645	1.0062	1.0031
No log	20.8571	292	1.1483	0.5781	1.1483	1.0716
No log	21.0	294	1.3106	0.5197	1.3106	1.1448
No log	21.1429	296	1.3243	0.5197	1.3243	1.1508
No log	21.2857	298	1.1886	0.5736	1.1886	1.0902
No log	21.4286	300	1.0303	0.5781	1.0303	1.0151
No log	21.5714	302	0.9109	0.5714	0.9109	0.9544
No log	21.7143	304	0.8478	0.6094	0.8478	0.9208
No log	21.8571	306	0.8379	0.5938	0.8379	0.9154
No log	22.0	308	0.9267	0.5846	0.9267	0.9627
No log	22.1429	310	1.0974	0.5802	1.0974	1.0476
No log	22.2857	312	1.1172	0.5271	1.1172	1.0570
No log	22.4286	314	1.0362	0.5891	1.0362	1.0180
No log	22.5714	316	1.0185	0.5891	1.0185	1.0092
No log	22.7143	318	0.9941	0.5846	0.9941	0.9970
No log	22.8571	320	1.0057	0.5846	1.0057	1.0029
No log	23.0	322	0.9261	0.5909	0.9261	0.9623
No log	23.1429	324	0.8964	0.5846	0.8964	0.9468
No log	23.2857	326	0.9553	0.5846	0.9553	0.9774
No log	23.4286	328	0.9801	0.5781	0.9801	0.9900
No log	23.5714	330	1.0640	0.5827	1.0640	1.0315
No log	23.7143	332	1.1885	0.5469	1.1885	1.0902
No log	23.8571	334	1.2201	0.5426	1.2201	1.1046
No log	24.0	336	1.1016	0.6	1.1016	1.0496
No log	24.1429	338	0.9728	0.5781	0.9728	0.9863
No log	24.2857	340	0.8789	0.5714	0.8789	0.9375
No log	24.4286	342	0.8615	0.5714	0.8615	0.9281
No log	24.5714	344	0.9361	0.5891	0.9361	0.9675
No log	24.7143	346	1.0887	0.6	1.0887	1.0434
No log	24.8571	348	1.1971	0.5426	1.1971	1.0941
No log	25.0	350	1.1777	0.5954	1.1777	1.0852
No log	25.1429	352	1.1349	0.5891	1.1349	1.0653
No log	25.2857	354	1.0716	0.5846	1.0716	1.0352
No log	25.4286	356	1.0575	0.5846	1.0575	1.0284
No log	25.5714	358	1.0982	0.5846	1.0982	1.0479
No log	25.7143	360	1.1609	0.5758	1.1609	1.0775
No log	25.8571	362	1.0847	0.5846	1.0847	1.0415
No log	26.0	364	0.9502	0.6	0.9502	0.9748
No log	26.1429	366	0.8626	0.6308	0.8626	0.9287
No log	26.2857	368	0.8495	0.6308	0.8495	0.9217
No log	26.4286	370	0.8390	0.6308	0.8390	0.9159
No log	26.5714	372	0.8657	0.6308	0.8657	0.9304
No log	26.7143	374	0.9078	0.6094	0.9078	0.9528
No log	26.8571	376	0.9401	0.6094	0.9401	0.9696
No log	27.0	378	0.9662	0.6357	0.9662	0.9830
No log	27.1429	380	1.0139	0.6462	1.0139	1.0069
No log	27.2857	382	1.0602	0.6412	1.0602	1.0297
No log	27.4286	384	1.0712	0.6412	1.0712	1.0350
No log	27.5714	386	1.0750	0.6412	1.0750	1.0368
No log	27.7143	388	1.0750	0.625	1.0750	1.0368
No log	27.8571	390	1.0746	0.5873	1.0746	1.0366
No log	28.0	392	1.0710	0.592	1.0710	1.0349
No log	28.1429	394	1.0686	0.6299	1.0686	1.0337
No log	28.2857	396	1.1092	0.6047	1.1092	1.0532
No log	28.4286	398	1.0913	0.6154	1.0913	1.0446
No log	28.5714	400	1.1283	0.5954	1.1283	1.0622
No log	28.7143	402	1.1023	0.6154	1.1023	1.0499
No log	28.8571	404	1.0474	0.6154	1.0474	1.0234
No log	29.0	406	0.9595	0.625	0.9595	0.9795
No log	29.1429	408	0.9387	0.5984	0.9387	0.9689
No log	29.2857	410	0.9742	0.625	0.9742	0.9870
No log	29.4286	412	1.0886	0.5625	1.0886	1.0434
No log	29.5714	414	1.2127	0.5156	1.2127	1.1012
No log	29.7143	416	1.2272	0.5354	1.2272	1.1078
No log	29.8571	418	1.1711	0.5238	1.1711	1.0822
No log	30.0	420	1.0829	0.6032	1.0829	1.0406
No log	30.1429	422	1.0230	0.5873	1.0230	1.0114
No log	30.2857	424	1.0221	0.5827	1.0221	1.0110
No log	30.4286	426	1.0782	0.5984	1.0782	1.0384
No log	30.5714	428	1.2207	0.5625	1.2207	1.1048
No log	30.7143	430	1.3621	0.5231	1.3621	1.1671
No log	30.8571	432	1.4077	0.5	1.4077	1.1865
No log	31.0	434	1.3177	0.5156	1.3177	1.1479
No log	31.1429	436	1.1443	0.5827	1.1443	1.0697
No log	31.2857	438	1.0629	0.6032	1.0629	1.0310
No log	31.4286	440	1.0624	0.6032	1.0624	1.0307
No log	31.5714	442	1.1093	0.6094	1.1093	1.0532
No log	31.7143	444	1.1609	0.5625	1.1609	1.0774
No log	31.8571	446	1.1276	0.5625	1.1276	1.0619
No log	32.0	448	1.0748	0.6142	1.0748	1.0367
No log	32.1429	450	1.0138	0.6032	1.0138	1.0069
No log	32.2857	452	0.9977	0.6032	0.9977	0.9988
No log	32.4286	454	0.9914	0.5968	0.9914	0.9957
No log	32.5714	456	0.9555	0.5873	0.9555	0.9775
No log	32.7143	458	0.9618	0.6032	0.9618	0.9807
No log	32.8571	460	1.0375	0.6357	1.0375	1.0186
No log	33.0	462	1.1507	0.5625	1.1507	1.0727
No log	33.1429	464	1.1696	0.5625	1.1696	1.0815
No log	33.2857	466	1.1184	0.5891	1.1184	1.0576
No log	33.4286	468	1.0298	0.5938	1.0298	1.0148
No log	33.5714	470	1.0064	0.6094	1.0064	1.0032
No log	33.7143	472	1.0495	0.6032	1.0495	1.0244
No log	33.8571	474	1.1285	0.5556	1.1285	1.0623
No log	34.0	476	1.2255	0.5625	1.2255	1.1070
No log	34.1429	478	1.2523	0.5354	1.2523	1.1191
No log	34.2857	480	1.2741	0.5354	1.2741	1.1288
No log	34.4286	482	1.2889	0.5079	1.2889	1.1353
No log	34.5714	484	1.2429	0.5354	1.2429	1.1149
No log	34.7143	486	1.1582	0.5781	1.1582	1.0762
No log	34.8571	488	1.0664	0.5827	1.0664	1.0327
No log	35.0	490	1.0045	0.5920	1.0045	1.0023
No log	35.1429	492	0.9872	0.6032	0.9872	0.9936
No log	35.2857	494	0.9912	0.6299	0.9912	0.9956
No log	35.4286	496	0.9914	0.6299	0.9914	0.9957
No log	35.5714	498	0.9633	0.625	0.9633	0.9815
0.2639	35.7143	500	0.9596	0.625	0.9596	0.9796
0.2639	35.8571	502	0.9851	0.6299	0.9851	0.9925
0.2639	36.0	504	1.0212	0.6202	1.0212	1.0105
0.2639	36.1429	506	1.0516	0.6202	1.0516	1.0255
0.2639	36.2857	508	1.0200	0.6154	1.0200	1.0100
0.2639	36.4286	510	0.9473	0.6462	0.9473	0.9733
0.2639	36.5714	512	0.9148	0.6412	0.9148	0.9565
0.2639	36.7143	514	0.8978	0.6412	0.8978	0.9475
0.2639	36.8571	516	0.8607	0.5891	0.8607	0.9278
0.2639	37.0	518	0.8455	0.5891	0.8455	0.9195
0.2639	37.1429	520	0.8390	0.5938	0.8390	0.9160
0.2639	37.2857	522	0.8603	0.5891	0.8603	0.9275
0.2639	37.4286	524	0.9349	0.6357	0.9349	0.9669
0.2639	37.5714	526	1.0450	0.6142	1.0450	1.0222
0.2639	37.7143	528	1.1167	0.5938	1.1167	1.0567
0.2639	37.8571	530	1.1095	0.6142	1.1095	1.0533
0.2639	38.0	532	1.0475	0.6142	1.0475	1.0235
0.2639	38.1429	534	0.9474	0.6406	0.9474	0.9733
0.2639	38.2857	536	0.9145	0.6094	0.9145	0.9563
0.2639	38.4286	538	0.9275	0.6094	0.9275	0.9631
0.2639	38.5714	540	0.9961	0.6299	0.9961	0.9980
0.2639	38.7143	542	1.0809	0.6154	1.0809	1.0397
0.2639	38.8571	544	1.1618	0.5649	1.1618	1.0779
0.2639	39.0	546	1.2296	0.5455	1.2296	1.1089
0.2639	39.1429	548	1.2117	0.5385	1.2117	1.1008
0.2639	39.2857	550	1.1391	0.6047	1.1391	1.0673

Framework versions

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