ArabicNewSplits_FineTuningAraBERT_AugV5_k10_task2_organization_fold1

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: 0.7550
• Qwk: 0.5459
• Mse: 0.7550
• Rmse: 0.8689

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	0.0541	2	5.6929	0.0168	5.6929	2.3860
No log	0.1081	4	3.7957	-0.0504	3.7957	1.9482
No log	0.1622	6	2.4211	-0.0634	2.4211	1.5560
No log	0.2162	8	1.2069	0.1229	1.2069	1.0986
No log	0.2703	10	0.7455	0.3504	0.7455	0.8634
No log	0.3243	12	0.6705	0.3964	0.6705	0.8189
No log	0.3784	14	0.6063	0.3985	0.6063	0.7787
No log	0.4324	16	1.2184	0.2456	1.2184	1.1038
No log	0.4865	18	2.7432	0.0645	2.7432	1.6563
No log	0.5405	20	2.7317	0.0292	2.7317	1.6528
No log	0.5946	22	1.6697	0.1299	1.6697	1.2922
No log	0.6486	24	1.1355	0.2109	1.1355	1.0656
No log	0.7027	26	0.9269	0.0466	0.9269	0.9627
No log	0.7568	28	0.6940	0.0878	0.6940	0.8331
No log	0.8108	30	0.5686	0.2062	0.5686	0.7540
No log	0.8649	32	0.6367	0.0989	0.6367	0.7979
No log	0.9189	34	0.7941	0.0480	0.7941	0.8911
No log	0.9730	36	1.2396	0.0849	1.2396	1.1134
No log	1.0270	38	1.8189	-0.1222	1.8189	1.3487
No log	1.0811	40	1.9419	-0.0428	1.9419	1.3935
No log	1.1351	42	1.8103	0.0193	1.8103	1.3455
No log	1.1892	44	1.5323	0.1906	1.5323	1.2379
No log	1.2432	46	1.2593	0.1742	1.2593	1.1222
No log	1.2973	48	1.0140	0.1961	1.0140	1.0070
No log	1.3514	50	0.9861	0.1439	0.9861	0.9930
No log	1.4054	52	0.9284	0.1354	0.9284	0.9636
No log	1.4595	54	0.7346	0.1160	0.7346	0.8571
No log	1.5135	56	0.6562	0.1234	0.6562	0.8101
No log	1.5676	58	0.7188	0.1273	0.7188	0.8478
No log	1.6216	60	0.9836	0.1598	0.9836	0.9918
No log	1.6757	62	1.2634	0.1529	1.2634	1.1240
No log	1.7297	64	1.1770	0.2106	1.1770	1.0849
No log	1.7838	66	1.0210	0.1480	1.0210	1.0105
No log	1.8378	68	0.8964	0.1273	0.8964	0.9468
No log	1.8919	70	0.8348	0.0813	0.8348	0.9137
No log	1.9459	72	0.8526	0.1273	0.8526	0.9233
No log	2.0	74	0.9668	0.1273	0.9668	0.9832
No log	2.0541	76	1.1918	0.1409	1.1918	1.0917
No log	2.1081	78	1.2674	0.1251	1.2674	1.1258
No log	2.1622	80	1.2560	0.1386	1.2560	1.1207
No log	2.2162	82	1.2286	0.1249	1.2286	1.1084
No log	2.2703	84	1.1476	0.1529	1.1476	1.0712
No log	2.3243	86	1.0467	0.2024	1.0467	1.0231
No log	2.3784	88	0.9094	0.3233	0.9094	0.9536
No log	2.4324	90	0.8638	0.3036	0.8638	0.9294
No log	2.4865	92	0.8111	0.4016	0.8111	0.9006
No log	2.5405	94	0.7352	0.4171	0.7352	0.8575
No log	2.5946	96	0.7403	0.4171	0.7403	0.8604
No log	2.6486	98	0.7732	0.4213	0.7732	0.8793
No log	2.7027	100	0.8820	0.3990	0.8820	0.9391
No log	2.7568	102	1.1033	0.2820	1.1033	1.0504
No log	2.8108	104	1.0757	0.2723	1.0757	1.0372
No log	2.8649	106	0.7935	0.3854	0.7935	0.8908
No log	2.9189	108	0.6562	0.1752	0.6562	0.8101
No log	2.9730	110	0.6886	0.0268	0.6886	0.8298
No log	3.0270	112	0.6660	0.0463	0.6660	0.8161
No log	3.0811	114	0.6120	0.3165	0.6120	0.7823
No log	3.1351	116	0.6552	0.3955	0.6552	0.8095
No log	3.1892	118	0.8944	0.4193	0.8944	0.9458
No log	3.2432	120	0.9683	0.3371	0.9683	0.9840
No log	3.2973	122	0.8323	0.4158	0.8323	0.9123
No log	3.3514	124	0.6300	0.3615	0.6300	0.7937
No log	3.4054	126	0.5232	0.3898	0.5232	0.7233
No log	3.4595	128	0.5052	0.4048	0.5052	0.7108
No log	3.5135	130	0.5179	0.3640	0.5179	0.7196
No log	3.5676	132	0.5660	0.2901	0.5660	0.7523
No log	3.6216	134	0.6349	0.3424	0.6349	0.7968
No log	3.6757	136	0.7058	0.2846	0.7058	0.8401
No log	3.7297	138	0.7156	0.2846	0.7156	0.8459
No log	3.7838	140	0.6752	0.3024	0.6752	0.8217
No log	3.8378	142	0.6498	0.3556	0.6498	0.8061
No log	3.8919	144	0.5990	0.3874	0.5990	0.7739
No log	3.9459	146	0.5524	0.3409	0.5524	0.7432
No log	4.0	148	0.5109	0.3433	0.5109	0.7147
No log	4.0541	150	0.5000	0.4007	0.5000	0.7071
No log	4.1081	152	0.4991	0.4007	0.4991	0.7065
No log	4.1622	154	0.5548	0.4646	0.5548	0.7448
No log	4.2162	156	0.6463	0.5051	0.6463	0.8039
No log	4.2703	158	0.6549	0.5164	0.6549	0.8093
No log	4.3243	160	0.5922	0.4650	0.5922	0.7695
No log	4.3784	162	0.5201	0.4561	0.5201	0.7211
No log	4.4324	164	0.5091	0.5645	0.5091	0.7135
No log	4.4865	166	0.5208	0.5633	0.5208	0.7217
No log	4.5405	168	0.5425	0.5296	0.5425	0.7366
No log	4.5946	170	0.5928	0.5098	0.5928	0.7699
No log	4.6486	172	0.6982	0.4571	0.6982	0.8356
No log	4.7027	174	0.8857	0.4358	0.8857	0.9411
No log	4.7568	176	1.0183	0.3789	1.0183	1.0091
No log	4.8108	178	1.0296	0.3789	1.0296	1.0147
No log	4.8649	180	0.8922	0.4258	0.8922	0.9446
No log	4.9189	182	0.7415	0.4340	0.7415	0.8611
No log	4.9730	184	0.6244	0.4828	0.6244	0.7902
No log	5.0270	186	0.5802	0.5005	0.5802	0.7617
No log	5.0811	188	0.5859	0.5005	0.5859	0.7654
No log	5.1351	190	0.6190	0.4830	0.6190	0.7868
No log	5.1892	192	0.6819	0.4928	0.6819	0.8258
No log	5.2432	194	0.7083	0.4796	0.7083	0.8416
No log	5.2973	196	0.6724	0.5163	0.6724	0.8200
No log	5.3514	198	0.6181	0.4584	0.6181	0.7862
No log	5.4054	200	0.6118	0.5422	0.6118	0.7822
No log	5.4595	202	0.6340	0.5300	0.6340	0.7962
No log	5.5135	204	0.6590	0.5297	0.6590	0.8118
No log	5.5676	206	0.6986	0.5488	0.6986	0.8358
No log	5.6216	208	0.7406	0.5459	0.7406	0.8606
No log	5.6757	210	0.7644	0.5347	0.7644	0.8743
No log	5.7297	212	0.7944	0.5133	0.7944	0.8913
No log	5.7838	214	0.8237	0.4808	0.8237	0.9076
No log	5.8378	216	0.8410	0.4032	0.8410	0.9171
No log	5.8919	218	0.8483	0.4638	0.8483	0.9210
No log	5.9459	220	0.8522	0.4645	0.8522	0.9231
No log	6.0	222	0.8327	0.5335	0.8327	0.9125
No log	6.0541	224	0.8150	0.5170	0.8150	0.9028
No log	6.1081	226	0.7994	0.5085	0.7994	0.8941
No log	6.1622	228	0.7608	0.5175	0.7608	0.8723
No log	6.2162	230	0.7277	0.4964	0.7277	0.8530
No log	6.2703	232	0.7029	0.5063	0.7029	0.8384
No log	6.3243	234	0.6840	0.5400	0.6840	0.8270
No log	6.3784	236	0.6801	0.4979	0.6801	0.8247
No log	6.4324	238	0.6943	0.4980	0.6943	0.8332
No log	6.4865	240	0.7060	0.4980	0.7060	0.8402
No log	6.5405	242	0.7361	0.4959	0.7361	0.8579
No log	6.5946	244	0.7468	0.4873	0.7468	0.8642
No log	6.6486	246	0.7588	0.5081	0.7588	0.8711
No log	6.7027	248	0.7599	0.5081	0.7599	0.8717
No log	6.7568	250	0.7519	0.5252	0.7519	0.8671
No log	6.8108	252	0.7436	0.5034	0.7436	0.8623
No log	6.8649	254	0.7459	0.5113	0.7459	0.8637
No log	6.9189	256	0.7410	0.5323	0.7410	0.8608
No log	6.9730	258	0.7277	0.5113	0.7277	0.8530
No log	7.0270	260	0.7237	0.5030	0.7237	0.8507
No log	7.0811	262	0.7356	0.5061	0.7356	0.8577
No log	7.1351	264	0.7403	0.5067	0.7403	0.8604
No log	7.1892	266	0.7351	0.5061	0.7351	0.8574
No log	7.2432	268	0.7327	0.5061	0.7327	0.8560
No log	7.2973	270	0.7279	0.5155	0.7279	0.8532
No log	7.3514	272	0.7205	0.5163	0.7205	0.8488
No log	7.4054	274	0.7113	0.5478	0.7113	0.8434
No log	7.4595	276	0.7059	0.5721	0.7059	0.8402
No log	7.5135	278	0.7050	0.5206	0.7050	0.8396
No log	7.5676	280	0.6901	0.4996	0.6901	0.8307
No log	7.6216	282	0.6742	0.5407	0.6742	0.8211
No log	7.6757	284	0.6730	0.5400	0.6730	0.8204
No log	7.7297	286	0.6754	0.5055	0.6754	0.8218
No log	7.7838	288	0.6846	0.5376	0.6846	0.8274
No log	7.8378	290	0.6972	0.5376	0.6972	0.8350
No log	7.8919	292	0.7148	0.5366	0.7148	0.8455
No log	7.9459	294	0.7280	0.5351	0.7280	0.8532
No log	8.0	296	0.7420	0.5243	0.7420	0.8614
No log	8.0541	298	0.7519	0.5233	0.7519	0.8671
No log	8.1081	300	0.7572	0.5141	0.7572	0.8702
No log	8.1622	302	0.7571	0.5450	0.7571	0.8701
No log	8.2162	304	0.7541	0.5450	0.7541	0.8684
No log	8.2703	306	0.7484	0.5459	0.7484	0.8651
No log	8.3243	308	0.7468	0.5459	0.7468	0.8642
No log	8.3784	310	0.7590	0.5459	0.7590	0.8712
No log	8.4324	312	0.7698	0.5437	0.7698	0.8774
No log	8.4865	314	0.7794	0.5124	0.7794	0.8828
No log	8.5405	316	0.7936	0.4709	0.7936	0.8908
No log	8.5946	318	0.8003	0.4699	0.8003	0.8946
No log	8.6486	320	0.8010	0.4699	0.8010	0.8950
No log	8.7027	322	0.7944	0.4804	0.7944	0.8913
No log	8.7568	324	0.7895	0.4936	0.7895	0.8885
No log	8.8108	326	0.7852	0.5233	0.7852	0.8861
No log	8.8649	328	0.7817	0.5158	0.7817	0.8842
No log	8.9189	330	0.7839	0.4977	0.7839	0.8854
No log	8.9730	332	0.7884	0.5178	0.7884	0.8879
No log	9.0270	334	0.7910	0.5281	0.7910	0.8894
No log	9.0811	336	0.7891	0.5178	0.7891	0.8883
No log	9.1351	338	0.7883	0.5178	0.7883	0.8879
No log	9.1892	340	0.7871	0.4977	0.7871	0.8872
No log	9.2432	342	0.7844	0.5068	0.7844	0.8856
No log	9.2973	344	0.7804	0.5068	0.7804	0.8834
No log	9.3514	346	0.7744	0.5459	0.7744	0.8800
No log	9.4054	348	0.7703	0.5464	0.7703	0.8777
No log	9.4595	350	0.7672	0.5464	0.7672	0.8759
No log	9.5135	352	0.7637	0.5464	0.7637	0.8739
No log	9.5676	354	0.7620	0.5464	0.7620	0.8729
No log	9.6216	356	0.7591	0.5464	0.7591	0.8713
No log	9.6757	358	0.7575	0.5464	0.7575	0.8704
No log	9.7297	360	0.7563	0.5464	0.7563	0.8697
No log	9.7838	362	0.7557	0.5464	0.7557	0.8693
No log	9.8378	364	0.7551	0.5464	0.7551	0.8690
No log	9.8919	366	0.7547	0.5459	0.7547	0.8688
No log	9.9459	368	0.7549	0.5459	0.7549	0.8689
No log	10.0	370	0.7550	0.5459	0.7550	0.8689

Framework versions

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