ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k4_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: 0.9651
• Qwk: 0.1660
• Mse: 0.9651
• Rmse: 0.9824

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	0.0769	2	3.9306	0.0013	3.9306	1.9826
No log	0.1538	4	2.3851	-0.0732	2.3851	1.5444
No log	0.2308	6	1.3062	0.0255	1.3062	1.1429
No log	0.3077	8	1.9680	-0.0028	1.9680	1.4029
No log	0.3846	10	2.4502	0.0152	2.4502	1.5653
No log	0.4615	12	1.6767	-0.0070	1.6767	1.2949
No log	0.5385	14	0.8754	0.0745	0.8754	0.9356
No log	0.6154	16	0.6747	0.2787	0.6747	0.8214
No log	0.6923	18	0.7657	-0.1111	0.7657	0.8750
No log	0.7692	20	0.9357	-0.0700	0.9357	0.9673
No log	0.8462	22	1.3130	0.0	1.3130	1.1458
No log	0.9231	24	1.5685	-0.0036	1.5685	1.2524
No log	1.0	26	1.3302	-0.0036	1.3302	1.1533
No log	1.0769	28	1.2439	-0.0036	1.2439	1.1153
No log	1.1538	30	1.0579	0.0	1.0579	1.0286
No log	1.2308	32	1.0405	0.0	1.0405	1.0201
No log	1.3077	34	0.9891	0.0	0.9891	0.9945
No log	1.3846	36	0.8213	0.0380	0.8213	0.9062
No log	1.4615	38	0.6932	-0.0068	0.6932	0.8326
No log	1.5385	40	0.6857	0.0556	0.6857	0.8281
No log	1.6154	42	0.7715	-0.1905	0.7715	0.8784
No log	1.6923	44	1.0767	0.0476	1.0767	1.0376
No log	1.7692	46	1.3352	0.0154	1.3352	1.1555
No log	1.8462	48	1.2714	0.0476	1.2714	1.1276
No log	1.9231	50	1.0349	-0.0370	1.0349	1.0173
No log	2.0	52	1.1364	-0.0233	1.1364	1.0660
No log	2.0769	54	1.2473	-0.0233	1.2473	1.1168
No log	2.1538	56	1.7061	-0.0309	1.7061	1.3062
No log	2.2308	58	1.8099	-0.0596	1.8099	1.3453
No log	2.3077	60	1.9034	-0.0596	1.9034	1.3796
No log	2.3846	62	1.4021	0.0036	1.4021	1.1841
No log	2.4615	64	0.8295	-0.1034	0.8295	0.9108
No log	2.5385	66	0.6867	0.0145	0.6867	0.8287
No log	2.6154	68	0.7096	-0.0196	0.7096	0.8424
No log	2.6923	70	0.8202	0.0647	0.8202	0.9057
No log	2.7692	72	0.8820	0.1493	0.8820	0.9392
No log	2.8462	74	1.1536	0.1074	1.1536	1.0741
No log	2.9231	76	1.4554	0.0256	1.4554	1.2064
No log	3.0	78	1.6758	0.0115	1.6758	1.2945
No log	3.0769	80	1.5600	0.0500	1.5600	1.2490
No log	3.1538	82	1.0794	0.1276	1.0794	1.0389
No log	3.2308	84	0.8912	0.0800	0.8912	0.9440
No log	3.3077	86	0.8956	0.0291	0.8956	0.9464
No log	3.3846	88	1.0343	0.1130	1.0343	1.0170
No log	3.4615	90	1.2984	0.0903	1.2984	1.1395
No log	3.5385	92	1.4083	0.0530	1.4083	1.1867
No log	3.6154	94	1.0902	0.125	1.0902	1.0441
No log	3.6923	96	0.9872	0.1203	0.9872	0.9936
No log	3.7692	98	1.0320	0.136	1.0320	1.0159
No log	3.8462	100	0.9511	0.0717	0.9511	0.9752
No log	3.9231	102	0.9958	0.0717	0.9958	0.9979
No log	4.0	104	1.2524	0.1264	1.2524	1.1191
No log	4.0769	106	1.6843	0.0716	1.6843	1.2978
No log	4.1538	108	1.8537	0.0622	1.8537	1.3615
No log	4.2308	110	1.5422	0.1155	1.5422	1.2419
No log	4.3077	112	1.0870	0.0667	1.0870	1.0426
No log	4.3846	114	1.0137	0.0694	1.0137	1.0068
No log	4.4615	116	1.0142	0.0947	1.0142	1.0071
No log	4.5385	118	1.1555	0.0492	1.1555	1.0750
No log	4.6154	120	1.2699	0.0843	1.2699	1.1269
No log	4.6923	122	1.2531	0.0894	1.2531	1.1194
No log	4.7692	124	1.2659	0.1429	1.2659	1.1251
No log	4.8462	126	1.3463	0.1212	1.3463	1.1603
No log	4.9231	128	1.5337	0.0769	1.5337	1.2384
No log	5.0	130	1.4532	0.0747	1.4532	1.2055
No log	5.0769	132	1.4731	0.0355	1.4731	1.2137
No log	5.1538	134	1.2962	0.0815	1.2962	1.1385
No log	5.2308	136	0.9794	0.2068	0.9794	0.9897
No log	5.3077	138	0.8861	0.0933	0.8861	0.9413
No log	5.3846	140	0.8211	0.1193	0.8211	0.9061
No log	5.4615	142	0.8053	0.0685	0.8053	0.8974
No log	5.5385	144	0.8413	0.0933	0.8413	0.9172
No log	5.6154	146	0.9297	0.1741	0.9297	0.9642
No log	5.6923	148	1.3049	0.2000	1.3049	1.1423
No log	5.7692	150	1.6378	0.1038	1.6378	1.2798
No log	5.8462	152	1.4061	0.1900	1.4061	1.1858
No log	5.9231	154	1.0504	0.2124	1.0504	1.0249
No log	6.0	156	0.8611	0.2134	0.8611	0.9279
No log	6.0769	158	1.0053	0.1074	1.0053	1.0027
No log	6.1538	160	0.9556	0.1652	0.9556	0.9775
No log	6.2308	162	0.8399	0.2000	0.8399	0.9165
No log	6.3077	164	1.1143	0.2000	1.1143	1.0556
No log	6.3846	166	1.3790	0.1273	1.3790	1.1743
No log	6.4615	168	1.2910	0.1943	1.2910	1.1362
No log	6.5385	170	1.1868	0.1882	1.1868	1.0894
No log	6.6154	172	0.9771	0.0916	0.9771	0.9885
No log	6.6923	174	0.9096	0.1130	0.9096	0.9537
No log	6.7692	176	0.9409	0.1020	0.9409	0.9700
No log	6.8462	178	0.9467	0.2000	0.9467	0.9730
No log	6.9231	180	0.8850	0.1652	0.8850	0.9407
No log	7.0	182	0.8378	0.1570	0.8378	0.9153
No log	7.0769	184	0.8536	0.1504	0.8536	0.9239
No log	7.1538	186	0.8639	0.2000	0.8639	0.9295
No log	7.2308	188	0.9469	0.2000	0.9469	0.9731
No log	7.3077	190	0.9890	0.1815	0.9890	0.9945
No log	7.3846	192	1.1170	0.2174	1.1170	1.0569
No log	7.4615	194	1.2232	0.1608	1.2232	1.1060
No log	7.5385	196	1.1305	0.2000	1.1305	1.0632
No log	7.6154	198	0.9389	0.1093	0.9389	0.9690
No log	7.6923	200	0.8810	0.1245	0.8810	0.9386
No log	7.7692	202	0.8942	0.1245	0.8942	0.9456
No log	7.8462	204	1.0077	0.1698	1.0077	1.0038
No log	7.9231	206	1.1086	0.2000	1.1086	1.0529
No log	8.0	208	1.2102	0.2058	1.2102	1.1001
No log	8.0769	210	1.1928	0.1828	1.1928	1.0922
No log	8.1538	212	1.0505	0.2121	1.0505	1.0249
No log	8.2308	214	0.9567	0.2000	0.9567	0.9781
No log	8.3077	216	0.9203	0.0631	0.9203	0.9593
No log	8.3846	218	0.9289	0.0631	0.9289	0.9638
No log	8.4615	220	0.9391	0.0901	0.9391	0.9691
No log	8.5385	222	0.9883	0.1597	0.9883	0.9941
No log	8.6154	224	1.0836	0.2184	1.0836	1.0410
No log	8.6923	226	1.1806	0.1355	1.1806	1.0866
No log	8.7692	228	1.2651	0.1777	1.2651	1.1248
No log	8.8462	230	1.2520	0.1777	1.2520	1.1189
No log	8.9231	232	1.1508	0.1355	1.1508	1.0727
No log	9.0	234	1.0489	0.2184	1.0489	1.0242
No log	9.0769	236	1.0196	0.1535	1.0196	1.0098
No log	9.1538	238	0.9873	0.1535	0.9873	0.9936
No log	9.2308	240	0.9795	0.1535	0.9795	0.9897
No log	9.3077	242	0.9735	0.1933	0.9735	0.9866
No log	9.3846	244	0.9802	0.1535	0.9802	0.9901
No log	9.4615	246	0.9854	0.1535	0.9854	0.9926
No log	9.5385	248	0.9846	0.1535	0.9846	0.9923
No log	9.6154	250	0.9752	0.1535	0.9752	0.9875
No log	9.6923	252	0.9775	0.1535	0.9775	0.9887
No log	9.7692	254	0.9689	0.1660	0.9689	0.9843
No log	9.8462	256	0.9655	0.1660	0.9655	0.9826
No log	9.9231	258	0.9636	0.1660	0.9636	0.9816
No log	10.0	260	0.9651	0.1660	0.9651	0.9824

Framework versions

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