ArabicNewSplits6_FineTuningAraBERT_run2_AugV5_k12_task5_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: 0.6848
• Qwk: 0.7663
• Mse: 0.6848
• Rmse: 0.8275

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	2.2715	-0.0139	2.2715	1.5072
No log	0.0870	4	1.5557	0.1376	1.5557	1.2473
No log	0.1304	6	1.5186	0.1045	1.5186	1.2323
No log	0.1739	8	1.4253	0.1728	1.4253	1.1939
No log	0.2174	10	1.4374	0.3298	1.4374	1.1989
No log	0.2609	12	1.9256	0.1779	1.9256	1.3877
No log	0.3043	14	1.9915	0.1113	1.9915	1.4112
No log	0.3478	16	1.8612	0.0730	1.8612	1.3642
No log	0.3913	18	1.4179	0.3085	1.4179	1.1908
No log	0.4348	20	1.1762	0.1781	1.1762	1.0845
No log	0.4783	22	1.0580	0.3582	1.0580	1.0286
No log	0.5217	24	1.0518	0.3743	1.0518	1.0256
No log	0.5652	26	1.0597	0.4210	1.0597	1.0294
No log	0.6087	28	0.9997	0.4166	0.9997	0.9998
No log	0.6522	30	1.0195	0.5620	1.0195	1.0097
No log	0.6957	32	1.0735	0.5427	1.0735	1.0361
No log	0.7391	34	1.0045	0.5621	1.0045	1.0023
No log	0.7826	36	1.0008	0.5439	1.0008	1.0004
No log	0.8261	38	1.0146	0.4054	1.0146	1.0073
No log	0.8696	40	1.0233	0.4369	1.0233	1.0116
No log	0.9130	42	1.1073	0.4857	1.1073	1.0523
No log	0.9565	44	1.1796	0.4432	1.1796	1.0861
No log	1.0	46	1.1872	0.2968	1.1872	1.0896
No log	1.0435	48	1.1475	0.2653	1.1475	1.0712
No log	1.0870	50	1.1064	0.2981	1.1064	1.0518
No log	1.1304	52	1.0262	0.3743	1.0262	1.0130
No log	1.1739	54	1.0094	0.4897	1.0094	1.0047
No log	1.2174	56	1.0218	0.4808	1.0218	1.0109
No log	1.2609	58	1.0435	0.5222	1.0435	1.0215
No log	1.3043	60	1.1365	0.4720	1.1365	1.0661
No log	1.3478	62	1.3227	0.4206	1.3227	1.1501
No log	1.3913	64	1.2752	0.4597	1.2752	1.1293
No log	1.4348	66	1.0702	0.5288	1.0702	1.0345
No log	1.4783	68	0.9094	0.5868	0.9094	0.9536
No log	1.5217	70	0.9568	0.6327	0.9568	0.9781
No log	1.5652	72	1.0886	0.5458	1.0886	1.0434
No log	1.6087	74	0.9261	0.6272	0.9261	0.9623
No log	1.6522	76	0.8080	0.6297	0.8080	0.8989
No log	1.6957	78	0.7998	0.6538	0.7998	0.8943
No log	1.7391	80	0.8511	0.6547	0.8511	0.9226
No log	1.7826	82	1.0728	0.5175	1.0728	1.0358
No log	1.8261	84	0.9703	0.5535	0.9703	0.9850
No log	1.8696	86	0.7838	0.6961	0.7838	0.8853
No log	1.9130	88	0.8156	0.6849	0.8156	0.9031
No log	1.9565	90	0.7628	0.6999	0.7628	0.8734
No log	2.0	92	0.7248	0.7141	0.7248	0.8513
No log	2.0435	94	0.7837	0.6751	0.7837	0.8852
No log	2.0870	96	1.0416	0.5613	1.0416	1.0206
No log	2.1304	98	1.1426	0.5575	1.1426	1.0689
No log	2.1739	100	0.9194	0.6473	0.9194	0.9589
No log	2.2174	102	0.7571	0.6839	0.7571	0.8701
No log	2.2609	104	0.7463	0.6858	0.7463	0.8639
No log	2.3043	106	0.8418	0.6891	0.8418	0.9175
No log	2.3478	108	1.1578	0.5949	1.1578	1.0760
No log	2.3913	110	1.1808	0.6003	1.1808	1.0866
No log	2.4348	112	0.9181	0.6270	0.9181	0.9582
No log	2.4783	114	0.8200	0.6911	0.8200	0.9055
No log	2.5217	116	0.8525	0.6696	0.8525	0.9233
No log	2.5652	118	0.8589	0.6645	0.8589	0.9268
No log	2.6087	120	0.9295	0.6411	0.9295	0.9641
No log	2.6522	122	1.0625	0.6000	1.0625	1.0308
No log	2.6957	124	1.0073	0.6211	1.0073	1.0037
No log	2.7391	126	0.8197	0.6841	0.8197	0.9054
No log	2.7826	128	0.7388	0.7143	0.7388	0.8596
No log	2.8261	130	0.7680	0.7025	0.7680	0.8763
No log	2.8696	132	0.7373	0.7299	0.7373	0.8587
No log	2.9130	134	0.7699	0.7159	0.7699	0.8774
No log	2.9565	136	0.7609	0.6985	0.7609	0.8723
No log	3.0	138	0.7775	0.6533	0.7775	0.8818
No log	3.0435	140	0.7995	0.6265	0.7995	0.8941
No log	3.0870	142	0.8965	0.5933	0.8965	0.9468
No log	3.1304	144	1.0468	0.5744	1.0468	1.0232
No log	3.1739	146	0.9928	0.6107	0.9928	0.9964
No log	3.2174	148	0.8182	0.7039	0.8182	0.9045
No log	3.2609	150	0.7757	0.7056	0.7757	0.8807
No log	3.3043	152	0.7340	0.7470	0.7340	0.8568
No log	3.3478	154	0.7234	0.7509	0.7234	0.8505
No log	3.3913	156	0.7467	0.7331	0.7467	0.8641
No log	3.4348	158	0.8150	0.7004	0.8150	0.9028
No log	3.4783	160	0.7354	0.7552	0.7354	0.8576
No log	3.5217	162	0.6756	0.7352	0.6756	0.8220
No log	3.5652	164	0.6900	0.7397	0.6900	0.8306
No log	3.6087	166	0.7284	0.7277	0.7284	0.8535
No log	3.6522	168	0.7345	0.7271	0.7345	0.8570
No log	3.6957	170	0.7458	0.7224	0.7458	0.8636
No log	3.7391	172	0.7527	0.7363	0.7527	0.8676
No log	3.7826	174	0.7603	0.7195	0.7603	0.8720
No log	3.8261	176	0.7407	0.7371	0.7407	0.8606
No log	3.8696	178	0.7009	0.7823	0.7009	0.8372
No log	3.9130	180	0.6689	0.7750	0.6689	0.8179
No log	3.9565	182	0.7512	0.7480	0.7512	0.8667
No log	4.0	184	0.7666	0.7480	0.7666	0.8756
No log	4.0435	186	0.8638	0.7089	0.8638	0.9294
No log	4.0870	188	0.9713	0.6850	0.9713	0.9856
No log	4.1304	190	1.0686	0.6409	1.0686	1.0337
No log	4.1739	192	1.0198	0.6672	1.0198	1.0099
No log	4.2174	194	0.8099	0.7101	0.8099	0.8999
No log	4.2609	196	0.7656	0.7294	0.7656	0.8750
No log	4.3043	198	0.8367	0.6695	0.8367	0.9147
No log	4.3478	200	0.8225	0.6813	0.8225	0.9069
No log	4.3913	202	0.7340	0.7309	0.7340	0.8567
No log	4.4348	204	0.6579	0.7454	0.6579	0.8111
No log	4.4783	206	0.6972	0.7360	0.6972	0.8350
No log	4.5217	208	0.8172	0.6645	0.8172	0.9040
No log	4.5652	210	0.8584	0.6720	0.8584	0.9265
No log	4.6087	212	0.7936	0.6644	0.7936	0.8908
No log	4.6522	214	0.7282	0.7039	0.7282	0.8533
No log	4.6957	216	0.7002	0.7086	0.7002	0.8368
No log	4.7391	218	0.8032	0.6830	0.8032	0.8962
No log	4.7826	220	0.9867	0.6348	0.9867	0.9933
No log	4.8261	222	1.1090	0.5899	1.1090	1.0531
No log	4.8696	224	1.0610	0.5802	1.0610	1.0301
No log	4.9130	226	0.8751	0.6435	0.8751	0.9355
No log	4.9565	228	0.7257	0.6600	0.7257	0.8519
No log	5.0	230	0.6635	0.7410	0.6635	0.8146
No log	5.0435	232	0.6673	0.7264	0.6673	0.8169
No log	5.0870	234	0.7132	0.7084	0.7132	0.8445
No log	5.1304	236	0.8416	0.6788	0.8416	0.9174
No log	5.1739	238	0.9249	0.6631	0.9249	0.9617
No log	5.2174	240	0.9188	0.6622	0.9188	0.9585
No log	5.2609	242	0.7944	0.7126	0.7944	0.8913
No log	5.3043	244	0.7108	0.7470	0.7108	0.8431
No log	5.3478	246	0.6399	0.7371	0.6399	0.7999
No log	5.3913	248	0.6341	0.7371	0.6341	0.7963
No log	5.4348	250	0.6755	0.7614	0.6755	0.8219
No log	5.4783	252	0.7617	0.7414	0.7617	0.8727
No log	5.5217	254	0.8401	0.7181	0.8401	0.9166
No log	5.5652	256	0.8515	0.6823	0.8515	0.9228
No log	5.6087	258	0.7590	0.7301	0.7590	0.8712
No log	5.6522	260	0.6784	0.7545	0.6784	0.8237
No log	5.6957	262	0.6586	0.7291	0.6586	0.8115
No log	5.7391	264	0.6867	0.7441	0.6867	0.8287
No log	5.7826	266	0.7457	0.7347	0.7457	0.8635
No log	5.8261	268	0.7865	0.7053	0.7865	0.8868
No log	5.8696	270	0.8337	0.6996	0.8337	0.9130
No log	5.9130	272	0.8089	0.7110	0.8089	0.8994
No log	5.9565	274	0.7473	0.7252	0.7473	0.8645
No log	6.0	276	0.7713	0.7289	0.7713	0.8782
No log	6.0435	278	0.8291	0.7110	0.8291	0.9106
No log	6.0870	280	0.8376	0.7019	0.8376	0.9152
No log	6.1304	282	0.8247	0.7303	0.8247	0.9081
No log	6.1739	284	0.8332	0.7134	0.8332	0.9128
No log	6.2174	286	0.7942	0.7289	0.7942	0.8912
No log	6.2609	288	0.7007	0.7366	0.7007	0.8371
No log	6.3043	290	0.6698	0.7380	0.6698	0.8184
No log	6.3478	292	0.6903	0.7131	0.6903	0.8308
No log	6.3913	294	0.7450	0.7364	0.7450	0.8631
No log	6.4348	296	0.7839	0.7315	0.7839	0.8854
No log	6.4783	298	0.8827	0.6962	0.8827	0.9395
No log	6.5217	300	0.9232	0.6817	0.9232	0.9608
No log	6.5652	302	0.8518	0.6947	0.8518	0.9229
No log	6.6087	304	0.7960	0.7214	0.7960	0.8922
No log	6.6522	306	0.7011	0.7251	0.7011	0.8373
No log	6.6957	308	0.6476	0.7321	0.6476	0.8047
No log	6.7391	310	0.6399	0.7344	0.6399	0.8000
No log	6.7826	312	0.6425	0.7405	0.6425	0.8016
No log	6.8261	314	0.6625	0.7351	0.6625	0.8139
No log	6.8696	316	0.7236	0.7273	0.7236	0.8507
No log	6.9130	318	0.7737	0.6944	0.7737	0.8796
No log	6.9565	320	0.7670	0.6944	0.7670	0.8758
No log	7.0	322	0.7044	0.7258	0.7044	0.8393
No log	7.0435	324	0.6443	0.7554	0.6443	0.8027
No log	7.0870	326	0.6316	0.7517	0.6316	0.7947
No log	7.1304	328	0.6408	0.7592	0.6408	0.8005
No log	7.1739	330	0.6727	0.7750	0.6727	0.8202
No log	7.2174	332	0.7392	0.7234	0.7392	0.8597
No log	7.2609	334	0.7964	0.7179	0.7964	0.8924
No log	7.3043	336	0.8070	0.7288	0.8070	0.8984
No log	7.3478	338	0.7681	0.7319	0.7681	0.8764
No log	7.3913	340	0.7306	0.7292	0.7306	0.8547
No log	7.4348	342	0.6938	0.7436	0.6938	0.8329
No log	7.4783	344	0.6576	0.7685	0.6576	0.8109
No log	7.5217	346	0.6580	0.7725	0.6580	0.8112
No log	7.5652	348	0.6693	0.7599	0.6693	0.8181
No log	7.6087	350	0.6568	0.7779	0.6568	0.8104
No log	7.6522	352	0.6520	0.7779	0.6520	0.8075
No log	7.6957	354	0.6732	0.7821	0.6732	0.8205
No log	7.7391	356	0.7273	0.7417	0.7273	0.8528
No log	7.7826	358	0.7681	0.7088	0.7681	0.8764
No log	7.8261	360	0.8351	0.7062	0.8351	0.9138
No log	7.8696	362	0.8576	0.6818	0.8576	0.9260
No log	7.9130	364	0.8319	0.7049	0.8319	0.9121
No log	7.9565	366	0.8103	0.7049	0.8103	0.9002
No log	8.0	368	0.7569	0.7261	0.7569	0.8700
No log	8.0435	370	0.6991	0.7663	0.6991	0.8361
No log	8.0870	372	0.6696	0.7590	0.6696	0.8183
No log	8.1304	374	0.6552	0.7751	0.6552	0.8094
No log	8.1739	376	0.6574	0.7751	0.6574	0.8108
No log	8.2174	378	0.6665	0.7733	0.6665	0.8164
No log	8.2609	380	0.6623	0.7889	0.6623	0.8138
No log	8.3043	382	0.6768	0.7733	0.6768	0.8227
No log	8.3478	384	0.6914	0.7733	0.6914	0.8315
No log	8.3913	386	0.6830	0.7733	0.6830	0.8265
No log	8.4348	388	0.6703	0.7663	0.6703	0.8187
No log	8.4783	390	0.6575	0.7780	0.6575	0.8109
No log	8.5217	392	0.6451	0.7810	0.6451	0.8032
No log	8.5652	394	0.6257	0.7968	0.6257	0.7910
No log	8.6087	396	0.6049	0.7850	0.6049	0.7778
No log	8.6522	398	0.6015	0.7814	0.6015	0.7755
No log	8.6957	400	0.6058	0.7814	0.6058	0.7783
No log	8.7391	402	0.6136	0.7902	0.6136	0.7833
No log	8.7826	404	0.6309	0.7856	0.6309	0.7943
No log	8.8261	406	0.6489	0.7810	0.6489	0.8055
No log	8.8696	408	0.6656	0.7854	0.6656	0.8158
No log	8.9130	410	0.6699	0.7854	0.6699	0.8185
No log	8.9565	412	0.6723	0.7814	0.6723	0.8200
No log	9.0	414	0.6684	0.7810	0.6684	0.8175
No log	9.0435	416	0.6531	0.7851	0.6531	0.8082
No log	9.0870	418	0.6352	0.7851	0.6352	0.7970
No log	9.1304	420	0.6195	0.7973	0.6195	0.7871
No log	9.1739	422	0.6112	0.7814	0.6112	0.7818
No log	9.2174	424	0.6064	0.7899	0.6064	0.7787
No log	9.2609	426	0.6073	0.7814	0.6073	0.7793
No log	9.3043	428	0.6142	0.7814	0.6142	0.7837
No log	9.3478	430	0.6258	0.7825	0.6258	0.7911
No log	9.3913	432	0.6382	0.7851	0.6382	0.7989
No log	9.4348	434	0.6481	0.7851	0.6481	0.8050
No log	9.4783	436	0.6510	0.7851	0.6510	0.8069
No log	9.5217	438	0.6571	0.7810	0.6571	0.8106
No log	9.5652	440	0.6624	0.7769	0.6624	0.8139
No log	9.6087	442	0.6691	0.7769	0.6691	0.8180
No log	9.6522	444	0.6715	0.7769	0.6715	0.8195
No log	9.6957	446	0.6728	0.7805	0.6728	0.8202
No log	9.7391	448	0.6750	0.7805	0.6750	0.8216
No log	9.7826	450	0.6770	0.7805	0.6770	0.8228
No log	9.8261	452	0.6790	0.7805	0.6790	0.8240
No log	9.8696	454	0.6827	0.7663	0.6827	0.8262
No log	9.9130	456	0.6836	0.7663	0.6836	0.8268
No log	9.9565	458	0.6845	0.7663	0.6845	0.8273
No log	10.0	460	0.6848	0.7663	0.6848	0.8275

Framework versions

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