ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k10_task5_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: 0.8700
• Qwk: 0.6554
• Mse: 0.8700
• Rmse: 0.9327

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	2.2479	-0.0268	2.2479	1.4993
No log	0.1026	4	1.5295	0.1228	1.5295	1.2367
No log	0.1538	6	1.5088	0.0967	1.5088	1.2283
No log	0.2051	8	1.3615	0.1981	1.3615	1.1668
No log	0.2564	10	1.2766	0.2372	1.2766	1.1299
No log	0.3077	12	1.2145	0.1858	1.2145	1.1021
No log	0.3590	14	1.1974	0.1779	1.1974	1.0943
No log	0.4103	16	1.2356	0.2970	1.2356	1.1116
No log	0.4615	18	1.2148	0.3917	1.2148	1.1022
No log	0.5128	20	1.2239	0.3706	1.2239	1.1063
No log	0.5641	22	1.1733	0.2735	1.1733	1.0832
No log	0.6154	24	1.1356	0.2183	1.1356	1.0656
No log	0.6667	26	1.1123	0.3190	1.1123	1.0547
No log	0.7179	28	1.1638	0.3002	1.1638	1.0788
No log	0.7692	30	1.4051	0.3137	1.4051	1.1854
No log	0.8205	32	1.5359	0.2040	1.5359	1.2393
No log	0.8718	34	1.4522	0.2189	1.4522	1.2051
No log	0.9231	36	1.2267	0.2543	1.2267	1.1075
No log	0.9744	38	1.1452	0.2530	1.1452	1.0701
No log	1.0256	40	1.1690	0.2751	1.1690	1.0812
No log	1.0769	42	1.1806	0.3271	1.1806	1.0866
No log	1.1282	44	1.1250	0.2483	1.1250	1.0606
No log	1.1795	46	1.1719	0.3125	1.1719	1.0825
No log	1.2308	48	1.2573	0.3872	1.2573	1.1213
No log	1.2821	50	1.2252	0.3869	1.2252	1.1069
No log	1.3333	52	1.0949	0.4256	1.0949	1.0464
No log	1.3846	54	1.0142	0.4237	1.0142	1.0071
No log	1.4359	56	0.9818	0.4255	0.9818	0.9909
No log	1.4872	58	0.9453	0.4805	0.9453	0.9722
No log	1.5385	60	0.9596	0.5439	0.9596	0.9796
No log	1.5897	62	0.9876	0.5337	0.9876	0.9938
No log	1.6410	64	1.0474	0.4819	1.0474	1.0234
No log	1.6923	66	0.9873	0.5188	0.9873	0.9936
No log	1.7436	68	0.8509	0.6079	0.8509	0.9224
No log	1.7949	70	0.8060	0.5882	0.8060	0.8977
No log	1.8462	72	0.8300	0.6175	0.8300	0.9111
No log	1.8974	74	0.9322	0.5412	0.9322	0.9655
No log	1.9487	76	0.9903	0.5570	0.9903	0.9952
No log	2.0	78	0.8651	0.5924	0.8651	0.9301
No log	2.0513	80	0.8106	0.5999	0.8106	0.9004
No log	2.1026	82	0.7897	0.6120	0.7897	0.8886
No log	2.1538	84	0.8270	0.5896	0.8270	0.9094
No log	2.2051	86	0.8945	0.5535	0.8945	0.9458
No log	2.2564	88	0.8944	0.5284	0.8944	0.9457
No log	2.3077	90	0.9225	0.5266	0.9225	0.9605
No log	2.3590	92	0.9735	0.5570	0.9735	0.9867
No log	2.4103	94	1.1823	0.5068	1.1823	1.0873
No log	2.4615	96	1.1838	0.5211	1.1838	1.0880
No log	2.5128	98	1.0520	0.5440	1.0520	1.0257
No log	2.5641	100	0.8300	0.6284	0.8300	0.9111
No log	2.6154	102	0.7571	0.6233	0.7571	0.8701
No log	2.6667	104	0.7465	0.6182	0.7465	0.8640
No log	2.7179	106	0.8294	0.6156	0.8294	0.9107
No log	2.7692	108	1.0125	0.5062	1.0125	1.0062
No log	2.8205	110	1.0547	0.4913	1.0547	1.0270
No log	2.8718	112	0.9721	0.4980	0.9721	0.9859
No log	2.9231	114	0.8531	0.5731	0.8531	0.9236
No log	2.9744	116	0.8292	0.5939	0.8292	0.9106
No log	3.0256	118	0.8152	0.5927	0.8152	0.9029
No log	3.0769	120	0.9454	0.5459	0.9454	0.9723
No log	3.1282	122	1.1062	0.5483	1.1062	1.0518
No log	3.1795	124	1.0601	0.5620	1.0601	1.0296
No log	3.2308	126	0.8628	0.6034	0.8628	0.9289
No log	3.2821	128	0.7588	0.7106	0.7588	0.8711
No log	3.3333	130	0.7433	0.7205	0.7433	0.8622
No log	3.3846	132	0.7243	0.7186	0.7243	0.8510
No log	3.4359	134	0.7385	0.7082	0.7385	0.8593
No log	3.4872	136	0.8482	0.6764	0.8482	0.9210
No log	3.5385	138	0.8943	0.6525	0.8943	0.9457
No log	3.5897	140	0.7927	0.6929	0.7927	0.8903
No log	3.6410	142	0.6875	0.7035	0.6875	0.8292
No log	3.6923	144	0.6542	0.6783	0.6542	0.8088
No log	3.7436	146	0.6654	0.6952	0.6654	0.8157
No log	3.7949	148	0.7786	0.6788	0.7786	0.8824
No log	3.8462	150	0.9550	0.6118	0.9550	0.9773
No log	3.8974	152	0.9589	0.6011	0.9589	0.9792
No log	3.9487	154	0.8172	0.6354	0.8172	0.9040
No log	4.0	156	0.7835	0.6686	0.7835	0.8852
No log	4.0513	158	0.7329	0.6735	0.7329	0.8561
No log	4.1026	160	0.7381	0.6735	0.7381	0.8591
No log	4.1538	162	0.8018	0.6764	0.8018	0.8954
No log	4.2051	164	1.0356	0.5889	1.0356	1.0177
No log	4.2564	166	1.4167	0.5568	1.4167	1.1902
No log	4.3077	168	1.4844	0.5536	1.4844	1.2184
No log	4.3590	170	1.2578	0.5638	1.2578	1.1215
No log	4.4103	172	1.0327	0.5976	1.0327	1.0162
No log	4.4615	174	0.8118	0.6668	0.8118	0.9010
No log	4.5128	176	0.7781	0.6655	0.7781	0.8821
No log	4.5641	178	0.8230	0.6569	0.8230	0.9072
No log	4.6154	180	0.9440	0.6061	0.9440	0.9716
No log	4.6667	182	1.0904	0.5450	1.0904	1.0442
No log	4.7179	184	1.2125	0.5258	1.2125	1.1012
No log	4.7692	186	1.2203	0.5385	1.2203	1.1047
No log	4.8205	188	1.0600	0.5671	1.0600	1.0296
No log	4.8718	190	0.9495	0.5881	0.9495	0.9744
No log	4.9231	192	0.8131	0.6753	0.8131	0.9017
No log	4.9744	194	0.7897	0.6745	0.7897	0.8887
No log	5.0256	196	0.8393	0.6461	0.8393	0.9161
No log	5.0769	198	0.9699	0.5673	0.9699	0.9848
No log	5.1282	200	1.0951	0.5495	1.0951	1.0464
No log	5.1795	202	1.1077	0.5638	1.1077	1.0525
No log	5.2308	204	1.0444	0.5901	1.0444	1.0220
No log	5.2821	206	0.8766	0.6627	0.8766	0.9363
No log	5.3333	208	0.7992	0.7116	0.7992	0.8940
No log	5.3846	210	0.7579	0.7199	0.7579	0.8706
No log	5.4359	212	0.7396	0.7162	0.7396	0.8600
No log	5.4872	214	0.8077	0.6951	0.8077	0.8987
No log	5.5385	216	0.9566	0.6314	0.9566	0.9780
No log	5.5897	218	0.9789	0.6095	0.9789	0.9894
No log	5.6410	220	0.9706	0.6125	0.9706	0.9852
No log	5.6923	222	0.8683	0.6433	0.8683	0.9318
No log	5.7436	224	0.7805	0.6971	0.7805	0.8835
No log	5.7949	226	0.7678	0.6971	0.7678	0.8763
No log	5.8462	228	0.8109	0.6573	0.8109	0.9005
No log	5.8974	230	0.8870	0.6467	0.8870	0.9418
No log	5.9487	232	0.9549	0.6139	0.9549	0.9772
No log	6.0	234	1.0301	0.5878	1.0301	1.0149
No log	6.0513	236	1.0494	0.5694	1.0494	1.0244
No log	6.1026	238	1.0753	0.5651	1.0753	1.0370
No log	6.1538	240	1.0370	0.5682	1.0370	1.0183
No log	6.2051	242	0.9620	0.5913	0.9620	0.9808
No log	6.2564	244	0.9031	0.6365	0.9031	0.9503
No log	6.3077	246	0.9100	0.6322	0.9100	0.9539
No log	6.3590	248	1.0120	0.5725	1.0120	1.0060
No log	6.4103	250	1.0757	0.5694	1.0757	1.0371
No log	6.4615	252	1.0313	0.5572	1.0313	1.0155
No log	6.5128	254	0.9089	0.6440	0.9089	0.9534
No log	6.5641	256	0.7886	0.6884	0.7886	0.8880
No log	6.6154	258	0.7432	0.7325	0.7432	0.8621
No log	6.6667	260	0.7450	0.7118	0.7450	0.8631
No log	6.7179	262	0.7615	0.6848	0.7615	0.8727
No log	6.7692	264	0.7688	0.6884	0.7688	0.8768
No log	6.8205	266	0.8309	0.6749	0.8309	0.9115
No log	6.8718	268	0.9554	0.6286	0.9554	0.9774
No log	6.9231	270	1.0532	0.5914	1.0532	1.0263
No log	6.9744	272	1.1109	0.5644	1.1109	1.0540
No log	7.0256	274	1.1077	0.5644	1.1077	1.0525
No log	7.0769	276	1.0213	0.6086	1.0213	1.0106
No log	7.1282	278	0.9466	0.6087	0.9466	0.9730
No log	7.1795	280	0.9182	0.6130	0.9182	0.9582
No log	7.2308	282	0.8806	0.6088	0.8806	0.9384
No log	7.2821	284	0.8109	0.6522	0.8109	0.9005
No log	7.3333	286	0.7867	0.6716	0.7867	0.8869
No log	7.3846	288	0.8061	0.6707	0.8061	0.8978
No log	7.4359	290	0.8457	0.6264	0.8457	0.9196
No log	7.4872	292	0.9060	0.6107	0.9060	0.9519
No log	7.5385	294	0.9754	0.5854	0.9754	0.9876
No log	7.5897	296	1.0087	0.5793	1.0087	1.0044
No log	7.6410	298	1.0005	0.5757	1.0005	1.0003
No log	7.6923	300	1.0176	0.5824	1.0176	1.0088
No log	7.7436	302	1.0024	0.5757	1.0024	1.0012
No log	7.7949	304	0.9562	0.6036	0.9562	0.9779
No log	7.8462	306	0.9299	0.6266	0.9299	0.9643
No log	7.8974	308	0.8905	0.6346	0.8905	0.9437
No log	7.9487	310	0.8564	0.6810	0.8564	0.9254
No log	8.0	312	0.8663	0.6631	0.8663	0.9308
No log	8.0513	314	0.9145	0.6202	0.9145	0.9563
No log	8.1026	316	0.9590	0.6066	0.9590	0.9793
No log	8.1538	318	0.9980	0.5780	0.9980	0.9990
No log	8.2051	320	1.0223	0.5636	1.0223	1.0111
No log	8.2564	322	1.0359	0.5702	1.0359	1.0178
No log	8.3077	324	1.0072	0.5690	1.0072	1.0036
No log	8.3590	326	0.9639	0.6242	0.9639	0.9818
No log	8.4103	328	0.9150	0.6409	0.9150	0.9566
No log	8.4615	330	0.8894	0.6389	0.8894	0.9431
No log	8.5128	332	0.8531	0.6609	0.8531	0.9236
No log	8.5641	334	0.8374	0.6862	0.8374	0.9151
No log	8.6154	336	0.8443	0.6899	0.8443	0.9188
No log	8.6667	338	0.8625	0.6680	0.8625	0.9287
No log	8.7179	340	0.8888	0.6266	0.8888	0.9428
No log	8.7692	342	0.9102	0.6266	0.9102	0.9541
No log	8.8205	344	0.9166	0.6266	0.9166	0.9574
No log	8.8718	346	0.9234	0.6330	0.9234	0.9610
No log	8.9231	348	0.9257	0.6266	0.9257	0.9621
No log	8.9744	350	0.9229	0.6331	0.9229	0.9607
No log	9.0256	352	0.9267	0.6286	0.9267	0.9626
No log	9.0769	354	0.9453	0.6286	0.9453	0.9723
No log	9.1282	356	0.9491	0.6286	0.9491	0.9742
No log	9.1795	358	0.9548	0.6115	0.9548	0.9771
No log	9.2308	360	0.9455	0.6286	0.9455	0.9724
No log	9.2821	362	0.9219	0.6286	0.9219	0.9602
No log	9.3333	364	0.9052	0.6509	0.9052	0.9514
No log	9.3846	366	0.8885	0.6509	0.8885	0.9426
No log	9.4359	368	0.8733	0.6554	0.8733	0.9345
No log	9.4872	370	0.8661	0.6554	0.8661	0.9307
No log	9.5385	372	0.8601	0.6554	0.8601	0.9274
No log	9.5897	374	0.8605	0.6554	0.8605	0.9276
No log	9.6410	376	0.8614	0.6554	0.8614	0.9281
No log	9.6923	378	0.8643	0.6554	0.8643	0.9297
No log	9.7436	380	0.8689	0.6554	0.8689	0.9321
No log	9.7949	382	0.8728	0.6554	0.8728	0.9342
No log	9.8462	384	0.8728	0.6554	0.8728	0.9342
No log	9.8974	386	0.8709	0.6554	0.8709	0.9332
No log	9.9487	388	0.8702	0.6554	0.8702	0.9329
No log	10.0	390	0.8700	0.6554	0.8700	0.9327

Framework versions

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