ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k1_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: 0.8507
• Qwk: 0.3879
• Mse: 0.8507
• Rmse: 0.9223

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	4.6515	-0.0693	4.6515	2.1567
No log	0.8	4	2.7809	-0.1701	2.7809	1.6676
No log	1.2	6	2.6156	-0.0969	2.6156	1.6173
No log	1.6	8	1.6115	-0.1732	1.6115	1.2694
No log	2.0	10	1.2239	-0.0587	1.2239	1.1063
No log	2.4	12	1.1762	0.0319	1.1762	1.0845
No log	2.8	14	1.1795	0.1167	1.1795	1.0860
No log	3.2	16	1.1028	0.2467	1.1028	1.0501
No log	3.6	18	1.0020	0.3498	1.0020	1.0010
No log	4.0	20	1.0000	0.2588	1.0000	1.0000
No log	4.4	22	1.0343	0.2635	1.0343	1.0170
No log	4.8	24	1.0295	0.2880	1.0295	1.0147
No log	5.2	26	0.9686	0.2341	0.9686	0.9842
No log	5.6	28	0.9683	0.2449	0.9683	0.9840
No log	6.0	30	1.0237	0.3474	1.0237	1.0118
No log	6.4	32	1.0185	0.2674	1.0185	1.0092
No log	6.8	34	0.9981	0.2553	0.9981	0.9991
No log	7.2	36	0.9620	0.2865	0.9620	0.9808
No log	7.6	38	0.9444	0.3017	0.9444	0.9718
No log	8.0	40	0.9638	0.3080	0.9638	0.9817
No log	8.4	42	0.9500	0.3154	0.9500	0.9747
No log	8.8	44	0.9498	0.2993	0.9498	0.9746
No log	9.2	46	1.0957	0.2831	1.0957	1.0468
No log	9.6	48	1.1835	0.2991	1.1835	1.0879
No log	10.0	50	1.0207	0.4127	1.0207	1.0103
No log	10.4	52	0.9416	0.3072	0.9416	0.9704
No log	10.8	54	0.9797	0.2982	0.9797	0.9898
No log	11.2	56	0.9746	0.3466	0.9746	0.9872
No log	11.6	58	0.9297	0.3421	0.9297	0.9642
No log	12.0	60	1.0421	0.3359	1.0421	1.0208
No log	12.4	62	0.9438	0.4147	0.9438	0.9715
No log	12.8	64	0.9658	0.4034	0.9658	0.9827
No log	13.2	66	1.1124	0.3046	1.1124	1.0547
No log	13.6	68	1.0995	0.2857	1.0995	1.0486
No log	14.0	70	1.0067	0.3219	1.0067	1.0033
No log	14.4	72	0.8741	0.3418	0.8741	0.9349
No log	14.8	74	0.8909	0.4363	0.8909	0.9439
No log	15.2	76	0.8781	0.4225	0.8781	0.9371
No log	15.6	78	0.9275	0.3697	0.9275	0.9631
No log	16.0	80	0.9562	0.4159	0.9562	0.9779
No log	16.4	82	0.9458	0.4086	0.9458	0.9725
No log	16.8	84	0.9120	0.4930	0.9120	0.9550
No log	17.2	86	0.8785	0.4027	0.8785	0.9373
No log	17.6	88	0.9451	0.4176	0.9451	0.9722
No log	18.0	90	0.9757	0.4496	0.9757	0.9878
No log	18.4	92	0.8992	0.3722	0.8992	0.9483
No log	18.8	94	0.8644	0.4089	0.8644	0.9297
No log	19.2	96	0.8620	0.3715	0.8620	0.9284
No log	19.6	98	0.8703	0.3472	0.8703	0.9329
No log	20.0	100	0.8675	0.4159	0.8675	0.9314
No log	20.4	102	0.8183	0.4995	0.8183	0.9046
No log	20.8	104	0.8359	0.5098	0.8359	0.9143
No log	21.2	106	0.8156	0.4460	0.8156	0.9031
No log	21.6	108	0.8827	0.4186	0.8827	0.9395
No log	22.0	110	0.9850	0.3293	0.9850	0.9925
No log	22.4	112	1.0257	0.3293	1.0257	1.0128
No log	22.8	114	0.9601	0.3293	0.9601	0.9798
No log	23.2	116	0.8995	0.4398	0.8995	0.9484
No log	23.6	118	0.8597	0.4417	0.8597	0.9272
No log	24.0	120	0.8319	0.4203	0.8319	0.9121
No log	24.4	122	0.8349	0.4646	0.8349	0.9137
No log	24.8	124	0.9283	0.3567	0.9283	0.9635
No log	25.2	126	0.9676	0.3944	0.9676	0.9836
No log	25.6	128	0.8991	0.4203	0.8991	0.9482
No log	26.0	130	0.9065	0.3726	0.9065	0.9521
No log	26.4	132	0.8994	0.3949	0.8994	0.9484
No log	26.8	134	0.8887	0.4076	0.8887	0.9427
No log	27.2	136	0.8694	0.4645	0.8694	0.9324
No log	27.6	138	0.8680	0.4645	0.8680	0.9317
No log	28.0	140	0.8758	0.4631	0.8758	0.9358
No log	28.4	142	0.8915	0.4257	0.8915	0.9442
No log	28.8	144	0.8577	0.4025	0.8577	0.9261
No log	29.2	146	0.8356	0.4706	0.8356	0.9141
No log	29.6	148	0.8312	0.5217	0.8312	0.9117
No log	30.0	150	0.8142	0.4912	0.8142	0.9023
No log	30.4	152	0.8800	0.3788	0.8800	0.9381
No log	30.8	154	0.9651	0.3783	0.9651	0.9824
No log	31.2	156	0.9230	0.4143	0.9230	0.9607
No log	31.6	158	0.8864	0.3821	0.8864	0.9415
No log	32.0	160	0.8926	0.3949	0.8926	0.9448
No log	32.4	162	0.9027	0.4632	0.9027	0.9501
No log	32.8	164	0.9409	0.3930	0.9409	0.9700
No log	33.2	166	0.9050	0.4148	0.9050	0.9513
No log	33.6	168	0.8568	0.4544	0.8568	0.9256
No log	34.0	170	0.8551	0.4576	0.8551	0.9247
No log	34.4	172	0.8609	0.4411	0.8609	0.9278
No log	34.8	174	0.9201	0.3639	0.9201	0.9592
No log	35.2	176	1.0851	0.3059	1.0851	1.0417
No log	35.6	178	1.1647	0.3444	1.1647	1.0792
No log	36.0	180	1.1986	0.2972	1.1986	1.0948
No log	36.4	182	1.1625	0.3601	1.1625	1.0782
No log	36.8	184	1.0387	0.3692	1.0387	1.0192
No log	37.2	186	0.9560	0.3792	0.9560	0.9778
No log	37.6	188	0.9075	0.4082	0.9075	0.9526
No log	38.0	190	0.8755	0.3733	0.8755	0.9357
No log	38.4	192	0.8452	0.4565	0.8452	0.9194
No log	38.8	194	0.8407	0.4391	0.8407	0.9169
No log	39.2	196	0.8437	0.4382	0.8437	0.9185
No log	39.6	198	0.8579	0.4143	0.8579	0.9262
No log	40.0	200	0.8682	0.4143	0.8682	0.9318
No log	40.4	202	0.8687	0.4495	0.8687	0.9320
No log	40.8	204	0.8776	0.5067	0.8776	0.9368
No log	41.2	206	0.8418	0.4754	0.8418	0.9175
No log	41.6	208	0.8468	0.4676	0.8468	0.9202
No log	42.0	210	0.8715	0.4778	0.8715	0.9335
No log	42.4	212	0.9305	0.4406	0.9305	0.9646
No log	42.8	214	0.9582	0.4060	0.9582	0.9789
No log	43.2	216	0.9638	0.3747	0.9638	0.9818
No log	43.6	218	0.9168	0.4176	0.9168	0.9575
No log	44.0	220	0.8570	0.4982	0.8570	0.9257
No log	44.4	222	0.8303	0.5016	0.8303	0.9112
No log	44.8	224	0.8287	0.5002	0.8287	0.9104
No log	45.2	226	0.8402	0.4648	0.8402	0.9166
No log	45.6	228	0.8478	0.5081	0.8478	0.9207
No log	46.0	230	0.8287	0.4181	0.8287	0.9103
No log	46.4	232	0.8284	0.4181	0.8284	0.9102
No log	46.8	234	0.8212	0.4429	0.8212	0.9062
No log	47.2	236	0.8421	0.4382	0.8421	0.9177
No log	47.6	238	0.8529	0.4257	0.8529	0.9235
No log	48.0	240	0.8304	0.4169	0.8304	0.9113
No log	48.4	242	0.8276	0.4661	0.8276	0.9097
No log	48.8	244	0.8249	0.4153	0.8249	0.9082
No log	49.2	246	0.8517	0.4257	0.8517	0.9229
No log	49.6	248	0.8913	0.3913	0.8913	0.9441
No log	50.0	250	0.8717	0.3560	0.8717	0.9337
No log	50.4	252	0.8153	0.4879	0.8153	0.9029
No log	50.8	254	0.8101	0.4676	0.8101	0.9001
No log	51.2	256	0.8211	0.4305	0.8211	0.9061
No log	51.6	258	0.8257	0.4537	0.8257	0.9087
No log	52.0	260	0.8239	0.4661	0.8239	0.9077
No log	52.4	262	0.8470	0.4023	0.8470	0.9203
No log	52.8	264	0.8439	0.4008	0.8439	0.9186
No log	53.2	266	0.8439	0.4164	0.8439	0.9186
No log	53.6	268	0.8426	0.4407	0.8426	0.9179
No log	54.0	270	0.8754	0.3771	0.8754	0.9356
No log	54.4	272	0.9403	0.4377	0.9403	0.9697
No log	54.8	274	0.9532	0.4058	0.9532	0.9763
No log	55.2	276	0.9075	0.4143	0.9075	0.9526
No log	55.6	278	0.8739	0.4164	0.8739	0.9348
No log	56.0	280	0.8486	0.3966	0.8486	0.9212
No log	56.4	282	0.8497	0.4083	0.8497	0.9218
No log	56.8	284	0.8432	0.4329	0.8432	0.9183
No log	57.2	286	0.8414	0.4770	0.8414	0.9173
No log	57.6	288	0.8388	0.5125	0.8388	0.9159
No log	58.0	290	0.8375	0.5116	0.8375	0.9151
No log	58.4	292	0.8374	0.5116	0.8374	0.9151
No log	58.8	294	0.8415	0.5116	0.8415	0.9174
No log	59.2	296	0.8600	0.4647	0.8600	0.9274
No log	59.6	298	0.8515	0.5125	0.8515	0.9228
No log	60.0	300	0.8383	0.4907	0.8383	0.9156
No log	60.4	302	0.8361	0.4565	0.8361	0.9144
No log	60.8	304	0.8360	0.4907	0.8360	0.9143
No log	61.2	306	0.8637	0.4754	0.8637	0.9294
No log	61.6	308	0.9144	0.4292	0.9144	0.9562
No log	62.0	310	0.9126	0.4073	0.9126	0.9553
No log	62.4	312	0.8698	0.4603	0.8698	0.9326
No log	62.8	314	0.8306	0.4631	0.8306	0.9114
No log	63.2	316	0.8226	0.4974	0.8226	0.9070
No log	63.6	318	0.8235	0.4968	0.8235	0.9075
No log	64.0	320	0.8468	0.4484	0.8468	0.9202
No log	64.4	322	0.8734	0.4708	0.8734	0.9346
No log	64.8	324	0.8889	0.4377	0.8889	0.9428
No log	65.2	326	0.8527	0.4484	0.8527	0.9234
No log	65.6	328	0.8195	0.4282	0.8195	0.9052
No log	66.0	330	0.8080	0.4982	0.8080	0.8989
No log	66.4	332	0.8032	0.4647	0.8032	0.8962
No log	66.8	334	0.8085	0.4297	0.8085	0.8992
No log	67.2	336	0.8199	0.4148	0.8199	0.9055
No log	67.6	338	0.8464	0.3914	0.8464	0.9200
No log	68.0	340	0.8589	0.4020	0.8589	0.9268
No log	68.4	342	0.8936	0.4127	0.8936	0.9453
No log	68.8	344	0.8890	0.4127	0.8890	0.9429
No log	69.2	346	0.8596	0.3771	0.8596	0.9272
No log	69.6	348	0.8348	0.3728	0.8348	0.9137
No log	70.0	350	0.8318	0.3728	0.8318	0.9120
No log	70.4	352	0.8446	0.375	0.8446	0.9190
No log	70.8	354	0.8684	0.3771	0.8684	0.9319
No log	71.2	356	0.8886	0.3771	0.8886	0.9426
No log	71.6	358	0.8865	0.375	0.8865	0.9415
No log	72.0	360	0.8681	0.3768	0.8681	0.9317
No log	72.4	362	0.8701	0.3768	0.8701	0.9328
No log	72.8	364	0.8792	0.4257	0.8792	0.9377
No log	73.2	366	0.9071	0.4131	0.9071	0.9524
No log	73.6	368	0.9162	0.4131	0.9162	0.9572
No log	74.0	370	0.9212	0.4143	0.9212	0.9598
No log	74.4	372	0.8971	0.4257	0.8971	0.9471
No log	74.8	374	0.8804	0.4257	0.8804	0.9383
No log	75.2	376	0.8675	0.3418	0.8675	0.9314
No log	75.6	378	0.8607	0.3308	0.8607	0.9277
No log	76.0	380	0.8567	0.3437	0.8567	0.9256
No log	76.4	382	0.8533	0.3804	0.8533	0.9238
No log	76.8	384	0.8495	0.4784	0.8495	0.9217
No log	77.2	386	0.8544	0.3308	0.8544	0.9243
No log	77.6	388	0.8742	0.4148	0.8742	0.9350
No log	78.0	390	0.8919	0.4257	0.8919	0.9444
No log	78.4	392	0.8871	0.4257	0.8871	0.9418
No log	78.8	394	0.8674	0.3806	0.8674	0.9313
No log	79.2	396	0.8505	0.3675	0.8505	0.9222
No log	79.6	398	0.8462	0.3675	0.8462	0.9199
No log	80.0	400	0.8464	0.3675	0.8464	0.9200
No log	80.4	402	0.8484	0.3675	0.8484	0.9211
No log	80.8	404	0.8619	0.4257	0.8619	0.9284
No log	81.2	406	0.8810	0.4250	0.8810	0.9386
No log	81.6	408	0.8922	0.4250	0.8922	0.9445
No log	82.0	410	0.8850	0.4250	0.8850	0.9408
No log	82.4	412	0.8708	0.4366	0.8708	0.9332
No log	82.8	414	0.8692	0.4366	0.8692	0.9323
No log	83.2	416	0.8654	0.4366	0.8654	0.9303
No log	83.6	418	0.8616	0.4382	0.8616	0.9282
No log	84.0	420	0.8600	0.4273	0.8600	0.9274
No log	84.4	422	0.8610	0.4273	0.8610	0.9279
No log	84.8	424	0.8652	0.3914	0.8652	0.9301
No log	85.2	426	0.8717	0.4257	0.8717	0.9336
No log	85.6	428	0.8720	0.4257	0.8720	0.9338
No log	86.0	430	0.8814	0.4366	0.8814	0.9388
No log	86.4	432	0.8819	0.4366	0.8819	0.9391
No log	86.8	434	0.8765	0.4257	0.8765	0.9362
No log	87.2	436	0.8773	0.4257	0.8773	0.9367
No log	87.6	438	0.8756	0.3768	0.8756	0.9357
No log	88.0	440	0.8752	0.3879	0.8752	0.9355
No log	88.4	442	0.8797	0.3879	0.8797	0.9379
No log	88.8	444	0.8816	0.375	0.8816	0.9389
No log	89.2	446	0.8805	0.375	0.8805	0.9384
No log	89.6	448	0.8716	0.3879	0.8716	0.9336
No log	90.0	450	0.8647	0.3879	0.8647	0.9299
No log	90.4	452	0.8561	0.3528	0.8561	0.9253
No log	90.8	454	0.8471	0.4153	0.8471	0.9204
No log	91.2	456	0.8451	0.4153	0.8451	0.9193
No log	91.6	458	0.8463	0.3897	0.8463	0.9200
No log	92.0	460	0.8457	0.3897	0.8457	0.9196
No log	92.4	462	0.8452	0.3879	0.8452	0.9194
No log	92.8	464	0.8451	0.3879	0.8451	0.9193
No log	93.2	466	0.8484	0.3879	0.8484	0.9211
No log	93.6	468	0.8524	0.3879	0.8524	0.9232
No log	94.0	470	0.8533	0.3879	0.8533	0.9237
No log	94.4	472	0.8508	0.3879	0.8508	0.9224
No log	94.8	474	0.8501	0.3879	0.8501	0.9220
No log	95.2	476	0.8459	0.3879	0.8459	0.9197
No log	95.6	478	0.8419	0.3879	0.8419	0.9176
No log	96.0	480	0.8392	0.4503	0.8392	0.9161
No log	96.4	482	0.8395	0.4503	0.8395	0.9163
No log	96.8	484	0.8412	0.3768	0.8412	0.9171
No log	97.2	486	0.8430	0.3768	0.8430	0.9182
No log	97.6	488	0.8452	0.3768	0.8452	0.9194
No log	98.0	490	0.8470	0.3879	0.8470	0.9203
No log	98.4	492	0.8490	0.3879	0.8490	0.9214
No log	98.8	494	0.8506	0.3879	0.8506	0.9223
No log	99.2	496	0.8508	0.3879	0.8508	0.9224
No log	99.6	498	0.8507	0.3879	0.8507	0.9223
0.1821	100.0	500	0.8507	0.3879	0.8507	0.9223

Framework versions

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