ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k4_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: 0.9401
• Qwk: 0.5849
• Mse: 0.9401
• Rmse: 0.9696

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	0.0952	2	5.4575	-0.0034	5.4575	2.3361
No log	0.1905	4	3.1915	0.0731	3.1915	1.7865
No log	0.2857	6	1.8557	0.0957	1.8557	1.3622
No log	0.3810	8	1.4128	0.1749	1.4128	1.1886
No log	0.4762	10	1.0893	0.3875	1.0893	1.0437
No log	0.5714	12	1.1042	0.2166	1.1042	1.0508
No log	0.6667	14	1.3794	0.0728	1.3794	1.1745
No log	0.7619	16	1.5201	-0.0560	1.5201	1.2329
No log	0.8571	18	1.2366	0.1539	1.2366	1.1120
No log	0.9524	20	1.0312	0.3123	1.0312	1.0155
No log	1.0476	22	1.4037	0.1251	1.4037	1.1848
No log	1.1429	24	1.6946	0.0882	1.6946	1.3018
No log	1.2381	26	1.6512	0.0882	1.6512	1.2850
No log	1.3333	28	1.4524	0.0529	1.4524	1.2051
No log	1.4286	30	1.2110	0.2151	1.2110	1.1005
No log	1.5238	32	0.9643	0.4183	0.9643	0.9820
No log	1.6190	34	0.8673	0.3342	0.8673	0.9313
No log	1.7143	36	0.8385	0.3633	0.8385	0.9157
No log	1.8095	38	1.2718	0.4045	1.2718	1.1277
No log	1.9048	40	1.7599	0.2156	1.7599	1.3266
No log	2.0	42	1.4785	0.3494	1.4785	1.2159
No log	2.0952	44	1.0005	0.4799	1.0005	1.0002
No log	2.1905	46	0.7626	0.4805	0.7626	0.8733
No log	2.2857	48	0.7505	0.5026	0.7505	0.8663
No log	2.3810	50	0.8496	0.5164	0.8496	0.9218
No log	2.4762	52	0.9954	0.5145	0.9954	0.9977
No log	2.5714	54	1.0639	0.4970	1.0639	1.0314
No log	2.6667	56	1.0107	0.5376	1.0107	1.0053
No log	2.7619	58	0.8754	0.5797	0.8754	0.9356
No log	2.8571	60	0.7233	0.6734	0.7233	0.8505
No log	2.9524	62	0.6455	0.7091	0.6455	0.8034
No log	3.0476	64	0.7534	0.5901	0.7534	0.8680
No log	3.1429	66	0.8320	0.6319	0.8320	0.9121
No log	3.2381	68	0.6828	0.6539	0.6828	0.8263
No log	3.3333	70	0.6806	0.6755	0.6806	0.8250
No log	3.4286	72	1.0626	0.5521	1.0626	1.0308
No log	3.5238	74	1.0541	0.5339	1.0541	1.0267
No log	3.6190	76	0.7691	0.6977	0.7691	0.8770
No log	3.7143	78	0.7173	0.6963	0.7173	0.8469
No log	3.8095	80	0.6900	0.7160	0.6900	0.8307
No log	3.9048	82	0.6835	0.7116	0.6835	0.8268
No log	4.0	84	0.6671	0.7187	0.6671	0.8167
No log	4.0952	86	0.6888	0.6905	0.6888	0.8299
No log	4.1905	88	0.6539	0.7262	0.6539	0.8086
No log	4.2857	90	0.6823	0.6888	0.6823	0.8260
No log	4.3810	92	0.8224	0.6600	0.8224	0.9069
No log	4.4762	94	0.8017	0.6841	0.8017	0.8954
No log	4.5714	96	0.6653	0.7032	0.6653	0.8157
No log	4.6667	98	0.6265	0.7176	0.6265	0.7915
No log	4.7619	100	0.6367	0.7515	0.6367	0.7979
No log	4.8571	102	0.6516	0.6924	0.6516	0.8072
No log	4.9524	104	0.7635	0.7186	0.7635	0.8738
No log	5.0476	106	0.8807	0.7040	0.8807	0.9385
No log	5.1429	108	0.8814	0.6959	0.8814	0.9388
No log	5.2381	110	0.8061	0.7077	0.8061	0.8978
No log	5.3333	112	0.7662	0.6913	0.7662	0.8753
No log	5.4286	114	0.8448	0.6391	0.8448	0.9192
No log	5.5238	116	0.8666	0.5946	0.8666	0.9309
No log	5.6190	118	0.7983	0.6373	0.7983	0.8935
No log	5.7143	120	0.7500	0.6940	0.7500	0.8660
No log	5.8095	122	0.7349	0.7001	0.7349	0.8572
No log	5.9048	124	0.7388	0.6828	0.7388	0.8596
No log	6.0	126	0.7880	0.6628	0.7880	0.8877
No log	6.0952	128	0.8013	0.6418	0.8013	0.8952
No log	6.1905	130	0.7775	0.6908	0.7775	0.8817
No log	6.2857	132	0.7579	0.6832	0.7579	0.8706
No log	6.3810	134	0.8110	0.6508	0.8110	0.9005
No log	6.4762	136	0.8547	0.6139	0.8547	0.9245
No log	6.5714	138	0.8054	0.6431	0.8054	0.8974
No log	6.6667	140	0.7537	0.6719	0.7537	0.8682
No log	6.7619	142	0.7179	0.7130	0.7179	0.8473
No log	6.8571	144	0.7280	0.7225	0.7280	0.8532
No log	6.9524	146	0.7667	0.6541	0.7667	0.8756
No log	7.0476	148	0.7783	0.6466	0.7783	0.8822
No log	7.1429	150	0.7795	0.6555	0.7795	0.8829
No log	7.2381	152	0.7830	0.6609	0.7830	0.8848
No log	7.3333	154	0.7539	0.6582	0.7539	0.8683
No log	7.4286	156	0.7009	0.7104	0.7009	0.8372
No log	7.5238	158	0.6876	0.7148	0.6876	0.8292
No log	7.6190	160	0.7004	0.6873	0.7004	0.8369
No log	7.7143	162	0.7365	0.6846	0.7365	0.8582
No log	7.8095	164	0.7143	0.6915	0.7143	0.8451
No log	7.9048	166	0.6949	0.7243	0.6949	0.8336
No log	8.0	168	0.7128	0.6349	0.7128	0.8443
No log	8.0952	170	0.7157	0.6492	0.7157	0.8460
No log	8.1905	172	0.7063	0.6421	0.7063	0.8404
No log	8.2857	174	0.7267	0.6677	0.7267	0.8525
No log	8.3810	176	0.7439	0.6889	0.7439	0.8625
No log	8.4762	178	0.7644	0.7019	0.7644	0.8743
No log	8.5714	180	0.8771	0.6426	0.8771	0.9365
No log	8.6667	182	1.0764	0.6114	1.0764	1.0375
No log	8.7619	184	1.1206	0.6130	1.1206	1.0586
No log	8.8571	186	1.0494	0.6175	1.0494	1.0244
No log	8.9524	188	1.0154	0.5909	1.0154	1.0077
No log	9.0476	190	0.8940	0.6230	0.8940	0.9455
No log	9.1429	192	0.7919	0.6635	0.7919	0.8899
No log	9.2381	194	0.7696	0.6788	0.7696	0.8773
No log	9.3333	196	0.7810	0.6739	0.7810	0.8837
No log	9.4286	198	0.8130	0.6652	0.8130	0.9016
No log	9.5238	200	0.8609	0.6574	0.8609	0.9278
No log	9.6190	202	0.8953	0.6729	0.8953	0.9462
No log	9.7143	204	0.8610	0.6683	0.8610	0.9279
No log	9.8095	206	0.8261	0.6640	0.8261	0.9089
No log	9.9048	208	0.7443	0.7147	0.7443	0.8627
No log	10.0	210	0.7295	0.6981	0.7295	0.8541
No log	10.0952	212	0.7299	0.6713	0.7299	0.8543
No log	10.1905	214	0.7392	0.6867	0.7392	0.8597
No log	10.2857	216	0.7688	0.7376	0.7688	0.8768
No log	10.3810	218	0.8126	0.6736	0.8126	0.9014
No log	10.4762	220	0.7865	0.6728	0.7865	0.8868
No log	10.5714	222	0.7320	0.7262	0.7320	0.8556
No log	10.6667	224	0.7640	0.6997	0.7640	0.8741
No log	10.7619	226	0.8037	0.6808	0.8037	0.8965
No log	10.8571	228	0.8000	0.6853	0.8000	0.8944
No log	10.9524	230	0.7734	0.6841	0.7734	0.8794
No log	11.0476	232	0.7051	0.7267	0.7051	0.8397
No log	11.1429	234	0.7574	0.6769	0.7574	0.8703
No log	11.2381	236	0.8742	0.6163	0.8742	0.9350
No log	11.3333	238	0.8715	0.6224	0.8715	0.9336
No log	11.4286	240	0.7738	0.6282	0.7738	0.8797
No log	11.5238	242	0.7076	0.6076	0.7076	0.8412
No log	11.6190	244	0.6982	0.6555	0.6982	0.8356
No log	11.7143	246	0.7184	0.6903	0.7184	0.8476
No log	11.8095	248	0.7735	0.7022	0.7735	0.8795
No log	11.9048	250	0.9330	0.6574	0.9330	0.9659
No log	12.0	252	1.0010	0.6151	1.0010	1.0005
No log	12.0952	254	0.8962	0.6145	0.8962	0.9467
No log	12.1905	256	0.7193	0.6884	0.7193	0.8481
No log	12.2857	258	0.6898	0.6220	0.6898	0.8305
No log	12.3810	260	0.6998	0.6449	0.6998	0.8365
No log	12.4762	262	0.7083	0.7005	0.7083	0.8416
No log	12.5714	264	0.7162	0.7037	0.7162	0.8463
No log	12.6667	266	0.7923	0.6739	0.7923	0.8901
No log	12.7619	268	0.9672	0.5968	0.9672	0.9835
No log	12.8571	270	0.9872	0.5923	0.9872	0.9936
No log	12.9524	272	0.8682	0.6297	0.8682	0.9318
No log	13.0476	274	0.7290	0.6732	0.7290	0.8538
No log	13.1429	276	0.6667	0.7112	0.6667	0.8165
No log	13.2381	278	0.7001	0.7223	0.7001	0.8367
No log	13.3333	280	0.7306	0.7111	0.7306	0.8548
No log	13.4286	282	0.7216	0.7170	0.7216	0.8495
No log	13.5238	284	0.7185	0.7098	0.7185	0.8476
No log	13.6190	286	0.7334	0.6867	0.7334	0.8564
No log	13.7143	288	0.7696	0.6584	0.7696	0.8773
No log	13.8095	290	0.7355	0.6730	0.7355	0.8576
No log	13.9048	292	0.6874	0.6954	0.6874	0.8291
No log	14.0	294	0.6980	0.7184	0.6980	0.8354
No log	14.0952	296	0.7219	0.7018	0.7219	0.8496
No log	14.1905	298	0.7144	0.7131	0.7144	0.8452
No log	14.2857	300	0.7203	0.6887	0.7203	0.8487
No log	14.3810	302	0.7663	0.6868	0.7663	0.8754
No log	14.4762	304	0.7878	0.6485	0.7878	0.8876
No log	14.5714	306	0.7444	0.6813	0.7444	0.8628
No log	14.6667	308	0.6641	0.7356	0.6641	0.8149
No log	14.7619	310	0.6729	0.7227	0.6729	0.8203
No log	14.8571	312	0.7039	0.6989	0.7039	0.8390
No log	14.9524	314	0.7269	0.7071	0.7269	0.8526
No log	15.0476	316	0.7792	0.6754	0.7792	0.8827
No log	15.1429	318	0.7796	0.7011	0.7796	0.8830
No log	15.2381	320	0.7581	0.7072	0.7581	0.8707
No log	15.3333	322	0.7734	0.6918	0.7734	0.8794
No log	15.4286	324	0.7548	0.7122	0.7548	0.8688
No log	15.5238	326	0.7103	0.7443	0.7103	0.8428
No log	15.6190	328	0.7013	0.7223	0.7013	0.8375
No log	15.7143	330	0.7106	0.7346	0.7106	0.8430
No log	15.8095	332	0.7155	0.7283	0.7155	0.8459
No log	15.9048	334	0.7659	0.6874	0.7659	0.8751
No log	16.0	336	0.7934	0.6780	0.7934	0.8907
No log	16.0952	338	0.7485	0.7149	0.7485	0.8652
No log	16.1905	340	0.7063	0.7284	0.7063	0.8404
No log	16.2857	342	0.6836	0.7123	0.6836	0.8268
No log	16.3810	344	0.6934	0.6944	0.6934	0.8327
No log	16.4762	346	0.6968	0.7181	0.6968	0.8347
No log	16.5714	348	0.7301	0.7285	0.7301	0.8545
No log	16.6667	350	0.7747	0.6986	0.7747	0.8802
No log	16.7619	352	0.8192	0.7050	0.8192	0.9051
No log	16.8571	354	0.8820	0.6178	0.8820	0.9391
No log	16.9524	356	0.8570	0.6200	0.8570	0.9257
No log	17.0476	358	0.7794	0.6768	0.7794	0.8828
No log	17.1429	360	0.7383	0.7102	0.7383	0.8593
No log	17.2381	362	0.7260	0.7107	0.7260	0.8521
No log	17.3333	364	0.7229	0.6920	0.7229	0.8502
No log	17.4286	366	0.7208	0.7023	0.7208	0.8490
No log	17.5238	368	0.7334	0.7094	0.7334	0.8564
No log	17.6190	370	0.7571	0.6771	0.7571	0.8701
No log	17.7143	372	0.7687	0.6865	0.7687	0.8768
No log	17.8095	374	0.7824	0.6965	0.7824	0.8845
No log	17.9048	376	0.7747	0.7062	0.7747	0.8802
No log	18.0	378	0.7464	0.7055	0.7464	0.8639
No log	18.0952	380	0.7322	0.7017	0.7322	0.8557
No log	18.1905	382	0.7316	0.7016	0.7316	0.8554
No log	18.2857	384	0.7056	0.7006	0.7056	0.8400
No log	18.3810	386	0.6816	0.6787	0.6816	0.8256
No log	18.4762	388	0.6785	0.6787	0.6785	0.8237
No log	18.5714	390	0.6821	0.6955	0.6821	0.8259
No log	18.6667	392	0.7246	0.6954	0.7246	0.8512
No log	18.7619	394	0.8160	0.6482	0.8160	0.9033
No log	18.8571	396	0.9554	0.6448	0.9554	0.9774
No log	18.9524	398	0.9377	0.6835	0.9377	0.9684
No log	19.0476	400	0.8252	0.6824	0.8252	0.9084
No log	19.1429	402	0.7104	0.7353	0.7104	0.8428
No log	19.2381	404	0.6716	0.6988	0.6716	0.8195
No log	19.3333	406	0.6608	0.6965	0.6608	0.8129
No log	19.4286	408	0.6399	0.7047	0.6399	0.7999
No log	19.5238	410	0.6539	0.7121	0.6539	0.8086
No log	19.6190	412	0.7612	0.6782	0.7612	0.8724
No log	19.7143	414	0.8422	0.6542	0.8422	0.9177
No log	19.8095	416	0.8343	0.6454	0.8343	0.9134
No log	19.9048	418	0.7521	0.6964	0.7521	0.8672
No log	20.0	420	0.7340	0.6975	0.7340	0.8567
No log	20.0952	422	0.7538	0.6870	0.7538	0.8682
No log	20.1905	424	0.7551	0.7053	0.7551	0.8689
No log	20.2857	426	0.7711	0.7086	0.7711	0.8781
No log	20.3810	428	0.7551	0.6990	0.7551	0.8690
No log	20.4762	430	0.7282	0.7322	0.7282	0.8533
No log	20.5714	432	0.7406	0.6847	0.7406	0.8606
No log	20.6667	434	0.7784	0.6745	0.7784	0.8823
No log	20.7619	436	0.7737	0.6693	0.7737	0.8796
No log	20.8571	438	0.7294	0.6815	0.7294	0.8540
No log	20.9524	440	0.6986	0.7049	0.6986	0.8358
No log	21.0476	442	0.6728	0.6813	0.6728	0.8202
No log	21.1429	444	0.6793	0.6987	0.6793	0.8242
No log	21.2381	446	0.6986	0.7537	0.6986	0.8358
No log	21.3333	448	0.7409	0.7064	0.7409	0.8608
No log	21.4286	450	0.7434	0.7221	0.7434	0.8622
No log	21.5238	452	0.7188	0.7233	0.7188	0.8478
No log	21.6190	454	0.6918	0.7190	0.6918	0.8317
No log	21.7143	456	0.6904	0.6778	0.6904	0.8309
No log	21.8095	458	0.6943	0.6962	0.6943	0.8332
No log	21.9048	460	0.7065	0.6798	0.7065	0.8406
No log	22.0	462	0.7490	0.7076	0.7490	0.8655
No log	22.0952	464	0.7863	0.6803	0.7863	0.8867
No log	22.1905	466	0.8044	0.6792	0.8044	0.8969
No log	22.2857	468	0.7795	0.6806	0.7795	0.8829
No log	22.3810	470	0.7605	0.6830	0.7605	0.8720
No log	22.4762	472	0.7679	0.6824	0.7679	0.8763
No log	22.5714	474	0.7950	0.7102	0.7950	0.8916
No log	22.6667	476	0.8536	0.6439	0.8536	0.9239
No log	22.7619	478	0.8551	0.6491	0.8551	0.9247
No log	22.8571	480	0.7671	0.6665	0.7671	0.8758
No log	22.9524	482	0.6859	0.6642	0.6859	0.8282
No log	23.0476	484	0.6636	0.6588	0.6636	0.8146
No log	23.1429	486	0.6650	0.6693	0.6650	0.8155
No log	23.2381	488	0.7066	0.6989	0.7066	0.8406
No log	23.3333	490	0.8044	0.6648	0.8044	0.8969
No log	23.4286	492	0.9309	0.6399	0.9309	0.9648
No log	23.5238	494	0.9085	0.6329	0.9085	0.9532
No log	23.6190	496	0.7899	0.7113	0.7899	0.8888
No log	23.7143	498	0.7225	0.7097	0.7225	0.8500
0.383	23.8095	500	0.7061	0.7307	0.7061	0.8403
0.383	23.9048	502	0.7147	0.7277	0.7147	0.8454
0.383	24.0	504	0.7425	0.6926	0.7425	0.8617
0.383	24.0952	506	0.8179	0.6667	0.8179	0.9044
0.383	24.1905	508	0.8761	0.5997	0.8761	0.9360
0.383	24.2857	510	0.9401	0.5849	0.9401	0.9696

Framework versions

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