README.md

metadata

library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: >-
      ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k4_task1_organization
    results: []

ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k4_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: 0.9623
• Qwk: 0.6423
• Mse: 0.9623
• Rmse: 0.9810

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	0.0667	2	6.5898	0.0308	6.5898	2.5671
No log	0.1333	4	4.1002	0.1096	4.1002	2.0249
No log	0.2	6	2.8690	0.0988	2.8690	1.6938
No log	0.2667	8	2.1510	0.0839	2.1510	1.4666
No log	0.3333	10	2.0596	0.1552	2.0596	1.4351
No log	0.4	12	2.0180	0.1416	2.0180	1.4206
No log	0.4667	14	2.3763	-0.0455	2.3763	1.5415
No log	0.5333	16	2.2862	0.0458	2.2862	1.5120
No log	0.6	18	1.7609	0.2281	1.7609	1.3270
No log	0.6667	20	1.4508	0.2593	1.4508	1.2045
No log	0.7333	22	1.4121	0.2430	1.4121	1.1883
No log	0.8	24	1.3413	0.3119	1.3413	1.1582
No log	0.8667	26	1.4091	0.2593	1.4091	1.1870
No log	0.9333	28	1.5483	0.2586	1.5483	1.2443
No log	1.0	30	1.5390	0.2881	1.5390	1.2406
No log	1.0667	32	1.2379	0.4211	1.2379	1.1126
No log	1.1333	34	1.1614	0.4746	1.1614	1.0777
No log	1.2	36	1.1503	0.4959	1.1503	1.0725
No log	1.2667	38	1.0579	0.56	1.0579	1.0285
No log	1.3333	40	1.1309	0.5806	1.1309	1.0634
No log	1.4	42	1.0754	0.5760	1.0754	1.0370
No log	1.4667	44	1.1479	0.5077	1.1479	1.0714
No log	1.5333	46	1.2002	0.4480	1.2002	1.0955
No log	1.6	48	1.0564	0.6	1.0564	1.0278
No log	1.6667	50	1.0704	0.5758	1.0704	1.0346
No log	1.7333	52	1.0743	0.5481	1.0743	1.0365
No log	1.8	54	1.2541	0.5735	1.2541	1.1199
No log	1.8667	56	1.4963	0.4397	1.4963	1.2232
No log	1.9333	58	1.2862	0.6187	1.2862	1.1341
No log	2.0	60	1.0796	0.6197	1.0796	1.0390
No log	2.0667	62	1.0801	0.6351	1.0801	1.0393
No log	2.1333	64	1.1478	0.6358	1.1478	1.0714
No log	2.2	66	1.0344	0.6081	1.0344	1.0171
No log	2.2667	68	1.3379	0.4427	1.3379	1.1567
No log	2.3333	70	1.5250	0.3939	1.5250	1.2349
No log	2.4	72	1.0353	0.6667	1.0353	1.0175
No log	2.4667	74	1.5442	0.5730	1.5442	1.2427
No log	2.5333	76	1.6867	0.4706	1.6867	1.2987
No log	2.6	78	1.2340	0.56	1.2340	1.1109
No log	2.6667	80	0.8541	0.6715	0.8541	0.9242
No log	2.7333	82	0.9859	0.6418	0.9859	0.9929
No log	2.8	84	0.8516	0.7015	0.8516	0.9228
No log	2.8667	86	0.8169	0.6475	0.8169	0.9038
No log	2.9333	88	0.8734	0.6377	0.8734	0.9346
No log	3.0	90	0.9176	0.6522	0.9176	0.9579
No log	3.0667	92	0.9204	0.6131	0.9204	0.9594
No log	3.1333	94	0.9179	0.6486	0.9179	0.9581
No log	3.2	96	0.9576	0.6410	0.9576	0.9786
No log	3.2667	98	0.9264	0.6923	0.9264	0.9625
No log	3.3333	100	0.8061	0.6980	0.8061	0.8978
No log	3.4	102	0.8356	0.7413	0.8356	0.9141
No log	3.4667	104	0.8203	0.7194	0.8203	0.9057
No log	3.5333	106	0.8020	0.6714	0.8020	0.8956
No log	3.6	108	0.8542	0.6429	0.8542	0.9242
No log	3.6667	110	1.0296	0.6331	1.0296	1.0147
No log	3.7333	112	1.0753	0.6755	1.0753	1.0370
No log	3.8	114	0.9588	0.6667	0.9588	0.9792
No log	3.8667	116	0.8876	0.6531	0.8876	0.9421
No log	3.9333	118	0.8772	0.6901	0.8772	0.9366
No log	4.0	120	0.9096	0.6667	0.9096	0.9537
No log	4.0667	122	0.9657	0.6755	0.9657	0.9827
No log	4.1333	124	0.8346	0.6619	0.8346	0.9136
No log	4.2	126	0.8225	0.6525	0.8225	0.9069
No log	4.2667	128	0.8480	0.6714	0.8480	0.9208
No log	4.3333	130	0.8679	0.6187	0.8679	0.9316
No log	4.4	132	0.8787	0.6757	0.8787	0.9374
No log	4.4667	134	0.8485	0.6757	0.8485	0.9212
No log	4.5333	136	0.8708	0.6753	0.8708	0.9332
No log	4.6	138	0.9105	0.6626	0.9105	0.9542
No log	4.6667	140	0.8824	0.6792	0.8824	0.9394
No log	4.7333	142	0.9089	0.7134	0.9089	0.9534
No log	4.8	144	0.8693	0.6423	0.8693	0.9324
No log	4.8667	146	0.8799	0.6466	0.8799	0.9380
No log	4.9333	148	0.9244	0.6324	0.9244	0.9615
No log	5.0	150	0.8927	0.6522	0.8927	0.9448
No log	5.0667	152	0.9597	0.6533	0.9597	0.9797
No log	5.1333	154	1.1648	0.6626	1.1648	1.0793
No log	5.2	156	1.0693	0.6541	1.0693	1.0341
No log	5.2667	158	0.7995	0.6892	0.7995	0.8941
No log	5.3333	160	0.7091	0.7050	0.7091	0.8421
No log	5.4	162	0.7041	0.7007	0.7041	0.8391
No log	5.4667	164	0.7466	0.6525	0.7466	0.8641
No log	5.5333	166	0.8796	0.6759	0.8796	0.9379
No log	5.6	168	0.9083	0.6846	0.9083	0.9530
No log	5.6667	170	0.9503	0.6968	0.9503	0.9748
No log	5.7333	172	0.8548	0.6620	0.8548	0.9246
No log	5.8	174	0.7393	0.7234	0.7393	0.8598
No log	5.8667	176	0.7585	0.7042	0.7585	0.8709
No log	5.9333	178	0.8468	0.6573	0.8468	0.9202
No log	6.0	180	0.8371	0.7	0.8371	0.9149
No log	6.0667	182	0.7581	0.6716	0.7581	0.8707
No log	6.1333	184	0.7501	0.6963	0.7501	0.8661
No log	6.2	186	0.8186	0.6861	0.8186	0.9048
No log	6.2667	188	0.8324	0.6715	0.8324	0.9124
No log	6.3333	190	0.7225	0.6912	0.7225	0.8500
No log	6.4	192	0.6160	0.7286	0.6160	0.7849
No log	6.4667	194	0.6252	0.7286	0.6252	0.7907
No log	6.5333	196	0.7215	0.7027	0.7215	0.8494
No log	6.6	198	1.0630	0.6923	1.0630	1.0310
No log	6.6667	200	1.4818	0.5820	1.4818	1.2173
No log	6.7333	202	1.4016	0.6038	1.4016	1.1839
No log	6.8	204	1.0635	0.6286	1.0635	1.0313
No log	6.8667	206	0.8135	0.6429	0.8135	0.9019
No log	6.9333	208	0.6309	0.7692	0.6309	0.7943
No log	7.0	210	0.5882	0.7397	0.5882	0.7669
No log	7.0667	212	0.6221	0.7578	0.6221	0.7887
No log	7.1333	214	0.6629	0.7662	0.6629	0.8142
No log	7.2	216	0.7156	0.7133	0.7156	0.8459
No log	7.2667	218	0.7985	0.7067	0.7985	0.8936
No log	7.3333	220	0.8546	0.6623	0.8546	0.9245
No log	7.4	222	0.8947	0.6624	0.8947	0.9459
No log	7.4667	224	0.7794	0.6846	0.7794	0.8828
No log	7.5333	226	0.7250	0.7183	0.7250	0.8515
No log	7.6	228	0.7134	0.6906	0.7134	0.8446
No log	7.6667	230	0.7353	0.7	0.7353	0.8575
No log	7.7333	232	0.7388	0.7143	0.7388	0.8595
No log	7.8	234	0.7667	0.6857	0.7667	0.8756
No log	7.8667	236	0.8228	0.6443	0.8228	0.9071
No log	7.9333	238	0.8296	0.6584	0.8296	0.9108
No log	8.0	240	0.8301	0.6584	0.8301	0.9111
No log	8.0667	242	0.8927	0.6918	0.8927	0.9448
No log	8.1333	244	0.9754	0.6358	0.9754	0.9876
No log	8.2	246	0.9609	0.6475	0.9609	0.9803
No log	8.2667	248	0.8882	0.6619	0.8882	0.9424
No log	8.3333	250	0.8000	0.6667	0.8000	0.8944
No log	8.4	252	0.7797	0.6759	0.7797	0.8830
No log	8.4667	254	0.8174	0.6792	0.8174	0.9041
No log	8.5333	256	0.8627	0.7	0.8627	0.9288
No log	8.6	258	0.9078	0.6879	0.9078	0.9528
No log	8.6667	260	0.9506	0.6795	0.9506	0.9750
No log	8.7333	262	1.0135	0.6914	1.0135	1.0067
No log	8.8	264	0.9392	0.6918	0.9392	0.9691
No log	8.8667	266	0.8188	0.6187	0.8188	0.9049
No log	8.9333	268	0.7519	0.7007	0.7519	0.8671
No log	9.0	270	0.7534	0.6714	0.7534	0.8680
No log	9.0667	272	0.8321	0.6933	0.8321	0.9122
No log	9.1333	274	0.9466	0.6883	0.9466	0.9729
No log	9.2	276	0.9984	0.6797	0.9984	0.9992
No log	9.2667	278	0.9535	0.6667	0.9535	0.9765
No log	9.3333	280	0.8545	0.6471	0.8545	0.9244
No log	9.4	282	0.7851	0.6519	0.7851	0.8860
No log	9.4667	284	0.7610	0.6528	0.7610	0.8723
No log	9.5333	286	0.8096	0.7059	0.8096	0.8998
No log	9.6	288	0.8675	0.6901	0.8675	0.9314
No log	9.6667	290	0.8885	0.6711	0.8885	0.9426
No log	9.7333	292	0.8709	0.6753	0.8709	0.9332
No log	9.8	294	0.7805	0.6806	0.7805	0.8834
No log	9.8667	296	0.7907	0.6667	0.7907	0.8892
No log	9.9333	298	0.8183	0.6383	0.8183	0.9046
No log	10.0	300	0.8798	0.6800	0.8798	0.9380
No log	10.0667	302	0.9333	0.6531	0.9333	0.9661
No log	10.1333	304	0.9721	0.6389	0.9721	0.9860
No log	10.2	306	0.9860	0.6434	0.9860	0.9930
No log	10.2667	308	0.9670	0.5970	0.9670	0.9833
No log	10.3333	310	0.9505	0.5581	0.9505	0.9749
No log	10.4	312	0.9518	0.5714	0.9518	0.9756
No log	10.4667	314	0.9779	0.625	0.9779	0.9889
No log	10.5333	316	0.9451	0.6623	0.9451	0.9722
No log	10.6	318	0.8618	0.7044	0.8618	0.9283
No log	10.6667	320	0.7837	0.6962	0.7837	0.8853
No log	10.7333	322	0.7495	0.7114	0.7495	0.8657
No log	10.8	324	0.7643	0.7368	0.7643	0.8742
No log	10.8667	326	0.9595	0.7126	0.9595	0.9795
No log	10.9333	328	1.0521	0.6821	1.0521	1.0257
No log	11.0	330	1.0081	0.6821	1.0081	1.0040
No log	11.0667	332	0.7862	0.7368	0.7862	0.8867
No log	11.1333	334	0.6482	0.7324	0.6482	0.8051
No log	11.2	336	0.6450	0.6957	0.6450	0.8031
No log	11.2667	338	0.6401	0.7273	0.6401	0.8001
No log	11.3333	340	0.7108	0.7453	0.7108	0.8431
No log	11.4	342	0.9454	0.7033	0.9454	0.9723
No log	11.4667	344	1.1103	0.6740	1.1103	1.0537
No log	11.5333	346	1.0559	0.6927	1.0559	1.0276
No log	11.6	348	0.9332	0.6909	0.9332	0.9660
No log	11.6667	350	0.8719	0.6710	0.8719	0.9337
No log	11.7333	352	0.8469	0.6710	0.8469	0.9203
No log	11.8	354	0.8208	0.6755	0.8208	0.9060
No log	11.8667	356	0.7294	0.6617	0.7294	0.8541
No log	11.9333	358	0.7217	0.7068	0.7217	0.8495
No log	12.0	360	0.7425	0.6617	0.7425	0.8617
No log	12.0667	362	0.8143	0.6471	0.8143	0.9024
No log	12.1333	364	0.8158	0.6479	0.8158	0.9032
No log	12.2	366	0.7990	0.6667	0.7990	0.8939
No log	12.2667	368	0.7183	0.6718	0.7183	0.8475
No log	12.3333	370	0.6947	0.6963	0.6947	0.8335
No log	12.4	372	0.6912	0.7042	0.6912	0.8314
No log	12.4667	374	0.7607	0.7067	0.7607	0.8722
No log	12.5333	376	0.8340	0.6962	0.8340	0.9132
No log	12.6	378	0.8934	0.7097	0.8934	0.9452
No log	12.6667	380	0.8405	0.6974	0.8405	0.9168
No log	12.7333	382	0.7367	0.7000	0.7367	0.8583
No log	12.8	384	0.7013	0.6906	0.7013	0.8374
No log	12.8667	386	0.7070	0.7234	0.7070	0.8408
No log	12.9333	388	0.7528	0.7234	0.7528	0.8677
No log	13.0	390	0.8443	0.6757	0.8443	0.9188
No log	13.0667	392	0.8975	0.6757	0.8975	0.9474
No log	13.1333	394	0.8717	0.6471	0.8717	0.9336
No log	13.2	396	0.7901	0.6618	0.7901	0.8889
No log	13.2667	398	0.7323	0.6565	0.7323	0.8557
No log	13.3333	400	0.7102	0.6763	0.7102	0.8427
No log	13.4	402	0.7029	0.6857	0.7029	0.8384
No log	13.4667	404	0.7288	0.7421	0.7288	0.8537
No log	13.5333	406	0.8497	0.7209	0.8497	0.9218
No log	13.6	408	0.8999	0.7052	0.8999	0.9486
No log	13.6667	410	0.8398	0.7168	0.8398	0.9164
No log	13.7333	412	0.7564	0.7453	0.7564	0.8697
No log	13.8	414	0.6652	0.7397	0.6652	0.8156
No log	13.8667	416	0.6202	0.75	0.6202	0.7875
No log	13.9333	418	0.6382	0.7518	0.6382	0.7989
No log	14.0	420	0.6875	0.7383	0.6875	0.8292
No log	14.0667	422	0.7636	0.7317	0.7636	0.8739
No log	14.1333	424	0.7962	0.7239	0.7962	0.8923
No log	14.2	426	0.8544	0.7011	0.8544	0.9243
No log	14.2667	428	0.8612	0.7011	0.8612	0.9280
No log	14.3333	430	0.7854	0.7006	0.7854	0.8862
No log	14.4	432	0.6887	0.7034	0.6887	0.8299
No log	14.4667	434	0.6668	0.7413	0.6668	0.8166
No log	14.5333	436	0.6481	0.7651	0.6481	0.8050
No log	14.6	438	0.6567	0.7568	0.6567	0.8104
No log	14.6667	440	0.7198	0.7172	0.7198	0.8484
No log	14.7333	442	0.8552	0.6486	0.8552	0.9248
No log	14.8	444	0.9370	0.6623	0.9370	0.9680
No log	14.8667	446	0.9147	0.6621	0.9147	0.9564
No log	14.9333	448	0.8590	0.6331	0.8590	0.9268
No log	15.0	450	0.7815	0.6462	0.7815	0.8840
No log	15.0667	452	0.7460	0.6617	0.7460	0.8637
No log	15.1333	454	0.7534	0.6716	0.7534	0.8680
No log	15.2	456	0.7613	0.6471	0.7613	0.8725
No log	15.2667	458	0.8049	0.6621	0.8049	0.8972
No log	15.3333	460	0.8072	0.6757	0.8072	0.8984
No log	15.4	462	0.7956	0.6331	0.7956	0.8919
No log	15.4667	464	0.8230	0.6621	0.8230	0.9072
No log	15.5333	466	0.8422	0.7006	0.8422	0.9177
No log	15.6	468	0.8554	0.6839	0.8554	0.9249
No log	15.6667	470	0.8584	0.6711	0.8584	0.9265
No log	15.7333	472	0.8662	0.6338	0.8662	0.9307
No log	15.8	474	0.8628	0.6331	0.8628	0.9289
No log	15.8667	476	0.8646	0.6176	0.8646	0.9299
No log	15.9333	478	0.8689	0.6176	0.8689	0.9322
No log	16.0	480	0.9225	0.6176	0.9225	0.9605
No log	16.0667	482	1.0289	0.6187	1.0289	1.0143
No log	16.1333	484	1.0436	0.6187	1.0436	1.0216
No log	16.2	486	0.9546	0.6029	0.9546	0.9770
No log	16.2667	488	0.8682	0.6316	0.8682	0.9318
No log	16.3333	490	0.8093	0.6515	0.8093	0.8996
No log	16.4	492	0.7927	0.6765	0.7927	0.8903
No log	16.4667	494	0.7957	0.6471	0.7957	0.8920
No log	16.5333	496	0.8585	0.6957	0.8585	0.9266
No log	16.6	498	0.8677	0.7073	0.8677	0.9315
0.3285	16.6667	500	0.8179	0.6619	0.8179	0.9044
0.3285	16.7333	502	0.8098	0.6667	0.8098	0.8999
0.3285	16.8	504	0.8096	0.6718	0.8096	0.8998
0.3285	16.8667	506	0.8420	0.6515	0.8420	0.9176
0.3285	16.9333	508	0.8654	0.6515	0.8654	0.9303
0.3285	17.0	510	0.8929	0.6515	0.8929	0.9449
0.3285	17.0667	512	0.9919	0.6832	0.9919	0.9960
0.3285	17.1333	514	1.1133	0.6857	1.1133	1.0551
0.3285	17.2	516	1.0949	0.6746	1.0949	1.0464
0.3285	17.2667	518	0.9684	0.6579	0.9684	0.9841
0.3285	17.3333	520	0.8481	0.6515	0.8481	0.9209
0.3285	17.4	522	0.8142	0.6667	0.8142	0.9023
0.3285	17.4667	524	0.8133	0.6667	0.8133	0.9019
0.3285	17.5333	526	0.8190	0.6412	0.8190	0.9050
0.3285	17.6	528	0.8312	0.6515	0.8312	0.9117
0.3285	17.6667	530	0.8522	0.6667	0.8522	0.9232
0.3285	17.7333	532	0.8804	0.6933	0.8804	0.9383
0.3285	17.8	534	0.8994	0.6928	0.8994	0.9484
0.3285	17.8667	536	0.8993	0.6667	0.8993	0.9483
0.3285	17.9333	538	0.9062	0.6324	0.9062	0.9520
0.3285	18.0	540	0.8769	0.6316	0.8769	0.9364
0.3285	18.0667	542	0.8570	0.6316	0.8570	0.9258
0.3285	18.1333	544	0.8864	0.6316	0.8864	0.9415
0.3285	18.2	546	0.9364	0.6711	0.9364	0.9677
0.3285	18.2667	548	0.9597	0.6946	0.9597	0.9796
0.3285	18.3333	550	0.9022	0.7059	0.9022	0.9498
0.3285	18.4	552	0.8338	0.7108	0.8338	0.9131
0.3285	18.4667	554	0.7915	0.7089	0.7915	0.8897
0.3285	18.5333	556	0.8113	0.6711	0.8113	0.9007
0.3285	18.6	558	0.9303	0.6573	0.9303	0.9645
0.3285	18.6667	560	1.0452	0.6525	1.0452	1.0223
0.3285	18.7333	562	1.0327	0.6377	1.0327	1.0162
0.3285	18.8	564	1.0406	0.6377	1.0406	1.0201
0.3285	18.8667	566	0.9623	0.6423	0.9623	0.9810

Framework versions

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