ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k15_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: 0.9718
• Qwk: 0.5869
• Mse: 0.9718
• Rmse: 0.9858

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	0.0270	2	5.2652	-0.0444	5.2652	2.2946
No log	0.0541	4	3.3296	0.0423	3.3296	1.8247
No log	0.0811	6	3.0388	-0.1004	3.0388	1.7432
No log	0.1081	8	2.8726	-0.1469	2.8726	1.6949
No log	0.1351	10	2.0572	0.0165	2.0572	1.4343
No log	0.1622	12	1.4628	0.1562	1.4628	1.2095
No log	0.1892	14	1.4456	0.1108	1.4456	1.2023
No log	0.2162	16	1.4447	0.1249	1.4447	1.2019
No log	0.2432	18	1.2750	0.2070	1.2750	1.1292
No log	0.2703	20	1.2565	0.2566	1.2565	1.1209
No log	0.2973	22	1.4655	0.0888	1.4655	1.2106
No log	0.3243	24	1.8653	0.0919	1.8653	1.3657
No log	0.3514	26	1.5642	0.1589	1.5642	1.2507
No log	0.3784	28	1.2449	0.2578	1.2449	1.1158
No log	0.4054	30	1.0854	0.2149	1.0854	1.0418
No log	0.4324	32	1.1676	0.1360	1.1676	1.0805
No log	0.4595	34	1.1373	0.1684	1.1373	1.0664
No log	0.4865	36	1.1595	0.2732	1.1595	1.0768
No log	0.5135	38	1.1718	0.2743	1.1718	1.0825
No log	0.5405	40	1.1384	0.2642	1.1384	1.0670
No log	0.5676	42	1.1154	0.1634	1.1154	1.0561
No log	0.5946	44	1.2685	0.0689	1.2685	1.1263
No log	0.6216	46	1.3135	0.0599	1.3135	1.1461
No log	0.6486	48	1.1151	0.2654	1.1151	1.0560
No log	0.6757	50	1.0186	0.3651	1.0186	1.0093
No log	0.7027	52	1.2317	0.2500	1.2317	1.1098
No log	0.7297	54	1.2985	0.2453	1.2985	1.1395
No log	0.7568	56	1.1774	0.3371	1.1774	1.0851
No log	0.7838	58	1.0072	0.3827	1.0072	1.0036
No log	0.8108	60	0.9244	0.3808	0.9244	0.9614
No log	0.8378	62	0.9340	0.4632	0.9340	0.9664
No log	0.8649	64	0.9502	0.4185	0.9502	0.9748
No log	0.8919	66	0.9759	0.5060	0.9759	0.9879
No log	0.9189	68	1.0127	0.4575	1.0127	1.0063
No log	0.9459	70	1.0519	0.4858	1.0519	1.0256
No log	0.9730	72	0.9942	0.4958	0.9942	0.9971
No log	1.0	74	1.0416	0.4580	1.0416	1.0206
No log	1.0270	76	1.2953	0.3881	1.2953	1.1381
No log	1.0541	78	1.5306	0.3673	1.5306	1.2372
No log	1.0811	80	1.5913	0.3250	1.5913	1.2615
No log	1.1081	82	1.3732	0.3498	1.3732	1.1718
No log	1.1351	84	1.1382	0.4477	1.1382	1.0668
No log	1.1622	86	1.0778	0.4645	1.0778	1.0382
No log	1.1892	88	1.0905	0.3802	1.0905	1.0443
No log	1.2162	90	1.0866	0.3918	1.0866	1.0424
No log	1.2432	92	1.2451	0.4255	1.2451	1.1158
No log	1.2703	94	1.6542	0.2941	1.6542	1.2862
No log	1.2973	96	1.8006	0.2779	1.8006	1.3419
No log	1.3243	98	1.4506	0.3622	1.4506	1.2044
No log	1.3514	100	0.9674	0.4839	0.9674	0.9836
No log	1.3784	102	0.9575	0.4317	0.9575	0.9785
No log	1.4054	104	0.8913	0.5028	0.8913	0.9441
No log	1.4324	106	0.8840	0.5955	0.8840	0.9402
No log	1.4595	108	1.0480	0.5065	1.0480	1.0237
No log	1.4865	110	1.0783	0.5167	1.0783	1.0384
No log	1.5135	112	0.8989	0.5904	0.8989	0.9481
No log	1.5405	114	0.7575	0.6524	0.7575	0.8704
No log	1.5676	116	0.8234	0.6440	0.8234	0.9074
No log	1.5946	118	0.8218	0.6107	0.8218	0.9065
No log	1.6216	120	0.7424	0.6372	0.7424	0.8616
No log	1.6486	122	0.7250	0.6079	0.7250	0.8515
No log	1.6757	124	0.7572	0.6248	0.7572	0.8702
No log	1.7027	126	0.7073	0.6037	0.7073	0.8410
No log	1.7297	128	0.7368	0.6116	0.7368	0.8584
No log	1.7568	130	0.7981	0.5778	0.7981	0.8934
No log	1.7838	132	0.7703	0.5695	0.7703	0.8777
No log	1.8108	134	0.7777	0.6069	0.7777	0.8819
No log	1.8378	136	0.7919	0.6044	0.7919	0.8899
No log	1.8649	138	0.8227	0.6084	0.8227	0.9070
No log	1.8919	140	0.7773	0.6183	0.7773	0.8816
No log	1.9189	142	0.7385	0.5862	0.7385	0.8594
No log	1.9459	144	0.7441	0.5758	0.7441	0.8626
No log	1.9730	146	0.8058	0.5668	0.8058	0.8976
No log	2.0	148	0.9510	0.5866	0.9510	0.9752
No log	2.0270	150	0.8616	0.6197	0.8616	0.9282
No log	2.0541	152	0.7507	0.6168	0.7507	0.8665
No log	2.0811	154	0.7219	0.6476	0.7219	0.8497
No log	2.1081	156	0.7561	0.6481	0.7561	0.8696
No log	2.1351	158	0.7985	0.6618	0.7985	0.8936
No log	2.1622	160	0.8175	0.6627	0.8175	0.9042
No log	2.1892	162	0.8304	0.6463	0.8304	0.9113
No log	2.2162	164	0.7916	0.6527	0.7916	0.8897
No log	2.2432	166	0.7655	0.6481	0.7655	0.8749
No log	2.2703	168	0.8235	0.6515	0.8235	0.9075
No log	2.2973	170	0.9389	0.5990	0.9389	0.9689
No log	2.3243	172	0.8947	0.6309	0.8947	0.9459
No log	2.3514	174	0.8178	0.6349	0.8178	0.9043
No log	2.3784	176	0.7999	0.6672	0.7999	0.8944
No log	2.4054	178	0.8184	0.6673	0.8184	0.9047
No log	2.4324	180	0.7988	0.6857	0.7988	0.8938
No log	2.4595	182	0.7845	0.6353	0.7845	0.8857
No log	2.4865	184	0.7963	0.5726	0.7963	0.8924
No log	2.5135	186	0.8010	0.5227	0.8010	0.8950
No log	2.5405	188	0.7986	0.4937	0.7986	0.8936
No log	2.5676	190	0.7727	0.5691	0.7727	0.8791
No log	2.5946	192	0.7417	0.5720	0.7417	0.8612
No log	2.6216	194	0.7224	0.5410	0.7224	0.8499
No log	2.6486	196	0.7038	0.5842	0.7038	0.8389
No log	2.6757	198	0.7033	0.6482	0.7034	0.8387
No log	2.7027	200	0.6940	0.6348	0.6940	0.8331
No log	2.7297	202	0.6820	0.6215	0.6820	0.8258
No log	2.7568	204	0.7310	0.6624	0.7310	0.8550
No log	2.7838	206	0.8913	0.6398	0.8913	0.9441
No log	2.8108	208	0.7910	0.6372	0.7910	0.8894
No log	2.8378	210	0.6743	0.6898	0.6743	0.8212
No log	2.8649	212	0.6695	0.6582	0.6695	0.8182
No log	2.8919	214	0.6673	0.6276	0.6673	0.8169
No log	2.9189	216	0.6722	0.5921	0.6722	0.8199
No log	2.9459	218	0.7111	0.6349	0.7111	0.8433
No log	2.9730	220	0.7604	0.6366	0.7604	0.8720
No log	3.0	222	0.7106	0.6480	0.7106	0.8430
No log	3.0270	224	0.6499	0.7000	0.6499	0.8062
No log	3.0541	226	0.6521	0.6842	0.6521	0.8075
No log	3.0811	228	0.7053	0.6731	0.7053	0.8398
No log	3.1081	230	0.7726	0.6713	0.7726	0.8790
No log	3.1351	232	0.7210	0.6683	0.7210	0.8491
No log	3.1622	234	0.6814	0.6480	0.6814	0.8255
No log	3.1892	236	0.7618	0.5694	0.7618	0.8728
No log	3.2162	238	0.7617	0.5229	0.7617	0.8728
No log	3.2432	240	0.7166	0.5350	0.7166	0.8465
No log	3.2703	242	0.6945	0.5887	0.6945	0.8334
No log	3.2973	244	0.6956	0.6140	0.6956	0.8340
No log	3.3243	246	0.6735	0.6718	0.6735	0.8207
No log	3.3514	248	0.6834	0.6672	0.6834	0.8267
No log	3.3784	250	0.7174	0.6505	0.7174	0.8470
No log	3.4054	252	0.6811	0.6529	0.6811	0.8253
No log	3.4324	254	0.6776	0.6311	0.6776	0.8231
No log	3.4595	256	0.6769	0.5898	0.6769	0.8227
No log	3.4865	258	0.6805	0.5748	0.6805	0.8249
No log	3.5135	260	0.7254	0.6048	0.7254	0.8517
No log	3.5405	262	0.7240	0.6162	0.7240	0.8509
No log	3.5676	264	0.6794	0.6537	0.6794	0.8243
No log	3.5946	266	0.6732	0.6865	0.6732	0.8205
No log	3.6216	268	0.7232	0.6422	0.7232	0.8504
No log	3.6486	270	0.7232	0.6422	0.7232	0.8504
No log	3.6757	272	0.6899	0.6622	0.6899	0.8306
No log	3.7027	274	0.7752	0.6127	0.7752	0.8805
No log	3.7297	276	0.8544	0.5719	0.8544	0.9243
No log	3.7568	278	0.8610	0.5587	0.8610	0.9279
No log	3.7838	280	0.7514	0.6071	0.7514	0.8669
No log	3.8108	282	0.6915	0.6487	0.6915	0.8316
No log	3.8378	284	0.6945	0.6306	0.6945	0.8334
No log	3.8649	286	0.6861	0.6554	0.6861	0.8283
No log	3.8919	288	0.6867	0.6417	0.6867	0.8286
No log	3.9189	290	0.7150	0.6501	0.7150	0.8456
No log	3.9459	292	0.6999	0.6683	0.6999	0.8366
No log	3.9730	294	0.6862	0.6386	0.6862	0.8283
No log	4.0	296	0.7066	0.6561	0.7066	0.8406
No log	4.0270	298	0.7981	0.6395	0.7981	0.8934
No log	4.0541	300	0.8251	0.6414	0.8251	0.9083
No log	4.0811	302	0.8084	0.6475	0.8084	0.8991
No log	4.1081	304	0.8059	0.6417	0.8059	0.8977
No log	4.1351	306	0.7707	0.6477	0.7707	0.8779
No log	4.1622	308	0.7511	0.6440	0.7511	0.8667
No log	4.1892	310	0.7223	0.6436	0.7223	0.8499
No log	4.2162	312	0.7441	0.6157	0.7441	0.8626
No log	4.2432	314	0.7398	0.6147	0.7398	0.8601
No log	4.2703	316	0.6819	0.6366	0.6819	0.8258
No log	4.2973	318	0.6945	0.5807	0.6945	0.8334
No log	4.3243	320	0.7025	0.5689	0.7025	0.8381
No log	4.3514	322	0.6920	0.5926	0.6920	0.8319
No log	4.3784	324	0.6864	0.6598	0.6864	0.8285
No log	4.4054	326	0.6937	0.6585	0.6937	0.8329
No log	4.4324	328	0.7295	0.6301	0.7295	0.8541
No log	4.4595	330	0.8005	0.6134	0.8005	0.8947
No log	4.4865	332	0.7939	0.5952	0.7939	0.8910
No log	4.5135	334	0.7284	0.6291	0.7284	0.8535
No log	4.5405	336	0.7230	0.6055	0.7230	0.8503
No log	4.5676	338	0.7237	0.6388	0.7237	0.8507
No log	4.5946	340	0.7252	0.5951	0.7252	0.8516
No log	4.6216	342	0.7412	0.5712	0.7412	0.8609
No log	4.6486	344	0.7117	0.5660	0.7117	0.8436
No log	4.6757	346	0.7573	0.6164	0.7573	0.8702
No log	4.7027	348	0.8902	0.5853	0.8902	0.9435
No log	4.7297	350	0.8615	0.5892	0.8615	0.9282
No log	4.7568	352	0.7371	0.6381	0.7371	0.8585
No log	4.7838	354	0.7100	0.6424	0.7100	0.8426
No log	4.8108	356	0.7144	0.6689	0.7144	0.8452
No log	4.8378	358	0.7318	0.6340	0.7318	0.8554
No log	4.8649	360	0.9004	0.5892	0.9004	0.9489
No log	4.8919	362	1.0551	0.5706	1.0551	1.0272
No log	4.9189	364	0.9801	0.5892	0.9801	0.9900
No log	4.9459	366	0.7871	0.6003	0.7871	0.8872
No log	4.9730	368	0.7314	0.6301	0.7314	0.8552
No log	5.0	370	0.7333	0.6075	0.7333	0.8563
No log	5.0270	372	0.7813	0.6040	0.7813	0.8839
No log	5.0541	374	0.8672	0.6064	0.8672	0.9312
No log	5.0811	376	0.7973	0.6385	0.7973	0.8929
No log	5.1081	378	0.6893	0.6880	0.6893	0.8302
No log	5.1351	380	0.6884	0.6717	0.6884	0.8297
No log	5.1622	382	0.7580	0.6215	0.7580	0.8706
No log	5.1892	384	0.7114	0.6065	0.7114	0.8435
No log	5.2162	386	0.6948	0.6141	0.6948	0.8335
No log	5.2432	388	0.7157	0.5600	0.7157	0.8460
No log	5.2703	390	0.7132	0.5249	0.7132	0.8445
No log	5.2973	392	0.7094	0.5574	0.7094	0.8422
No log	5.3243	394	0.7140	0.5776	0.7140	0.8450
No log	5.3514	396	0.7340	0.6035	0.7340	0.8568
No log	5.3784	398	0.7185	0.6248	0.7185	0.8476
No log	5.4054	400	0.6567	0.6711	0.6567	0.8103
No log	5.4324	402	0.7595	0.6174	0.7595	0.8715
No log	5.4595	404	0.8770	0.5835	0.8770	0.9365
No log	5.4865	406	0.8379	0.6104	0.8379	0.9153
No log	5.5135	408	0.7214	0.6729	0.7214	0.8494
No log	5.5405	410	0.7043	0.7111	0.7043	0.8392
No log	5.5676	412	0.7252	0.6864	0.7252	0.8516
No log	5.5946	414	0.7630	0.6451	0.7630	0.8735
No log	5.6216	416	0.7382	0.6145	0.7382	0.8592
No log	5.6486	418	0.7065	0.6722	0.7065	0.8406
No log	5.6757	420	0.6929	0.6799	0.6929	0.8324
No log	5.7027	422	0.6884	0.6527	0.6884	0.8297
No log	5.7297	424	0.6949	0.6507	0.6949	0.8336
No log	5.7568	426	0.7127	0.5980	0.7127	0.8442
No log	5.7838	428	0.7278	0.5840	0.7278	0.8531
No log	5.8108	430	0.7144	0.5928	0.7144	0.8452
No log	5.8378	432	0.6882	0.6348	0.6882	0.8296
No log	5.8649	434	0.6866	0.6538	0.6866	0.8286
No log	5.8919	436	0.6830	0.6924	0.6830	0.8264
No log	5.9189	438	0.6818	0.7275	0.6818	0.8257
No log	5.9459	440	0.6803	0.7214	0.6803	0.8248
No log	5.9730	442	0.6957	0.7165	0.6957	0.8341
No log	6.0	444	0.6955	0.7182	0.6955	0.8340
No log	6.0270	446	0.7096	0.6721	0.7096	0.8424
No log	6.0541	448	0.7622	0.6322	0.7622	0.8730
No log	6.0811	450	0.7604	0.6248	0.7604	0.8720
No log	6.1081	452	0.7434	0.6357	0.7434	0.8622
No log	6.1351	454	0.7653	0.6379	0.7653	0.8748
No log	6.1622	456	0.7560	0.6518	0.7560	0.8695
No log	6.1892	458	0.7922	0.6225	0.7922	0.8901
No log	6.2162	460	0.8962	0.6002	0.8962	0.9467
No log	6.2432	462	0.9143	0.5730	0.9143	0.9562
No log	6.2703	464	0.8554	0.5892	0.8554	0.9249
No log	6.2973	466	0.7723	0.5791	0.7723	0.8788
No log	6.3243	468	0.7523	0.5746	0.7523	0.8673
No log	6.3514	470	0.7734	0.6575	0.7734	0.8794
No log	6.3784	472	0.8043	0.6579	0.8043	0.8968
No log	6.4054	474	0.8332	0.6496	0.8332	0.9128
No log	6.4324	476	0.7882	0.6701	0.7882	0.8878
No log	6.4595	478	0.8114	0.6323	0.8114	0.9008
No log	6.4865	480	0.8783	0.5978	0.8783	0.9372
No log	6.5135	482	0.8291	0.6087	0.8291	0.9105
No log	6.5405	484	0.7517	0.6095	0.7517	0.8670
No log	6.5676	486	0.7472	0.6014	0.7472	0.8644
No log	6.5946	488	0.7487	0.6095	0.7487	0.8653
No log	6.6216	490	0.7504	0.6014	0.7504	0.8663
No log	6.6486	492	0.7603	0.5955	0.7603	0.8719
No log	6.6757	494	0.7789	0.5959	0.7789	0.8825
No log	6.7027	496	0.8746	0.5911	0.8746	0.9352
No log	6.7297	498	0.9989	0.5539	0.9989	0.9995
0.4492	6.7568	500	0.9524	0.5869	0.9524	0.9759
0.4492	6.7838	502	0.7769	0.6357	0.7769	0.8814
0.4492	6.8108	504	0.7054	0.6409	0.7054	0.8399
0.4492	6.8378	506	0.7193	0.6239	0.7193	0.8481
0.4492	6.8649	508	0.7224	0.6171	0.7224	0.8499
0.4492	6.8919	510	0.7680	0.5713	0.7680	0.8764
0.4492	6.9189	512	0.7968	0.5783	0.7968	0.8926
0.4492	6.9459	514	0.7274	0.6468	0.7274	0.8529
0.4492	6.9730	516	0.6779	0.6821	0.6779	0.8233
0.4492	7.0	518	0.6765	0.6857	0.6765	0.8225
0.4492	7.0270	520	0.6852	0.6928	0.6852	0.8278
0.4492	7.0541	522	0.6936	0.6928	0.6936	0.8329
0.4492	7.0811	524	0.6945	0.7105	0.6945	0.8333
0.4492	7.1081	526	0.7289	0.6625	0.7289	0.8538
0.4492	7.1351	528	0.7619	0.6098	0.7619	0.8728
0.4492	7.1622	530	0.7632	0.6018	0.7632	0.8736
0.4492	7.1892	532	0.8095	0.6043	0.8095	0.8997
0.4492	7.2162	534	0.9177	0.5757	0.9177	0.9580
0.4492	7.2432	536	1.0416	0.5421	1.0416	1.0206
0.4492	7.2703	538	1.0663	0.5616	1.0663	1.0326
0.4492	7.2973	540	1.0062	0.5679	1.0062	1.0031
0.4492	7.3243	542	0.9718	0.5869	0.9718	0.9858

Framework versions

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