ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run3_AugV5_k13_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: 0.9195
• Qwk: 0.5771
• Mse: 0.9195
• Rmse: 0.9589

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	0.0312	2	5.2918	-0.0202	5.2918	2.3004
No log	0.0625	4	3.0472	0.0638	3.0472	1.7456
No log	0.0938	6	2.1681	-0.0330	2.1681	1.4725
No log	0.125	8	1.6412	0.1276	1.6412	1.2811
No log	0.1562	10	1.1834	0.2536	1.1834	1.0879
No log	0.1875	12	1.2319	0.2773	1.2319	1.1099
No log	0.2188	14	1.3486	0.2163	1.3486	1.1613
No log	0.25	16	1.6305	0.1442	1.6305	1.2769
No log	0.2812	18	1.4296	0.2114	1.4296	1.1956
No log	0.3125	20	1.0414	0.3798	1.0414	1.0205
No log	0.3438	22	1.0364	0.2438	1.0364	1.0180
No log	0.375	24	1.3753	0.0681	1.3753	1.1727
No log	0.4062	26	1.1921	0.1822	1.1921	1.0918
No log	0.4375	28	1.0818	0.3719	1.0818	1.0401
No log	0.4688	30	1.1579	0.3223	1.1579	1.0761
No log	0.5	32	1.1226	0.3064	1.1226	1.0595
No log	0.5312	34	1.1217	0.2862	1.1217	1.0591
No log	0.5625	36	1.0475	0.3373	1.0475	1.0235
No log	0.5938	38	0.9756	0.3883	0.9756	0.9877
No log	0.625	40	1.1647	0.3235	1.1647	1.0792
No log	0.6562	42	1.8507	0.1887	1.8507	1.3604
No log	0.6875	44	2.0252	0.1862	2.0252	1.4231
No log	0.7188	46	1.6714	0.1614	1.6714	1.2928
No log	0.75	48	1.0956	0.3703	1.0956	1.0467
No log	0.7812	50	0.9619	0.4376	0.9619	0.9808
No log	0.8125	52	0.9735	0.3867	0.9735	0.9866
No log	0.8438	54	1.2083	0.2339	1.2083	1.0992
No log	0.875	56	1.1419	0.2946	1.1419	1.0686
No log	0.9062	58	1.0015	0.4760	1.0015	1.0007
No log	0.9375	60	1.1256	0.3705	1.1256	1.0610
No log	0.9688	62	1.3689	0.2590	1.3689	1.1700
No log	1.0	64	1.2818	0.3737	1.2818	1.1322
No log	1.0312	66	1.3796	0.3224	1.3796	1.1746
No log	1.0625	68	1.3140	0.3750	1.3140	1.1463
No log	1.0938	70	1.1629	0.4123	1.1629	1.0784
No log	1.125	72	1.2374	0.3506	1.2374	1.1124
No log	1.1562	74	1.1322	0.4467	1.1322	1.0640
No log	1.1875	76	0.9681	0.5107	0.9681	0.9839
No log	1.2188	78	1.1327	0.4734	1.1327	1.0643
No log	1.25	80	1.4729	0.3405	1.4729	1.2136
No log	1.2812	82	1.5505	0.2444	1.5505	1.2452
No log	1.3125	84	1.2044	0.4044	1.2044	1.0974
No log	1.3438	86	1.1459	0.4317	1.1459	1.0705
No log	1.375	88	0.9634	0.5211	0.9634	0.9815
No log	1.4062	90	0.7962	0.5778	0.7962	0.8923
No log	1.4375	92	0.8433	0.5698	0.8433	0.9183
No log	1.4688	94	1.1808	0.4570	1.1808	1.0867
No log	1.5	96	1.2750	0.4134	1.2750	1.1292
No log	1.5312	98	1.1251	0.5235	1.1251	1.0607
No log	1.5625	100	0.9932	0.4711	0.9932	0.9966
No log	1.5938	102	1.0460	0.5065	1.0460	1.0228
No log	1.625	104	1.2039	0.4226	1.2039	1.0972
No log	1.6562	106	1.2339	0.4029	1.2339	1.1108
No log	1.6875	108	1.2448	0.3974	1.2448	1.1157
No log	1.7188	110	1.2463	0.4065	1.2463	1.1164
No log	1.75	112	1.0511	0.4984	1.0511	1.0252
No log	1.7812	114	0.8031	0.6697	0.8031	0.8961
No log	1.8125	116	0.8799	0.5704	0.8799	0.9380
No log	1.8438	118	1.3483	0.4244	1.3483	1.1612
No log	1.875	120	1.4800	0.3853	1.4800	1.2165
No log	1.9062	122	1.0994	0.4899	1.0994	1.0485
No log	1.9375	124	0.9795	0.5390	0.9795	0.9897
No log	1.9688	126	0.7817	0.6868	0.7817	0.8841
No log	2.0	128	0.8106	0.6647	0.8106	0.9003
No log	2.0312	130	0.7799	0.6746	0.7799	0.8831
No log	2.0625	132	0.9009	0.5922	0.9009	0.9491
No log	2.0938	134	0.8355	0.6611	0.8355	0.9141
No log	2.125	136	0.7205	0.6634	0.7205	0.8488
No log	2.1562	138	0.7511	0.6605	0.7511	0.8666
No log	2.1875	140	0.7392	0.6711	0.7392	0.8598
No log	2.2188	142	0.7694	0.6614	0.7694	0.8771
No log	2.25	144	0.9131	0.6262	0.9131	0.9555
No log	2.2812	146	1.0374	0.5265	1.0374	1.0185
No log	2.3125	148	0.8705	0.5959	0.8705	0.9330
No log	2.3438	150	0.7311	0.6820	0.7311	0.8551
No log	2.375	152	0.7305	0.6245	0.7305	0.8547
No log	2.4062	154	0.7148	0.6780	0.7148	0.8455
No log	2.4375	156	0.8635	0.6800	0.8635	0.9292
No log	2.4688	158	1.1518	0.5404	1.1518	1.0732
No log	2.5	160	1.0384	0.5902	1.0384	1.0190
No log	2.5312	162	1.0376	0.5839	1.0376	1.0186
No log	2.5625	164	1.0167	0.5657	1.0167	1.0083
No log	2.5938	166	0.7584	0.6377	0.7584	0.8709
No log	2.625	168	0.6813	0.6775	0.6813	0.8254
No log	2.6562	170	0.7033	0.6803	0.7033	0.8386
No log	2.6875	172	0.9616	0.5817	0.9616	0.9806
No log	2.7188	174	1.2032	0.5454	1.2032	1.0969
No log	2.75	176	1.0400	0.6081	1.0400	1.0198
No log	2.7812	178	0.6959	0.7061	0.6959	0.8342
No log	2.8125	180	0.6605	0.7083	0.6605	0.8127
No log	2.8438	182	0.6833	0.6629	0.6833	0.8266
No log	2.875	184	0.6413	0.7038	0.6413	0.8008
No log	2.9062	186	0.6917	0.6997	0.6917	0.8317
No log	2.9375	188	0.7081	0.7072	0.7081	0.8415
No log	2.9688	190	0.6509	0.6980	0.6509	0.8068
No log	3.0	192	0.6302	0.718	0.6302	0.7939
No log	3.0312	194	0.7992	0.6349	0.7992	0.8940
No log	3.0625	196	0.7792	0.6292	0.7792	0.8827
No log	3.0938	198	0.6337	0.7171	0.6337	0.7961
No log	3.125	200	0.7760	0.6416	0.7760	0.8809
No log	3.1562	202	1.0195	0.5385	1.0195	1.0097
No log	3.1875	204	1.0225	0.5339	1.0225	1.0112
No log	3.2188	206	0.8183	0.6263	0.8183	0.9046
No log	3.25	208	0.7793	0.6036	0.7793	0.8828
No log	3.2812	210	0.8218	0.6252	0.8218	0.9066
No log	3.3125	212	0.9014	0.5482	0.9014	0.9494
No log	3.3438	214	0.9483	0.5471	0.9483	0.9738
No log	3.375	216	0.9009	0.5586	0.9009	0.9492
No log	3.4062	218	0.9365	0.5586	0.9365	0.9677
No log	3.4375	220	0.9036	0.5500	0.9036	0.9506
No log	3.4688	222	0.8879	0.5849	0.8879	0.9423
No log	3.5	224	0.8487	0.6099	0.8487	0.9213
No log	3.5312	226	0.9078	0.5818	0.9078	0.9528
No log	3.5625	228	1.0547	0.5056	1.0547	1.0270
No log	3.5938	230	1.2533	0.4434	1.2533	1.1195
No log	3.625	232	1.1783	0.4809	1.1783	1.0855
No log	3.6562	234	0.9272	0.5243	0.9272	0.9629
No log	3.6875	236	0.8335	0.4962	0.8335	0.9129
No log	3.7188	238	0.8415	0.5974	0.8415	0.9174
No log	3.75	240	0.8893	0.5893	0.8893	0.9430
No log	3.7812	242	1.0187	0.5729	1.0187	1.0093
No log	3.8125	244	0.9022	0.6251	0.9022	0.9499
No log	3.8438	246	0.7966	0.6638	0.7966	0.8925
No log	3.875	248	0.7387	0.6796	0.7387	0.8595
No log	3.9062	250	0.7132	0.6770	0.7132	0.8445
No log	3.9375	252	0.7841	0.6398	0.7841	0.8855
No log	3.9688	254	0.7675	0.6066	0.7675	0.8761
No log	4.0	256	1.0422	0.5485	1.0422	1.0209
No log	4.0312	258	1.1589	0.5203	1.1589	1.0765
No log	4.0625	260	0.9020	0.5857	0.9020	0.9497
No log	4.0938	262	0.6721	0.6663	0.6721	0.8198
No log	4.125	264	0.6509	0.6505	0.6509	0.8068
No log	4.1562	266	0.7053	0.6106	0.7053	0.8398
No log	4.1875	268	0.7845	0.6025	0.7845	0.8857
No log	4.2188	270	0.8383	0.5988	0.8383	0.9156
No log	4.25	272	0.7454	0.6088	0.7454	0.8633
No log	4.2812	274	0.6740	0.6397	0.6740	0.8210
No log	4.3125	276	0.6910	0.6474	0.6910	0.8312
No log	4.3438	278	0.7635	0.6609	0.7635	0.8738
No log	4.375	280	0.7178	0.6579	0.7178	0.8472
No log	4.4062	282	0.6605	0.6525	0.6605	0.8127
No log	4.4375	284	0.6690	0.6363	0.6690	0.8180
No log	4.4688	286	0.7964	0.6556	0.7964	0.8924
No log	4.5	288	0.9526	0.5758	0.9526	0.9760
No log	4.5312	290	1.0052	0.5644	1.0052	1.0026
No log	4.5625	292	0.9092	0.5758	0.9092	0.9535
No log	4.5938	294	0.8713	0.5874	0.8713	0.9334
No log	4.625	296	0.7942	0.5867	0.7942	0.8912
No log	4.6562	298	0.7476	0.5987	0.7476	0.8647
No log	4.6875	300	0.7485	0.6130	0.7485	0.8652
No log	4.7188	302	0.7612	0.6393	0.7612	0.8725
No log	4.75	304	0.7915	0.6537	0.7915	0.8897
No log	4.7812	306	0.9609	0.6201	0.9609	0.9803
No log	4.8125	308	1.0765	0.5847	1.0765	1.0375
No log	4.8438	310	0.9199	0.6177	0.9199	0.9591
No log	4.875	312	0.6820	0.6693	0.6820	0.8258
No log	4.9062	314	0.6325	0.6733	0.6325	0.7953
No log	4.9375	316	0.6495	0.6332	0.6495	0.8059
No log	4.9688	318	0.6473	0.6348	0.6473	0.8046
No log	5.0	320	0.7612	0.6211	0.7612	0.8725
No log	5.0312	322	0.8905	0.5951	0.8905	0.9437
No log	5.0625	324	0.9627	0.5998	0.9627	0.9812
No log	5.0938	326	0.8858	0.6130	0.8858	0.9412
No log	5.125	328	0.7415	0.6637	0.7415	0.8611
No log	5.1562	330	0.6631	0.6626	0.6631	0.8143
No log	5.1875	332	0.6650	0.6680	0.6650	0.8155
No log	5.2188	334	0.6639	0.6671	0.6639	0.8148
No log	5.25	336	0.6829	0.6247	0.6829	0.8264
No log	5.2812	338	0.7603	0.6046	0.7603	0.8720
No log	5.3125	340	0.8341	0.5893	0.8341	0.9133
No log	5.3438	342	0.8130	0.6287	0.8130	0.9016
No log	5.375	344	0.6959	0.6362	0.6959	0.8342
No log	5.4062	346	0.6326	0.6919	0.6326	0.7954
No log	5.4375	348	0.6380	0.6710	0.6380	0.7987
No log	5.4688	350	0.6713	0.6723	0.6713	0.8193
No log	5.5	352	0.9304	0.6048	0.9304	0.9646
No log	5.5312	354	1.3192	0.4756	1.3192	1.1486
No log	5.5625	356	1.3836	0.4275	1.3836	1.1763
No log	5.5938	358	1.1989	0.4946	1.1989	1.0950
No log	5.625	360	0.9204	0.5822	0.9204	0.9594
No log	5.6562	362	0.8107	0.6296	0.8107	0.9004
No log	5.6875	364	0.8289	0.624	0.8289	0.9104
No log	5.7188	366	0.9136	0.6045	0.9136	0.9558
No log	5.75	368	0.9816	0.5732	0.9816	0.9908
No log	5.7812	370	1.0331	0.5659	1.0331	1.0164
No log	5.8125	372	0.9281	0.5745	0.9281	0.9634
No log	5.8438	374	0.7863	0.5699	0.7863	0.8868
No log	5.875	376	0.7654	0.5497	0.7654	0.8749
No log	5.9062	378	0.7687	0.5815	0.7687	0.8767
No log	5.9375	380	0.7800	0.6221	0.7800	0.8832
No log	5.9688	382	0.7722	0.6359	0.7722	0.8787
No log	6.0	384	0.7875	0.6498	0.7875	0.8874
No log	6.0312	386	0.7579	0.6362	0.7579	0.8706
No log	6.0625	388	0.7721	0.6369	0.7721	0.8787
No log	6.0938	390	0.7694	0.6131	0.7694	0.8771
No log	6.125	392	0.7384	0.6011	0.7384	0.8593
No log	6.1562	394	0.7133	0.6050	0.7133	0.8446
No log	6.1875	396	0.7292	0.6152	0.7292	0.8539
No log	6.2188	398	0.7480	0.6310	0.7480	0.8649
No log	6.25	400	0.8029	0.6505	0.8029	0.8960
No log	6.2812	402	0.8463	0.6464	0.8463	0.9200
No log	6.3125	404	0.7970	0.6629	0.7970	0.8927
No log	6.3438	406	0.6966	0.6567	0.6966	0.8346
No log	6.375	408	0.6479	0.6815	0.6479	0.8049
No log	6.4062	410	0.6472	0.6794	0.6472	0.8045
No log	6.4375	412	0.6666	0.6565	0.6666	0.8165
No log	6.4688	414	0.8292	0.6317	0.8292	0.9106
No log	6.5	416	1.0221	0.5658	1.0221	1.0110
No log	6.5312	418	1.0052	0.5632	1.0052	1.0026
No log	6.5625	420	0.8472	0.5908	0.8472	0.9204
No log	6.5938	422	0.7058	0.6525	0.7058	0.8401
No log	6.625	424	0.6799	0.6546	0.6799	0.8245
No log	6.6562	426	0.7261	0.6372	0.7261	0.8521
No log	6.6875	428	0.9178	0.5874	0.9178	0.9580
No log	6.7188	430	1.0660	0.5330	1.0660	1.0325
No log	6.75	432	0.9966	0.5862	0.9966	0.9983
No log	6.7812	434	0.8192	0.5959	0.8192	0.9051
No log	6.8125	436	0.7200	0.6375	0.7200	0.8485
No log	6.8438	438	0.6975	0.6446	0.6975	0.8352
No log	6.875	440	0.7192	0.6337	0.7192	0.8480
No log	6.9062	442	0.7103	0.6358	0.7103	0.8428
No log	6.9375	444	0.7765	0.6088	0.7765	0.8812
No log	6.9688	446	0.7679	0.6290	0.7679	0.8763
No log	7.0	448	0.6771	0.6173	0.6771	0.8228
No log	7.0312	450	0.6372	0.6539	0.6372	0.7983
No log	7.0625	452	0.6345	0.6548	0.6345	0.7966
No log	7.0938	454	0.6439	0.6486	0.6439	0.8024
No log	7.125	456	0.6432	0.6486	0.6432	0.8020
No log	7.1562	458	0.6302	0.6694	0.6302	0.7938
No log	7.1875	460	0.6104	0.7037	0.6104	0.7813
No log	7.2188	462	0.6080	0.7104	0.6080	0.7797
No log	7.25	464	0.6965	0.6617	0.6965	0.8346
No log	7.2812	466	0.7090	0.6617	0.7090	0.8420
No log	7.3125	468	0.6991	0.6763	0.6991	0.8361
No log	7.3438	470	0.6522	0.6920	0.6522	0.8076
No log	7.375	472	0.6416	0.6718	0.6416	0.8010
No log	7.4062	474	0.6905	0.6268	0.6905	0.8310
No log	7.4375	476	0.8274	0.6077	0.8274	0.9096
No log	7.4688	478	1.0591	0.5008	1.0591	1.0291
No log	7.5	480	1.1174	0.4789	1.1174	1.0571
No log	7.5312	482	1.0896	0.5203	1.0896	1.0438
No log	7.5625	484	0.8907	0.5615	0.8907	0.9438
No log	7.5938	486	0.7653	0.6843	0.7653	0.8748
No log	7.625	488	0.7402	0.6982	0.7402	0.8603
No log	7.6562	490	0.7592	0.6982	0.7592	0.8713
No log	7.6875	492	0.8488	0.6549	0.8488	0.9213
No log	7.7188	494	0.9966	0.5943	0.9966	0.9983
No log	7.75	496	1.0428	0.5433	1.0428	1.0212
No log	7.7812	498	1.0522	0.5257	1.0522	1.0258
0.4178	7.8125	500	0.9035	0.6009	0.9035	0.9505
0.4178	7.8438	502	0.7904	0.6148	0.7904	0.8890
0.4178	7.875	504	0.7337	0.6476	0.7337	0.8566
0.4178	7.9062	506	0.7127	0.6594	0.7127	0.8442
0.4178	7.9375	508	0.7083	0.6695	0.7083	0.8416
0.4178	7.9688	510	0.7405	0.6764	0.7405	0.8605
0.4178	8.0	512	0.7683	0.6567	0.7683	0.8765
0.4178	8.0312	514	0.8383	0.6005	0.8383	0.9156
0.4178	8.0625	516	0.8763	0.5718	0.8763	0.9361
0.4178	8.0938	518	0.8574	0.6054	0.8574	0.9260
0.4178	8.125	520	0.8617	0.5978	0.8617	0.9283
0.4178	8.1562	522	0.7933	0.6268	0.7933	0.8906
0.4178	8.1875	524	0.7707	0.6322	0.7707	0.8779
0.4178	8.2188	526	0.8345	0.5960	0.8345	0.9135
0.4178	8.25	528	0.9144	0.5771	0.9144	0.9562
0.4178	8.2812	530	1.0017	0.5466	1.0017	1.0008
0.4178	8.3125	532	0.9979	0.5466	0.9979	0.9990
0.4178	8.3438	534	0.9195	0.5771	0.9195	0.9589

Framework versions

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