ArabicNewSplits6_FineTuningAraBERT_run3_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: 0.5946
• Qwk: 0.3575
• Mse: 0.5946
• Rmse: 0.7711

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	3.7859	0.0026	3.7859	1.9457
No log	0.1026	4	2.3511	-0.0144	2.3511	1.5333
No log	0.1538	6	1.1186	0.0255	1.1186	1.0576
No log	0.2051	8	0.7638	0.2709	0.7638	0.8739
No log	0.2564	10	0.5701	0.0569	0.5701	0.7550
No log	0.3077	12	0.5718	0.0569	0.5718	0.7562
No log	0.3590	14	0.5789	0.1220	0.5789	0.7609
No log	0.4103	16	0.8995	0.0698	0.8995	0.9484
No log	0.4615	18	1.0993	0.0	1.0993	1.0485
No log	0.5128	20	0.8796	0.1059	0.8796	0.9378
No log	0.5641	22	0.6890	0.0933	0.6890	0.8301
No log	0.6154	24	0.8874	0.0476	0.8874	0.9420
No log	0.6667	26	1.0897	0.0569	1.0897	1.0439
No log	0.7179	28	0.6523	0.0222	0.6523	0.8077
No log	0.7692	30	0.6169	-0.0159	0.6169	0.7854
No log	0.8205	32	0.6452	-0.0370	0.6452	0.8032
No log	0.8718	34	0.7957	0.0	0.7957	0.8920
No log	0.9231	36	1.0578	0.0745	1.0578	1.0285
No log	0.9744	38	1.0376	0.0745	1.0376	1.0186
No log	1.0256	40	0.6529	0.0476	0.6529	0.8080
No log	1.0769	42	0.6053	-0.0081	0.6053	0.7780
No log	1.1282	44	0.6161	-0.0159	0.6161	0.7849
No log	1.1795	46	0.6672	0.1895	0.6672	0.8168
No log	1.2308	48	0.6993	0.0053	0.6993	0.8362
No log	1.2821	50	0.6763	0.1429	0.6763	0.8224
No log	1.3333	52	0.7017	0.0417	0.7017	0.8377
No log	1.3846	54	0.6999	0.125	0.6999	0.8366
No log	1.4359	56	0.8538	0.1861	0.8538	0.9240
No log	1.4872	58	0.7789	0.2222	0.7789	0.8826
No log	1.5385	60	0.7135	0.1765	0.7135	0.8447
No log	1.5897	62	0.5366	0.2000	0.5366	0.7325
No log	1.6410	64	0.5160	0.1667	0.5160	0.7183
No log	1.6923	66	0.5702	0.2381	0.5702	0.7551
No log	1.7436	68	0.5445	0.3103	0.5445	0.7379
No log	1.7949	70	0.8894	0.1245	0.8894	0.9431
No log	1.8462	72	0.9814	0.1736	0.9814	0.9906
No log	1.8974	74	0.5951	0.4152	0.5951	0.7714
No log	1.9487	76	0.6271	0.2273	0.6271	0.7919
No log	2.0	78	0.6370	0.2093	0.6370	0.7981
No log	2.0513	80	0.6747	0.1832	0.6747	0.8214
No log	2.1026	82	0.6660	0.1323	0.6660	0.8161
No log	2.1538	84	0.6957	0.2626	0.6957	0.8341
No log	2.2051	86	0.7329	0.2174	0.7329	0.8561
No log	2.2564	88	0.8637	0.2300	0.8637	0.9294
No log	2.3077	90	0.7129	0.1489	0.7129	0.8444
No log	2.3590	92	0.6986	0.1323	0.6986	0.8358
No log	2.4103	94	0.8121	0.1848	0.8121	0.9012
No log	2.4615	96	0.8135	0.1481	0.8135	0.9019
No log	2.5128	98	0.7321	0.1340	0.7321	0.8556
No log	2.5641	100	0.7395	0.2410	0.7395	0.8599
No log	2.6154	102	0.7754	0.1776	0.7754	0.8806
No log	2.6667	104	0.6900	0.28	0.6900	0.8306
No log	2.7179	106	0.6480	0.2577	0.6480	0.8050
No log	2.7692	108	0.6149	0.3962	0.6149	0.7842
No log	2.8205	110	0.6810	0.2646	0.6810	0.8252
No log	2.8718	112	1.1223	0.1362	1.1223	1.0594
No log	2.9231	114	0.9305	0.2688	0.9305	0.9646
No log	2.9744	116	0.5903	0.5215	0.5903	0.7683
No log	3.0256	118	0.8568	0.2593	0.8568	0.9256
No log	3.0769	120	0.5693	0.4404	0.5693	0.7545
No log	3.1282	122	0.9013	0.2424	0.9013	0.9494
No log	3.1795	124	1.2577	0.1000	1.2577	1.1215
No log	3.2308	126	1.0374	0.2000	1.0374	1.0185
No log	3.2821	128	0.5560	0.2941	0.5560	0.7456
No log	3.3333	130	0.6113	0.2842	0.6113	0.7819
No log	3.3846	132	0.5716	0.2967	0.5716	0.7560
No log	3.4359	134	0.6445	0.3333	0.6445	0.8028
No log	3.4872	136	0.9677	0.2239	0.9677	0.9837
No log	3.5385	138	1.0433	0.1378	1.0433	1.0214
No log	3.5897	140	0.7767	0.2000	0.7767	0.8813
No log	3.6410	142	0.6804	0.1753	0.6804	0.8249
No log	3.6923	144	0.7049	0.1753	0.7049	0.8396
No log	3.7436	146	0.7925	0.2000	0.7925	0.8902
No log	3.7949	148	0.7780	0.2000	0.7780	0.8820
No log	3.8462	150	0.7355	0.2464	0.7355	0.8576
No log	3.8974	152	0.8124	0.2711	0.8124	0.9013
No log	3.9487	154	0.9062	0.2685	0.9062	0.9520
No log	4.0	156	0.7097	0.3231	0.7097	0.8425
No log	4.0513	158	0.7179	0.3171	0.7179	0.8473
No log	4.1026	160	0.8859	0.2374	0.8859	0.9412
No log	4.1538	162	0.7163	0.3524	0.7163	0.8464
No log	4.2051	164	0.5925	0.2707	0.5925	0.7697
No log	4.2564	166	0.6476	0.3730	0.6476	0.8048
No log	4.3077	168	0.7006	0.4010	0.7006	0.8370
No log	4.3590	170	0.6039	0.3778	0.6039	0.7771
No log	4.4103	172	0.5673	0.4424	0.5673	0.7532
No log	4.4615	174	0.5601	0.3778	0.5601	0.7484
No log	4.5128	176	0.5755	0.3661	0.5755	0.7586
No log	4.5641	178	0.5918	0.3548	0.5918	0.7693
No log	4.6154	180	0.7470	0.3128	0.7470	0.8643
No log	4.6667	182	0.8223	0.2743	0.8223	0.9068
No log	4.7179	184	0.7372	0.3091	0.7372	0.8586
No log	4.7692	186	0.6568	0.3478	0.6568	0.8104
No log	4.8205	188	0.6610	0.4033	0.6610	0.8130
No log	4.8718	190	0.7217	0.3028	0.7217	0.8495
No log	4.9231	192	0.6751	0.3010	0.6751	0.8216
No log	4.9744	194	0.6533	0.3010	0.6533	0.8082
No log	5.0256	196	0.7335	0.2372	0.7335	0.8564
No log	5.0769	198	0.6979	0.2692	0.6979	0.8354
No log	5.1282	200	0.6833	0.2607	0.6833	0.8266
No log	5.1795	202	0.8494	0.2713	0.8494	0.9216
No log	5.2308	204	0.8117	0.3058	0.8117	0.9010
No log	5.2821	206	0.7837	0.3455	0.7837	0.8853
No log	5.3333	208	0.7815	0.3362	0.7815	0.8840
No log	5.3846	210	0.8661	0.2698	0.8661	0.9306
No log	5.4359	212	0.7543	0.2775	0.7543	0.8685
No log	5.4872	214	0.5660	0.5238	0.5660	0.7523
No log	5.5385	216	0.5336	0.4222	0.5336	0.7305
No log	5.5897	218	0.5353	0.4620	0.5353	0.7317
No log	5.6410	220	0.6200	0.3333	0.6200	0.7874
No log	5.6923	222	0.7651	0.3537	0.7651	0.8747
No log	5.7436	224	0.6306	0.3333	0.6306	0.7941
No log	5.7949	226	0.5263	0.4483	0.5263	0.7254
No log	5.8462	228	0.5159	0.4350	0.5159	0.7183
No log	5.8974	230	0.5182	0.4483	0.5182	0.7199
No log	5.9487	232	0.5407	0.4286	0.5407	0.7353
No log	6.0	234	0.5357	0.3684	0.5357	0.7319
No log	6.0513	236	0.5800	0.3684	0.5800	0.7616
No log	6.1026	238	0.5516	0.4220	0.5516	0.7427
No log	6.1538	240	0.5597	0.4157	0.5597	0.7481
No log	6.2051	242	0.6182	0.4341	0.6182	0.7862
No log	6.2564	244	0.6566	0.4233	0.6566	0.8103
No log	6.3077	246	0.9036	0.2353	0.9036	0.9506
No log	6.3590	248	1.1496	0.1894	1.1496	1.0722
No log	6.4103	250	1.0396	0.2334	1.0396	1.0196
No log	6.4615	252	0.7737	0.2759	0.7737	0.8796
No log	6.5128	254	0.5845	0.3575	0.5845	0.7645
No log	6.5641	256	0.5679	0.3661	0.5679	0.7536
No log	6.6154	258	0.6405	0.3951	0.6405	0.8003
No log	6.6667	260	0.7089	0.3301	0.7089	0.8419
No log	6.7179	262	0.6148	0.4	0.6148	0.7841
No log	6.7692	264	0.5291	0.4220	0.5291	0.7274
No log	6.8205	266	0.5105	0.5254	0.5105	0.7145
No log	6.8718	268	0.5110	0.5111	0.5110	0.7148
No log	6.9231	270	0.5049	0.5402	0.5049	0.7106
No log	6.9744	272	0.6122	0.4341	0.6122	0.7824
No log	7.0256	274	0.7183	0.2857	0.7183	0.8475
No log	7.0769	276	0.6630	0.3548	0.6630	0.8143
No log	7.1282	278	0.5696	0.4105	0.5696	0.7547
No log	7.1795	280	0.5756	0.4051	0.5756	0.7587
No log	7.2308	282	0.5695	0.3730	0.5695	0.7546
No log	7.2821	284	0.6177	0.4341	0.6177	0.7860
No log	7.3333	286	0.6078	0.4341	0.6078	0.7796
No log	7.3846	288	0.5499	0.4545	0.5499	0.7416
No log	7.4359	290	0.5485	0.4413	0.5485	0.7406
No log	7.4872	292	0.5770	0.4157	0.5770	0.7596
No log	7.5385	294	0.5606	0.4220	0.5606	0.7488
No log	7.5897	296	0.5401	0.4667	0.5401	0.7349
No log	7.6410	298	0.5485	0.375	0.5485	0.7406
No log	7.6923	300	0.5398	0.4667	0.5398	0.7347
No log	7.7436	302	0.5465	0.3846	0.5465	0.7393
No log	7.7949	304	0.5766	0.4157	0.5766	0.7593
No log	7.8462	306	0.6449	0.4178	0.6449	0.8031
No log	7.8974	308	0.6687	0.4178	0.6687	0.8178
No log	7.9487	310	0.6357	0.4178	0.6357	0.7973
No log	8.0	312	0.6061	0.3978	0.6061	0.7786
No log	8.0513	314	0.5746	0.4413	0.5746	0.7580
No log	8.1026	316	0.5765	0.3846	0.5765	0.7593
No log	8.1538	318	0.6180	0.3978	0.6180	0.7861
No log	8.2051	320	0.6593	0.4178	0.6593	0.8120
No log	8.2564	322	0.6826	0.4178	0.6826	0.8262
No log	8.3077	324	0.6556	0.4178	0.6556	0.8097
No log	8.3590	326	0.6438	0.3846	0.6438	0.8024
No log	8.4103	328	0.6668	0.4178	0.6668	0.8166
No log	8.4615	330	0.6870	0.4128	0.6870	0.8288
No log	8.5128	332	0.7337	0.3667	0.7337	0.8565
No log	8.5641	334	0.7516	0.3306	0.7516	0.8669
No log	8.6154	336	0.7335	0.3667	0.7335	0.8565
No log	8.6667	338	0.6752	0.4128	0.6752	0.8217
No log	8.7179	340	0.6035	0.3878	0.6035	0.7768
No log	8.7692	342	0.5721	0.4348	0.5721	0.7564
No log	8.8205	344	0.5629	0.4413	0.5629	0.7503
No log	8.8718	346	0.5541	0.4413	0.5541	0.7444
No log	8.9231	348	0.5537	0.4413	0.5537	0.7441
No log	8.9744	350	0.5569	0.4413	0.5569	0.7463
No log	9.0256	352	0.5641	0.4413	0.5641	0.7511
No log	9.0769	354	0.5904	0.3878	0.5904	0.7684
No log	9.1282	356	0.6057	0.3575	0.6057	0.7783
No log	9.1795	358	0.6239	0.3535	0.6239	0.7899
No log	9.2308	360	0.6217	0.3535	0.6217	0.7885
No log	9.2821	362	0.6309	0.3535	0.6309	0.7943
No log	9.3333	364	0.6340	0.3535	0.6340	0.7962
No log	9.3846	366	0.6404	0.4231	0.6404	0.8002
No log	9.4359	368	0.6497	0.4231	0.6497	0.8060
No log	9.4872	370	0.6399	0.4231	0.6399	0.7999
No log	9.5385	372	0.6246	0.3535	0.6246	0.7903
No log	9.5897	374	0.6111	0.3575	0.6111	0.7817
No log	9.6410	376	0.5963	0.3575	0.5963	0.7722
No log	9.6923	378	0.5859	0.3617	0.5859	0.7654
No log	9.7436	380	0.5819	0.3617	0.5819	0.7628
No log	9.7949	382	0.5834	0.3617	0.5834	0.7638
No log	9.8462	384	0.5881	0.3617	0.5881	0.7669
No log	9.8974	386	0.5914	0.3575	0.5914	0.7690
No log	9.9487	388	0.5940	0.3575	0.5940	0.7707
No log	10.0	390	0.5946	0.3575	0.5946	0.7711

Framework versions

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