ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k6_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: 0.6213
• Qwk: 0.7259
• Mse: 0.6213
• Rmse: 0.7883

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	0.0606	2	5.1716	-0.0336	5.1716	2.2741
No log	0.1212	4	3.1515	0.0840	3.1515	1.7752
No log	0.1818	6	2.6529	-0.1073	2.6529	1.6288
No log	0.2424	8	1.9169	-0.0161	1.9169	1.3845
No log	0.3030	10	1.3331	0.1716	1.3331	1.1546
No log	0.3636	12	1.2217	0.2738	1.2217	1.1053
No log	0.4242	14	1.6960	0.0471	1.6960	1.3023
No log	0.4848	16	2.1428	0.1294	2.1428	1.4638
No log	0.5455	18	1.7629	0.0846	1.7629	1.3277
No log	0.6061	20	1.2428	0.2622	1.2428	1.1148
No log	0.6667	22	1.1485	0.2137	1.1485	1.0717
No log	0.7273	24	1.2069	0.1486	1.2069	1.0986
No log	0.7879	26	1.2510	0.1620	1.2510	1.1185
No log	0.8485	28	1.2093	0.1918	1.2093	1.0997
No log	0.9091	30	1.1191	0.2560	1.1191	1.0579
No log	0.9697	32	1.1024	0.3052	1.1024	1.0500
No log	1.0303	34	1.3082	0.1584	1.3082	1.1438
No log	1.0909	36	1.4531	0.0542	1.4531	1.2054
No log	1.1515	38	1.4133	0.0542	1.4133	1.1888
No log	1.2121	40	1.1808	0.3219	1.1808	1.0866
No log	1.2727	42	1.1072	0.3461	1.1072	1.0523
No log	1.3333	44	0.9813	0.4136	0.9813	0.9906
No log	1.3939	46	0.8714	0.4188	0.8714	0.9335
No log	1.4545	48	0.8582	0.4200	0.8582	0.9264
No log	1.5152	50	1.0155	0.4058	1.0155	1.0077
No log	1.5758	52	0.9988	0.4281	0.9988	0.9994
No log	1.6364	54	1.0183	0.4375	1.0183	1.0091
No log	1.6970	56	1.1114	0.4361	1.1114	1.0543
No log	1.7576	58	0.9248	0.5137	0.9248	0.9617
No log	1.8182	60	0.8142	0.5409	0.8142	0.9023
No log	1.8788	62	0.8669	0.5468	0.8669	0.9311
No log	1.9394	64	1.1888	0.4665	1.1888	1.0903
No log	2.0	66	1.5774	0.3833	1.5774	1.2560
No log	2.0606	68	1.6236	0.3514	1.6236	1.2742
No log	2.1212	70	1.3887	0.4201	1.3887	1.1785
No log	2.1818	72	0.9900	0.5099	0.9900	0.9950
No log	2.2424	74	0.9784	0.4088	0.9784	0.9891
No log	2.3030	76	1.1334	0.3278	1.1334	1.0646
No log	2.3636	78	0.9367	0.4638	0.9367	0.9678
No log	2.4242	80	0.7326	0.6233	0.7326	0.8559
No log	2.4848	82	0.9364	0.5079	0.9364	0.9677
No log	2.5455	84	1.2815	0.4286	1.2815	1.1320
No log	2.6061	86	1.4325	0.3701	1.4325	1.1969
No log	2.6667	88	1.4568	0.3837	1.4568	1.2070
No log	2.7273	90	1.3241	0.4205	1.3241	1.1507
No log	2.7879	92	1.1296	0.4900	1.1296	1.0628
No log	2.8485	94	0.7812	0.6672	0.7812	0.8839
No log	2.9091	96	0.5977	0.6724	0.5977	0.7731
No log	2.9697	98	0.5827	0.7399	0.5827	0.7633
No log	3.0303	100	0.5914	0.7021	0.5914	0.7690
No log	3.0909	102	0.6722	0.6912	0.6722	0.8199
No log	3.1515	104	0.9546	0.5917	0.9546	0.9770
No log	3.2121	106	1.1594	0.5116	1.1594	1.0768
No log	3.2727	108	1.1932	0.4966	1.1931	1.0923
No log	3.3333	110	1.1889	0.4966	1.1889	1.0904
No log	3.3939	112	0.9951	0.5725	0.9951	0.9975
No log	3.4545	114	0.7583	0.6219	0.7583	0.8708
No log	3.5152	116	0.6564	0.6506	0.6564	0.8102
No log	3.5758	118	0.6203	0.6938	0.6203	0.7876
No log	3.6364	120	0.5830	0.7290	0.5830	0.7635
No log	3.6970	122	0.6031	0.7003	0.6031	0.7766
No log	3.7576	124	0.6617	0.7107	0.6617	0.8135
No log	3.8182	126	0.7321	0.6700	0.7321	0.8556
No log	3.8788	128	0.6531	0.7005	0.6531	0.8082
No log	3.9394	130	0.5573	0.7042	0.5573	0.7465
No log	4.0	132	0.5524	0.7219	0.5524	0.7432
No log	4.0606	134	0.5679	0.7154	0.5679	0.7536
No log	4.1212	136	0.6148	0.7286	0.6148	0.7841
No log	4.1818	138	0.6153	0.7286	0.6153	0.7844
No log	4.2424	140	0.5826	0.7217	0.5826	0.7633
No log	4.3030	142	0.5736	0.7185	0.5736	0.7574
No log	4.3636	144	0.5824	0.7432	0.5824	0.7631
No log	4.4242	146	0.5887	0.7420	0.5887	0.7672
No log	4.4848	148	0.5630	0.7451	0.5630	0.7503
No log	4.5455	150	0.5792	0.7608	0.5792	0.7611
No log	4.6061	152	0.6118	0.7690	0.6118	0.7822
No log	4.6667	154	0.6388	0.7591	0.6388	0.7993
No log	4.7273	156	0.6286	0.7608	0.6286	0.7928
No log	4.7879	158	0.6051	0.7728	0.6051	0.7779
No log	4.8485	160	0.5955	0.7745	0.5955	0.7717
No log	4.9091	162	0.5881	0.7535	0.5881	0.7669
No log	4.9697	164	0.5954	0.7535	0.5954	0.7716
No log	5.0303	166	0.5945	0.7338	0.5945	0.7710
No log	5.0909	168	0.6129	0.7086	0.6129	0.7829
No log	5.1515	170	0.6463	0.7114	0.6463	0.8039
No log	5.2121	172	0.6282	0.7013	0.6282	0.7926
No log	5.2727	174	0.5952	0.7291	0.5952	0.7715
No log	5.3333	176	0.6244	0.7607	0.6244	0.7902
No log	5.3939	178	0.6649	0.7277	0.6649	0.8154
No log	5.4545	180	0.6719	0.7349	0.6719	0.8197
No log	5.5152	182	0.6060	0.7352	0.6060	0.7785
No log	5.5758	184	0.5767	0.7351	0.5767	0.7594
No log	5.6364	186	0.6306	0.7197	0.6306	0.7941
No log	5.6970	188	0.7099	0.6682	0.7099	0.8425
No log	5.7576	190	0.6853	0.6990	0.6853	0.8278
No log	5.8182	192	0.6075	0.7366	0.6075	0.7794
No log	5.8788	194	0.5832	0.7109	0.5832	0.7637
No log	5.9394	196	0.5971	0.7151	0.5971	0.7727
No log	6.0	198	0.6568	0.7034	0.6568	0.8104
No log	6.0606	200	0.6925	0.6949	0.6925	0.8322
No log	6.1212	202	0.6507	0.6929	0.6507	0.8067
No log	6.1818	204	0.6176	0.7251	0.6176	0.7858
No log	6.2424	206	0.6202	0.7370	0.6202	0.7875
No log	6.3030	208	0.6192	0.7438	0.6192	0.7869
No log	6.3636	210	0.6051	0.7334	0.6051	0.7779
No log	6.4242	212	0.6010	0.7237	0.6010	0.7752
No log	6.4848	214	0.6012	0.7137	0.6012	0.7753
No log	6.5455	216	0.6188	0.6910	0.6188	0.7867
No log	6.6061	218	0.6342	0.6860	0.6342	0.7964
No log	6.6667	220	0.6100	0.7150	0.6100	0.7810
No log	6.7273	222	0.5944	0.7060	0.5944	0.7710
No log	6.7879	224	0.6019	0.7344	0.6019	0.7758
No log	6.8485	226	0.6061	0.7283	0.6061	0.7785
No log	6.9091	228	0.5982	0.7181	0.5982	0.7735
No log	6.9697	230	0.5960	0.7189	0.5960	0.7720
No log	7.0303	232	0.6095	0.7472	0.6095	0.7807
No log	7.0909	234	0.6349	0.7421	0.6349	0.7968
No log	7.1515	236	0.6289	0.7464	0.6289	0.7930
No log	7.2121	238	0.6036	0.7175	0.6036	0.7769
No log	7.2727	240	0.6177	0.7054	0.6177	0.7859
No log	7.3333	242	0.6614	0.7015	0.6614	0.8132
No log	7.3939	244	0.6612	0.7152	0.6612	0.8131
No log	7.4545	246	0.6321	0.7011	0.6321	0.7951
No log	7.5152	248	0.6276	0.6823	0.6276	0.7922
No log	7.5758	250	0.6554	0.7522	0.6554	0.8096
No log	7.6364	252	0.7092	0.7207	0.7092	0.8421
No log	7.6970	254	0.7307	0.7138	0.7307	0.8548
No log	7.7576	256	0.7030	0.7381	0.7030	0.8384
No log	7.8182	258	0.6593	0.7463	0.6593	0.8119
No log	7.8788	260	0.6394	0.7052	0.6394	0.7996
No log	7.9394	262	0.6372	0.7076	0.6372	0.7983
No log	8.0	264	0.6604	0.6705	0.6604	0.8126
No log	8.0606	266	0.6878	0.6530	0.6878	0.8293
No log	8.1212	268	0.6917	0.6530	0.6917	0.8317
No log	8.1818	270	0.6671	0.6436	0.6671	0.8168
No log	8.2424	272	0.6353	0.6625	0.6353	0.7970
No log	8.3030	274	0.6205	0.7178	0.6205	0.7877
No log	8.3636	276	0.6225	0.7217	0.6225	0.7890
No log	8.4242	278	0.6331	0.7407	0.6331	0.7957
No log	8.4848	280	0.6403	0.7466	0.6403	0.8002
No log	8.5455	282	0.6476	0.7466	0.6476	0.8047
No log	8.6061	284	0.6447	0.7603	0.6447	0.8029
No log	8.6667	286	0.6461	0.7640	0.6461	0.8038
No log	8.7273	288	0.6480	0.7659	0.6480	0.8050
No log	8.7879	290	0.6489	0.7616	0.6489	0.8055
No log	8.8485	292	0.6464	0.7603	0.6464	0.8040
No log	8.9091	294	0.6403	0.7301	0.6403	0.8002
No log	8.9697	296	0.6318	0.7151	0.6318	0.7948
No log	9.0303	298	0.6290	0.7185	0.6290	0.7931
No log	9.0909	300	0.6285	0.7065	0.6285	0.7928
No log	9.1515	302	0.6263	0.7068	0.6263	0.7914
No log	9.2121	304	0.6239	0.7028	0.6239	0.7898
No log	9.2727	306	0.6210	0.7088	0.6210	0.7880
No log	9.3333	308	0.6198	0.7118	0.6198	0.7873
No log	9.3939	310	0.6187	0.7118	0.6187	0.7866
No log	9.4545	312	0.6182	0.7118	0.6182	0.7862
No log	9.5152	314	0.6195	0.7193	0.6195	0.7871
No log	9.5758	316	0.6202	0.7151	0.6202	0.7875
No log	9.6364	318	0.6204	0.7151	0.6204	0.7877
No log	9.6970	320	0.6212	0.7201	0.6212	0.7882
No log	9.7576	322	0.6220	0.7201	0.6220	0.7887
No log	9.8182	324	0.6221	0.7259	0.6221	0.7887
No log	9.8788	326	0.6219	0.7259	0.6219	0.7886
No log	9.9394	328	0.6215	0.7259	0.6215	0.7884
No log	10.0	330	0.6213	0.7259	0.6213	0.7883

Framework versions

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