ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k7_task1_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: 0.7061
• Qwk: 0.7224
• Mse: 0.7061
• Rmse: 0.8403

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	5.3399	-0.0005	5.3399	2.3108
No log	0.0870	4	3.0758	0.0366	3.0758	1.7538
No log	0.1304	6	2.6954	-0.1090	2.6954	1.6418
No log	0.1739	8	2.6509	-0.1328	2.6509	1.6282
No log	0.2174	10	1.8076	0.0516	1.8076	1.3445
No log	0.2609	12	1.6063	0.0894	1.6063	1.2674
No log	0.3043	14	1.6274	0.0846	1.6274	1.2757
No log	0.3478	16	1.5010	0.0901	1.5010	1.2251
No log	0.3913	18	1.4633	0.1215	1.4633	1.2097
No log	0.4348	20	1.4082	0.1176	1.4082	1.1867
No log	0.4783	22	1.1669	0.3330	1.1669	1.0802
No log	0.5217	24	1.0736	0.3511	1.0736	1.0362
No log	0.5652	26	1.1176	0.3370	1.1176	1.0572
No log	0.6087	28	1.4262	0.1048	1.4262	1.1942
No log	0.6522	30	1.7564	0.0819	1.7564	1.3253
No log	0.6957	32	1.7564	0.0990	1.7564	1.3253
No log	0.7391	34	1.5579	0.1279	1.5579	1.2482
No log	0.7826	36	1.3392	0.1965	1.3392	1.1572
No log	0.8261	38	1.2107	0.3343	1.2107	1.1003
No log	0.8696	40	1.0805	0.4124	1.0805	1.0395
No log	0.9130	42	1.1607	0.3727	1.1607	1.0774
No log	0.9565	44	1.5255	0.3689	1.5255	1.2351
No log	1.0	46	1.9381	0.3036	1.9381	1.3922
No log	1.0435	48	1.9718	0.2844	1.9718	1.4042
No log	1.0870	50	1.9832	0.2892	1.9832	1.4083
No log	1.1304	52	1.6459	0.3938	1.6459	1.2829
No log	1.1739	54	1.3080	0.4560	1.3080	1.1437
No log	1.2174	56	0.9874	0.5351	0.9874	0.9937
No log	1.2609	58	0.8858	0.5873	0.8858	0.9412
No log	1.3043	60	0.8095	0.5809	0.8095	0.8997
No log	1.3478	62	0.8362	0.5691	0.8362	0.9144
No log	1.3913	64	0.8891	0.5793	0.8891	0.9429
No log	1.4348	66	1.0204	0.5511	1.0204	1.0101
No log	1.4783	68	1.0976	0.5090	1.0976	1.0477
No log	1.5217	70	0.9730	0.5839	0.9730	0.9864
No log	1.5652	72	0.9512	0.5839	0.9512	0.9753
No log	1.6087	74	0.8361	0.5441	0.8361	0.9144
No log	1.6522	76	0.8260	0.5707	0.8260	0.9088
No log	1.6957	78	0.8256	0.5803	0.8256	0.9086
No log	1.7391	80	0.8887	0.5544	0.8887	0.9427
No log	1.7826	82	1.1341	0.5516	1.1341	1.0649
No log	1.8261	84	1.3158	0.4941	1.3158	1.1471
No log	1.8696	86	1.5108	0.4324	1.5108	1.2292
No log	1.9130	88	1.3079	0.5026	1.3079	1.1437
No log	1.9565	90	0.9981	0.5880	0.9981	0.9990
No log	2.0	92	0.9208	0.5733	0.9208	0.9596
No log	2.0435	94	0.8731	0.6185	0.8731	0.9344
No log	2.0870	96	0.8903	0.6254	0.8903	0.9436
No log	2.1304	98	0.7551	0.7072	0.7551	0.8689
No log	2.1739	100	0.7350	0.6911	0.7350	0.8573
No log	2.2174	102	0.7365	0.6993	0.7365	0.8582
No log	2.2609	104	0.7327	0.7040	0.7327	0.8560
No log	2.3043	106	0.7043	0.6750	0.7043	0.8392
No log	2.3478	108	0.6722	0.7005	0.6722	0.8199
No log	2.3913	110	0.6608	0.7051	0.6608	0.8129
No log	2.4348	112	0.7460	0.6284	0.7460	0.8637
No log	2.4783	114	0.8291	0.5822	0.8291	0.9105
No log	2.5217	116	0.8143	0.5945	0.8143	0.9024
No log	2.5652	118	0.6973	0.6563	0.6973	0.8350
No log	2.6087	120	0.6553	0.7465	0.6553	0.8095
No log	2.6522	122	0.7105	0.6737	0.7105	0.8429
No log	2.6957	124	0.7238	0.6823	0.7238	0.8508
No log	2.7391	126	0.7330	0.6606	0.7330	0.8562
No log	2.7826	128	0.9110	0.6045	0.9110	0.9545
No log	2.8261	130	1.0697	0.5562	1.0697	1.0343
No log	2.8696	132	1.0277	0.5631	1.0277	1.0138
No log	2.9130	134	0.8926	0.6085	0.8926	0.9448
No log	2.9565	136	0.8171	0.6297	0.8171	0.9040
No log	3.0	138	0.7900	0.6479	0.7900	0.8888
No log	3.0435	140	0.8495	0.5744	0.8495	0.9217
No log	3.0870	142	1.0781	0.4924	1.0781	1.0383
No log	3.1304	144	1.1157	0.5030	1.1157	1.0563
No log	3.1739	146	0.9228	0.5499	0.9228	0.9606
No log	3.2174	148	0.7389	0.6045	0.7389	0.8596
No log	3.2609	150	0.7086	0.6360	0.7086	0.8418
No log	3.3043	152	0.7834	0.6073	0.7834	0.8851
No log	3.3478	154	0.9609	0.5742	0.9609	0.9803
No log	3.3913	156	0.9121	0.5836	0.9121	0.9550
No log	3.4348	158	0.8124	0.6868	0.8124	0.9013
No log	3.4783	160	0.6549	0.7078	0.6549	0.8093
No log	3.5217	162	0.6347	0.7468	0.6347	0.7967
No log	3.5652	164	0.6533	0.7218	0.6533	0.8083
No log	3.6087	166	0.6246	0.7107	0.6246	0.7903
No log	3.6522	168	0.6260	0.7316	0.6260	0.7912
No log	3.6957	170	0.7475	0.6618	0.7475	0.8646
No log	3.7391	172	0.8542	0.6364	0.8542	0.9242
No log	3.7826	174	0.8107	0.6560	0.8107	0.9004
No log	3.8261	176	0.6933	0.6737	0.6933	0.8327
No log	3.8696	178	0.6339	0.7040	0.6339	0.7961
No log	3.9130	180	0.6819	0.6773	0.6819	0.8258
No log	3.9565	182	0.6958	0.6783	0.6958	0.8342
No log	4.0	184	0.6607	0.7028	0.6607	0.8128
No log	4.0435	186	0.6542	0.7258	0.6542	0.8088
No log	4.0870	188	0.6646	0.7218	0.6646	0.8153
No log	4.1304	190	0.6705	0.7109	0.6705	0.8188
No log	4.1739	192	0.6925	0.7124	0.6925	0.8322
No log	4.2174	194	0.6716	0.7122	0.6716	0.8195
No log	4.2609	196	0.6588	0.7229	0.6588	0.8117
No log	4.3043	198	0.6619	0.7003	0.6619	0.8136
No log	4.3478	200	0.6647	0.6953	0.6647	0.8153
No log	4.3913	202	0.6890	0.6745	0.6890	0.8301
No log	4.4348	204	0.7232	0.6615	0.7232	0.8504
No log	4.4783	206	0.8097	0.6231	0.8097	0.8998
No log	4.5217	208	0.8057	0.6400	0.8057	0.8976
No log	4.5652	210	0.7533	0.6265	0.7533	0.8679
No log	4.6087	212	0.7026	0.6372	0.7026	0.8382
No log	4.6522	214	0.6755	0.6719	0.6755	0.8219
No log	4.6957	216	0.6761	0.6769	0.6761	0.8222
No log	4.7391	218	0.6827	0.6528	0.6827	0.8262
No log	4.7826	220	0.6799	0.6761	0.6799	0.8246
No log	4.8261	222	0.6709	0.6649	0.6709	0.8191
No log	4.8696	224	0.6858	0.6624	0.6858	0.8281
No log	4.9130	226	0.6853	0.6823	0.6853	0.8278
No log	4.9565	228	0.6902	0.7004	0.6902	0.8308
No log	5.0	230	0.6619	0.6896	0.6619	0.8136
No log	5.0435	232	0.6506	0.7106	0.6506	0.8066
No log	5.0870	234	0.6540	0.7138	0.6540	0.8087
No log	5.1304	236	0.6704	0.6970	0.6704	0.8188
No log	5.1739	238	0.6878	0.6854	0.6878	0.8293
No log	5.2174	240	0.6917	0.6854	0.6917	0.8317
No log	5.2609	242	0.6773	0.7275	0.6773	0.8230
No log	5.3043	244	0.6711	0.6964	0.6711	0.8192
No log	5.3478	246	0.6993	0.7025	0.6993	0.8363
No log	5.3913	248	0.7011	0.6893	0.7011	0.8373
No log	5.4348	250	0.6831	0.6931	0.6831	0.8265
No log	5.4783	252	0.6678	0.6903	0.6678	0.8172
No log	5.5217	254	0.6461	0.6983	0.6461	0.8038
No log	5.5652	256	0.6407	0.6997	0.6407	0.8004
No log	5.6087	258	0.6428	0.7056	0.6428	0.8018
No log	5.6522	260	0.6402	0.7071	0.6402	0.8001
No log	5.6957	262	0.6323	0.7093	0.6323	0.7952
No log	5.7391	264	0.6164	0.7202	0.6164	0.7851
No log	5.7826	266	0.6209	0.7275	0.6209	0.7880
No log	5.8261	268	0.6420	0.6879	0.6420	0.8013
No log	5.8696	270	0.6812	0.7315	0.6812	0.8254
No log	5.9130	272	0.6866	0.7195	0.6866	0.8286
No log	5.9565	274	0.6659	0.7108	0.6659	0.8160
No log	6.0	276	0.6777	0.6970	0.6777	0.8232
No log	6.0435	278	0.6863	0.6847	0.6863	0.8285
No log	6.0870	280	0.6802	0.6990	0.6802	0.8247
No log	6.1304	282	0.7015	0.6984	0.7015	0.8376
No log	6.1739	284	0.7460	0.6609	0.7460	0.8637
No log	6.2174	286	0.7574	0.6654	0.7574	0.8703
No log	6.2609	288	0.7270	0.6859	0.7270	0.8527
No log	6.3043	290	0.6977	0.6976	0.6977	0.8353
No log	6.3478	292	0.6952	0.6802	0.6952	0.8338
No log	6.3913	294	0.6970	0.6601	0.6970	0.8348
No log	6.4348	296	0.6906	0.6533	0.6906	0.8310
No log	6.4783	298	0.6972	0.6655	0.6972	0.8350
No log	6.5217	300	0.6907	0.6655	0.6907	0.8311
No log	6.5652	302	0.6733	0.6495	0.6733	0.8206
No log	6.6087	304	0.6697	0.6593	0.6697	0.8184
No log	6.6522	306	0.6700	0.6593	0.6700	0.8186
No log	6.6957	308	0.6634	0.6462	0.6634	0.8145
No log	6.7391	310	0.6639	0.6936	0.6639	0.8148
No log	6.7826	312	0.6685	0.6844	0.6685	0.8176
No log	6.8261	314	0.6784	0.7090	0.6784	0.8236
No log	6.8696	316	0.6971	0.6983	0.6971	0.8349
No log	6.9130	318	0.7112	0.6867	0.7112	0.8433
No log	6.9565	320	0.7186	0.6867	0.7186	0.8477
No log	7.0	322	0.7323	0.6988	0.7323	0.8557
No log	7.0435	324	0.7421	0.7027	0.7421	0.8614
No log	7.0870	326	0.7415	0.7027	0.7415	0.8611
No log	7.1304	328	0.7341	0.6949	0.7341	0.8568
No log	7.1739	330	0.7410	0.7041	0.7410	0.8608
No log	7.2174	332	0.7382	0.7041	0.7382	0.8592
No log	7.2609	334	0.7218	0.7008	0.7218	0.8496
No log	7.3043	336	0.7078	0.6892	0.7078	0.8413
No log	7.3478	338	0.7125	0.6903	0.7125	0.8441
No log	7.3913	340	0.7281	0.6630	0.7281	0.8533
No log	7.4348	342	0.7501	0.6714	0.7501	0.8661
No log	7.4783	344	0.7764	0.6835	0.7764	0.8812
No log	7.5217	346	0.7963	0.6859	0.7963	0.8924
No log	7.5652	348	0.8321	0.6710	0.8321	0.9122
No log	7.6087	350	0.8335	0.6693	0.8335	0.9130
No log	7.6522	352	0.8229	0.6750	0.8229	0.9072
No log	7.6957	354	0.8088	0.6842	0.8088	0.8993
No log	7.7391	356	0.7713	0.6901	0.7713	0.8783
No log	7.7826	358	0.7457	0.6937	0.7457	0.8636
No log	7.8261	360	0.7391	0.6864	0.7391	0.8597
No log	7.8696	362	0.7463	0.6827	0.7463	0.8639
No log	7.9130	364	0.7434	0.6816	0.7434	0.8622
No log	7.9565	366	0.7535	0.6907	0.7535	0.8681
No log	8.0	368	0.7528	0.7020	0.7528	0.8676
No log	8.0435	370	0.7407	0.7035	0.7407	0.8607
No log	8.0870	372	0.7277	0.6975	0.7277	0.8530
No log	8.1304	374	0.7291	0.7018	0.7291	0.8539
No log	8.1739	376	0.7317	0.7018	0.7317	0.8554
No log	8.2174	378	0.7343	0.7018	0.7343	0.8569
No log	8.2609	380	0.7344	0.6975	0.7344	0.8570
No log	8.3043	382	0.7397	0.7120	0.7397	0.8600
No log	8.3478	384	0.7378	0.7120	0.7378	0.8589
No log	8.3913	386	0.7303	0.6877	0.7303	0.8546
No log	8.4348	388	0.7135	0.7128	0.7135	0.8447
No log	8.4783	390	0.6936	0.7114	0.6936	0.8328
No log	8.5217	392	0.6826	0.6934	0.6826	0.8262
No log	8.5652	394	0.6743	0.6592	0.6743	0.8212
No log	8.6087	396	0.6705	0.6725	0.6705	0.8188
No log	8.6522	398	0.6717	0.6680	0.6717	0.8195
No log	8.6957	400	0.6765	0.6719	0.6765	0.8225
No log	8.7391	402	0.6868	0.7181	0.6868	0.8288
No log	8.7826	404	0.6894	0.7181	0.6894	0.8303
No log	8.8261	406	0.6888	0.7181	0.6888	0.8299
No log	8.8696	408	0.6854	0.7181	0.6854	0.8279
No log	8.9130	410	0.6859	0.7181	0.6859	0.8282
No log	8.9565	412	0.6821	0.7040	0.6821	0.8259
No log	9.0	414	0.6794	0.7040	0.6794	0.8243
No log	9.0435	416	0.6798	0.7040	0.6798	0.8245
No log	9.0870	418	0.6866	0.7181	0.6866	0.8286
No log	9.1304	420	0.6931	0.7181	0.6931	0.8325
No log	9.1739	422	0.7001	0.7181	0.7001	0.8367
No log	9.2174	424	0.7036	0.7181	0.7036	0.8388
No log	9.2609	426	0.7035	0.7181	0.7035	0.8388
No log	9.3043	428	0.7052	0.7181	0.7052	0.8397
No log	9.3478	430	0.7066	0.7181	0.7066	0.8406
No log	9.3913	432	0.7025	0.7181	0.7025	0.8381
No log	9.4348	434	0.6985	0.7083	0.6985	0.8358
No log	9.4783	436	0.6963	0.7083	0.6963	0.8345
No log	9.5217	438	0.6947	0.7083	0.6947	0.8335
No log	9.5652	440	0.6928	0.6928	0.6928	0.8324
No log	9.6087	442	0.6931	0.6928	0.6931	0.8325
No log	9.6522	444	0.6944	0.7022	0.6944	0.8333
No log	9.6957	446	0.6966	0.7083	0.6966	0.8346
No log	9.7391	448	0.6995	0.7083	0.6995	0.8364
No log	9.7826	450	0.7011	0.7083	0.7011	0.8373
No log	9.8261	452	0.7031	0.7224	0.7031	0.8385
No log	9.8696	454	0.7044	0.7224	0.7044	0.8393
No log	9.9130	456	0.7053	0.7224	0.7053	0.8398
No log	9.9565	458	0.7059	0.7224	0.7059	0.8402
No log	10.0	460	0.7061	0.7224	0.7061	0.8403

Framework versions

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