arabert_baseline_augmented_more_organization_task1_fold0

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: 0.7158
• Qwk: 0.7172
• Mse: 0.7158
• Rmse: 0.8461

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	0.0417	2	1.7016	0.1642	1.7016	1.3044
No log	0.0833	4	1.2738	0.1750	1.2738	1.1286
No log	0.125	6	1.2622	0.1736	1.2622	1.1235
No log	0.1667	8	1.4336	0.0742	1.4336	1.1973
No log	0.2083	10	1.6089	0.2006	1.6089	1.2684
No log	0.25	12	1.8224	0.0533	1.8224	1.3500
No log	0.2917	14	1.8011	0.0385	1.8011	1.3420
No log	0.3333	16	1.5946	0.1582	1.5946	1.2628
No log	0.375	18	1.4496	0.0742	1.4496	1.2040
No log	0.4167	20	1.3713	0.1736	1.3713	1.1710
No log	0.4583	22	1.2801	0.1736	1.2801	1.1314
No log	0.5	24	1.1589	0.1463	1.1589	1.0765
No log	0.5417	26	1.1683	0.3636	1.1683	1.0809
No log	0.5833	28	1.1922	0.2910	1.1922	1.0919
No log	0.625	30	1.1586	0.1463	1.1586	1.0764
No log	0.6667	32	1.2494	0.1413	1.2494	1.1178
No log	0.7083	34	1.2074	0.1555	1.2074	1.0988
No log	0.75	36	1.1404	0.2478	1.1404	1.0679
No log	0.7917	38	1.2618	0.2125	1.2618	1.1233
No log	0.8333	40	1.5388	0.2254	1.5388	1.2405
No log	0.875	42	1.6423	0.1778	1.6423	1.2815
No log	0.9167	44	1.7744	0.1600	1.7744	1.3321
No log	0.9583	46	1.5268	0.2990	1.5268	1.2356
No log	1.0	48	1.2378	0.2958	1.2378	1.1126
No log	1.0417	50	1.1977	0.1876	1.1977	1.0944
No log	1.0833	52	1.1358	0.1876	1.1358	1.0657
No log	1.125	54	1.0778	0.2102	1.0778	1.0382
No log	1.1667	56	1.0462	0.4173	1.0462	1.0229
No log	1.2083	58	1.0130	0.4867	1.0130	1.0065
No log	1.25	60	0.9262	0.4639	0.9262	0.9624
No log	1.2917	62	0.8585	0.5107	0.8585	0.9265
No log	1.3333	64	0.8122	0.4324	0.8122	0.9012
No log	1.375	66	0.7755	0.5108	0.7755	0.8806
No log	1.4167	68	0.7536	0.5108	0.7536	0.8681
No log	1.4583	70	0.7520	0.5097	0.7520	0.8672
No log	1.5	72	0.8661	0.5970	0.8661	0.9306
No log	1.5417	74	0.8993	0.6011	0.8993	0.9483
No log	1.5833	76	0.9214	0.5772	0.9214	0.9599
No log	1.625	78	0.9799	0.5772	0.9799	0.9899
No log	1.6667	80	0.9062	0.6100	0.9062	0.9519
No log	1.7083	82	0.9675	0.3121	0.9675	0.9836
No log	1.75	84	0.9513	0.3721	0.9513	0.9753
No log	1.7917	86	0.9122	0.3541	0.9122	0.9551
No log	1.8333	88	0.9007	0.4106	0.9007	0.9490
No log	1.875	90	0.8584	0.4607	0.8584	0.9265
No log	1.9167	92	0.7580	0.5629	0.7580	0.8706
No log	1.9583	94	0.7066	0.5098	0.7066	0.8406
No log	2.0	96	0.7098	0.5290	0.7098	0.8425
No log	2.0417	98	0.7480	0.5473	0.7480	0.8649
No log	2.0833	100	0.8287	0.6143	0.8287	0.9104
No log	2.125	102	0.7862	0.5488	0.7862	0.8867
No log	2.1667	104	0.7394	0.5281	0.7394	0.8599
No log	2.2083	106	0.6726	0.5283	0.6726	0.8201
No log	2.25	108	0.6606	0.5283	0.6606	0.8128
No log	2.2917	110	0.6648	0.5283	0.6648	0.8154
No log	2.3333	112	0.6614	0.5468	0.6614	0.8133
No log	2.375	114	0.6454	0.5640	0.6454	0.8034
No log	2.4167	116	0.6557	0.5640	0.6557	0.8098
No log	2.4583	118	0.6659	0.5818	0.6659	0.8160
No log	2.5	120	0.6556	0.5818	0.6556	0.8097
No log	2.5417	122	0.6791	0.5468	0.6791	0.8241
No log	2.5833	124	0.7349	0.7342	0.7349	0.8573
No log	2.625	126	0.7328	0.7986	0.7328	0.8560
No log	2.6667	128	0.8162	0.7823	0.8162	0.9035
No log	2.7083	130	0.9252	0.7221	0.9252	0.9619
No log	2.75	132	0.9043	0.7139	0.9043	0.9510
No log	2.7917	134	0.8027	0.7623	0.8027	0.8959
No log	2.8333	136	0.7367	0.7801	0.7367	0.8583
No log	2.875	138	0.6459	0.6775	0.6459	0.8037
No log	2.9167	140	0.6098	0.6774	0.6098	0.7809
No log	2.9583	142	0.5942	0.6316	0.5942	0.7709
No log	3.0	144	0.6023	0.6316	0.6023	0.7761
No log	3.0417	146	0.6150	0.6488	0.6150	0.7842
No log	3.0833	148	0.6189	0.6488	0.6189	0.7867
No log	3.125	150	0.6059	0.6488	0.6059	0.7784
No log	3.1667	152	0.6189	0.6602	0.6189	0.7867
No log	3.2083	154	0.6219	0.6602	0.6219	0.7886
No log	3.25	156	0.6274	0.6310	0.6274	0.7921
No log	3.2917	158	0.6464	0.6310	0.6464	0.8040
No log	3.3333	160	0.6717	0.6898	0.6717	0.8195
No log	3.375	162	0.7372	0.6909	0.7372	0.8586
No log	3.4167	164	0.7792	0.6909	0.7792	0.8827
No log	3.4583	166	0.9314	0.7221	0.9314	0.9651
No log	3.5	168	1.0842	0.7221	1.0842	1.0412
No log	3.5417	170	1.0153	0.7221	1.0153	1.0076
No log	3.5833	172	0.8811	0.7221	0.8811	0.9387
No log	3.625	174	0.7166	0.5906	0.7166	0.8465
No log	3.6667	176	0.6945	0.5291	0.6945	0.8334
No log	3.7083	178	0.6979	0.4745	0.6979	0.8354
No log	3.75	180	0.6615	0.5285	0.6615	0.8133
No log	3.7917	182	0.6267	0.5462	0.6267	0.7917
No log	3.8333	184	0.6119	0.5660	0.6119	0.7823
No log	3.875	186	0.6251	0.6781	0.6251	0.7906
No log	3.9167	188	0.6571	0.7360	0.6571	0.8106
No log	3.9583	190	0.6702	0.6588	0.6702	0.8187
No log	4.0	192	0.7479	0.7717	0.7479	0.8648
No log	4.0417	194	0.7891	0.7623	0.7891	0.8883
No log	4.0833	196	0.7511	0.7623	0.7511	0.8666
No log	4.125	198	0.6949	0.7525	0.6949	0.8336
No log	4.1667	200	0.6489	0.5898	0.6489	0.8055
No log	4.2083	202	0.6396	0.6216	0.6396	0.7997
No log	4.25	204	0.6271	0.6175	0.6271	0.7919
No log	4.2917	206	0.6576	0.6898	0.6576	0.8109
No log	4.3333	208	0.7410	0.7139	0.7410	0.8608
No log	4.375	210	0.8531	0.7139	0.8531	0.9236
No log	4.4167	212	0.8413	0.7063	0.8413	0.9172
No log	4.4583	214	0.7067	0.7289	0.7067	0.8407
No log	4.5	216	0.6722	0.7225	0.6722	0.8199
No log	4.5417	218	0.6839	0.6885	0.6839	0.8270
No log	4.5833	220	0.7297	0.5786	0.7297	0.8542
No log	4.625	222	0.8156	0.5266	0.8156	0.9031
No log	4.6667	224	0.8218	0.5266	0.8218	0.9066
No log	4.7083	226	0.7851	0.4887	0.7851	0.8860
No log	4.75	228	0.7643	0.6418	0.7643	0.8743
No log	4.7917	230	0.7446	0.6992	0.7446	0.8629
No log	4.8333	232	0.7711	0.7063	0.7711	0.8781
No log	4.875	234	0.7149	0.7447	0.7149	0.8455
No log	4.9167	236	0.6441	0.6975	0.6441	0.8026
No log	4.9583	238	0.6134	0.7209	0.6134	0.7832
No log	5.0	240	0.6157	0.7209	0.6157	0.7847
No log	5.0417	242	0.6495	0.6975	0.6495	0.8059
No log	5.0833	244	0.6703	0.6975	0.6703	0.8187
No log	5.125	246	0.6821	0.6813	0.6821	0.8259
No log	5.1667	248	0.6653	0.6818	0.6653	0.8156
No log	5.2083	250	0.6940	0.6813	0.6940	0.8331
No log	5.25	252	0.7257	0.6813	0.7257	0.8519
No log	5.2917	254	0.8274	0.7522	0.8274	0.9096
No log	5.3333	256	0.9021	0.7264	0.9021	0.9498
No log	5.375	258	0.9698	0.7426	0.9698	0.9848
No log	5.4167	260	1.0117	0.7516	1.0117	1.0058
No log	5.4583	262	1.0087	0.7221	1.0087	1.0043
No log	5.5	264	0.9675	0.7418	0.9675	0.9836
No log	5.5417	266	0.8617	0.6564	0.8617	0.9283
No log	5.5833	268	0.7616	0.5522	0.7616	0.8727
No log	5.625	270	0.7146	0.4878	0.7146	0.8453
No log	5.6667	272	0.6756	0.5476	0.6756	0.8219
No log	5.7083	274	0.6580	0.58	0.6580	0.8112
No log	5.75	276	0.6531	0.6182	0.6531	0.8081
No log	5.7917	278	0.6787	0.6261	0.6787	0.8238
No log	5.8333	280	0.7087	0.6301	0.7087	0.8419
No log	5.875	282	0.7417	0.6642	0.7417	0.8612
No log	5.9167	284	0.7604	0.6642	0.7604	0.8720
No log	5.9583	286	0.8006	0.6951	0.8006	0.8947
No log	6.0	288	0.8069	0.7139	0.8069	0.8983
No log	6.0417	290	0.8402	0.7139	0.8402	0.9166
No log	6.0833	292	0.8419	0.7139	0.8419	0.9175
No log	6.125	294	0.8049	0.6951	0.8049	0.8972
No log	6.1667	296	0.7841	0.6882	0.7841	0.8855
No log	6.2083	298	0.8166	0.7063	0.8166	0.9036
No log	6.25	300	0.8454	0.7063	0.8454	0.9194
No log	6.2917	302	0.8753	0.7063	0.8753	0.9356
No log	6.3333	304	0.8271	0.6882	0.8271	0.9095
No log	6.375	306	0.7625	0.6871	0.7625	0.8732
No log	6.4167	308	0.7187	0.6975	0.7187	0.8477
No log	6.4583	310	0.6845	0.6662	0.6845	0.8273
No log	6.5	312	0.6827	0.6662	0.6827	0.8262
No log	6.5417	314	0.7055	0.6714	0.7055	0.8400
No log	6.5833	316	0.7257	0.5823	0.7257	0.8519
No log	6.625	318	0.7211	0.6254	0.7211	0.8492
No log	6.6667	320	0.6997	0.5867	0.6997	0.8365
No log	6.7083	322	0.7039	0.5898	0.7039	0.8390
No log	6.75	324	0.7067	0.6107	0.7067	0.8407
No log	6.7917	326	0.7139	0.6719	0.7139	0.8449
No log	6.8333	328	0.7371	0.6143	0.7371	0.8586
No log	6.875	330	0.7933	0.6353	0.7933	0.8907
No log	6.9167	332	0.8818	0.6903	0.8818	0.9391
No log	6.9583	334	0.9674	0.7221	0.9674	0.9836
No log	7.0	336	1.0250	0.7221	1.0250	1.0124
No log	7.0417	338	1.0158	0.7221	1.0158	1.0079
No log	7.0833	340	0.9518	0.7221	0.9518	0.9756
No log	7.125	342	0.8565	0.7139	0.8565	0.9255
No log	7.1667	344	0.8147	0.7139	0.8147	0.9026
No log	7.2083	346	0.7584	0.6882	0.7584	0.8708
No log	7.25	348	0.7248	0.6702	0.7248	0.8513
No log	7.2917	350	0.7168	0.6882	0.7168	0.8466
No log	7.3333	352	0.7216	0.6882	0.7216	0.8494
No log	7.375	354	0.7302	0.6882	0.7302	0.8545
No log	7.4167	356	0.7388	0.6882	0.7388	0.8596
No log	7.4583	358	0.7314	0.6882	0.7314	0.8552
No log	7.5	360	0.7059	0.6888	0.7059	0.8402
No log	7.5417	362	0.7043	0.7342	0.7043	0.8392
No log	7.5833	364	0.7178	0.6702	0.7178	0.8472
No log	7.625	366	0.7557	0.6882	0.7557	0.8693
No log	7.6667	368	0.7766	0.6882	0.7766	0.8813
No log	7.7083	370	0.7843	0.6951	0.7843	0.8856
No log	7.75	372	0.7778	0.6951	0.7778	0.8819
No log	7.7917	374	0.8034	0.7139	0.8034	0.8963
No log	7.8333	376	0.8331	0.7139	0.8331	0.9127
No log	7.875	378	0.8335	0.7139	0.8335	0.9130
No log	7.9167	380	0.8116	0.7139	0.8116	0.9009
No log	7.9583	382	0.8013	0.7139	0.8013	0.8952
No log	8.0	384	0.7915	0.7139	0.7915	0.8897
No log	8.0417	386	0.7726	0.6951	0.7726	0.8790
No log	8.0833	388	0.7600	0.6951	0.7600	0.8718
No log	8.125	390	0.7533	0.7427	0.7533	0.8679
No log	8.1667	392	0.7511	0.7427	0.7511	0.8667
No log	8.2083	394	0.7375	0.7427	0.7375	0.8588
No log	8.25	396	0.7214	0.7337	0.7214	0.8494
No log	8.2917	398	0.7239	0.7172	0.7239	0.8508
No log	8.3333	400	0.7236	0.7172	0.7236	0.8506
No log	8.375	402	0.7197	0.7172	0.7197	0.8483
No log	8.4167	404	0.7017	0.7172	0.7017	0.8377
No log	8.4583	406	0.6943	0.7172	0.6943	0.8333
No log	8.5	408	0.6936	0.7172	0.6936	0.8328
No log	8.5417	410	0.6889	0.7172	0.6889	0.8300
No log	8.5833	412	0.6949	0.7172	0.6949	0.8336
No log	8.625	414	0.7042	0.7172	0.7042	0.8392
No log	8.6667	416	0.7194	0.7172	0.7194	0.8482
No log	8.7083	418	0.7559	0.7172	0.7559	0.8694
No log	8.75	420	0.7810	0.7346	0.7810	0.8838
No log	8.7917	422	0.8087	0.7346	0.8087	0.8993
No log	8.8333	424	0.8240	0.7346	0.8240	0.9078
No log	8.875	426	0.8176	0.7346	0.8176	0.9042
No log	8.9167	428	0.8155	0.7346	0.8155	0.9030
No log	8.9583	430	0.8001	0.7346	0.8001	0.8945
No log	9.0	432	0.7936	0.7346	0.7936	0.8908
No log	9.0417	434	0.7872	0.7346	0.7872	0.8873
No log	9.0833	436	0.7933	0.7346	0.7933	0.8907
No log	9.125	438	0.8034	0.7346	0.8034	0.8964
No log	9.1667	440	0.8099	0.7346	0.8099	0.8999
No log	9.2083	442	0.8032	0.7346	0.8032	0.8962
No log	9.25	444	0.7911	0.7346	0.7911	0.8894
No log	9.2917	446	0.7743	0.7346	0.7743	0.8800
No log	9.3333	448	0.7545	0.7346	0.7545	0.8686
No log	9.375	450	0.7459	0.7172	0.7459	0.8637
No log	9.4167	452	0.7456	0.7172	0.7456	0.8635
No log	9.4583	454	0.7395	0.7172	0.7395	0.8600
No log	9.5	456	0.7343	0.7172	0.7343	0.8569
No log	9.5417	458	0.7290	0.7172	0.7290	0.8538
No log	9.5833	460	0.7256	0.7172	0.7256	0.8518
No log	9.625	462	0.7242	0.7172	0.7242	0.8510
No log	9.6667	464	0.7226	0.7172	0.7226	0.8501
No log	9.7083	466	0.7208	0.7172	0.7208	0.8490
No log	9.75	468	0.7213	0.7172	0.7213	0.8493
No log	9.7917	470	0.7198	0.7172	0.7198	0.8484
No log	9.8333	472	0.7181	0.7172	0.7181	0.8474
No log	9.875	474	0.7164	0.7172	0.7164	0.8464
No log	9.9167	476	0.7156	0.7172	0.7156	0.8459
No log	9.9583	478	0.7158	0.7172	0.7158	0.8461
No log	10.0	480	0.7158	0.7172	0.7158	0.8461

Framework versions

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