ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k7_task7_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: 0.4645
• Qwk: 0.5414
• Mse: 0.4645
• Rmse: 0.6815

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.1	2	2.5233	-0.0924	2.5233	1.5885
No log	0.2	4	1.3088	-0.0141	1.3088	1.1440
No log	0.3	6	0.8683	-0.0841	0.8683	0.9318
No log	0.4	8	0.7302	0.1232	0.7302	0.8545
No log	0.5	10	0.7162	0.1321	0.7162	0.8463
No log	0.6	12	0.6981	0.0851	0.6981	0.8355
No log	0.7	14	0.7524	0.2558	0.7524	0.8674
No log	0.8	16	0.8060	0.3173	0.8060	0.8978
No log	0.9	18	0.8405	0.2841	0.8405	0.9168
No log	1.0	20	0.7620	0.1372	0.7620	0.8729
No log	1.1	22	0.7405	-0.0500	0.7405	0.8605
No log	1.2	24	0.7865	0.1313	0.7865	0.8869
No log	1.3	26	0.7876	0.3099	0.7876	0.8875
No log	1.4	28	0.7940	0.1550	0.7940	0.8911
No log	1.5	30	0.7659	0.1007	0.7659	0.8751
No log	1.6	32	0.7374	0.1508	0.7374	0.8587
No log	1.7	34	0.6885	0.0717	0.6885	0.8298
No log	1.8	36	0.6536	0.1942	0.6536	0.8084
No log	1.9	38	0.6287	0.3019	0.6287	0.7929
No log	2.0	40	0.6473	0.2522	0.6473	0.8046
No log	2.1	42	0.6844	0.2464	0.6844	0.8273
No log	2.2	44	0.6941	0.2526	0.6941	0.8331
No log	2.3	46	0.6201	0.1903	0.6201	0.7874
No log	2.4	48	0.7380	0.3699	0.7380	0.8591
No log	2.5	50	0.8358	0.3409	0.8358	0.9142
No log	2.6	52	0.7689	0.2574	0.7689	0.8769
No log	2.7	54	0.6042	0.3274	0.6042	0.7773
No log	2.8	56	0.5931	0.3151	0.5931	0.7702
No log	2.9	58	0.5894	0.3499	0.5894	0.7677
No log	3.0	60	0.5806	0.3105	0.5806	0.7620
No log	3.1	62	0.5450	0.3151	0.5450	0.7383
No log	3.2	64	0.5751	0.4330	0.5751	0.7584
No log	3.3	66	0.6648	0.3799	0.6648	0.8154
No log	3.4	68	0.6144	0.3843	0.6144	0.7838
No log	3.5	70	0.5593	0.4795	0.5593	0.7479
No log	3.6	72	0.5600	0.5056	0.5600	0.7483
No log	3.7	74	0.6526	0.3544	0.6526	0.8078
No log	3.8	76	0.5819	0.3813	0.5819	0.7628
No log	3.9	78	0.5555	0.3945	0.5555	0.7453
No log	4.0	80	0.5708	0.4044	0.5708	0.7555
No log	4.1	82	0.6447	0.3662	0.6447	0.8029
No log	4.2	84	0.6419	0.2843	0.6419	0.8012
No log	4.3	86	0.5694	0.4322	0.5694	0.7546
No log	4.4	88	0.5370	0.4908	0.5370	0.7328
No log	4.5	90	0.5236	0.5373	0.5236	0.7236
No log	4.6	92	0.4961	0.5283	0.4961	0.7044
No log	4.7	94	0.4922	0.4938	0.4922	0.7016
No log	4.8	96	0.5326	0.4315	0.5326	0.7298
No log	4.9	98	0.7995	0.4542	0.7995	0.8941
No log	5.0	100	0.8886	0.4305	0.8886	0.9426
No log	5.1	102	0.6931	0.4646	0.6931	0.8325
No log	5.2	104	0.6230	0.4134	0.6230	0.7893
No log	5.3	106	0.5970	0.4473	0.5970	0.7726
No log	5.4	108	0.5134	0.5815	0.5134	0.7165
No log	5.5	110	0.5123	0.6377	0.5123	0.7158
No log	5.6	112	0.5193	0.5177	0.5193	0.7206
No log	5.7	114	0.6263	0.4550	0.6263	0.7914
No log	5.8	116	0.7560	0.4667	0.7560	0.8695
No log	5.9	118	0.6685	0.4197	0.6685	0.8176
No log	6.0	120	0.5907	0.4801	0.5907	0.7686
No log	6.1	122	0.5248	0.4937	0.5248	0.7244
No log	6.2	124	0.5209	0.5289	0.5209	0.7217
No log	6.3	126	0.5522	0.5357	0.5522	0.7431
No log	6.4	128	0.6117	0.4933	0.6117	0.7821
No log	6.5	130	0.7040	0.5175	0.7040	0.8391
No log	6.6	132	0.5287	0.5024	0.5287	0.7271
No log	6.7	134	0.4620	0.5555	0.4620	0.6797
No log	6.8	136	0.4635	0.5479	0.4635	0.6808
No log	6.9	138	0.4618	0.5846	0.4618	0.6795
No log	7.0	140	0.4756	0.6377	0.4756	0.6897
No log	7.1	142	0.5106	0.6340	0.5106	0.7146
No log	7.2	144	0.5337	0.5332	0.5337	0.7306
No log	7.3	146	0.5209	0.6492	0.5209	0.7217
No log	7.4	148	0.5015	0.5593	0.5015	0.7082
No log	7.5	150	0.5069	0.5323	0.5069	0.7120
No log	7.6	152	0.5101	0.5095	0.5101	0.7142
No log	7.7	154	0.5196	0.5326	0.5196	0.7209
No log	7.8	156	0.5499	0.4795	0.5499	0.7415
No log	7.9	158	0.5499	0.5056	0.5499	0.7415
No log	8.0	160	0.5942	0.3471	0.5942	0.7708
No log	8.1	162	0.6585	0.4424	0.6585	0.8115
No log	8.2	164	0.5898	0.4473	0.5898	0.7680
No log	8.3	166	0.5671	0.5056	0.5671	0.7530
No log	8.4	168	0.5678	0.5379	0.5678	0.7535
No log	8.5	170	0.5724	0.5304	0.5724	0.7566
No log	8.6	172	0.5710	0.6156	0.5710	0.7557
No log	8.7	174	0.5871	0.5201	0.5871	0.7662
No log	8.8	176	0.6356	0.4864	0.6356	0.7972
No log	8.9	178	0.6221	0.4864	0.6221	0.7887
No log	9.0	180	0.6404	0.4864	0.6404	0.8002
No log	9.1	182	0.5869	0.5034	0.5869	0.7661
No log	9.2	184	0.5781	0.4617	0.5781	0.7604
No log	9.3	186	0.5876	0.4828	0.5876	0.7666
No log	9.4	188	0.6450	0.4513	0.6450	0.8031
No log	9.5	190	0.7526	0.3941	0.7526	0.8675
No log	9.6	192	0.6579	0.4522	0.6579	0.8111
No log	9.7	194	0.5595	0.5800	0.5595	0.7480
No log	9.8	196	0.6151	0.4817	0.6151	0.7843
No log	9.9	198	0.6127	0.4654	0.6127	0.7828
No log	10.0	200	0.5582	0.5681	0.5582	0.7471
No log	10.1	202	0.5665	0.5567	0.5665	0.7527
No log	10.2	204	0.5797	0.5141	0.5797	0.7614
No log	10.3	206	0.6011	0.4895	0.6011	0.7753
No log	10.4	208	0.6128	0.5123	0.6128	0.7828
No log	10.5	210	0.6439	0.4444	0.6439	0.8024
No log	10.6	212	0.6599	0.4369	0.6599	0.8124
No log	10.7	214	0.6075	0.4764	0.6075	0.7794
No log	10.8	216	0.5642	0.4622	0.5642	0.7511
No log	10.9	218	0.5540	0.5098	0.5540	0.7443
No log	11.0	220	0.5694	0.4112	0.5694	0.7546
No log	11.1	222	0.5907	0.4522	0.5907	0.7686
No log	11.2	224	0.6347	0.4531	0.6347	0.7967
No log	11.3	226	0.6701	0.4684	0.6701	0.8186
No log	11.4	228	0.6204	0.4822	0.6204	0.7877
No log	11.5	230	0.6308	0.4822	0.6308	0.7942
No log	11.6	232	0.6835	0.4606	0.6835	0.8267
No log	11.7	234	0.7278	0.4512	0.7278	0.8531
No log	11.8	236	0.6679	0.4444	0.6679	0.8173
No log	11.9	238	0.5834	0.3942	0.5834	0.7638
No log	12.0	240	0.5323	0.3625	0.5323	0.7296
No log	12.1	242	0.5180	0.3502	0.5180	0.7197
No log	12.2	244	0.5147	0.4278	0.5147	0.7174
No log	12.3	246	0.5528	0.5098	0.5528	0.7435
No log	12.4	248	0.5705	0.5957	0.5705	0.7553
No log	12.5	250	0.6012	0.5934	0.6012	0.7754
No log	12.6	252	0.5870	0.5934	0.5870	0.7662
No log	12.7	254	0.5270	0.6052	0.5270	0.7260
No log	12.8	256	0.5129	0.5306	0.5129	0.7162
No log	12.9	258	0.5053	0.5075	0.5053	0.7108
No log	13.0	260	0.5094	0.4953	0.5094	0.7138
No log	13.1	262	0.5552	0.3498	0.5552	0.7451
No log	13.2	264	0.6488	0.3843	0.6488	0.8055
No log	13.3	266	0.7558	0.3675	0.7558	0.8694
No log	13.4	268	0.7034	0.4154	0.7034	0.8387
No log	13.5	270	0.5562	0.3471	0.5562	0.7458
No log	13.6	272	0.5382	0.6047	0.5382	0.7336
No log	13.7	274	0.5766	0.5808	0.5766	0.7593
No log	13.8	276	0.5390	0.5983	0.5390	0.7342
No log	13.9	278	0.4994	0.5141	0.4994	0.7067
No log	14.0	280	0.5967	0.5068	0.5967	0.7725
No log	14.1	282	0.6183	0.5068	0.6183	0.7863
No log	14.2	284	0.5351	0.5149	0.5351	0.7315
No log	14.3	286	0.5019	0.5750	0.5019	0.7084
No log	14.4	288	0.5201	0.5422	0.5201	0.7212
No log	14.5	290	0.5200	0.5918	0.5200	0.7211
No log	14.6	292	0.5246	0.5783	0.5246	0.7243
No log	14.7	294	0.5952	0.5748	0.5952	0.7715
No log	14.8	296	0.6999	0.4286	0.6999	0.8366
No log	14.9	298	0.6607	0.4385	0.6607	0.8128
No log	15.0	300	0.5755	0.4081	0.5755	0.7586
No log	15.1	302	0.5475	0.4314	0.5475	0.7399
No log	15.2	304	0.5521	0.3399	0.5521	0.7430
No log	15.3	306	0.6277	0.4197	0.6277	0.7923
No log	15.4	308	0.7178	0.4203	0.7178	0.8472
No log	15.5	310	0.6724	0.3819	0.6724	0.8200
No log	15.6	312	0.5596	0.3918	0.5596	0.7480
No log	15.7	314	0.5105	0.3728	0.5105	0.7145
No log	15.8	316	0.5010	0.4878	0.5010	0.7078
No log	15.9	318	0.4991	0.5268	0.4991	0.7065
No log	16.0	320	0.5198	0.4493	0.5198	0.7210
No log	16.1	322	0.5731	0.5098	0.5731	0.7571
No log	16.2	324	0.6530	0.4243	0.6530	0.8081
No log	16.3	326	0.6408	0.3776	0.6408	0.8005
No log	16.4	328	0.5736	0.3867	0.5736	0.7574
No log	16.5	330	0.5075	0.4459	0.5075	0.7124
No log	16.6	332	0.5018	0.4267	0.5018	0.7084
No log	16.7	334	0.5321	0.4352	0.5321	0.7294
No log	16.8	336	0.5329	0.4997	0.5329	0.7300
No log	16.9	338	0.5077	0.4534	0.5077	0.7125
No log	17.0	340	0.5141	0.4451	0.5141	0.7170
No log	17.1	342	0.5649	0.4898	0.5649	0.7516
No log	17.2	344	0.6486	0.4468	0.6486	0.8054
No log	17.3	346	0.6606	0.4468	0.6606	0.8128
No log	17.4	348	0.5764	0.4444	0.5764	0.7592
No log	17.5	350	0.5268	0.4451	0.5268	0.7258
No log	17.6	352	0.5082	0.4948	0.5082	0.7129
No log	17.7	354	0.5052	0.5159	0.5052	0.7108
No log	17.8	356	0.5185	0.3701	0.5185	0.7200
No log	17.9	358	0.5292	0.3894	0.5292	0.7275
No log	18.0	360	0.5554	0.4219	0.5554	0.7452
No log	18.1	362	0.5570	0.4925	0.5570	0.7464
No log	18.2	364	0.5342	0.4451	0.5342	0.7309
No log	18.3	366	0.5252	0.4212	0.5252	0.7247
No log	18.4	368	0.5239	0.4724	0.5239	0.7238
No log	18.5	370	0.5112	0.5289	0.5112	0.7150
No log	18.6	372	0.5109	0.5344	0.5109	0.7148
No log	18.7	374	0.5131	0.5584	0.5131	0.7163
No log	18.8	376	0.5163	0.4591	0.5163	0.7186
No log	18.9	378	0.5312	0.4684	0.5312	0.7288
No log	19.0	380	0.5930	0.3918	0.5930	0.7701
No log	19.1	382	0.7395	0.4961	0.7395	0.8599
No log	19.2	384	0.7928	0.4961	0.7928	0.8904
No log	19.3	386	0.7184	0.4648	0.7184	0.8476
No log	19.4	388	0.5833	0.4444	0.5833	0.7637
No log	19.5	390	0.5267	0.4451	0.5267	0.7257
No log	19.6	392	0.5365	0.4451	0.5365	0.7325
No log	19.7	394	0.5965	0.4444	0.5965	0.7723
No log	19.8	396	0.6128	0.4444	0.6128	0.7828
No log	19.9	398	0.5881	0.4531	0.5881	0.7669
No log	20.0	400	0.5256	0.4270	0.5256	0.7250
No log	20.1	402	0.5106	0.5899	0.5106	0.7146
No log	20.2	404	0.5181	0.5956	0.5181	0.7198
No log	20.3	406	0.5098	0.5003	0.5098	0.7140
No log	20.4	408	0.5077	0.4726	0.5077	0.7125
No log	20.5	410	0.5377	0.4835	0.5377	0.7333
No log	20.6	412	0.5999	0.4819	0.5999	0.7745
No log	20.7	414	0.6034	0.4819	0.6034	0.7768
No log	20.8	416	0.5823	0.4664	0.5823	0.7631
No log	20.9	418	0.5612	0.4835	0.5612	0.7491
No log	21.0	420	0.5255	0.4437	0.5255	0.7249
No log	21.1	422	0.5185	0.3701	0.5185	0.7200
No log	21.2	424	0.5317	0.3976	0.5317	0.7292
No log	21.3	426	0.5557	0.3814	0.5557	0.7455
No log	21.4	428	0.5698	0.3867	0.5698	0.7549
No log	21.5	430	0.5721	0.4350	0.5721	0.7564
No log	21.6	432	0.5772	0.3918	0.5772	0.7597
No log	21.7	434	0.5424	0.4502	0.5424	0.7365
No log	21.8	436	0.5021	0.4569	0.5021	0.7086
No log	21.9	438	0.4888	0.5475	0.4888	0.6991
No log	22.0	440	0.4842	0.5890	0.4842	0.6958
No log	22.1	442	0.4766	0.5812	0.4766	0.6904
No log	22.2	444	0.4724	0.5831	0.4724	0.6873
No log	22.3	446	0.4801	0.5831	0.4801	0.6929
No log	22.4	448	0.4800	0.6024	0.4800	0.6928
No log	22.5	450	0.4861	0.6269	0.4861	0.6972
No log	22.6	452	0.4922	0.6389	0.4922	0.7015
No log	22.7	454	0.4971	0.6553	0.4971	0.7050
No log	22.8	456	0.5077	0.6620	0.5077	0.7125
No log	22.9	458	0.4969	0.6024	0.4969	0.7049
No log	23.0	460	0.4976	0.5472	0.4976	0.7054
No log	23.1	462	0.5079	0.5533	0.5079	0.7127
No log	23.2	464	0.5652	0.3891	0.5652	0.7518
No log	23.3	466	0.6062	0.4315	0.6062	0.7786
No log	23.4	468	0.6202	0.4315	0.6202	0.7875
No log	23.5	470	0.6658	0.4721	0.6658	0.8160
No log	23.6	472	0.6369	0.4315	0.6369	0.7980
No log	23.7	474	0.5770	0.3914	0.5770	0.7596
No log	23.8	476	0.5135	0.4788	0.5135	0.7166
No log	23.9	478	0.4954	0.5671	0.4954	0.7039
No log	24.0	480	0.4957	0.5437	0.4957	0.7040
No log	24.1	482	0.5109	0.4704	0.5109	0.7148
No log	24.2	484	0.5617	0.4759	0.5617	0.7494
No log	24.3	486	0.5574	0.4389	0.5574	0.7466
No log	24.4	488	0.5202	0.5036	0.5202	0.7212
No log	24.5	490	0.5074	0.4929	0.5074	0.7123
No log	24.6	492	0.5108	0.5714	0.5108	0.7147
No log	24.7	494	0.5240	0.5945	0.5240	0.7239
No log	24.8	496	0.5447	0.5649	0.5447	0.7380
No log	24.9	498	0.5432	0.5999	0.5432	0.7370
0.2974	25.0	500	0.5465	0.6101	0.5465	0.7393
0.2974	25.1	502	0.5456	0.5340	0.5456	0.7387
0.2974	25.2	504	0.5209	0.5875	0.5209	0.7217
0.2974	25.3	506	0.4932	0.5812	0.4932	0.7023
0.2974	25.4	508	0.4808	0.5266	0.4808	0.6934
0.2974	25.5	510	0.4645	0.5414	0.4645	0.6815

Framework versions

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