ArabicNewSplits6_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: 0.6130
• Qwk: 0.4171
• Mse: 0.6130
• Rmse: 0.7829

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	0.0513	2	3.5412	0.0026	3.5412	1.8818
No log	0.1026	4	1.9672	-0.0070	1.9672	1.4026
No log	0.1538	6	1.4146	0.0255	1.4146	1.1894
No log	0.2051	8	1.8714	0.0716	1.8714	1.3680
No log	0.2564	10	1.3464	0.0588	1.3464	1.1604
No log	0.3077	12	0.5972	0.0476	0.5972	0.7728
No log	0.3590	14	0.5647	0.0	0.5647	0.7515
No log	0.4103	16	0.5771	0.0	0.5771	0.7597
No log	0.4615	18	0.6413	0.1565	0.6413	0.8008
No log	0.5128	20	0.6142	0.1773	0.6142	0.7837
No log	0.5641	22	0.5993	0.0815	0.5993	0.7742
No log	0.6154	24	0.5913	0.0	0.5913	0.7690
No log	0.6667	26	0.5664	0.1008	0.5664	0.7526
No log	0.7179	28	0.6566	0.1264	0.6566	0.8103
No log	0.7692	30	1.0964	0.0843	1.0964	1.0471
No log	0.8205	32	0.7392	0.1373	0.7392	0.8598
No log	0.8718	34	0.5587	0.1667	0.5587	0.7475
No log	0.9231	36	0.5898	0.1515	0.5898	0.7680
No log	0.9744	38	0.8658	0.1169	0.8658	0.9305
No log	1.0256	40	0.9922	0.1059	0.9922	0.9961
No log	1.0769	42	0.9063	0.1165	0.9063	0.9520
No log	1.1282	44	0.6175	0.1905	0.6175	0.7858
No log	1.1795	46	0.5618	0.0569	0.5618	0.7495
No log	1.2308	48	0.5895	0.0569	0.5895	0.7678
No log	1.2821	50	0.5616	0.0569	0.5616	0.7494
No log	1.3333	52	0.5313	0.1111	0.5313	0.7289
No log	1.3846	54	0.6861	0.2083	0.6861	0.8283
No log	1.4359	56	0.7996	0.2593	0.7996	0.8942
No log	1.4872	58	0.5713	0.1373	0.5713	0.7559
No log	1.5385	60	0.6251	0.0569	0.6251	0.7906
No log	1.5897	62	0.6910	-0.0159	0.6910	0.8312
No log	1.6410	64	0.6149	0.1111	0.6149	0.7841
No log	1.6923	66	0.9260	0.1861	0.9260	0.9623
No log	1.7436	68	1.3881	0.1377	1.3881	1.1782
No log	1.7949	70	0.9788	0.1803	0.9788	0.9893
No log	1.8462	72	0.6384	0.1556	0.6384	0.7990
No log	1.8974	74	0.5609	0.0569	0.5609	0.7489
No log	1.9487	76	0.5799	0.125	0.5799	0.7615
No log	2.0	78	0.5319	0.1533	0.5319	0.7293
No log	2.0513	80	0.5183	0.2222	0.5183	0.7200
No log	2.1026	82	0.6758	0.2464	0.6758	0.8221
No log	2.1538	84	0.9544	0.0843	0.9544	0.9769
No log	2.2051	86	0.9909	0.0843	0.9909	0.9954
No log	2.2564	88	0.7172	0.2381	0.7172	0.8468
No log	2.3077	90	0.5596	0.2195	0.5596	0.7480
No log	2.3590	92	0.5585	0.2877	0.5585	0.7473
No log	2.4103	94	0.6720	0.0968	0.6720	0.8197
No log	2.4615	96	0.9375	0.1515	0.9375	0.9682
No log	2.5128	98	0.6784	0.1038	0.6784	0.8236
No log	2.5641	100	0.6444	0.3455	0.6444	0.8028
No log	2.6154	102	0.6471	0.2832	0.6471	0.8044
No log	2.6667	104	0.7179	0.2563	0.7179	0.8473
No log	2.7179	106	0.8537	0.1855	0.8537	0.9239
No log	2.7692	108	0.6213	0.2889	0.6213	0.7882
No log	2.8205	110	0.6251	0.3533	0.6251	0.7906
No log	2.8718	112	0.6492	0.3563	0.6492	0.8058
No log	2.9231	114	0.6706	0.0674	0.6706	0.8189
No log	2.9744	116	1.1450	0.1884	1.1450	1.0700
No log	3.0256	118	1.1231	0.1396	1.1231	1.0597
No log	3.0769	120	0.6985	0.1230	0.6985	0.8358
No log	3.1282	122	0.7860	0.2000	0.7860	0.8866
No log	3.1795	124	0.8413	0.0476	0.8413	0.9172
No log	3.2308	126	0.6636	0.3161	0.6636	0.8146
No log	3.2821	128	0.7111	0.2079	0.7111	0.8433
No log	3.3333	130	0.6995	0.2464	0.6995	0.8363
No log	3.3846	132	0.6257	0.3402	0.6257	0.7910
No log	3.4359	134	0.8988	0.2121	0.8988	0.9480
No log	3.4872	136	0.8896	0.2302	0.8896	0.9432
No log	3.5385	138	0.6228	0.2990	0.6228	0.7891
No log	3.5897	140	0.6263	0.3575	0.6263	0.7914
No log	3.6410	142	0.6547	0.3367	0.6547	0.8091
No log	3.6923	144	0.6895	0.2990	0.6895	0.8304
No log	3.7436	146	0.8995	0.2124	0.8995	0.9484
No log	3.7949	148	1.0077	0.1608	1.0077	1.0039
No log	3.8462	150	0.8943	0.2000	0.8943	0.9457
No log	3.8974	152	0.9005	0.1741	0.9005	0.9490
No log	3.9487	154	0.9391	0.2472	0.9391	0.9690
No log	4.0	156	0.9783	0.2000	0.9783	0.9891
No log	4.0513	158	0.9876	0.2054	0.9876	0.9938
No log	4.1026	160	0.7947	0.2061	0.7947	0.8915
No log	4.1538	162	0.6043	0.3641	0.6043	0.7774
No log	4.2051	164	0.6431	0.3778	0.6431	0.8019
No log	4.2564	166	0.6933	0.3929	0.6933	0.8326
No log	4.3077	168	0.8607	0.2058	0.8607	0.9277
No log	4.3590	170	0.8801	0.2056	0.8801	0.9381
No log	4.4103	172	0.6915	0.3722	0.6915	0.8316
No log	4.4615	174	0.5706	0.3591	0.5706	0.7554
No log	4.5128	176	0.5709	0.3591	0.5709	0.7555
No log	4.5641	178	0.5808	0.3073	0.5808	0.7621
No log	4.6154	180	0.5979	0.3224	0.5979	0.7732
No log	4.6667	182	0.6533	0.2081	0.6533	0.8082
No log	4.7179	184	0.6213	0.2821	0.6213	0.7882
No log	4.7692	186	0.8924	0.2000	0.8924	0.9447
No log	4.8205	188	1.1365	0.1293	1.1365	1.0661
No log	4.8718	190	0.9264	0.2000	0.9264	0.9625
No log	4.9231	192	0.7619	0.3333	0.7619	0.8729
No log	4.9744	194	0.6372	0.2487	0.6372	0.7983
No log	5.0256	196	0.6469	0.2897	0.6469	0.8043
No log	5.0769	198	0.7704	0.2941	0.7704	0.8777
No log	5.1282	200	0.8651	0.2296	0.8651	0.9301
No log	5.1795	202	0.8177	0.2941	0.8177	0.9043
No log	5.2308	204	0.6024	0.2653	0.6024	0.7762
No log	5.2821	206	0.5915	0.2421	0.5915	0.7691
No log	5.3333	208	0.5728	0.2169	0.5728	0.7569
No log	5.3846	210	0.6946	0.3427	0.6946	0.8334
No log	5.4359	212	1.0232	0.1329	1.0232	1.0116
No log	5.4872	214	1.0012	0.1489	1.0012	1.0006
No log	5.5385	216	0.7232	0.3427	0.7232	0.8504
No log	5.5897	218	0.6327	0.2421	0.6327	0.7954
No log	5.6410	220	0.6516	0.2746	0.6516	0.8072
No log	5.6923	222	0.7044	0.3905	0.7044	0.8393
No log	5.7436	224	0.8335	0.2459	0.8335	0.9129
No log	5.7949	226	1.1603	0.0355	1.1603	1.0772
No log	5.8462	228	1.2379	0.0490	1.2379	1.1126
No log	5.8974	230	1.0291	0.0769	1.0291	1.0145
No log	5.9487	232	0.7582	0.4233	0.7582	0.8707
No log	6.0	234	0.7037	0.2315	0.7037	0.8389
No log	6.0513	236	0.6793	0.2251	0.6793	0.8242
No log	6.1026	238	0.7164	0.3917	0.7164	0.8464
No log	6.1538	240	0.7804	0.2520	0.7804	0.8834
No log	6.2051	242	0.8454	0.2569	0.8454	0.9194
No log	6.2564	244	0.7664	0.2531	0.7664	0.8754
No log	6.3077	246	0.6439	0.3161	0.6439	0.8025
No log	6.3590	248	0.6463	0.2227	0.6463	0.8039
No log	6.4103	250	0.6611	0.2727	0.6611	0.8131
No log	6.4615	252	0.7850	0.3092	0.7850	0.8860
No log	6.5128	254	0.7777	0.2713	0.7777	0.8819
No log	6.5641	256	0.7036	0.3623	0.7036	0.8388
No log	6.6154	258	0.6336	0.2487	0.6336	0.7960
No log	6.6667	260	0.6353	0.2536	0.6353	0.7971
No log	6.7179	262	0.6145	0.2487	0.6145	0.7839
No log	6.7692	264	0.6873	0.3548	0.6873	0.8290
No log	6.8205	266	0.7737	0.2846	0.7737	0.8796
No log	6.8718	268	0.7190	0.3665	0.7190	0.8479
No log	6.9231	270	0.6318	0.3299	0.6318	0.7948
No log	6.9744	272	0.5908	0.2766	0.5908	0.7686
No log	7.0256	274	0.5936	0.2865	0.5936	0.7705
No log	7.0769	276	0.6681	0.3704	0.6681	0.8174
No log	7.1282	278	0.7907	0.3043	0.7907	0.8892
No log	7.1795	280	0.8473	0.2672	0.8473	0.9205
No log	7.2308	282	0.7618	0.2982	0.7618	0.8728
No log	7.2821	284	0.6721	0.3333	0.6721	0.8198
No log	7.3333	286	0.6208	0.3161	0.6208	0.7879
No log	7.3846	288	0.6223	0.2965	0.6223	0.7888
No log	7.4359	290	0.6614	0.3267	0.6614	0.8133
No log	7.4872	292	0.7306	0.2920	0.7306	0.8547
No log	7.5385	294	0.7460	0.2900	0.7460	0.8637
No log	7.5897	296	0.7746	0.3220	0.7746	0.8801
No log	7.6410	298	0.7923	0.2903	0.7923	0.8901
No log	7.6923	300	0.7135	0.2593	0.7135	0.8447
No log	7.7436	302	0.6633	0.3725	0.6633	0.8145
No log	7.7949	304	0.6247	0.3200	0.6247	0.7904
No log	7.8462	306	0.6263	0.3200	0.6263	0.7914
No log	7.8974	308	0.6571	0.3725	0.6571	0.8106
No log	7.9487	310	0.7676	0.2863	0.7676	0.8761
No log	8.0	312	0.8991	0.2885	0.8991	0.9482
No log	8.0513	314	0.9033	0.2868	0.9033	0.9504
No log	8.1026	316	0.8150	0.2846	0.8150	0.9028
No log	8.1538	318	0.7186	0.3607	0.7186	0.8477
No log	8.2051	320	0.6811	0.3367	0.6811	0.8253
No log	8.2564	322	0.6575	0.3171	0.6575	0.8109
No log	8.3077	324	0.6630	0.3367	0.6630	0.8143
No log	8.3590	326	0.7103	0.2986	0.7103	0.8428
No log	8.4103	328	0.7728	0.2846	0.7728	0.8791
No log	8.4615	330	0.8287	0.2922	0.8287	0.9103
No log	8.5128	332	0.8159	0.2922	0.8159	0.9033
No log	8.5641	334	0.7441	0.2900	0.7441	0.8626
No log	8.6154	336	0.6631	0.3725	0.6631	0.8143
No log	8.6667	338	0.6328	0.4059	0.6328	0.7955
No log	8.7179	340	0.6261	0.4059	0.6261	0.7913
No log	8.7692	342	0.6441	0.3623	0.6441	0.8026
No log	8.8205	344	0.6744	0.3301	0.6744	0.8212
No log	8.8718	346	0.7153	0.3333	0.7153	0.8457
No log	8.9231	348	0.7411	0.3274	0.7411	0.8609
No log	8.9744	350	0.7196	0.3333	0.7196	0.8483
No log	9.0256	352	0.6694	0.3398	0.6694	0.8181
No log	9.0769	354	0.6415	0.3725	0.6415	0.8010
No log	9.1282	356	0.6151	0.4059	0.6151	0.7843
No log	9.1795	358	0.6097	0.4059	0.6097	0.7808
No log	9.2308	360	0.6149	0.4171	0.6149	0.7842
No log	9.2821	362	0.6312	0.4171	0.6312	0.7945
No log	9.3333	364	0.6475	0.3831	0.6475	0.8047
No log	9.3846	366	0.6493	0.3398	0.6493	0.8058
No log	9.4359	368	0.6537	0.3398	0.6537	0.8085
No log	9.4872	370	0.6455	0.3725	0.6455	0.8034
No log	9.5385	372	0.6318	0.4171	0.6318	0.7948
No log	9.5897	374	0.6183	0.4171	0.6183	0.7863
No log	9.6410	376	0.6063	0.3814	0.6063	0.7786
No log	9.6923	378	0.6004	0.3862	0.6004	0.7748
No log	9.7436	380	0.6000	0.3862	0.6000	0.7746
No log	9.7949	382	0.6024	0.3862	0.6024	0.7762
No log	9.8462	384	0.6075	0.4171	0.6075	0.7794
No log	9.8974	386	0.6114	0.4171	0.6114	0.7819
No log	9.9487	388	0.6125	0.4171	0.6125	0.7827
No log	10.0	390	0.6130	0.4171	0.6130	0.7829

Framework versions

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