ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k9_task2_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: 0.7986
• Qwk: 0.5287
• Mse: 0.7986
• Rmse: 0.8937

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	0.0435	2	4.0966	-0.0313	4.0966	2.0240
No log	0.0870	4	2.2832	0.0468	2.2832	1.5110
No log	0.1304	6	2.1838	-0.1226	2.1838	1.4778
No log	0.1739	8	1.5826	-0.0010	1.5826	1.2580
No log	0.2174	10	0.8319	0.0385	0.8319	0.9121
No log	0.2609	12	0.7673	0.1208	0.7673	0.8760
No log	0.3043	14	0.9202	0.0316	0.9202	0.9593
No log	0.3478	16	0.7622	0.0804	0.7622	0.8730
No log	0.3913	18	0.7568	0.0570	0.7568	0.8699
No log	0.4348	20	0.9889	0.0807	0.9889	0.9944
No log	0.4783	22	1.0113	0.1497	1.0113	1.0056
No log	0.5217	24	0.7838	0.2633	0.7838	0.8854
No log	0.5652	26	0.6620	0.2825	0.6620	0.8136
No log	0.6087	28	0.6632	0.2825	0.6632	0.8144
No log	0.6522	30	0.6545	0.3241	0.6545	0.8090
No log	0.6957	32	0.6368	0.3507	0.6368	0.7980
No log	0.7391	34	0.7016	0.3332	0.7016	0.8376
No log	0.7826	36	1.0187	0.2734	1.0187	1.0093
No log	0.8261	38	1.2701	0.2244	1.2701	1.1270
No log	0.8696	40	1.3238	0.1558	1.3238	1.1506
No log	0.9130	42	1.1235	0.1657	1.1235	1.0600
No log	0.9565	44	0.8890	0.2529	0.8890	0.9429
No log	1.0	46	0.6641	0.3573	0.6641	0.8149
No log	1.0435	48	0.5396	0.4577	0.5396	0.7346
No log	1.0870	50	0.5214	0.4543	0.5214	0.7221
No log	1.1304	52	0.5365	0.5496	0.5365	0.7325
No log	1.1739	54	0.7492	0.3821	0.7492	0.8655
No log	1.2174	56	1.5540	0.2638	1.5540	1.2466
No log	1.2609	58	1.9573	0.1637	1.9573	1.3990
No log	1.3043	60	1.5752	0.2645	1.5752	1.2551
No log	1.3478	62	1.0893	0.3939	1.0893	1.0437
No log	1.3913	64	0.7537	0.4257	0.7537	0.8682
No log	1.4348	66	0.6882	0.4690	0.6882	0.8296
No log	1.4783	68	0.6515	0.4898	0.6515	0.8072
No log	1.5217	70	0.5925	0.4773	0.5925	0.7698
No log	1.5652	72	0.5750	0.4575	0.5750	0.7583
No log	1.6087	74	0.5616	0.3851	0.5616	0.7494
No log	1.6522	76	0.5627	0.3627	0.5627	0.7501
No log	1.6957	78	0.5694	0.3627	0.5694	0.7546
No log	1.7391	80	0.5730	0.3834	0.5730	0.7570
No log	1.7826	82	0.5758	0.4236	0.5758	0.7588
No log	1.8261	84	0.5729	0.4286	0.5729	0.7569
No log	1.8696	86	0.5689	0.4702	0.5689	0.7543
No log	1.9130	88	0.5851	0.4702	0.5851	0.7649
No log	1.9565	90	0.6136	0.4392	0.6136	0.7833
No log	2.0	92	0.7650	0.4798	0.7650	0.8746
No log	2.0435	94	0.8764	0.4383	0.8764	0.9362
No log	2.0870	96	0.9638	0.3854	0.9638	0.9817
No log	2.1304	98	0.8663	0.4520	0.8663	0.9308
No log	2.1739	100	0.7312	0.4997	0.7312	0.8551
No log	2.2174	102	0.6351	0.6025	0.6351	0.7969
No log	2.2609	104	0.6338	0.5580	0.6338	0.7961
No log	2.3043	106	0.6384	0.6025	0.6384	0.7990
No log	2.3478	108	0.7158	0.5343	0.7158	0.8460
No log	2.3913	110	0.9676	0.4125	0.9676	0.9836
No log	2.4348	112	1.0036	0.3987	1.0036	1.0018
No log	2.4783	114	0.8294	0.4337	0.8294	0.9107
No log	2.5217	116	0.6639	0.5951	0.6639	0.8148
No log	2.5652	118	0.6496	0.6106	0.6496	0.8060
No log	2.6087	120	0.6571	0.5895	0.6571	0.8106
No log	2.6522	122	0.7016	0.5428	0.7016	0.8376
No log	2.6957	124	0.8201	0.4698	0.8201	0.9056
No log	2.7391	126	0.9149	0.4521	0.9149	0.9565
No log	2.7826	128	0.8738	0.4680	0.8738	0.9348
No log	2.8261	130	0.8061	0.5236	0.8061	0.8978
No log	2.8696	132	0.7894	0.4953	0.7894	0.8885
No log	2.9130	134	0.8038	0.4812	0.8038	0.8965
No log	2.9565	136	0.8460	0.4423	0.8460	0.9198
No log	3.0	138	0.8966	0.4989	0.8966	0.9469
No log	3.0435	140	0.9146	0.4938	0.9146	0.9564
No log	3.0870	142	0.8957	0.4925	0.8957	0.9464
No log	3.1304	144	0.8826	0.4982	0.8826	0.9395
No log	3.1739	146	0.8435	0.4871	0.8435	0.9184
No log	3.2174	148	0.8069	0.5069	0.8069	0.8983
No log	3.2609	150	0.8228	0.5147	0.8228	0.9071
No log	3.3043	152	0.8082	0.5180	0.8082	0.8990
No log	3.3478	154	0.8422	0.5215	0.8422	0.9177
No log	3.3913	156	0.9114	0.5335	0.9114	0.9547
No log	3.4348	158	0.9168	0.5130	0.9168	0.9575
No log	3.4783	160	0.8982	0.5099	0.8982	0.9478
No log	3.5217	162	0.9247	0.4838	0.9247	0.9616
No log	3.5652	164	0.9284	0.4985	0.9284	0.9635
No log	3.6087	166	0.8685	0.4890	0.8685	0.9319
No log	3.6522	168	0.8539	0.5145	0.8539	0.9241
No log	3.6957	170	0.8229	0.5274	0.8229	0.9072
No log	3.7391	172	0.7642	0.5302	0.7642	0.8742
No log	3.7826	174	0.7397	0.5421	0.7397	0.8601
No log	3.8261	176	0.7399	0.5499	0.7399	0.8602
No log	3.8696	178	0.7836	0.5034	0.7836	0.8852
No log	3.9130	180	0.7889	0.5220	0.7889	0.8882
No log	3.9565	182	0.7666	0.5461	0.7666	0.8756
No log	4.0	184	0.7692	0.5109	0.7692	0.8770
No log	4.0435	186	0.7727	0.5276	0.7727	0.8790
No log	4.0870	188	0.8143	0.5321	0.8143	0.9024
No log	4.1304	190	0.8902	0.4818	0.8902	0.9435
No log	4.1739	192	0.9015	0.4842	0.9015	0.9495
No log	4.2174	194	0.8527	0.4926	0.8527	0.9234
No log	4.2609	196	0.8166	0.5204	0.8166	0.9037
No log	4.3043	198	0.8235	0.5354	0.8235	0.9075
No log	4.3478	200	0.8283	0.5276	0.8283	0.9101
No log	4.3913	202	0.8193	0.4844	0.8193	0.9051
No log	4.4348	204	0.8362	0.4927	0.8362	0.9144
No log	4.4783	206	0.7994	0.5089	0.7994	0.8941
No log	4.5217	208	0.7508	0.5140	0.7508	0.8665
No log	4.5652	210	0.6846	0.5340	0.6846	0.8274
No log	4.6087	212	0.6754	0.5548	0.6754	0.8218
No log	4.6522	214	0.6768	0.5392	0.6768	0.8227
No log	4.6957	216	0.6758	0.5222	0.6758	0.8221
No log	4.7391	218	0.6818	0.5415	0.6818	0.8257
No log	4.7826	220	0.7060	0.5553	0.7060	0.8402
No log	4.8261	222	0.7234	0.5393	0.7234	0.8505
No log	4.8696	224	0.7806	0.5068	0.7806	0.8835
No log	4.9130	226	0.9067	0.5021	0.9067	0.9522
No log	4.9565	228	1.1332	0.4300	1.1332	1.0645
No log	5.0	230	1.2254	0.3824	1.2254	1.1070
No log	5.0435	232	1.1437	0.4067	1.1437	1.0694
No log	5.0870	234	0.9616	0.4951	0.9616	0.9806
No log	5.1304	236	0.8340	0.4891	0.8340	0.9132
No log	5.1739	238	0.8644	0.5262	0.8644	0.9297
No log	5.2174	240	0.8939	0.5391	0.8939	0.9455
No log	5.2609	242	0.8339	0.5300	0.8339	0.9132
No log	5.3043	244	0.7449	0.5431	0.7449	0.8631
No log	5.3478	246	0.7511	0.5037	0.7511	0.8667
No log	5.3913	248	0.8033	0.5201	0.8033	0.8963
No log	5.4348	250	0.8040	0.5187	0.8040	0.8966
No log	5.4783	252	0.7440	0.4937	0.7440	0.8626
No log	5.5217	254	0.7037	0.5536	0.7037	0.8389
No log	5.5652	256	0.7401	0.5122	0.7401	0.8603
No log	5.6087	258	0.7508	0.5122	0.7508	0.8665
No log	5.6522	260	0.7385	0.5149	0.7385	0.8593
No log	5.6957	262	0.7210	0.5361	0.7210	0.8491
No log	5.7391	264	0.7616	0.5218	0.7616	0.8727
No log	5.7826	266	0.8221	0.5087	0.8221	0.9067
No log	5.8261	268	0.8469	0.5117	0.8469	0.9203
No log	5.8696	270	0.8487	0.5089	0.8487	0.9213
No log	5.9130	272	0.8723	0.4790	0.8723	0.9340
No log	5.9565	274	0.8943	0.4813	0.8943	0.9457
No log	6.0	276	0.8986	0.4971	0.8986	0.9480
No log	6.0435	278	0.8867	0.4903	0.8867	0.9417
No log	6.0870	280	0.8578	0.4948	0.8578	0.9262
No log	6.1304	282	0.8366	0.4940	0.8366	0.9146
No log	6.1739	284	0.8008	0.5023	0.8008	0.8949
No log	6.2174	286	0.7541	0.4956	0.7541	0.8684
No log	6.2609	288	0.7255	0.5315	0.7255	0.8518
No log	6.3043	290	0.7058	0.5090	0.7058	0.8401
No log	6.3478	292	0.7019	0.5100	0.7019	0.8378
No log	6.3913	294	0.7064	0.5061	0.7064	0.8405
No log	6.4348	296	0.7089	0.5260	0.7089	0.8420
No log	6.4783	298	0.7203	0.5450	0.7203	0.8487
No log	6.5217	300	0.7287	0.5380	0.7287	0.8536
No log	6.5652	302	0.7229	0.5380	0.7229	0.8502
No log	6.6087	304	0.7032	0.5180	0.7032	0.8386
No log	6.6522	306	0.7117	0.5110	0.7117	0.8436
No log	6.6957	308	0.7179	0.5101	0.7179	0.8473
No log	6.7391	310	0.7229	0.5110	0.7229	0.8502
No log	6.7826	312	0.7333	0.5053	0.7333	0.8563
No log	6.8261	314	0.7515	0.5059	0.7515	0.8669
No log	6.8696	316	0.7713	0.4995	0.7713	0.8783
No log	6.9130	318	0.8013	0.5015	0.8013	0.8951
No log	6.9565	320	0.8360	0.4869	0.8360	0.9143
No log	7.0	322	0.8379	0.4869	0.8379	0.9154
No log	7.0435	324	0.8213	0.5132	0.8213	0.9063
No log	7.0870	326	0.8198	0.5155	0.8198	0.9054
No log	7.1304	328	0.8132	0.5084	0.8132	0.9018
No log	7.1739	330	0.7972	0.5290	0.7972	0.8929
No log	7.2174	332	0.7772	0.5364	0.7772	0.8816
No log	7.2609	334	0.7628	0.5289	0.7628	0.8734
No log	7.3043	336	0.7418	0.5285	0.7418	0.8613
No log	7.3478	338	0.7229	0.5283	0.7229	0.8503
No log	7.3913	340	0.7239	0.5147	0.7239	0.8508
No log	7.4348	342	0.7183	0.5147	0.7183	0.8475
No log	7.4783	344	0.7280	0.5283	0.7280	0.8532
No log	7.5217	346	0.7441	0.5232	0.7441	0.8626
No log	7.5652	348	0.7622	0.5375	0.7622	0.8730
No log	7.6087	350	0.7698	0.5364	0.7698	0.8774
No log	7.6522	352	0.7718	0.5237	0.7718	0.8785
No log	7.6957	354	0.7795	0.5364	0.7795	0.8829
No log	7.7391	356	0.7997	0.5441	0.7997	0.8943
No log	7.7826	358	0.8097	0.5238	0.8097	0.8998
No log	7.8261	360	0.8060	0.5364	0.8060	0.8978
No log	7.8696	362	0.8046	0.5223	0.8046	0.8970
No log	7.9130	364	0.8033	0.4854	0.8033	0.8962
No log	7.9565	366	0.8010	0.4689	0.8010	0.8950
No log	8.0	368	0.7873	0.4816	0.7873	0.8873
No log	8.0435	370	0.7679	0.5038	0.7679	0.8763
No log	8.0870	372	0.7448	0.5177	0.7448	0.8630
No log	8.1304	374	0.7264	0.5086	0.7264	0.8523
No log	8.1739	376	0.7206	0.5256	0.7206	0.8489
No log	8.2174	378	0.7138	0.5203	0.7138	0.8449
No log	8.2609	380	0.7057	0.5167	0.7057	0.8401
No log	8.3043	382	0.6949	0.5101	0.6949	0.8336
No log	8.3478	384	0.7006	0.5193	0.7006	0.8370
No log	8.3913	386	0.7253	0.5503	0.7253	0.8516
No log	8.4348	388	0.7575	0.5264	0.7575	0.8703
No log	8.4783	390	0.7866	0.5050	0.7866	0.8869
No log	8.5217	392	0.7919	0.5128	0.7920	0.8899
No log	8.5652	394	0.7820	0.5600	0.7820	0.8843
No log	8.6087	396	0.7703	0.4977	0.7703	0.8777
No log	8.6522	398	0.7650	0.5203	0.7650	0.8747
No log	8.6957	400	0.7722	0.5405	0.7722	0.8787
No log	8.7391	402	0.7764	0.5172	0.7764	0.8811
No log	8.7826	404	0.7805	0.5172	0.7805	0.8835
No log	8.8261	406	0.7833	0.5405	0.7833	0.8850
No log	8.8696	408	0.7825	0.5316	0.7825	0.8846
No log	8.9130	410	0.7877	0.5184	0.7877	0.8875
No log	8.9565	412	0.7978	0.5087	0.7978	0.8932
No log	9.0	414	0.8091	0.5243	0.8091	0.8995
No log	9.0435	416	0.8164	0.5243	0.8164	0.9035
No log	9.0870	418	0.8172	0.5191	0.8172	0.9040
No log	9.1304	420	0.8165	0.5087	0.8165	0.9036
No log	9.1739	422	0.8136	0.5287	0.8136	0.9020
No log	9.2174	424	0.8131	0.5419	0.8131	0.9017
No log	9.2609	426	0.8139	0.5419	0.8139	0.9022
No log	9.3043	428	0.8150	0.5160	0.8150	0.9028
No log	9.3478	430	0.8180	0.5087	0.8180	0.9044
No log	9.3913	432	0.8198	0.5191	0.8198	0.9054
No log	9.4348	434	0.8180	0.5139	0.8180	0.9044
No log	9.4783	436	0.8151	0.5139	0.8151	0.9028
No log	9.5217	438	0.8125	0.5087	0.8125	0.9014
No log	9.5652	440	0.8101	0.5087	0.8101	0.9001
No log	9.6087	442	0.8081	0.5087	0.8081	0.8989
No log	9.6522	444	0.8059	0.5087	0.8059	0.8977
No log	9.6957	446	0.8049	0.5154	0.8049	0.8972
No log	9.7391	448	0.8050	0.5154	0.8050	0.8972
No log	9.7826	450	0.8048	0.5160	0.8048	0.8971
No log	9.8261	452	0.8033	0.5160	0.8033	0.8963
No log	9.8696	454	0.8015	0.5287	0.8015	0.8953
No log	9.9130	456	0.7998	0.5287	0.7998	0.8943
No log	9.9565	458	0.7989	0.5287	0.7989	0.8938
No log	10.0	460	0.7986	0.5287	0.7986	0.8937

Framework versions

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