ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k15_task7_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: 0.7312
• Qwk: 0.3822
• Mse: 0.7312
• Rmse: 0.8551

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	0.04	2	2.4274	0.0052	2.4274	1.5580
No log	0.08	4	1.1765	0.0736	1.1765	1.0847
No log	0.12	6	0.9564	-0.0622	0.9564	0.9780
No log	0.16	8	0.8266	-0.0426	0.8266	0.9092
No log	0.2	10	0.7358	0.0428	0.7358	0.8578
No log	0.24	12	0.7339	0.0	0.7339	0.8567
No log	0.28	14	0.7785	0.0428	0.7785	0.8823
No log	0.32	16	0.7659	0.0	0.7659	0.8751
No log	0.36	18	0.7373	0.0	0.7373	0.8586
No log	0.4	20	0.7442	0.0428	0.7442	0.8627
No log	0.44	22	0.7170	0.0840	0.7170	0.8468
No log	0.48	24	0.7069	0.0798	0.7069	0.8408
No log	0.52	26	0.7456	0.0481	0.7456	0.8635
No log	0.56	28	0.7848	0.0053	0.7848	0.8859
No log	0.6	30	0.7799	-0.0339	0.7799	0.8831
No log	0.64	32	0.9028	0.1711	0.9028	0.9502
No log	0.68	34	0.9872	0.1618	0.9872	0.9936
No log	0.72	36	0.9041	0.2046	0.9041	0.9509
No log	0.76	38	0.8139	-0.0354	0.8139	0.9022
No log	0.8	40	0.8337	-0.1217	0.8337	0.9131
No log	0.84	42	0.9384	-0.1217	0.9384	0.9687
No log	0.88	44	1.1199	-0.0741	1.1199	1.0582
No log	0.92	46	0.9025	-0.1217	0.9025	0.9500
No log	0.96	48	0.7865	0.0	0.7865	0.8869
No log	1.0	50	0.9136	0.1345	0.9136	0.9558
No log	1.04	52	0.9775	0.1323	0.9775	0.9887
No log	1.08	54	0.8843	0.1328	0.8843	0.9404
No log	1.12	56	0.7788	0.1263	0.7788	0.8825
No log	1.16	58	0.7441	0.2317	0.7441	0.8626
No log	1.2	60	0.7116	0.2280	0.7116	0.8436
No log	1.24	62	0.7402	0.1673	0.7402	0.8604
No log	1.28	64	0.7879	0.0905	0.7879	0.8876
No log	1.32	66	0.7520	0.0798	0.7520	0.8672
No log	1.3600	68	0.7561	0.1863	0.7561	0.8695
No log	1.4	70	0.8336	0.2652	0.8336	0.9130
No log	1.44	72	0.7358	0.2718	0.7358	0.8578
No log	1.48	74	0.6614	0.2270	0.6614	0.8133
No log	1.52	76	0.6557	0.2930	0.6557	0.8098
No log	1.56	78	0.6466	0.2930	0.6466	0.8041
No log	1.6	80	0.6585	0.3546	0.6585	0.8115
No log	1.6400	82	0.7471	0.2950	0.7471	0.8643
No log	1.6800	84	0.7469	0.3166	0.7469	0.8643
No log	1.72	86	0.7328	0.2537	0.7328	0.8561
No log	1.76	88	0.7457	0.2036	0.7457	0.8635
No log	1.8	90	0.7577	0.2395	0.7577	0.8705
No log	1.8400	92	0.6830	0.2481	0.6830	0.8264
No log	1.88	94	0.6471	0.2677	0.6471	0.8044
No log	1.92	96	0.6638	0.3166	0.6638	0.8147
No log	1.96	98	0.6636	0.3166	0.6636	0.8146
No log	2.0	100	0.6602	0.2412	0.6602	0.8125
No log	2.04	102	0.6978	0.3407	0.6978	0.8353
No log	2.08	104	0.6805	0.3666	0.6805	0.8249
No log	2.12	106	0.6165	0.3070	0.6165	0.7852
No log	2.16	108	0.6135	0.3239	0.6135	0.7833
No log	2.2	110	0.6312	0.4124	0.6312	0.7945
No log	2.24	112	0.6614	0.4473	0.6614	0.8133
No log	2.2800	114	0.6648	0.4051	0.6648	0.8153
No log	2.32	116	0.6930	0.4193	0.6930	0.8325
No log	2.36	118	0.6933	0.4674	0.6933	0.8326
No log	2.4	120	0.6805	0.4674	0.6805	0.8249
No log	2.44	122	0.6622	0.4674	0.6622	0.8137
No log	2.48	124	0.6446	0.4244	0.6446	0.8029
No log	2.52	126	0.6384	0.3701	0.6384	0.7990
No log	2.56	128	0.6362	0.3976	0.6362	0.7976
No log	2.6	130	0.6191	0.3976	0.6191	0.7869
No log	2.64	132	0.6174	0.3153	0.6174	0.7857
No log	2.68	134	0.6226	0.2852	0.6226	0.7891
No log	2.7200	136	0.6031	0.3050	0.6031	0.7766
No log	2.76	138	0.6677	0.4052	0.6677	0.8171
No log	2.8	140	0.7138	0.4470	0.7138	0.8449
No log	2.84	142	0.6412	0.4144	0.6412	0.8008
No log	2.88	144	0.5717	0.3312	0.5717	0.7561
No log	2.92	146	0.5804	0.3603	0.5804	0.7619
No log	2.96	148	0.5864	0.3910	0.5864	0.7658
No log	3.0	150	0.6052	0.4147	0.6052	0.7779
No log	3.04	152	0.6525	0.2413	0.6525	0.8078
No log	3.08	154	0.6053	0.4012	0.6053	0.7780
No log	3.12	156	0.5813	0.4697	0.5813	0.7625
No log	3.16	158	0.5972	0.4923	0.5972	0.7728
No log	3.2	160	0.6184	0.4820	0.6184	0.7864
No log	3.24	162	0.6251	0.3887	0.6251	0.7906
No log	3.2800	164	0.6522	0.3942	0.6522	0.8076
No log	3.32	166	0.7626	0.3981	0.7626	0.8733
No log	3.36	168	0.8190	0.3665	0.8190	0.9050
No log	3.4	170	0.7365	0.2949	0.7365	0.8582
No log	3.44	172	0.6701	0.3865	0.6701	0.8186
No log	3.48	174	0.6744	0.4762	0.6744	0.8212
No log	3.52	176	0.6518	0.4953	0.6518	0.8074
No log	3.56	178	0.6513	0.3763	0.6513	0.8070
No log	3.6	180	0.7456	0.4197	0.7456	0.8635
No log	3.64	182	0.7882	0.4592	0.7882	0.8878
No log	3.68	184	0.6834	0.4295	0.6834	0.8267
No log	3.7200	186	0.6000	0.5123	0.6000	0.7746
No log	3.76	188	0.5895	0.4934	0.5895	0.7678
No log	3.8	190	0.5911	0.4526	0.5911	0.7688
No log	3.84	192	0.5921	0.4384	0.5921	0.7695
No log	3.88	194	0.5723	0.4747	0.5723	0.7565
No log	3.92	196	0.5636	0.4270	0.5636	0.7508
No log	3.96	198	0.5608	0.5379	0.5608	0.7489
No log	4.0	200	0.5640	0.5419	0.5640	0.7510
No log	4.04	202	0.5566	0.5742	0.5566	0.7461
No log	4.08	204	0.5370	0.5288	0.5370	0.7328
No log	4.12	206	0.5359	0.5306	0.5359	0.7320
No log	4.16	208	0.5686	0.4402	0.5686	0.7541
No log	4.2	210	0.6591	0.2847	0.6591	0.8119
No log	4.24	212	0.6738	0.2847	0.6738	0.8209
No log	4.28	214	0.6451	0.3651	0.6451	0.8032
No log	4.32	216	0.6266	0.5213	0.6266	0.7916
No log	4.36	218	0.6424	0.4455	0.6424	0.8015
No log	4.4	220	0.6619	0.4085	0.6619	0.8136
No log	4.44	222	0.6920	0.4592	0.6920	0.8319
No log	4.48	224	0.6724	0.4116	0.6724	0.8200
No log	4.52	226	0.6453	0.4154	0.6453	0.8033
No log	4.5600	228	0.6381	0.4526	0.6381	0.7988
No log	4.6	230	0.6885	0.4321	0.6885	0.8297
No log	4.64	232	0.6799	0.4858	0.6799	0.8246
No log	4.68	234	0.6394	0.4945	0.6394	0.7996
No log	4.72	236	0.6393	0.4342	0.6393	0.7996
No log	4.76	238	0.6353	0.4116	0.6353	0.7970
No log	4.8	240	0.6287	0.4190	0.6287	0.7929
No log	4.84	242	0.6402	0.4386	0.6402	0.8001
No log	4.88	244	0.6417	0.3481	0.6417	0.8011
No log	4.92	246	0.6747	0.3545	0.6747	0.8214
No log	4.96	248	0.8066	0.2754	0.8066	0.8981
No log	5.0	250	0.8043	0.2492	0.8043	0.8968
No log	5.04	252	0.7289	0.4020	0.7289	0.8538
No log	5.08	254	0.7174	0.3914	0.7174	0.8470
No log	5.12	256	0.6939	0.4377	0.6939	0.8330
No log	5.16	258	0.6843	0.4795	0.6843	0.8273
No log	5.2	260	0.6972	0.4176	0.6972	0.8350
No log	5.24	262	0.7394	0.3746	0.7394	0.8599
No log	5.28	264	0.6968	0.3746	0.6968	0.8348
No log	5.32	266	0.6740	0.3762	0.6740	0.8210
No log	5.36	268	0.6626	0.4029	0.6626	0.8140
No log	5.4	270	0.6439	0.3689	0.6439	0.8024
No log	5.44	272	0.6539	0.4186	0.6539	0.8087
No log	5.48	274	0.7257	0.4424	0.7257	0.8519
No log	5.52	276	0.6767	0.4165	0.6767	0.8226
No log	5.5600	278	0.6041	0.4660	0.6041	0.7773
No log	5.6	280	0.5952	0.4505	0.5952	0.7715
No log	5.64	282	0.6150	0.5032	0.6150	0.7842
No log	5.68	284	0.7016	0.4562	0.7016	0.8376
No log	5.72	286	0.7097	0.4562	0.7097	0.8424
No log	5.76	288	0.6046	0.4112	0.6046	0.7776
No log	5.8	290	0.5544	0.4438	0.5544	0.7446
No log	5.84	292	0.5784	0.4858	0.5784	0.7605
No log	5.88	294	0.5696	0.4615	0.5696	0.7547
No log	5.92	296	0.5764	0.4484	0.5764	0.7592
No log	5.96	298	0.5785	0.4591	0.5785	0.7606
No log	6.0	300	0.5834	0.4591	0.5834	0.7638
No log	6.04	302	0.5812	0.5114	0.5812	0.7624
No log	6.08	304	0.5857	0.4314	0.5857	0.7653
No log	6.12	306	0.6044	0.3966	0.6044	0.7774
No log	6.16	308	0.6554	0.3662	0.6554	0.8096
No log	6.2	310	0.6458	0.3942	0.6458	0.8036
No log	6.24	312	0.6404	0.4601	0.6404	0.8003
No log	6.28	314	0.6362	0.4919	0.6362	0.7976
No log	6.32	316	0.6572	0.4493	0.6572	0.8107
No log	6.36	318	0.7344	0.3942	0.7344	0.8570
No log	6.4	320	0.7887	0.3131	0.7887	0.8881
No log	6.44	322	0.7331	0.4212	0.7331	0.8562
No log	6.48	324	0.6939	0.4459	0.6939	0.8330
No log	6.52	326	0.6825	0.4459	0.6825	0.8261
No log	6.5600	328	0.6399	0.4354	0.6399	0.8000
No log	6.6	330	0.6121	0.4441	0.6121	0.7824
No log	6.64	332	0.6228	0.4137	0.6228	0.7891
No log	6.68	334	0.6502	0.5135	0.6502	0.8063
No log	6.72	336	0.6563	0.4288	0.6563	0.8101
No log	6.76	338	0.6926	0.3690	0.6926	0.8322
No log	6.8	340	0.7230	0.4441	0.7230	0.8503
No log	6.84	342	0.6944	0.4341	0.6944	0.8333
No log	6.88	344	0.6796	0.4789	0.6796	0.8244
No log	6.92	346	0.6716	0.4892	0.6716	0.8195
No log	6.96	348	0.6652	0.5101	0.6652	0.8156
No log	7.0	350	0.6921	0.4663	0.6921	0.8319
No log	7.04	352	0.7951	0.3868	0.7951	0.8917
No log	7.08	354	0.8334	0.3847	0.8334	0.9129
No log	7.12	356	0.7312	0.4023	0.7312	0.8551
No log	7.16	358	0.6664	0.5288	0.6664	0.8163
No log	7.2	360	0.6628	0.4771	0.6628	0.8141
No log	7.24	362	0.6810	0.5288	0.6810	0.8252
No log	7.28	364	0.7649	0.3667	0.7649	0.8746
No log	7.32	366	0.8399	0.4088	0.8399	0.9164
No log	7.36	368	0.7635	0.4404	0.7635	0.8738
No log	7.4	370	0.6856	0.5020	0.6856	0.8280
No log	7.44	372	0.6553	0.5135	0.6553	0.8095
No log	7.48	374	0.6384	0.5075	0.6384	0.7990
No log	7.52	376	0.6330	0.4919	0.6330	0.7956
No log	7.5600	378	0.6563	0.4819	0.6563	0.8101
No log	7.6	380	0.6292	0.5095	0.6292	0.7932
No log	7.64	382	0.6429	0.5039	0.6429	0.8018
No log	7.68	384	0.6684	0.4406	0.6684	0.8176
No log	7.72	386	0.6482	0.4692	0.6482	0.8051
No log	7.76	388	0.6332	0.4259	0.6332	0.7957
No log	7.8	390	0.6645	0.4484	0.6645	0.8152
No log	7.84	392	0.6261	0.4618	0.6261	0.7913
No log	7.88	394	0.5782	0.4278	0.5782	0.7604
No log	7.92	396	0.5975	0.4555	0.5975	0.7730
No log	7.96	398	0.6356	0.5044	0.6356	0.7972
No log	8.0	400	0.6112	0.5110	0.6112	0.7818
No log	8.04	402	0.5822	0.4857	0.5822	0.7630
No log	8.08	404	0.6031	0.4393	0.6031	0.7766
No log	8.12	406	0.6764	0.4369	0.6764	0.8224
No log	8.16	408	0.6584	0.4550	0.6584	0.8114
No log	8.2	410	0.5844	0.4624	0.5844	0.7645
No log	8.24	412	0.5819	0.4898	0.5819	0.7628
No log	8.28	414	0.5898	0.4753	0.5898	0.7680
No log	8.32	416	0.6123	0.4901	0.6123	0.7825
No log	8.36	418	0.6276	0.4662	0.6276	0.7922
No log	8.4	420	0.6287	0.4789	0.6287	0.7929
No log	8.44	422	0.6326	0.5397	0.6326	0.7954
No log	8.48	424	0.6263	0.5288	0.6263	0.7914
No log	8.52	426	0.6286	0.5121	0.6286	0.7928
No log	8.56	428	0.6186	0.5753	0.6186	0.7865
No log	8.6	430	0.6160	0.4855	0.6160	0.7849
No log	8.64	432	0.6613	0.4568	0.6613	0.8132
No log	8.68	434	0.6471	0.4065	0.6471	0.8044
No log	8.72	436	0.6502	0.3609	0.6502	0.8064
No log	8.76	438	0.6294	0.3794	0.6294	0.7933
No log	8.8	440	0.6102	0.4076	0.6102	0.7812
No log	8.84	442	0.6291	0.4076	0.6291	0.7931
No log	8.88	444	0.6416	0.4664	0.6416	0.8010
No log	8.92	446	0.6549	0.4665	0.6549	0.8092
No log	8.96	448	0.6032	0.5184	0.6032	0.7766
No log	9.0	450	0.6001	0.5397	0.6001	0.7747
No log	9.04	452	0.5908	0.5397	0.5908	0.7686
No log	9.08	454	0.5838	0.5397	0.5838	0.7641
No log	9.12	456	0.5866	0.5226	0.5866	0.7659
No log	9.16	458	0.6180	0.4531	0.6180	0.7861
No log	9.2	460	0.5910	0.4925	0.5910	0.7688
No log	9.24	462	0.5664	0.4857	0.5664	0.7526
No log	9.28	464	0.5691	0.4276	0.5691	0.7544
No log	9.32	466	0.5830	0.4639	0.5830	0.7636
No log	9.36	468	0.6095	0.4933	0.6095	0.7807
No log	9.4	470	0.6089	0.5306	0.6089	0.7803
No log	9.44	472	0.6092	0.5383	0.6092	0.7805
No log	9.48	474	0.6133	0.5450	0.6133	0.7832
No log	9.52	476	0.6409	0.5025	0.6409	0.8006
No log	9.56	478	0.6401	0.5008	0.6401	0.8000
No log	9.6	480	0.6658	0.4916	0.6658	0.8160
No log	9.64	482	0.8531	0.3848	0.8531	0.9236
No log	9.68	484	0.9948	0.3866	0.9948	0.9974
No log	9.72	486	0.9550	0.3690	0.9550	0.9772
No log	9.76	488	0.8077	0.3521	0.8077	0.8987
No log	9.8	490	0.6595	0.5016	0.6595	0.8121
No log	9.84	492	0.5997	0.4837	0.5997	0.7744
No log	9.88	494	0.6031	0.5373	0.6031	0.7766
No log	9.92	496	0.5987	0.5656	0.5987	0.7737
No log	9.96	498	0.6234	0.4901	0.6234	0.7895
0.3389	10.0	500	0.6875	0.4476	0.6875	0.8292
0.3389	10.04	502	0.7098	0.4104	0.7098	0.8425
0.3389	10.08	504	0.6939	0.4104	0.6939	0.8330
0.3389	10.12	506	0.6332	0.4901	0.6332	0.7958
0.3389	10.16	508	0.6172	0.4923	0.6172	0.7856
0.3389	10.2	510	0.6415	0.4349	0.6415	0.8010
0.3389	10.24	512	0.6316	0.4205	0.6316	0.7947
0.3389	10.28	514	0.6116	0.3677	0.6116	0.7821
0.3389	10.32	516	0.6396	0.4219	0.6396	0.7997
0.3389	10.36	518	0.7312	0.3822	0.7312	0.8551

Framework versions

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