ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k1_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: 0.8237
• Qwk: 0.3889
• Mse: 0.8237
• Rmse: 0.9076

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	0.4	2	2.6319	0.0231	2.6319	1.6223
No log	0.8	4	1.6978	0.0789	1.6978	1.3030
No log	1.2	6	0.8290	0.1372	0.8290	0.9105
No log	1.6	8	0.9415	-0.0103	0.9415	0.9703
No log	2.0	10	1.2405	-0.2388	1.2405	1.1138
No log	2.4	12	1.1827	-0.1052	1.1827	1.0875
No log	2.8	14	1.4619	-0.0206	1.4619	1.2091
No log	3.2	16	1.3265	0.0578	1.3265	1.1517
No log	3.6	18	1.0323	0.0653	1.0323	1.0160
No log	4.0	20	0.9716	0.1612	0.9716	0.9857
No log	4.4	22	1.2084	0.1265	1.2084	1.0993
No log	4.8	24	1.0794	0.1896	1.0794	1.0389
No log	5.2	26	0.8867	0.3175	0.8867	0.9417
No log	5.6	28	0.8776	0.3753	0.8776	0.9368
No log	6.0	30	0.9916	0.3012	0.9916	0.9958
No log	6.4	32	1.0695	0.2317	1.0695	1.0342
No log	6.8	34	1.0176	0.2814	1.0176	1.0088
No log	7.2	36	1.0378	0.3674	1.0378	1.0187
No log	7.6	38	1.0631	0.3496	1.0631	1.0311
No log	8.0	40	1.0376	0.3663	1.0376	1.0186
No log	8.4	42	0.9331	0.3717	0.9331	0.9660
No log	8.8	44	0.7185	0.4309	0.7185	0.8477
No log	9.2	46	0.7753	0.4386	0.7753	0.8805
No log	9.6	48	1.3021	0.3554	1.3021	1.1411
No log	10.0	50	1.6151	0.2906	1.6151	1.2709
No log	10.4	52	1.1525	0.4007	1.1525	1.0735
No log	10.8	54	0.7773	0.3944	0.7773	0.8817
No log	11.2	56	0.7175	0.4514	0.7175	0.8471
No log	11.6	58	0.9274	0.3333	0.9274	0.9630
No log	12.0	60	1.5488	0.2520	1.5488	1.2445
No log	12.4	62	1.4162	0.3024	1.4162	1.1900
No log	12.8	64	0.8180	0.3925	0.8180	0.9044
No log	13.2	66	0.6946	0.4342	0.6946	0.8334
No log	13.6	68	0.8080	0.4371	0.8080	0.8989
No log	14.0	70	1.0145	0.4104	1.0145	1.0072
No log	14.4	72	1.0445	0.4486	1.0445	1.0220
No log	14.8	74	0.7565	0.4421	0.7565	0.8698
No log	15.2	76	0.6978	0.4196	0.6978	0.8353
No log	15.6	78	0.8507	0.4303	0.8507	0.9224
No log	16.0	80	1.0856	0.3600	1.0856	1.0419
No log	16.4	82	1.3217	0.3323	1.3217	1.1497
No log	16.8	84	1.0711	0.3683	1.0711	1.0349
No log	17.2	86	0.6895	0.4186	0.6895	0.8304
No log	17.6	88	0.6152	0.4314	0.6152	0.7843
No log	18.0	90	0.5901	0.5076	0.5901	0.7682
No log	18.4	92	0.6543	0.4904	0.6543	0.8089
No log	18.8	94	0.7442	0.5382	0.7442	0.8627
No log	19.2	96	0.6292	0.5076	0.6292	0.7932
No log	19.6	98	0.5610	0.4441	0.5610	0.7490
No log	20.0	100	0.5974	0.4556	0.5974	0.7729
No log	20.4	102	0.5540	0.4923	0.5540	0.7443
No log	20.8	104	0.6248	0.4721	0.6248	0.7905
No log	21.2	106	0.8884	0.5077	0.8884	0.9425
No log	21.6	108	0.9722	0.4683	0.9722	0.9860
No log	22.0	110	0.7415	0.5219	0.7415	0.8611
No log	22.4	112	0.5775	0.5460	0.5775	0.7600
No log	22.8	114	0.5655	0.5379	0.5655	0.7520
No log	23.2	116	0.5875	0.4747	0.5875	0.7665
No log	23.6	118	0.7325	0.4124	0.7325	0.8559
No log	24.0	120	0.9333	0.4716	0.9333	0.9661
No log	24.4	122	0.9454	0.4365	0.9454	0.9723
No log	24.8	124	0.7337	0.4144	0.7337	0.8566
No log	25.2	126	0.6861	0.4239	0.6861	0.8283
No log	25.6	128	0.6999	0.4335	0.6999	0.8366
No log	26.0	130	0.7496	0.3889	0.7496	0.8658
No log	26.4	132	0.7363	0.4093	0.7363	0.8581
No log	26.8	134	0.6765	0.4473	0.6765	0.8225
No log	27.2	136	0.7005	0.4473	0.7005	0.8370
No log	27.6	138	0.8738	0.3461	0.8738	0.9348
No log	28.0	140	0.9191	0.3786	0.9191	0.9587
No log	28.4	142	0.8506	0.3461	0.8506	0.9223
No log	28.8	144	0.7634	0.4112	0.7634	0.8737
No log	29.2	146	0.7327	0.4134	0.7327	0.8560
No log	29.6	148	0.7013	0.4212	0.7013	0.8374
No log	30.0	150	0.7386	0.4542	0.7386	0.8594
No log	30.4	152	0.7942	0.4631	0.7942	0.8912
No log	30.8	154	0.7205	0.4282	0.7205	0.8488
No log	31.2	156	0.6229	0.4337	0.6229	0.7893
No log	31.6	158	0.6220	0.4337	0.6220	0.7887
No log	32.0	160	0.6438	0.4257	0.6438	0.8023
No log	32.4	162	0.7514	0.4218	0.7514	0.8668
No log	32.8	164	1.0046	0.3140	1.0046	1.0023
No log	33.2	166	1.0164	0.3026	1.0164	1.0082
No log	33.6	168	0.8572	0.4265	0.8572	0.9259
No log	34.0	170	0.6841	0.4314	0.6841	0.8271
No log	34.4	172	0.6554	0.4314	0.6554	0.8095
No log	34.8	174	0.7035	0.3769	0.7035	0.8387
No log	35.2	176	0.7992	0.4263	0.7992	0.8940
No log	35.6	178	0.8758	0.4237	0.8758	0.9358
No log	36.0	180	0.7902	0.4845	0.7902	0.8889
No log	36.4	182	0.6443	0.4493	0.6443	0.8027
No log	36.8	184	0.5904	0.4613	0.5904	0.7683
No log	37.2	186	0.5928	0.4970	0.5928	0.7700
No log	37.6	188	0.5952	0.4402	0.5952	0.7715
No log	38.0	190	0.6835	0.3966	0.6835	0.8267
No log	38.4	192	0.9864	0.3672	0.9864	0.9932
No log	38.8	194	1.2781	0.3155	1.2781	1.1305
No log	39.2	196	1.3104	0.3155	1.3104	1.1447
No log	39.6	198	1.0962	0.3675	1.0962	1.0470
No log	40.0	200	0.8502	0.3889	0.8502	0.9221
No log	40.4	202	0.7610	0.3798	0.7610	0.8723
No log	40.8	204	0.7262	0.4801	0.7262	0.8522
No log	41.2	206	0.7168	0.4721	0.7168	0.8466
No log	41.6	208	0.7322	0.4371	0.7322	0.8557
No log	42.0	210	0.6761	0.4582	0.6761	0.8222
No log	42.4	212	0.6381	0.4576	0.6381	0.7988
No log	42.8	214	0.6584	0.4314	0.6584	0.8114
No log	43.2	216	0.7378	0.3677	0.7378	0.8589
No log	43.6	218	0.9366	0.3689	0.9366	0.9678
No log	44.0	220	1.1096	0.3747	1.1096	1.0534
No log	44.4	222	1.1118	0.3866	1.1118	1.0544
No log	44.8	224	0.9532	0.4336	0.9532	0.9763
No log	45.2	226	0.7936	0.4284	0.7936	0.8909
No log	45.6	228	0.7475	0.4263	0.7475	0.8646
No log	46.0	230	0.7739	0.4353	0.7739	0.8797
No log	46.4	232	0.8205	0.4447	0.8205	0.9058
No log	46.8	234	0.8560	0.4367	0.8560	0.9252
No log	47.2	236	0.8231	0.4057	0.8231	0.9073
No log	47.6	238	0.7590	0.3914	0.7590	0.8712
No log	48.0	240	0.7171	0.3794	0.7171	0.8468
No log	48.4	242	0.7174	0.4190	0.7174	0.8470
No log	48.8	244	0.7493	0.3963	0.7493	0.8656
No log	49.2	246	0.8125	0.4315	0.8125	0.9014
No log	49.6	248	0.7999	0.4351	0.7999	0.8944
No log	50.0	250	0.8025	0.4199	0.8025	0.8958
No log	50.4	252	0.7446	0.4404	0.7446	0.8629
No log	50.8	254	0.6770	0.4165	0.6770	0.8228
No log	51.2	256	0.6719	0.4165	0.6719	0.8197
No log	51.6	258	0.6816	0.4165	0.6816	0.8256
No log	52.0	260	0.7445	0.4072	0.7445	0.8628
No log	52.4	262	0.8235	0.4153	0.8235	0.9075
No log	52.8	264	0.8564	0.4315	0.8564	0.9254
No log	53.2	266	0.8041	0.4104	0.8041	0.8967
No log	53.6	268	0.7690	0.4631	0.7690	0.8769
No log	54.0	270	0.7797	0.4631	0.7797	0.8830
No log	54.4	272	0.8282	0.4545	0.8282	0.9100
No log	54.8	274	0.8410	0.4545	0.8410	0.9170
No log	55.2	276	0.8437	0.4545	0.8437	0.9186
No log	55.6	278	0.8078	0.4199	0.8078	0.8988
No log	56.0	280	0.7464	0.3985	0.7464	0.8640
No log	56.4	282	0.7382	0.3985	0.7382	0.8592
No log	56.8	284	0.7425	0.3867	0.7425	0.8617
No log	57.2	286	0.7528	0.3867	0.7528	0.8677
No log	57.6	288	0.7710	0.3963	0.7710	0.8780
No log	58.0	290	0.7443	0.3985	0.7443	0.8627
No log	58.4	292	0.6858	0.4212	0.6858	0.8281
No log	58.8	294	0.6396	0.4808	0.6396	0.7998
No log	59.2	296	0.6312	0.4808	0.6312	0.7945
No log	59.6	298	0.6493	0.4808	0.6493	0.8058
No log	60.0	300	0.6623	0.4808	0.6623	0.8138
No log	60.4	302	0.7075	0.4724	0.7075	0.8411
No log	60.8	304	0.8055	0.4284	0.8055	0.8975
No log	61.2	306	0.8745	0.3866	0.8745	0.9352
No log	61.6	308	0.8656	0.3671	0.8656	0.9304
No log	62.0	310	0.8254	0.4217	0.8254	0.9085
No log	62.4	312	0.7848	0.4193	0.7848	0.8859
No log	62.8	314	0.7801	0.3776	0.7801	0.8832
No log	63.2	316	0.8064	0.3776	0.8064	0.8980
No log	63.6	318	0.8574	0.3097	0.8574	0.9260
No log	64.0	320	0.9523	0.3072	0.9523	0.9759
No log	64.4	322	1.0448	0.3412	1.0448	1.0222
No log	64.8	324	1.0669	0.3412	1.0669	1.0329
No log	65.2	326	1.0768	0.3464	1.0768	1.0377
No log	65.6	328	1.0366	0.3140	1.0366	1.0182
No log	66.0	330	1.0046	0.3412	1.0046	1.0023
No log	66.4	332	1.0058	0.3140	1.0058	1.0029
No log	66.8	334	1.0488	0.3140	1.0488	1.0241
No log	67.2	336	1.0074	0.3412	1.0074	1.0037
No log	67.6	338	0.9338	0.2881	0.9338	0.9664
No log	68.0	340	0.8779	0.2938	0.8779	0.9369
No log	68.4	342	0.8719	0.2938	0.8719	0.9338
No log	68.8	344	0.8406	0.3844	0.8406	0.9169
No log	69.2	346	0.8132	0.3844	0.8132	0.9018
No log	69.6	348	0.8086	0.3844	0.8086	0.8992
No log	70.0	350	0.8292	0.3844	0.8292	0.9106
No log	70.4	352	0.8504	0.4104	0.8504	0.9222
No log	70.8	354	0.8585	0.4104	0.8585	0.9266
No log	71.2	356	0.8443	0.4104	0.8443	0.9189
No log	71.6	358	0.8335	0.4104	0.8335	0.9129
No log	72.0	360	0.8270	0.4002	0.8270	0.9094
No log	72.4	362	0.8167	0.3776	0.8167	0.9037
No log	72.8	364	0.7709	0.4294	0.7709	0.8780
No log	73.2	366	0.7378	0.4190	0.7378	0.8590
No log	73.6	368	0.7536	0.4190	0.7536	0.8681
No log	74.0	370	0.7777	0.4112	0.7777	0.8819
No log	74.4	372	0.8346	0.4002	0.8346	0.9136
No log	74.8	374	0.8918	0.3652	0.8918	0.9444
No log	75.2	376	0.9700	0.3707	0.9700	0.9849
No log	75.6	378	1.0642	0.3865	1.0642	1.0316
No log	76.0	380	1.0975	0.3973	1.0975	1.0476
No log	76.4	382	1.0455	0.4021	1.0455	1.0225
No log	76.8	384	0.9340	0.4653	0.9340	0.9664
No log	77.2	386	0.8251	0.4092	0.8251	0.9084
No log	77.6	388	0.7386	0.4644	0.7386	0.8594
No log	78.0	390	0.6909	0.4336	0.6909	0.8312
No log	78.4	392	0.6789	0.4413	0.6789	0.8239
No log	78.8	394	0.6884	0.4428	0.6884	0.8297
No log	79.2	396	0.7088	0.4428	0.7088	0.8419
No log	79.6	398	0.7347	0.4495	0.7347	0.8572
No log	80.0	400	0.7461	0.4495	0.7461	0.8638
No log	80.4	402	0.7378	0.4408	0.7378	0.8590
No log	80.8	404	0.7155	0.4186	0.7155	0.8459
No log	81.2	406	0.6960	0.4562	0.6960	0.8342
No log	81.6	408	0.6756	0.4413	0.6756	0.8220
No log	82.0	410	0.6827	0.4336	0.6827	0.8262
No log	82.4	412	0.7067	0.4186	0.7067	0.8407
No log	82.8	414	0.7476	0.3914	0.7476	0.8647
No log	83.2	416	0.7947	0.4144	0.7947	0.8914
No log	83.6	418	0.8321	0.3992	0.8321	0.9122
No log	84.0	420	0.8467	0.3884	0.8467	0.9202
No log	84.4	422	0.8389	0.3884	0.8389	0.9159
No log	84.8	424	0.8322	0.4002	0.8322	0.9122
No log	85.2	426	0.8339	0.4002	0.8339	0.9132
No log	85.6	428	0.8584	0.3506	0.8584	0.9265
No log	86.0	430	0.8810	0.3451	0.8810	0.9386
No log	86.4	432	0.8819	0.3451	0.8819	0.9391
No log	86.8	434	0.8731	0.3144	0.8731	0.9344
No log	87.2	436	0.8508	0.3824	0.8508	0.9224
No log	87.6	438	0.8205	0.3710	0.8205	0.9058
No log	88.0	440	0.8102	0.4072	0.8102	0.9001
No log	88.4	442	0.8117	0.4072	0.8117	0.9009
No log	88.8	444	0.8130	0.4144	0.8130	0.9016
No log	89.2	446	0.8215	0.3992	0.8215	0.9064
No log	89.6	448	0.8350	0.3992	0.8350	0.9138
No log	90.0	450	0.8451	0.3929	0.8451	0.9193
No log	90.4	452	0.8354	0.3992	0.8354	0.9140
No log	90.8	454	0.8186	0.4556	0.8186	0.9047
No log	91.2	456	0.8083	0.4556	0.8083	0.8991
No log	91.6	458	0.7896	0.4556	0.7896	0.8886
No log	92.0	460	0.7686	0.4476	0.7686	0.8767
No log	92.4	462	0.7544	0.4495	0.7544	0.8685
No log	92.8	464	0.7470	0.4408	0.7470	0.8643
No log	93.2	466	0.7473	0.4165	0.7473	0.8645
No log	93.6	468	0.7516	0.4165	0.7516	0.8670
No log	94.0	470	0.7617	0.4165	0.7617	0.8727
No log	94.4	472	0.7686	0.4389	0.7686	0.8767
No log	94.8	474	0.7763	0.4389	0.7763	0.8811
No log	95.2	476	0.7886	0.4144	0.7886	0.8880
No log	95.6	478	0.8037	0.4334	0.8037	0.8965
No log	96.0	480	0.8180	0.4334	0.8180	0.9044
No log	96.4	482	0.8236	0.3992	0.8236	0.9075
No log	96.8	484	0.8298	0.3992	0.8298	0.9109
No log	97.2	486	0.8331	0.3992	0.8331	0.9128
No log	97.6	488	0.8320	0.3992	0.8320	0.9121
No log	98.0	490	0.8300	0.3992	0.8300	0.9111
No log	98.4	492	0.8269	0.3992	0.8269	0.9093
No log	98.8	494	0.8254	0.3889	0.8254	0.9085
No log	99.2	496	0.8253	0.3889	0.8253	0.9084
No log	99.6	498	0.8242	0.3889	0.8242	0.9078
0.1808	100.0	500	0.8237	0.3889	0.8237	0.9076

Framework versions

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