ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_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: 0.7436
• Qwk: 0.5930
• Mse: 0.7436
• Rmse: 0.8623

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	5.5681	-0.0008	5.5681	2.3597
No log	0.0625	4	3.4839	0.0794	3.4839	1.8665
No log	0.0938	6	2.2950	-0.0074	2.2950	1.5149
No log	0.125	8	1.7577	0.0485	1.7577	1.3258
No log	0.1562	10	1.2415	0.2275	1.2415	1.1142
No log	0.1875	12	1.1067	0.2657	1.1067	1.0520
No log	0.2188	14	1.1042	0.2235	1.1042	1.0508
No log	0.25	16	1.0936	0.2259	1.0936	1.0457
No log	0.2812	18	1.1722	0.3150	1.1722	1.0827
No log	0.3125	20	1.0897	0.3250	1.0897	1.0439
No log	0.3438	22	1.0482	0.3903	1.0482	1.0238
No log	0.375	24	1.3666	0.2675	1.3666	1.1690
No log	0.4062	26	1.3792	0.3018	1.3792	1.1744
No log	0.4375	28	1.3172	0.3102	1.3172	1.1477
No log	0.4688	30	0.9555	0.4043	0.9555	0.9775
No log	0.5	32	0.8530	0.4471	0.8530	0.9236
No log	0.5312	34	0.8410	0.4818	0.8410	0.9171
No log	0.5625	36	0.8427	0.4785	0.8427	0.9180
No log	0.5938	38	0.8323	0.4727	0.8323	0.9123
No log	0.625	40	0.7998	0.4761	0.7998	0.8943
No log	0.6562	42	0.8127	0.5301	0.8127	0.9015
No log	0.6875	44	0.8123	0.5531	0.8123	0.9013
No log	0.7188	46	0.8631	0.5695	0.8631	0.9290
No log	0.75	48	0.8339	0.5796	0.8339	0.9132
No log	0.7812	50	0.8039	0.5615	0.8039	0.8966
No log	0.8125	52	0.9726	0.5191	0.9726	0.9862
No log	0.8438	54	1.3580	0.4439	1.3580	1.1653
No log	0.875	56	1.1693	0.4035	1.1693	1.0813
No log	0.9062	58	0.7993	0.5399	0.7993	0.8940
No log	0.9375	60	0.8565	0.5567	0.8565	0.9255
No log	0.9688	62	0.9729	0.5398	0.9729	0.9864
No log	1.0	64	1.0232	0.5205	1.0232	1.0116
No log	1.0312	66	0.9349	0.4941	0.9349	0.9669
No log	1.0625	68	0.8709	0.5429	0.8709	0.9332
No log	1.0938	70	0.8826	0.5086	0.8826	0.9395
No log	1.125	72	0.8928	0.4669	0.8928	0.9449
No log	1.1562	74	0.9060	0.5070	0.9060	0.9518
No log	1.1875	76	1.0653	0.5080	1.0653	1.0321
No log	1.2188	78	1.2351	0.3797	1.2351	1.1113
No log	1.25	80	1.1914	0.4272	1.1914	1.0915
No log	1.2812	82	1.1606	0.4407	1.1606	1.0773
No log	1.3125	84	1.0231	0.4973	1.0231	1.0115
No log	1.3438	86	1.0431	0.4906	1.0431	1.0213
No log	1.375	88	1.0535	0.5099	1.0535	1.0264
No log	1.4062	90	1.3189	0.3948	1.3189	1.1484
No log	1.4375	92	1.2753	0.4743	1.2753	1.1293
No log	1.4688	94	0.9425	0.5691	0.9425	0.9708
No log	1.5	96	0.8330	0.6428	0.8330	0.9127
No log	1.5312	98	0.9254	0.5786	0.9254	0.9620
No log	1.5625	100	0.8840	0.6177	0.8840	0.9402
No log	1.5938	102	0.8220	0.6682	0.8220	0.9066
No log	1.625	104	0.7382	0.6881	0.7382	0.8592
No log	1.6562	106	0.7322	0.6571	0.7322	0.8557
No log	1.6875	108	0.6946	0.7020	0.6946	0.8334
No log	1.7188	110	0.7114	0.6840	0.7114	0.8435
No log	1.75	112	0.7324	0.6849	0.7324	0.8558
No log	1.7812	114	0.9200	0.5277	0.9200	0.9592
No log	1.8125	116	0.8805	0.5062	0.8805	0.9383
No log	1.8438	118	0.7021	0.6981	0.7021	0.8379
No log	1.875	120	0.6878	0.6782	0.6878	0.8294
No log	1.9062	122	0.7163	0.6357	0.7163	0.8464
No log	1.9375	124	0.9685	0.5598	0.9685	0.9841
No log	1.9688	126	1.0028	0.5516	1.0028	1.0014
No log	2.0	128	0.9864	0.5419	0.9864	0.9932
No log	2.0312	130	0.7553	0.5863	0.7553	0.8691
No log	2.0625	132	0.7133	0.6318	0.7133	0.8446
No log	2.0938	134	0.7877	0.6392	0.7877	0.8875
No log	2.125	136	0.7316	0.6318	0.7316	0.8553
No log	2.1562	138	0.7003	0.6255	0.7003	0.8368
No log	2.1875	140	0.6871	0.6218	0.6871	0.8289
No log	2.2188	142	0.6941	0.5859	0.6941	0.8331
No log	2.25	144	0.7101	0.5187	0.7101	0.8427
No log	2.2812	146	0.7438	0.5505	0.7438	0.8625
No log	2.3125	148	0.9436	0.5284	0.9436	0.9714
No log	2.3438	150	0.9093	0.5620	0.9093	0.9536
No log	2.375	152	0.7555	0.6174	0.7555	0.8692
No log	2.4062	154	0.6709	0.6368	0.6709	0.8191
No log	2.4375	156	0.7019	0.6468	0.7019	0.8378
No log	2.4688	158	0.6905	0.6622	0.6905	0.8310
No log	2.5	160	0.6462	0.7045	0.6462	0.8038
No log	2.5312	162	0.6450	0.6826	0.6450	0.8031
No log	2.5625	164	0.6896	0.6260	0.6896	0.8304
No log	2.5938	166	0.6448	0.6868	0.6448	0.8030
No log	2.625	168	0.6154	0.7033	0.6154	0.7845
No log	2.6562	170	0.7151	0.6497	0.7151	0.8456
No log	2.6875	172	0.8263	0.6006	0.8263	0.9090
No log	2.7188	174	0.6959	0.6599	0.6959	0.8342
No log	2.75	176	0.6541	0.6413	0.6541	0.8088
No log	2.7812	178	1.0260	0.5601	1.0260	1.0129
No log	2.8125	180	1.2428	0.4570	1.2428	1.1148
No log	2.8438	182	1.1463	0.4700	1.1463	1.0707
No log	2.875	184	0.8617	0.5935	0.8617	0.9283
No log	2.9062	186	0.6904	0.5997	0.6904	0.8309
No log	2.9375	188	0.6849	0.6090	0.6849	0.8276
No log	2.9688	190	0.6727	0.5984	0.6727	0.8202
No log	3.0	192	0.7207	0.6390	0.7207	0.8489
No log	3.0312	194	0.9381	0.5666	0.9381	0.9685
No log	3.0625	196	0.9936	0.5808	0.9936	0.9968
No log	3.0938	198	0.8763	0.6187	0.8763	0.9361
No log	3.125	200	0.6999	0.6412	0.6999	0.8366
No log	3.1562	202	0.6707	0.6554	0.6707	0.8190
No log	3.1875	204	0.6957	0.6653	0.6957	0.8341
No log	3.2188	206	0.6577	0.6707	0.6577	0.8110
No log	3.25	208	0.6392	0.6895	0.6392	0.7995
No log	3.2812	210	0.7357	0.6255	0.7357	0.8577
No log	3.3125	212	0.8983	0.5912	0.8983	0.9478
No log	3.3438	214	0.8654	0.5785	0.8654	0.9303
No log	3.375	216	0.7017	0.6337	0.7017	0.8377
No log	3.4062	218	0.6282	0.6703	0.6282	0.7926
No log	3.4375	220	0.6440	0.6541	0.6440	0.8025
No log	3.4688	222	0.6203	0.6895	0.6203	0.7876
No log	3.5	224	0.6522	0.6417	0.6522	0.8076
No log	3.5312	226	0.7341	0.6471	0.7341	0.8568
No log	3.5625	228	0.7050	0.625	0.7050	0.8396
No log	3.5938	230	0.6403	0.6484	0.6403	0.8002
No log	3.625	232	0.6026	0.6805	0.6026	0.7763
No log	3.6562	234	0.6902	0.6206	0.6902	0.8308
No log	3.6875	236	0.8255	0.5932	0.8255	0.9086
No log	3.7188	238	0.7669	0.5879	0.7669	0.8757
No log	3.75	240	0.6181	0.6924	0.6181	0.7862
No log	3.7812	242	0.6356	0.6899	0.6356	0.7972
No log	3.8125	244	0.6820	0.6915	0.6820	0.8259
No log	3.8438	246	0.6809	0.6914	0.6809	0.8252
No log	3.875	248	0.6762	0.6824	0.6762	0.8223
No log	3.9062	250	0.6611	0.7079	0.6611	0.8131
No log	3.9375	252	0.6460	0.6807	0.6460	0.8037
No log	3.9688	254	0.6438	0.6660	0.6438	0.8024
No log	4.0	256	0.6473	0.6691	0.6473	0.8046
No log	4.0312	258	0.6612	0.6594	0.6612	0.8132
No log	4.0625	260	0.6784	0.6656	0.6784	0.8237
No log	4.0938	262	0.6644	0.6625	0.6644	0.8151
No log	4.125	264	0.6315	0.6905	0.6315	0.7947
No log	4.1562	266	0.6297	0.6929	0.6297	0.7935
No log	4.1875	268	0.6346	0.7242	0.6346	0.7966
No log	4.2188	270	0.6404	0.7025	0.6404	0.8002
No log	4.25	272	0.7404	0.6874	0.7404	0.8605
No log	4.2812	274	0.8295	0.6403	0.8295	0.9108
No log	4.3125	276	0.7882	0.6619	0.7882	0.8878
No log	4.3438	278	0.7480	0.6817	0.7480	0.8648
No log	4.375	280	0.6995	0.6949	0.6995	0.8364
No log	4.4062	282	0.6960	0.7057	0.6960	0.8343
No log	4.4375	284	0.7023	0.7002	0.7023	0.8381
No log	4.4688	286	0.7530	0.6758	0.7530	0.8678
No log	4.5	288	0.6603	0.7000	0.6603	0.8126
No log	4.5312	290	0.6120	0.7635	0.6120	0.7823
No log	4.5625	292	0.6847	0.7057	0.6847	0.8275
No log	4.5938	294	0.6224	0.7316	0.6224	0.7889
No log	4.625	296	0.6428	0.7276	0.6428	0.8017
No log	4.6562	298	0.7437	0.6925	0.7437	0.8624
No log	4.6875	300	0.6600	0.6907	0.6600	0.8124
No log	4.7188	302	0.5947	0.6749	0.5947	0.7711
No log	4.75	304	0.6178	0.6514	0.6178	0.7860
No log	4.7812	306	0.5978	0.6958	0.5978	0.7732
No log	4.8125	308	0.6592	0.6846	0.6592	0.8119
No log	4.8438	310	0.7244	0.6864	0.7244	0.8511
No log	4.875	312	0.6651	0.7300	0.6651	0.8155
No log	4.9062	314	0.6390	0.7146	0.6390	0.7994
No log	4.9375	316	0.6695	0.7113	0.6695	0.8182
No log	4.9688	318	0.6728	0.6705	0.6728	0.8203
No log	5.0	320	0.6831	0.6603	0.6831	0.8265
No log	5.0312	322	0.6542	0.6798	0.6542	0.8088
No log	5.0625	324	0.6299	0.7079	0.6299	0.7936
No log	5.0938	326	0.6372	0.7076	0.6372	0.7983
No log	5.125	328	0.7059	0.7109	0.7059	0.8402
No log	5.1562	330	0.7525	0.7113	0.7525	0.8674
No log	5.1875	332	0.9028	0.6587	0.9028	0.9502
No log	5.2188	334	0.8105	0.6954	0.8105	0.9003
No log	5.25	336	0.6744	0.7483	0.6744	0.8212
No log	5.2812	338	0.6324	0.7396	0.6324	0.7952
No log	5.3125	340	0.6281	0.7404	0.6281	0.7925
No log	5.3438	342	0.6349	0.7293	0.6349	0.7968
No log	5.375	344	0.6540	0.7203	0.6540	0.8087
No log	5.4062	346	0.7020	0.6939	0.7020	0.8379
No log	5.4375	348	0.7098	0.7016	0.7098	0.8425
No log	5.4688	350	0.6763	0.7205	0.6763	0.8224
No log	5.5	352	0.7202	0.7231	0.7202	0.8487
No log	5.5312	354	0.7148	0.7138	0.7148	0.8455
No log	5.5625	356	0.6836	0.7343	0.6836	0.8268
No log	5.5938	358	0.6754	0.7350	0.6754	0.8218
No log	5.625	360	0.7114	0.7232	0.7114	0.8435
No log	5.6562	362	0.8263	0.6245	0.8263	0.9090
No log	5.6875	364	0.9386	0.5869	0.9386	0.9688
No log	5.7188	366	0.8861	0.5950	0.8861	0.9413
No log	5.75	368	0.8238	0.6336	0.8238	0.9077
No log	5.7812	370	0.7862	0.6523	0.7862	0.8867
No log	5.8125	372	0.8230	0.6646	0.8230	0.9072
No log	5.8438	374	0.8295	0.7018	0.8295	0.9107
No log	5.875	376	0.8658	0.6701	0.8658	0.9305
No log	5.9062	378	1.0030	0.5954	1.0030	1.0015
No log	5.9375	380	1.1044	0.5774	1.1044	1.0509
No log	5.9688	382	1.1745	0.5186	1.1745	1.0838
No log	6.0	384	1.2081	0.4987	1.2081	1.0991
No log	6.0312	386	1.0587	0.5186	1.0587	1.0289
No log	6.0625	388	0.9117	0.5717	0.9117	0.9548
No log	6.0938	390	0.8746	0.5554	0.8746	0.9352
No log	6.125	392	0.8181	0.6050	0.8181	0.9045
No log	6.1562	394	0.8226	0.6455	0.8226	0.9070
No log	6.1875	396	0.9257	0.5789	0.9257	0.9621
No log	6.2188	398	1.1022	0.5435	1.1022	1.0499
No log	6.25	400	1.1173	0.5335	1.1173	1.0570
No log	6.2812	402	0.9122	0.6037	0.9122	0.9551
No log	6.3125	404	0.7143	0.6477	0.7143	0.8452
No log	6.3438	406	0.6645	0.6096	0.6645	0.8152
No log	6.375	408	0.6477	0.6523	0.6477	0.8048
No log	6.4062	410	0.6489	0.7253	0.6489	0.8056
No log	6.4375	412	0.6873	0.7247	0.6873	0.8290
No log	6.4688	414	0.8042	0.6745	0.8042	0.8968
No log	6.5	416	0.9804	0.6291	0.9804	0.9901
No log	6.5312	418	1.0182	0.6167	1.0182	1.0090
No log	6.5625	420	0.9278	0.6288	0.9278	0.9632
No log	6.5938	422	0.8090	0.6299	0.8090	0.8995
No log	6.625	424	0.6970	0.6197	0.6970	0.8349
No log	6.6562	426	0.6498	0.6327	0.6498	0.8061
No log	6.6875	428	0.6575	0.6299	0.6575	0.8108
No log	6.7188	430	0.7276	0.6445	0.7276	0.8530
No log	6.75	432	0.7308	0.6279	0.7308	0.8549
No log	6.7812	434	0.6820	0.6358	0.6820	0.8258
No log	6.8125	436	0.6920	0.6266	0.6920	0.8318
No log	6.8438	438	0.6824	0.6322	0.6824	0.8261
No log	6.875	440	0.7490	0.6389	0.7490	0.8654
No log	6.9062	442	0.7877	0.6289	0.7877	0.8875
No log	6.9375	444	0.7415	0.6684	0.7415	0.8611
No log	6.9688	446	0.7357	0.6749	0.7357	0.8577
No log	7.0	448	0.7327	0.6760	0.7327	0.8560
No log	7.0312	450	0.6611	0.7044	0.6611	0.8131
No log	7.0625	452	0.6257	0.7299	0.6257	0.7910
No log	7.0938	454	0.6421	0.7052	0.6421	0.8013
No log	7.125	456	0.6445	0.6446	0.6445	0.8028
No log	7.1562	458	0.6928	0.6480	0.6928	0.8323
No log	7.1875	460	0.8152	0.6139	0.8152	0.9029
No log	7.2188	462	0.8134	0.6228	0.8134	0.9019
No log	7.25	464	0.7070	0.6614	0.7070	0.8408
No log	7.2812	466	0.6338	0.6836	0.6338	0.7961
No log	7.3125	468	0.6014	0.7292	0.6014	0.7755
No log	7.3438	470	0.5900	0.7356	0.5900	0.7681
No log	7.375	472	0.6294	0.7054	0.6294	0.7934
No log	7.4062	474	0.7646	0.6893	0.7646	0.8744
No log	7.4375	476	0.7724	0.6638	0.7724	0.8789
No log	7.4688	478	0.7149	0.6426	0.7149	0.8455
No log	7.5	480	0.6318	0.6642	0.6318	0.7949
No log	7.5312	482	0.6178	0.6912	0.6178	0.7860
No log	7.5625	484	0.6262	0.6912	0.6262	0.7913
No log	7.5938	486	0.6912	0.6685	0.6912	0.8314
No log	7.625	488	0.7252	0.6485	0.7252	0.8516
No log	7.6562	490	0.7613	0.6498	0.7613	0.8725
No log	7.6875	492	0.7696	0.6402	0.7696	0.8773
No log	7.7188	494	0.8098	0.6202	0.8098	0.8999
No log	7.75	496	0.8061	0.6303	0.8061	0.8978
No log	7.7812	498	0.7796	0.6159	0.7796	0.8829
0.3909	7.8125	500	0.7787	0.6005	0.7787	0.8824
0.3909	7.8438	502	0.7967	0.6083	0.7967	0.8926
0.3909	7.875	504	0.8099	0.6204	0.8099	0.8999
0.3909	7.9062	506	0.8026	0.6222	0.8026	0.8959
0.3909	7.9375	508	0.7431	0.6375	0.7431	0.8620
0.3909	7.9688	510	0.6893	0.6640	0.6893	0.8302
0.3909	8.0	512	0.6718	0.6617	0.6718	0.8197
0.3909	8.0312	514	0.6810	0.6385	0.6810	0.8252
0.3909	8.0625	516	0.6873	0.6640	0.6873	0.8291
0.3909	8.0938	518	0.7210	0.6614	0.7210	0.8491
0.3909	8.125	520	0.7061	0.6516	0.7061	0.8403
0.3909	8.1562	522	0.6814	0.6343	0.6814	0.8255
0.3909	8.1875	524	0.6998	0.6138	0.6998	0.8365
0.3909	8.2188	526	0.7208	0.5821	0.7208	0.8490
0.3909	8.25	528	0.7598	0.5440	0.7598	0.8717
0.3909	8.2812	530	0.8452	0.5957	0.8452	0.9193
0.3909	8.3125	532	0.8708	0.5704	0.8708	0.9332
0.3909	8.3438	534	0.7791	0.6330	0.7791	0.8827
0.3909	8.375	536	0.6752	0.7369	0.6752	0.8217
0.3909	8.4062	538	0.6540	0.7535	0.6540	0.8087
0.3909	8.4375	540	0.6889	0.6865	0.6889	0.8300
0.3909	8.4688	542	0.8010	0.6111	0.8010	0.8950
0.3909	8.5	544	0.8844	0.5600	0.8844	0.9404
0.3909	8.5312	546	0.8488	0.6002	0.8488	0.9213
0.3909	8.5625	548	0.7659	0.5963	0.7659	0.8752
0.3909	8.5938	550	0.7480	0.6273	0.7480	0.8649
0.3909	8.625	552	0.7568	0.6217	0.7568	0.8700
0.3909	8.6562	554	0.7556	0.6046	0.7556	0.8693
0.3909	8.6875	556	0.7891	0.5918	0.7891	0.8883
0.3909	8.7188	558	0.8732	0.5969	0.8732	0.9344
0.3909	8.75	560	0.8613	0.6002	0.8613	0.9281
0.3909	8.7812	562	0.7772	0.5653	0.7772	0.8816
0.3909	8.8125	564	0.7436	0.5930	0.7436	0.8623

Framework versions

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