ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k8_task3_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: 0.6326
• Qwk: 0.3089
• Mse: 0.6326
• Rmse: 0.7953

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0417	2	5.6379	-0.0428	5.6379	2.3744
No log	0.0833	4	2.7389	0.0017	2.7389	1.6550
No log	0.125	6	2.5429	0.0400	2.5429	1.5946
No log	0.1667	8	1.7050	-0.0361	1.7050	1.3058
No log	0.2083	10	0.7277	-0.0818	0.7277	0.8530
No log	0.25	12	0.9553	0.0288	0.9553	0.9774
No log	0.2917	14	1.1141	0.0	1.1141	1.0555
No log	0.3333	16	1.0405	0.0	1.0405	1.0201
No log	0.375	18	1.1250	0.0	1.1250	1.0606
No log	0.4167	20	0.8803	-0.0970	0.8803	0.9383
No log	0.4583	22	0.6704	0.0725	0.6704	0.8188
No log	0.5	24	0.8786	-0.0370	0.8786	0.9373
No log	0.5417	26	1.6968	0.0	1.6968	1.3026
No log	0.5833	28	1.6507	0.0	1.6507	1.2848
No log	0.625	30	1.0132	0.0431	1.0132	1.0066
No log	0.6667	32	0.7105	0.0256	0.7105	0.8429
No log	0.7083	34	0.7385	-0.0058	0.7385	0.8594
No log	0.75	36	0.8910	-0.0216	0.8910	0.9439
No log	0.7917	38	1.0724	0.0	1.0724	1.0356
No log	0.8333	40	0.8702	0.0038	0.8702	0.9329
No log	0.875	42	0.7381	0.0545	0.7381	0.8591
No log	0.9167	44	1.3100	0.0345	1.3100	1.1445
No log	0.9583	46	2.9128	0.0227	2.9128	1.7067
No log	1.0	48	2.6590	0.0239	2.6590	1.6306
No log	1.0417	50	1.5008	0.0	1.5008	1.2251
No log	1.0833	52	1.0517	0.0698	1.0517	1.0255
No log	1.125	54	0.8078	0.0798	0.8078	0.8988
No log	1.1667	56	0.6390	0.0476	0.6390	0.7994
No log	1.2083	58	0.7022	0.0476	0.7022	0.8380
No log	1.25	60	0.6233	0.1467	0.6233	0.7895
No log	1.2917	62	0.9746	0.0894	0.9746	0.9872
No log	1.3333	64	1.2341	0.0698	1.2341	1.1109
No log	1.375	66	1.5424	-0.0036	1.5424	1.2419
No log	1.4167	68	1.4219	-0.0036	1.4219	1.1924
No log	1.4583	70	0.8953	-0.1171	0.8953	0.9462
No log	1.5	72	0.7435	-0.0115	0.7435	0.8623
No log	1.5417	74	0.8812	-0.0704	0.8812	0.9387
No log	1.5833	76	0.7989	-0.0273	0.7989	0.8938
No log	1.625	78	0.6538	0.1884	0.6538	0.8086
No log	1.6667	80	0.7163	-0.0058	0.7163	0.8463
No log	1.7083	82	0.6811	0.1138	0.6811	0.8253
No log	1.75	84	0.6639	0.2329	0.6639	0.8148
No log	1.7917	86	0.7296	0.1138	0.7296	0.8542
No log	1.8333	88	1.1609	0.0476	1.1609	1.0775
No log	1.875	90	1.0065	-0.0079	1.0065	1.0033
No log	1.9167	92	0.7140	0.2611	0.7140	0.8450
No log	1.9583	94	0.7133	0.3208	0.7133	0.8446
No log	2.0	96	0.6883	0.3067	0.6883	0.8296
No log	2.0417	98	0.7740	0.0157	0.7740	0.8797
No log	2.0833	100	0.7645	0.0955	0.7645	0.8743
No log	2.125	102	0.7805	0.1287	0.7805	0.8835
No log	2.1667	104	0.8145	0.1691	0.8145	0.9025
No log	2.2083	106	0.7641	0.1691	0.7641	0.8741
No log	2.25	108	0.6684	0.2273	0.6684	0.8176
No log	2.2917	110	0.6464	0.2857	0.6464	0.8040
No log	2.3333	112	0.6413	0.2542	0.6413	0.8008
No log	2.375	114	0.6622	0.2914	0.6622	0.8137
No log	2.4167	116	0.9633	0.0519	0.9633	0.9815
No log	2.4583	118	0.7319	0.1753	0.7319	0.8555
No log	2.5	120	0.9662	0.1261	0.9662	0.9830
No log	2.5417	122	1.6331	0.1342	1.6331	1.2779
No log	2.5833	124	1.1847	0.1834	1.1847	1.0884
No log	2.625	126	0.7003	0.2350	0.7003	0.8369
No log	2.6667	128	0.7032	0.2000	0.7032	0.8385
No log	2.7083	130	0.7325	0.1568	0.7325	0.8559
No log	2.75	132	0.6601	0.2457	0.6601	0.8125
No log	2.7917	134	0.6879	0.3862	0.6879	0.8294
No log	2.8333	136	0.7886	0.1925	0.7886	0.8880
No log	2.875	138	0.6653	0.3402	0.6653	0.8157
No log	2.9167	140	0.6325	0.2179	0.6325	0.7953
No log	2.9583	142	0.7304	0.1287	0.7304	0.8546
No log	3.0	144	0.6632	0.2174	0.6632	0.8144
No log	3.0417	146	0.6609	0.3990	0.6609	0.8129
No log	3.0833	148	0.7078	0.2083	0.7078	0.8413
No log	3.125	150	0.7570	0.1683	0.7570	0.8701
No log	3.1667	152	0.9143	0.0826	0.9143	0.9562
No log	3.2083	154	1.1771	0.1777	1.1771	1.0849
No log	3.25	156	0.9174	0.1588	0.9174	0.9578
No log	3.2917	158	0.8516	0.2212	0.8516	0.9228
No log	3.3333	160	0.9214	0.1228	0.9214	0.9599
No log	3.375	162	0.9629	0.0933	0.9629	0.9813
No log	3.4167	164	0.8285	0.1776	0.8285	0.9102
No log	3.4583	166	0.8256	0.2074	0.8256	0.9086
No log	3.5	168	0.8242	0.2239	0.8242	0.9079
No log	3.5417	170	0.8163	0.2563	0.8163	0.9035
No log	3.5833	172	0.8788	0.1050	0.8788	0.9375
No log	3.625	174	0.8760	0.0857	0.8760	0.9360
No log	3.6667	176	0.7995	0.1028	0.7995	0.8941
No log	3.7083	178	0.7144	0.2593	0.7144	0.8452
No log	3.75	180	0.7189	0.2000	0.7189	0.8479
No log	3.7917	182	0.7284	0.1683	0.7284	0.8535
No log	3.8333	184	0.7231	0.1515	0.7231	0.8503
No log	3.875	186	0.7595	0.1469	0.7595	0.8715
No log	3.9167	188	0.7514	0.1388	0.7514	0.8668
No log	3.9583	190	0.7380	0.1841	0.7380	0.8591
No log	4.0	192	0.7845	0.2857	0.7845	0.8857
No log	4.0417	194	0.7458	0.2780	0.7458	0.8636
No log	4.0833	196	0.7568	0.1133	0.7568	0.8700
No log	4.125	198	0.7530	0.3010	0.7530	0.8677
No log	4.1667	200	0.7337	0.2432	0.7337	0.8566
No log	4.2083	202	0.7066	0.2787	0.7066	0.8406
No log	4.25	204	0.7669	0.1373	0.7669	0.8757
No log	4.2917	206	0.9130	0.1336	0.9130	0.9555
No log	4.3333	208	0.7981	0.1610	0.7981	0.8934
No log	4.375	210	0.8189	0.1443	0.8189	0.9049
No log	4.4167	212	0.8430	0.0493	0.8430	0.9181
No log	4.4583	214	1.0480	0.1245	1.0480	1.0237
No log	4.5	216	1.0918	0.1020	1.0918	1.0449
No log	4.5417	218	0.9699	0.1304	0.9699	0.9848
No log	4.5833	220	0.7810	0.1469	0.7810	0.8837
No log	4.625	222	0.8013	0.2153	0.8013	0.8951
No log	4.6667	224	0.7387	0.2766	0.7387	0.8595
No log	4.7083	226	0.7349	0.1841	0.7349	0.8573
No log	4.75	228	0.8309	0.1481	0.8309	0.9116
No log	4.7917	230	0.7140	0.2000	0.7140	0.8450
No log	4.8333	232	0.6365	0.2857	0.6365	0.7978
No log	4.875	234	0.6826	0.2917	0.6826	0.8262
No log	4.9167	236	0.6330	0.3412	0.6330	0.7956
No log	4.9583	238	0.6499	0.2967	0.6499	0.8061
No log	5.0	240	0.6547	0.2967	0.6547	0.8092
No log	5.0417	242	0.7960	0.1776	0.7961	0.8922
No log	5.0833	244	0.8242	0.1776	0.8242	0.9079
No log	5.125	246	0.7138	0.1429	0.7138	0.8449
No log	5.1667	248	0.7125	0.2000	0.7125	0.8441
No log	5.2083	250	0.7709	0.1600	0.7709	0.8780
No log	5.25	252	0.7473	0.1759	0.7473	0.8645
No log	5.2917	254	0.7403	0.2081	0.7403	0.8604
No log	5.3333	256	0.9812	0.0769	0.9812	0.9905
No log	5.375	258	0.9370	0.0667	0.9370	0.9680
No log	5.4167	260	0.7257	0.2787	0.7257	0.8519
No log	5.4583	262	0.7571	0.2990	0.7571	0.8701
No log	5.5	264	0.7244	0.2727	0.7244	0.8511
No log	5.5417	266	0.7144	0.2787	0.7144	0.8453
No log	5.5833	268	0.7825	0.1590	0.7825	0.8846
No log	5.625	270	0.7521	0.1357	0.7521	0.8672
No log	5.6667	272	0.7118	0.1658	0.7118	0.8437
No log	5.7083	274	0.6896	0.2593	0.6896	0.8304
No log	5.75	276	0.7048	0.2593	0.7048	0.8395
No log	5.7917	278	0.7242	0.2842	0.7242	0.8510
No log	5.8333	280	0.7160	0.2258	0.7160	0.8462
No log	5.875	282	0.7142	0.1832	0.7142	0.8451
No log	5.9167	284	0.7051	0.1832	0.7051	0.8397
No log	5.9583	286	0.7277	0.1414	0.7277	0.8530
No log	6.0	288	0.7344	0.1568	0.7344	0.8570
No log	6.0417	290	0.6772	0.2360	0.6772	0.8229
No log	6.0833	292	0.7015	0.2090	0.7015	0.8376
No log	6.125	294	0.7131	0.1828	0.7131	0.8444
No log	6.1667	296	0.6720	0.1908	0.6720	0.8197
No log	6.2083	298	0.7045	0.1913	0.7045	0.8394
No log	6.25	300	0.7762	0.1732	0.7762	0.8810
No log	6.2917	302	0.7064	0.2000	0.7064	0.8405
No log	6.3333	304	0.6609	0.2471	0.6609	0.8130
No log	6.375	306	0.7919	0.1416	0.7919	0.8899
No log	6.4167	308	0.8161	0.1289	0.8161	0.9034
No log	6.4583	310	0.7020	0.1638	0.7020	0.8379
No log	6.5	312	0.6794	0.2683	0.6794	0.8243
No log	6.5417	314	0.7135	0.2000	0.7135	0.8447
No log	6.5833	316	0.6858	0.2727	0.6858	0.8281
No log	6.625	318	0.6567	0.2683	0.6567	0.8103
No log	6.6667	320	0.6625	0.2941	0.6625	0.8139
No log	6.7083	322	0.6630	0.2575	0.6630	0.8143
No log	6.75	324	0.7008	0.2174	0.7008	0.8371
No log	6.7917	326	0.7476	0.1832	0.7476	0.8647
No log	6.8333	328	0.7950	0.2000	0.7950	0.8916
No log	6.875	330	0.7582	0.1915	0.7582	0.8708
No log	6.9167	332	0.6927	0.2083	0.6927	0.8323
No log	6.9583	334	0.6657	0.2471	0.6657	0.8159
No log	7.0	336	0.6504	0.2471	0.6504	0.8065
No log	7.0417	338	0.6267	0.2575	0.6267	0.7917
No log	7.0833	340	0.6504	0.2941	0.6504	0.8065
No log	7.125	342	0.6709	0.2663	0.6709	0.8191
No log	7.1667	344	0.6581	0.2289	0.6581	0.8112
No log	7.2083	346	0.5970	0.3158	0.5970	0.7726
No log	7.25	348	0.5782	0.2970	0.5782	0.7604
No log	7.2917	350	0.6455	0.2809	0.6455	0.8034
No log	7.3333	352	0.7137	0.2381	0.7137	0.8448
No log	7.375	354	0.6947	0.2239	0.6947	0.8335
No log	7.4167	356	0.6159	0.2184	0.6159	0.7848
No log	7.4583	358	0.6316	0.35	0.6316	0.7948
No log	7.5	360	0.8156	0.1064	0.8156	0.9031
No log	7.5417	362	0.9074	0.0924	0.9074	0.9525
No log	7.5833	364	0.8381	0.0385	0.8381	0.9155
No log	7.625	366	0.7124	0.2090	0.7124	0.8440
No log	7.6667	368	0.6233	0.2683	0.6233	0.7895
No log	7.7083	370	0.6281	0.2513	0.6281	0.7925
No log	7.75	372	0.6341	0.2513	0.6341	0.7963
No log	7.7917	374	0.6362	0.2766	0.6362	0.7976
No log	7.8333	376	0.6731	0.2360	0.6731	0.8204
No log	7.875	378	0.6693	0.2360	0.6693	0.8181
No log	7.9167	380	0.6476	0.2273	0.6476	0.8047
No log	7.9583	382	0.6266	0.3136	0.6266	0.7916
No log	8.0	384	0.6229	0.3043	0.6229	0.7893
No log	8.0417	386	0.6295	0.2941	0.6295	0.7934
No log	8.0833	388	0.6350	0.2967	0.6350	0.7969
No log	8.125	390	0.6206	0.2967	0.6206	0.7878
No log	8.1667	392	0.6204	0.2967	0.6204	0.7877
No log	8.2083	394	0.6090	0.2857	0.6090	0.7804
No log	8.25	396	0.6036	0.2857	0.6036	0.7769
No log	8.2917	398	0.6057	0.3136	0.6057	0.7783
No log	8.3333	400	0.6107	0.3253	0.6107	0.7815
No log	8.375	402	0.6129	0.3253	0.6129	0.7829
No log	8.4167	404	0.6139	0.3136	0.6139	0.7835
No log	8.4583	406	0.6160	0.3136	0.6160	0.7849
No log	8.5	408	0.6198	0.2471	0.6198	0.7873
No log	8.5417	410	0.6243	0.3136	0.6243	0.7901
No log	8.5833	412	0.6335	0.2749	0.6335	0.7959
No log	8.625	414	0.6527	0.2360	0.6527	0.8079
No log	8.6667	416	0.6502	0.2265	0.6502	0.8064
No log	8.7083	418	0.6320	0.3136	0.6320	0.7950
No log	8.75	420	0.6315	0.2179	0.6315	0.7946
No log	8.7917	422	0.6480	0.2340	0.6480	0.8050
No log	8.8333	424	0.6571	0.3089	0.6571	0.8106
No log	8.875	426	0.6564	0.3089	0.6564	0.8102
No log	8.9167	428	0.6451	0.2000	0.6451	0.8032
No log	8.9583	430	0.6329	0.2179	0.6329	0.7956
No log	9.0	432	0.6256	0.3023	0.6256	0.7909
No log	9.0417	434	0.6382	0.2727	0.6382	0.7989
No log	9.0833	436	0.6596	0.2360	0.6596	0.8121
No log	9.125	438	0.6659	0.2350	0.6659	0.8160
No log	9.1667	440	0.6588	0.2360	0.6588	0.8117
No log	9.2083	442	0.6541	0.2360	0.6541	0.8088
No log	9.25	444	0.6388	0.2265	0.6388	0.7992
No log	9.2917	446	0.6323	0.3216	0.6323	0.7952
No log	9.3333	448	0.6265	0.3023	0.6265	0.7915
No log	9.375	450	0.6256	0.3023	0.6256	0.7910
No log	9.4167	452	0.6276	0.2471	0.6276	0.7922
No log	9.4583	454	0.6289	0.2707	0.6289	0.7930
No log	9.5	456	0.6321	0.2174	0.6321	0.7950
No log	9.5417	458	0.6364	0.2174	0.6364	0.7977
No log	9.5833	460	0.6362	0.2174	0.6362	0.7976
No log	9.625	462	0.6359	0.2174	0.6359	0.7975
No log	9.6667	464	0.6346	0.2174	0.6346	0.7966
No log	9.7083	466	0.6340	0.2174	0.6340	0.7963
No log	9.75	468	0.6336	0.2174	0.6336	0.7960
No log	9.7917	470	0.6328	0.3118	0.6328	0.7955
No log	9.8333	472	0.6324	0.3118	0.6324	0.7952
No log	9.875	474	0.6325	0.3089	0.6325	0.7953
No log	9.9167	476	0.6326	0.3089	0.6326	0.7953
No log	9.9583	478	0.6326	0.3089	0.6326	0.7954
No log	10.0	480	0.6326	0.3089	0.6326	0.7953

Framework versions

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