ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k5_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: 0.6368
• Qwk: 0.6658
• Mse: 0.6368
• Rmse: 0.7980

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	0.0769	2	5.1556	-0.0237	5.1556	2.2706
No log	0.1538	4	3.2734	0.0160	3.2734	1.8092
No log	0.2308	6	2.2304	-0.0318	2.2304	1.4935
No log	0.3077	8	1.3465	0.2250	1.3465	1.1604
No log	0.3846	10	1.1781	0.2215	1.1781	1.0854
No log	0.4615	12	1.3354	0.0989	1.3354	1.1556
No log	0.5385	14	1.6160	0.0598	1.6160	1.2712
No log	0.6154	16	1.5811	0.1111	1.5811	1.2574
No log	0.6923	18	1.8612	0.0852	1.8612	1.3643
No log	0.7692	20	1.7221	0.1383	1.7221	1.3123
No log	0.8462	22	1.0020	0.3452	1.0020	1.0010
No log	0.9231	24	0.9195	0.3630	0.9195	0.9589
No log	1.0	26	1.2968	0.3424	1.2968	1.1388
No log	1.0769	28	2.0704	0.2487	2.0704	1.4389
No log	1.1538	30	1.8562	0.2394	1.8562	1.3624
No log	1.2308	32	1.1964	0.3659	1.1964	1.0938
No log	1.3077	34	0.8259	0.4834	0.8259	0.9088
No log	1.3846	36	0.7943	0.4979	0.7943	0.8912
No log	1.4615	38	0.8181	0.4700	0.8181	0.9045
No log	1.5385	40	1.0798	0.3765	1.0798	1.0391
No log	1.6154	42	1.3894	0.1948	1.3894	1.1787
No log	1.6923	44	1.3896	0.1641	1.3896	1.1788
No log	1.7692	46	1.2301	0.2768	1.2301	1.1091
No log	1.8462	48	0.8847	0.5180	0.8847	0.9406
No log	1.9231	50	0.7557	0.5798	0.7557	0.8693
No log	2.0	52	0.7141	0.5844	0.7141	0.8451
No log	2.0769	54	0.7126	0.6226	0.7126	0.8441
No log	2.1538	56	0.7633	0.6383	0.7633	0.8737
No log	2.2308	58	1.0474	0.5088	1.0474	1.0234
No log	2.3077	60	1.0246	0.5626	1.0246	1.0122
No log	2.3846	62	0.7609	0.6228	0.7609	0.8723
No log	2.4615	64	0.7346	0.6446	0.7346	0.8571
No log	2.5385	66	0.7192	0.6441	0.7192	0.8481
No log	2.6154	68	0.7847	0.5458	0.7847	0.8858
No log	2.6923	70	0.7851	0.5458	0.7851	0.8860
No log	2.7692	72	0.7210	0.6253	0.7210	0.8491
No log	2.8462	74	0.7921	0.5990	0.7921	0.8900
No log	2.9231	76	1.0806	0.5091	1.0806	1.0395
No log	3.0	78	0.9765	0.5464	0.9765	0.9882
No log	3.0769	80	0.6940	0.6371	0.6940	0.8331
No log	3.1538	82	0.7148	0.6528	0.7148	0.8454
No log	3.2308	84	0.6943	0.6575	0.6943	0.8332
No log	3.3077	86	0.8046	0.6400	0.8046	0.8970
No log	3.3846	88	0.7758	0.6469	0.7758	0.8808
No log	3.4615	90	0.7614	0.6701	0.7614	0.8726
No log	3.5385	92	0.8661	0.5902	0.8661	0.9307
No log	3.6154	94	0.7830	0.6533	0.7830	0.8848
No log	3.6923	96	0.7857	0.6260	0.7857	0.8864
No log	3.7692	98	1.1371	0.4971	1.1371	1.0663
No log	3.8462	100	1.0642	0.4943	1.0642	1.0316
No log	3.9231	102	0.8310	0.5806	0.8310	0.9116
No log	4.0	104	0.7417	0.5892	0.7417	0.8612
No log	4.0769	106	0.8395	0.5847	0.8395	0.9162
No log	4.1538	108	0.7225	0.5575	0.7225	0.8500
No log	4.2308	110	0.6902	0.6808	0.6902	0.8308
No log	4.3077	112	1.1172	0.4815	1.1172	1.0570
No log	4.3846	114	1.1755	0.4410	1.1755	1.0842
No log	4.4615	116	0.8007	0.6545	0.8007	0.8948
No log	4.5385	118	0.6765	0.6795	0.6765	0.8225
No log	4.6154	120	0.9752	0.5619	0.9752	0.9875
No log	4.6923	122	0.9811	0.5646	0.9811	0.9905
No log	4.7692	124	0.7440	0.6326	0.7440	0.8626
No log	4.8462	126	0.6754	0.6851	0.6754	0.8219
No log	4.9231	128	0.7523	0.6600	0.7523	0.8674
No log	5.0	130	0.7719	0.6449	0.7719	0.8786
No log	5.0769	132	0.6646	0.7001	0.6646	0.8152
No log	5.1538	134	0.6800	0.6367	0.6800	0.8246
No log	5.2308	136	0.7296	0.6058	0.7296	0.8542
No log	5.3077	138	0.6591	0.6468	0.6591	0.8118
No log	5.3846	140	0.6502	0.6701	0.6502	0.8063
No log	5.4615	142	0.6606	0.6603	0.6606	0.8127
No log	5.5385	144	0.6349	0.6757	0.6349	0.7968
No log	5.6154	146	0.6591	0.6736	0.6591	0.8118
No log	5.6923	148	0.7212	0.6575	0.7212	0.8492
No log	5.7692	150	0.6657	0.6890	0.6657	0.8159
No log	5.8462	152	0.6563	0.6657	0.6563	0.8101
No log	5.9231	154	0.6904	0.6133	0.6904	0.8309
No log	6.0	156	0.6544	0.6691	0.6544	0.8089
No log	6.0769	158	0.6736	0.6693	0.6736	0.8207
No log	6.1538	160	0.6806	0.6704	0.6806	0.8250
No log	6.2308	162	0.6797	0.6889	0.6797	0.8245
No log	6.3077	164	0.7096	0.6468	0.7096	0.8424
No log	6.3846	166	0.6964	0.6947	0.6964	0.8345
No log	6.4615	168	0.6838	0.6992	0.6838	0.8269
No log	6.5385	170	0.6721	0.6638	0.6721	0.8198
No log	6.6154	172	0.7232	0.6406	0.7232	0.8504
No log	6.6923	174	0.7394	0.6295	0.7394	0.8599
No log	6.7692	176	0.6576	0.6556	0.6576	0.8109
No log	6.8462	178	0.6600	0.6937	0.6600	0.8124
No log	6.9231	180	0.6744	0.6897	0.6744	0.8212
No log	7.0	182	0.6950	0.6952	0.6950	0.8337
No log	7.0769	184	0.7107	0.7075	0.7107	0.8430
No log	7.1538	186	0.7018	0.7117	0.7018	0.8377
No log	7.2308	188	0.6847	0.7166	0.6847	0.8275
No log	7.3077	190	0.6551	0.7054	0.6551	0.8094
No log	7.3846	192	0.6241	0.6968	0.6241	0.7900
No log	7.4615	194	0.6235	0.7227	0.6235	0.7896
No log	7.5385	196	0.6638	0.6193	0.6638	0.8147
No log	7.6154	198	0.6604	0.6000	0.6604	0.8127
No log	7.6923	200	0.6510	0.6246	0.6510	0.8068
No log	7.7692	202	0.6289	0.6799	0.6289	0.7931
No log	7.8462	204	0.6397	0.7060	0.6397	0.7998
No log	7.9231	206	0.6826	0.7011	0.6826	0.8262
No log	8.0	208	0.6730	0.6866	0.6730	0.8204
No log	8.0769	210	0.6734	0.6749	0.6734	0.8206
No log	8.1538	212	0.6810	0.6702	0.6810	0.8252
No log	8.2308	214	0.6625	0.6821	0.6625	0.8140
No log	8.3077	216	0.7156	0.6654	0.7156	0.8459
No log	8.3846	218	0.7710	0.6060	0.7710	0.8781
No log	8.4615	220	0.6879	0.6386	0.6879	0.8294
No log	8.5385	222	0.6576	0.6705	0.6576	0.8110
No log	8.6154	224	0.7509	0.6019	0.7509	0.8665
No log	8.6923	226	0.9663	0.5429	0.9663	0.9830
No log	8.7692	228	1.0024	0.5251	1.0024	1.0012
No log	8.8462	230	0.8169	0.6050	0.8169	0.9038
No log	8.9231	232	0.6819	0.6567	0.6819	0.8258
No log	9.0	234	0.7036	0.6393	0.7036	0.8388
No log	9.0769	236	0.7527	0.6576	0.7527	0.8676
No log	9.1538	238	0.6921	0.6598	0.6921	0.8320
No log	9.2308	240	0.7423	0.6431	0.7423	0.8616
No log	9.3077	242	0.8932	0.5960	0.8932	0.9451
No log	9.3846	244	0.8331	0.6119	0.8331	0.9128
No log	9.4615	246	0.6992	0.7014	0.6992	0.8362
No log	9.5385	248	0.7707	0.6646	0.7707	0.8779
No log	9.6154	250	0.8743	0.5889	0.8743	0.9350
No log	9.6923	252	0.7707	0.6627	0.7707	0.8779
No log	9.7692	254	0.6798	0.7306	0.6798	0.8245
No log	9.8462	256	0.7045	0.6848	0.7045	0.8394
No log	9.9231	258	0.6975	0.6968	0.6975	0.8352
No log	10.0	260	0.7285	0.6635	0.7285	0.8535
No log	10.0769	262	0.7047	0.6358	0.7047	0.8395
No log	10.1538	264	0.6963	0.6215	0.6963	0.8345
No log	10.2308	266	0.7344	0.6340	0.7344	0.8570
No log	10.3077	268	0.8998	0.5704	0.8998	0.9486
No log	10.3846	270	0.9656	0.5457	0.9656	0.9826
No log	10.4615	272	0.8231	0.6158	0.8231	0.9072
No log	10.5385	274	0.6550	0.6704	0.6550	0.8093
No log	10.6154	276	0.6187	0.6980	0.6187	0.7866
No log	10.6923	278	0.6231	0.6996	0.6231	0.7893
No log	10.7692	280	0.6922	0.6758	0.6922	0.8320
No log	10.8462	282	0.7735	0.6216	0.7735	0.8795
No log	10.9231	284	0.7066	0.6606	0.7066	0.8406
No log	11.0	286	0.6586	0.6956	0.6586	0.8115
No log	11.0769	288	0.6645	0.6840	0.6645	0.8151
No log	11.1538	290	0.6427	0.7042	0.6427	0.8017
No log	11.2308	292	0.6377	0.7141	0.6377	0.7985
No log	11.3077	294	0.6479	0.6742	0.6479	0.8049
No log	11.3846	296	0.6559	0.6916	0.6559	0.8099
No log	11.4615	298	0.6685	0.6780	0.6685	0.8176
No log	11.5385	300	0.6921	0.6662	0.6921	0.8319
No log	11.6154	302	0.7255	0.6394	0.7255	0.8518
No log	11.6923	304	0.6856	0.6601	0.6856	0.8280
No log	11.7692	306	0.6487	0.7193	0.6487	0.8054
No log	11.8462	308	0.7043	0.6862	0.7043	0.8392
No log	11.9231	310	0.7327	0.6676	0.7327	0.8560
No log	12.0	312	0.7616	0.6873	0.7616	0.8727
No log	12.0769	314	0.7949	0.7068	0.7949	0.8916
No log	12.1538	316	0.7998	0.6932	0.7998	0.8943
No log	12.2308	318	0.7364	0.6603	0.7364	0.8582
No log	12.3077	320	0.6874	0.6977	0.6874	0.8291
No log	12.3846	322	0.6804	0.6861	0.6804	0.8249
No log	12.4615	324	0.6852	0.6729	0.6852	0.8278
No log	12.5385	326	0.7217	0.6505	0.7217	0.8495
No log	12.6154	328	0.7831	0.5885	0.7831	0.8849
No log	12.6923	330	0.7485	0.6635	0.7485	0.8651
No log	12.7692	332	0.6639	0.6878	0.6639	0.8148
No log	12.8462	334	0.6925	0.6563	0.6925	0.8322
No log	12.9231	336	0.6983	0.6605	0.6983	0.8356
No log	13.0	338	0.6668	0.6531	0.6668	0.8166
No log	13.0769	340	0.6660	0.6423	0.6660	0.8161
No log	13.1538	342	0.6746	0.6200	0.6746	0.8213
No log	13.2308	344	0.6811	0.6381	0.6811	0.8253
No log	13.3077	346	0.6803	0.6150	0.6803	0.8248
No log	13.3846	348	0.6701	0.6661	0.6701	0.8186
No log	13.4615	350	0.6964	0.6776	0.6964	0.8345
No log	13.5385	352	0.6618	0.6592	0.6618	0.8135
No log	13.6154	354	0.6397	0.7061	0.6397	0.7998
No log	13.6923	356	0.6616	0.6955	0.6616	0.8134
No log	13.7692	358	0.6516	0.6893	0.6516	0.8072
No log	13.8462	360	0.6367	0.7195	0.6367	0.7980
No log	13.9231	362	0.6163	0.7165	0.6163	0.7851
No log	14.0	364	0.6288	0.7168	0.6288	0.7930
No log	14.0769	366	0.6264	0.7245	0.6264	0.7915
No log	14.1538	368	0.6149	0.7170	0.6149	0.7842
No log	14.2308	370	0.6164	0.7167	0.6164	0.7851
No log	14.3077	372	0.6011	0.7115	0.6011	0.7753
No log	14.3846	374	0.5936	0.7123	0.5936	0.7704
No log	14.4615	376	0.5997	0.7139	0.5997	0.7744
No log	14.5385	378	0.6184	0.7066	0.6184	0.7864
No log	14.6154	380	0.6484	0.6686	0.6484	0.8053
No log	14.6923	382	0.7118	0.6292	0.7118	0.8437
No log	14.7692	384	0.6908	0.6377	0.6908	0.8311
No log	14.8462	386	0.6126	0.7212	0.6126	0.7827
No log	14.9231	388	0.5927	0.7201	0.5927	0.7699
No log	15.0	390	0.6182	0.6992	0.6182	0.7863
No log	15.0769	392	0.6249	0.6979	0.6249	0.7905
No log	15.1538	394	0.6135	0.7369	0.6135	0.7833
No log	15.2308	396	0.6648	0.7263	0.6648	0.8153
No log	15.3077	398	0.6901	0.7098	0.6901	0.8307
No log	15.3846	400	0.6186	0.7294	0.6186	0.7865
No log	15.4615	402	0.5932	0.7167	0.5932	0.7702
No log	15.5385	404	0.5989	0.6863	0.5989	0.7739
No log	15.6154	406	0.5863	0.7187	0.5863	0.7657
No log	15.6923	408	0.5976	0.7427	0.5976	0.7730
No log	15.7692	410	0.6390	0.7348	0.6390	0.7994
No log	15.8462	412	0.6696	0.7186	0.6696	0.8183
No log	15.9231	414	0.6314	0.7134	0.6314	0.7946
No log	16.0	416	0.6062	0.7165	0.6062	0.7786
No log	16.0769	418	0.6271	0.7135	0.6271	0.7919
No log	16.1538	420	0.6199	0.7067	0.6199	0.7873
No log	16.2308	422	0.6406	0.7018	0.6406	0.8004
No log	16.3077	424	0.7361	0.6753	0.7361	0.8579
No log	16.3846	426	0.7324	0.6841	0.7324	0.8558
No log	16.4615	428	0.6740	0.6997	0.6740	0.8210
No log	16.5385	430	0.6435	0.6942	0.6435	0.8022
No log	16.6154	432	0.6167	0.7260	0.6167	0.7853
No log	16.6923	434	0.6120	0.7163	0.6120	0.7823
No log	16.7692	436	0.6352	0.7163	0.6352	0.7970
No log	16.8462	438	0.7072	0.6747	0.7072	0.8409
No log	16.9231	440	0.7579	0.6487	0.7579	0.8706
No log	17.0	442	0.7434	0.6354	0.7434	0.8622
No log	17.0769	444	0.7014	0.6419	0.7014	0.8375
No log	17.1538	446	0.6905	0.6487	0.6905	0.8310
No log	17.2308	448	0.7057	0.6426	0.7057	0.8401
No log	17.3077	450	0.7247	0.6381	0.7247	0.8513
No log	17.3846	452	0.6953	0.6596	0.6953	0.8339
No log	17.4615	454	0.6193	0.7230	0.6193	0.7870
No log	17.5385	456	0.6151	0.7169	0.6151	0.7843
No log	17.6154	458	0.6332	0.6935	0.6332	0.7958
No log	17.6923	460	0.6883	0.6675	0.6883	0.8297
No log	17.7692	462	0.7105	0.6409	0.7105	0.8429
No log	17.8462	464	0.6826	0.6499	0.6826	0.8262
No log	17.9231	466	0.6507	0.6628	0.6507	0.8066
No log	18.0	468	0.6471	0.6916	0.6471	0.8044
No log	18.0769	470	0.6426	0.6805	0.6426	0.8016
No log	18.1538	472	0.6503	0.6996	0.6503	0.8064
No log	18.2308	474	0.7234	0.6906	0.7234	0.8506
No log	18.3077	476	0.7787	0.6890	0.7787	0.8824
No log	18.3846	478	0.7463	0.6886	0.7463	0.8639
No log	18.4615	480	0.6795	0.7029	0.6795	0.8243
No log	18.5385	482	0.6929	0.7073	0.6929	0.8324
No log	18.6154	484	0.7122	0.6843	0.7122	0.8439
No log	18.6923	486	0.6722	0.6657	0.6722	0.8199
No log	18.7692	488	0.6450	0.7022	0.6450	0.8031
No log	18.8462	490	0.6827	0.6707	0.6827	0.8262
No log	18.9231	492	0.7450	0.6465	0.7450	0.8631
No log	19.0	494	0.7640	0.6434	0.7640	0.8741
No log	19.0769	496	0.7395	0.6465	0.7395	0.8599
No log	19.1538	498	0.6799	0.6674	0.6799	0.8245
0.3817	19.2308	500	0.6528	0.6835	0.6528	0.8080
0.3817	19.3077	502	0.6706	0.6362	0.6706	0.8189
0.3817	19.3846	504	0.6647	0.6656	0.6647	0.8153
0.3817	19.4615	506	0.6392	0.6819	0.6392	0.7995
0.3817	19.5385	508	0.6428	0.7008	0.6428	0.8017
0.3817	19.6154	510	0.6407	0.7008	0.6407	0.8004
0.3817	19.6923	512	0.6526	0.7008	0.6526	0.8078
0.3817	19.7692	514	0.6498	0.6965	0.6498	0.8061
0.3817	19.8462	516	0.6514	0.6969	0.6514	0.8071
0.3817	19.9231	518	0.6236	0.6815	0.6236	0.7897
0.3817	20.0	520	0.6129	0.6879	0.6129	0.7829
0.3817	20.0769	522	0.6181	0.6733	0.6181	0.7862
0.3817	20.1538	524	0.6151	0.6936	0.6151	0.7843
0.3817	20.2308	526	0.6222	0.6508	0.6222	0.7888
0.3817	20.3077	528	0.6437	0.6674	0.6437	0.8023
0.3817	20.3846	530	0.6371	0.6694	0.6371	0.7982
0.3817	20.4615	532	0.6166	0.6844	0.6166	0.7852
0.3817	20.5385	534	0.6109	0.6691	0.6109	0.7816
0.3817	20.6154	536	0.6186	0.6576	0.6186	0.7865
0.3817	20.6923	538	0.6318	0.6513	0.6318	0.7948
0.3817	20.7692	540	0.6298	0.6535	0.6298	0.7936
0.3817	20.8462	542	0.6368	0.6658	0.6368	0.7980

Framework versions

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