ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k7_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: 0.6432
• Qwk: 0.7386
• Mse: 0.6432
• Rmse: 0.8020

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	0.0444	2	5.8548	-0.0316	5.8548	2.4197
No log	0.0889	4	3.3464	0.0606	3.3464	1.8293
No log	0.1333	6	2.3601	-0.0558	2.3601	1.5363
No log	0.1778	8	1.7219	0.0998	1.7219	1.3122
No log	0.2222	10	1.3269	0.1937	1.3269	1.1519
No log	0.2667	12	1.1999	0.3672	1.1999	1.0954
No log	0.3111	14	1.2041	0.3431	1.2041	1.0973
No log	0.3556	16	1.3689	0.1706	1.3689	1.1700
No log	0.4	18	1.5706	0.1040	1.5706	1.2532
No log	0.4444	20	1.4896	0.1491	1.4896	1.2205
No log	0.4889	22	1.4981	0.1867	1.4981	1.2240
No log	0.5333	24	2.1962	0.1953	2.1962	1.4820
No log	0.5778	26	2.7530	0.1142	2.7530	1.6592
No log	0.6222	28	2.2695	0.2049	2.2695	1.5065
No log	0.6667	30	1.5610	0.2620	1.5610	1.2494
No log	0.7111	32	1.1775	0.4362	1.1775	1.0851
No log	0.7556	34	1.0168	0.4052	1.0168	1.0084
No log	0.8	36	0.9173	0.4665	0.9173	0.9577
No log	0.8444	38	1.2243	0.4441	1.2243	1.1065
No log	0.8889	40	1.8554	0.2376	1.8554	1.3621
No log	0.9333	42	1.8968	0.2413	1.8968	1.3773
No log	0.9778	44	1.3958	0.4196	1.3958	1.1815
No log	1.0222	46	0.7787	0.5916	0.7787	0.8824
No log	1.0667	48	0.6767	0.5836	0.6767	0.8226
No log	1.1111	50	0.6871	0.5705	0.6871	0.8289
No log	1.1556	52	0.7302	0.6064	0.7302	0.8545
No log	1.2	54	0.8036	0.6284	0.8036	0.8964
No log	1.2444	56	0.8659	0.6189	0.8659	0.9305
No log	1.2889	58	0.8447	0.6182	0.8447	0.9191
No log	1.3333	60	0.8276	0.6130	0.8276	0.9097
No log	1.3778	62	0.8137	0.6054	0.8137	0.9021
No log	1.4222	64	0.7836	0.6256	0.7836	0.8852
No log	1.4667	66	0.8330	0.5643	0.8330	0.9127
No log	1.5111	68	0.8372	0.5632	0.8372	0.9150
No log	1.5556	70	0.7868	0.5944	0.7868	0.8870
No log	1.6	72	0.6994	0.6222	0.6994	0.8363
No log	1.6444	74	0.6718	0.6798	0.6718	0.8196
No log	1.6889	76	0.8353	0.5750	0.8353	0.9140
No log	1.7333	78	0.8121	0.6087	0.8121	0.9012
No log	1.7778	80	0.6740	0.6817	0.6740	0.8210
No log	1.8222	82	0.6850	0.6480	0.6850	0.8276
No log	1.8667	84	0.7786	0.6156	0.7786	0.8824
No log	1.9111	86	0.7994	0.6059	0.7994	0.8941
No log	1.9556	88	0.7858	0.6251	0.7858	0.8865
No log	2.0	90	0.7132	0.6526	0.7132	0.8445
No log	2.0444	92	0.6150	0.6763	0.6150	0.7843
No log	2.0889	94	0.6680	0.7035	0.6680	0.8173
No log	2.1333	96	0.7901	0.6427	0.7901	0.8889
No log	2.1778	98	0.8194	0.6342	0.8194	0.9052
No log	2.2222	100	0.8301	0.6440	0.8301	0.9111
No log	2.2667	102	0.7786	0.6640	0.7786	0.8824
No log	2.3111	104	0.7676	0.6704	0.7676	0.8761
No log	2.3556	106	0.8023	0.6684	0.8023	0.8957
No log	2.4	108	0.8343	0.6700	0.8343	0.9134
No log	2.4444	110	0.7617	0.6817	0.7617	0.8728
No log	2.4889	112	0.6695	0.7115	0.6695	0.8182
No log	2.5333	114	0.6328	0.7187	0.6328	0.7955
No log	2.5778	116	0.6779	0.6963	0.6779	0.8233
No log	2.6222	118	0.7902	0.6670	0.7902	0.8889
No log	2.6667	120	1.1508	0.5366	1.1508	1.0728
No log	2.7111	122	1.2457	0.5054	1.2457	1.1161
No log	2.7556	124	0.9313	0.6164	0.9313	0.9650
No log	2.8	126	0.6429	0.7233	0.6429	0.8018
No log	2.8444	128	0.6812	0.7153	0.6812	0.8254
No log	2.8889	130	0.6968	0.7020	0.6968	0.8347
No log	2.9333	132	0.6254	0.7357	0.6254	0.7908
No log	2.9778	134	0.6365	0.7258	0.6365	0.7978
No log	3.0222	136	0.6599	0.7047	0.6599	0.8123
No log	3.0667	138	0.6178	0.7360	0.6178	0.7860
No log	3.1111	140	0.6091	0.7523	0.6091	0.7805
No log	3.1556	142	0.7110	0.6495	0.7110	0.8432
No log	3.2	144	0.7548	0.6074	0.7548	0.8688
No log	3.2444	146	0.6770	0.7064	0.6770	0.8228
No log	3.2889	148	0.6055	0.7432	0.6055	0.7781
No log	3.3333	150	0.6179	0.7208	0.6179	0.7861
No log	3.3778	152	0.6428	0.6987	0.6428	0.8018
No log	3.4222	154	0.6242	0.7393	0.6242	0.7900
No log	3.4667	156	0.6234	0.7158	0.6234	0.7896
No log	3.5111	158	0.6293	0.7120	0.6293	0.7933
No log	3.5556	160	0.6572	0.7051	0.6572	0.8107
No log	3.6	162	0.6894	0.7075	0.6894	0.8303
No log	3.6444	164	0.6583	0.7287	0.6583	0.8114
No log	3.6889	166	0.7038	0.7237	0.7038	0.8389
No log	3.7333	168	0.7579	0.7073	0.7579	0.8706
No log	3.7778	170	0.7504	0.7175	0.7504	0.8663
No log	3.8222	172	0.7292	0.7445	0.7292	0.8539
No log	3.8667	174	0.7454	0.6975	0.7454	0.8633
No log	3.9111	176	0.7314	0.7463	0.7314	0.8552
No log	3.9556	178	0.7605	0.6987	0.7605	0.8721
No log	4.0	180	0.7901	0.6678	0.7901	0.8889
No log	4.0444	182	0.7303	0.7108	0.7303	0.8546
No log	4.0889	184	0.6648	0.7384	0.6648	0.8153
No log	4.1333	186	0.6794	0.6973	0.6794	0.8243
No log	4.1778	188	0.6791	0.6824	0.6791	0.8240
No log	4.2222	190	0.6362	0.6868	0.6362	0.7976
No log	4.2667	192	0.6247	0.7405	0.6247	0.7904
No log	4.3111	194	0.6652	0.6990	0.6652	0.8156
No log	4.3556	196	0.6762	0.7040	0.6762	0.8223
No log	4.4	198	0.6470	0.7164	0.6470	0.8044
No log	4.4444	200	0.6375	0.7220	0.6375	0.7984
No log	4.4889	202	0.6405	0.7249	0.6405	0.8003
No log	4.5333	204	0.6600	0.7298	0.6600	0.8124
No log	4.5778	206	0.6848	0.7158	0.6848	0.8275
No log	4.6222	208	0.6773	0.7099	0.6773	0.8230
No log	4.6667	210	0.6308	0.7529	0.6308	0.7942
No log	4.7111	212	0.6293	0.7320	0.6293	0.7933
No log	4.7556	214	0.6779	0.7223	0.6779	0.8233
No log	4.8	216	0.6782	0.7203	0.6782	0.8235
No log	4.8444	218	0.6239	0.7367	0.6239	0.7899
No log	4.8889	220	0.5908	0.7487	0.5908	0.7687
No log	4.9333	222	0.6001	0.7230	0.6001	0.7746
No log	4.9778	224	0.6085	0.7109	0.6085	0.7801
No log	5.0222	226	0.6126	0.7197	0.6126	0.7827
No log	5.0667	228	0.5851	0.7358	0.5851	0.7649
No log	5.1111	230	0.5771	0.7422	0.5771	0.7597
No log	5.1556	232	0.6131	0.7576	0.6131	0.7830
No log	5.2	234	0.6213	0.7586	0.6213	0.7883
No log	5.2444	236	0.5988	0.7348	0.5988	0.7739
No log	5.2889	238	0.5897	0.7447	0.5897	0.7679
No log	5.3333	240	0.5970	0.7476	0.5970	0.7727
No log	5.3778	242	0.6042	0.7476	0.6042	0.7773
No log	5.4222	244	0.6046	0.7476	0.6046	0.7776
No log	5.4667	246	0.6122	0.7541	0.6122	0.7824
No log	5.5111	248	0.6114	0.7454	0.6114	0.7819
No log	5.5556	250	0.6147	0.7497	0.6147	0.7840
No log	5.6	252	0.6755	0.7037	0.6755	0.8219
No log	5.6444	254	0.7390	0.6826	0.7390	0.8596
No log	5.6889	256	0.7224	0.6922	0.7224	0.8499
No log	5.7333	258	0.6499	0.6949	0.6499	0.8061
No log	5.7778	260	0.5910	0.7522	0.5910	0.7688
No log	5.8222	262	0.6052	0.7243	0.6052	0.7779
No log	5.8667	264	0.6247	0.7071	0.6247	0.7904
No log	5.9111	266	0.6086	0.7103	0.6086	0.7801
No log	5.9556	268	0.5833	0.7312	0.5833	0.7637
No log	6.0	270	0.5932	0.7449	0.5932	0.7702
No log	6.0444	272	0.6125	0.7053	0.6125	0.7827
No log	6.0889	274	0.6298	0.7058	0.6298	0.7936
No log	6.1333	276	0.6155	0.7200	0.6155	0.7845
No log	6.1778	278	0.6065	0.7233	0.6065	0.7788
No log	6.2222	280	0.5983	0.7593	0.5983	0.7735
No log	6.2667	282	0.6094	0.7364	0.6094	0.7806
No log	6.3111	284	0.6170	0.7375	0.6170	0.7855
No log	6.3556	286	0.6213	0.7353	0.6213	0.7882
No log	6.4	288	0.6212	0.7447	0.6212	0.7881
No log	6.4444	290	0.6364	0.7571	0.6364	0.7977
No log	6.4889	292	0.6742	0.7412	0.6742	0.8211
No log	6.5333	294	0.6871	0.7265	0.6871	0.8289
No log	6.5778	296	0.6698	0.7463	0.6698	0.8184
No log	6.6222	298	0.6523	0.7509	0.6523	0.8077
No log	6.6667	300	0.6571	0.7468	0.6571	0.8106
No log	6.7111	302	0.6565	0.7468	0.6565	0.8103
No log	6.7556	304	0.6790	0.7250	0.6790	0.8240
No log	6.8	306	0.7070	0.7244	0.7070	0.8409
No log	6.8444	308	0.7484	0.6927	0.7484	0.8651
No log	6.8889	310	0.7384	0.6990	0.7384	0.8593
No log	6.9333	312	0.7061	0.6985	0.7061	0.8403
No log	6.9778	314	0.6709	0.7242	0.6709	0.8191
No log	7.0222	316	0.6355	0.7102	0.6355	0.7972
No log	7.0667	318	0.6278	0.7070	0.6278	0.7923
No log	7.1111	320	0.6231	0.7127	0.6231	0.7893
No log	7.1556	322	0.6257	0.7156	0.6257	0.7910
No log	7.2	324	0.6345	0.7116	0.6345	0.7965
No log	7.2444	326	0.6448	0.7233	0.6448	0.8030
No log	7.2889	328	0.6462	0.7233	0.6462	0.8038
No log	7.3333	330	0.6516	0.7269	0.6516	0.8072
No log	7.3778	332	0.6443	0.7269	0.6443	0.8027
No log	7.4222	334	0.6465	0.7269	0.6465	0.8041
No log	7.4667	336	0.6658	0.7272	0.6658	0.8160
No log	7.5111	338	0.6730	0.7187	0.6730	0.8203
No log	7.5556	340	0.6933	0.7240	0.6933	0.8326
No log	7.6	342	0.6857	0.7240	0.6857	0.8281
No log	7.6444	344	0.6689	0.7145	0.6689	0.8179
No log	7.6889	346	0.6608	0.7315	0.6608	0.8129
No log	7.7333	348	0.6499	0.7263	0.6499	0.8061
No log	7.7778	350	0.6426	0.7226	0.6426	0.8016
No log	7.8222	352	0.6414	0.7226	0.6414	0.8009
No log	7.8667	354	0.6397	0.7226	0.6397	0.7998
No log	7.9111	356	0.6279	0.7268	0.6279	0.7924
No log	7.9556	358	0.6220	0.7252	0.6220	0.7887
No log	8.0	360	0.6208	0.7232	0.6208	0.7879
No log	8.0444	362	0.6254	0.7268	0.6254	0.7908
No log	8.0889	364	0.6287	0.7299	0.6287	0.7929
No log	8.1333	366	0.6199	0.7240	0.6199	0.7873
No log	8.1778	368	0.6122	0.7246	0.6122	0.7824
No log	8.2222	370	0.6088	0.7283	0.6088	0.7803
No log	8.2667	372	0.6051	0.7283	0.6051	0.7779
No log	8.3111	374	0.6144	0.7299	0.6144	0.7838
No log	8.3556	376	0.6380	0.7382	0.6380	0.7987
No log	8.4	378	0.6607	0.7286	0.6607	0.8128
No log	8.4444	380	0.6788	0.7177	0.6788	0.8239
No log	8.4889	382	0.6780	0.7344	0.6780	0.8234
No log	8.5333	384	0.6732	0.7334	0.6732	0.8205
No log	8.5778	386	0.6638	0.7418	0.6638	0.8147
No log	8.6222	388	0.6493	0.7402	0.6493	0.8058
No log	8.6667	390	0.6443	0.7407	0.6443	0.8027
No log	8.7111	392	0.6425	0.7386	0.6425	0.8016
No log	8.7556	394	0.6375	0.7427	0.6375	0.7984
No log	8.8	396	0.6369	0.7427	0.6369	0.7981
No log	8.8444	398	0.6378	0.7427	0.6378	0.7986
No log	8.8889	400	0.6382	0.7386	0.6382	0.7988
No log	8.9333	402	0.6383	0.7386	0.6383	0.7989
No log	8.9778	404	0.6419	0.7386	0.6419	0.8012
No log	9.0222	406	0.6427	0.7386	0.6427	0.8017
No log	9.0667	408	0.6419	0.7386	0.6419	0.8012
No log	9.1111	410	0.6404	0.7407	0.6404	0.8003
No log	9.1556	412	0.6423	0.7407	0.6423	0.8015
No log	9.2	414	0.6407	0.7407	0.6407	0.8004
No log	9.2444	416	0.6452	0.7443	0.6452	0.8032
No log	9.2889	418	0.6538	0.7438	0.6538	0.8086
No log	9.3333	420	0.6549	0.7438	0.6549	0.8093
No log	9.3778	422	0.6574	0.7438	0.6574	0.8108
No log	9.4222	424	0.6557	0.7438	0.6557	0.8098
No log	9.4667	426	0.6564	0.7438	0.6564	0.8102
No log	9.5111	428	0.6580	0.7422	0.6580	0.8112
No log	9.5556	430	0.6557	0.7422	0.6557	0.8098
No log	9.6	432	0.6526	0.7422	0.6526	0.8079
No log	9.6444	434	0.6497	0.7422	0.6497	0.8060
No log	9.6889	436	0.6482	0.7422	0.6482	0.8051
No log	9.7333	438	0.6460	0.7422	0.6460	0.8037
No log	9.7778	440	0.6450	0.7386	0.6450	0.8031
No log	9.8222	442	0.6453	0.7386	0.6453	0.8033
No log	9.8667	444	0.6449	0.7422	0.6449	0.8031
No log	9.9111	446	0.6441	0.7386	0.6441	0.8025
No log	9.9556	448	0.6435	0.7386	0.6435	0.8022
No log	10.0	450	0.6432	0.7386	0.6432	0.8020

Framework versions

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