ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k5_task2_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: 0.6296
• Qwk: 0.4601
• Mse: 0.6296
• Rmse: 0.7935

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	0.0714	2	4.5269	-0.0218	4.5269	2.1276
No log	0.1429	4	2.6997	0.0262	2.6997	1.6431
No log	0.2143	6	1.6861	-0.0397	1.6861	1.2985
No log	0.2857	8	1.2813	-0.0217	1.2813	1.1319
No log	0.3571	10	1.2249	-0.0652	1.2249	1.1067
No log	0.4286	12	1.2182	-0.0041	1.2182	1.1037
No log	0.5	14	1.2225	-0.0641	1.2225	1.1057
No log	0.5714	16	0.8757	0.2636	0.8757	0.9358
No log	0.6429	18	0.7874	0.2068	0.7874	0.8874
No log	0.7143	20	0.7813	0.2965	0.7813	0.8839
No log	0.7857	22	0.9470	0.1905	0.9470	0.9732
No log	0.8571	24	1.0955	0.1053	1.0955	1.0467
No log	0.9286	26	1.0006	0.1612	1.0006	1.0003
No log	1.0	28	1.2258	0.0880	1.2258	1.1071
No log	1.0714	30	1.1954	0.1226	1.1954	1.0933
No log	1.1429	32	0.8266	0.2537	0.8266	0.9092
No log	1.2143	34	0.7398	0.3833	0.7398	0.8601
No log	1.2857	36	0.7335	0.2740	0.7335	0.8565
No log	1.3571	38	0.7211	0.3791	0.7211	0.8492
No log	1.4286	40	0.9231	0.2659	0.9231	0.9608
No log	1.5	42	1.0833	0.2218	1.0833	1.0408
No log	1.5714	44	0.8645	0.3757	0.8645	0.9298
No log	1.6429	46	0.6716	0.3525	0.6716	0.8195
No log	1.7143	48	0.6588	0.3607	0.6588	0.8116
No log	1.7857	50	0.6469	0.3622	0.6469	0.8043
No log	1.8571	52	0.6458	0.3552	0.6458	0.8036
No log	1.9286	54	0.6455	0.3992	0.6455	0.8034
No log	2.0	56	0.6451	0.3472	0.6451	0.8032
No log	2.0714	58	0.6569	0.3624	0.6569	0.8105
No log	2.1429	60	0.6625	0.4596	0.6625	0.8140
No log	2.2143	62	0.7447	0.4990	0.7447	0.8630
No log	2.2857	64	0.8528	0.4233	0.8528	0.9235
No log	2.3571	66	0.6848	0.4883	0.6848	0.8275
No log	2.4286	68	0.6615	0.4513	0.6615	0.8133
No log	2.5	70	0.6529	0.4467	0.6529	0.8080
No log	2.5714	72	0.6659	0.4621	0.6659	0.8160
No log	2.6429	74	0.7621	0.4107	0.7621	0.8730
No log	2.7143	76	0.9282	0.3934	0.9282	0.9634
No log	2.7857	78	0.7945	0.3907	0.7945	0.8913
No log	2.8571	80	0.7708	0.4274	0.7708	0.8780
No log	2.9286	82	0.8313	0.4482	0.8313	0.9117
No log	3.0	84	0.7120	0.4226	0.7120	0.8438
No log	3.0714	86	0.6796	0.4407	0.6796	0.8244
No log	3.1429	88	0.7026	0.3640	0.7026	0.8382
No log	3.2143	90	0.7135	0.4384	0.7135	0.8447
No log	3.2857	92	0.6582	0.4723	0.6582	0.8113
No log	3.3571	94	0.7215	0.3918	0.7215	0.8494
No log	3.4286	96	0.6620	0.4343	0.6620	0.8137
No log	3.5	98	0.6472	0.4443	0.6472	0.8045
No log	3.5714	100	0.6632	0.4430	0.6632	0.8143
No log	3.6429	102	0.6848	0.4476	0.6848	0.8275
No log	3.7143	104	0.8462	0.4434	0.8462	0.9199
No log	3.7857	106	0.7624	0.4254	0.7624	0.8732
No log	3.8571	108	0.7241	0.4981	0.7241	0.8509
No log	3.9286	110	0.7697	0.4162	0.7697	0.8773
No log	4.0	112	0.9030	0.4126	0.9030	0.9502
No log	4.0714	114	0.8098	0.4014	0.8098	0.8999
No log	4.1429	116	0.6946	0.4355	0.6946	0.8334
No log	4.2143	118	0.7392	0.3850	0.7392	0.8598
No log	4.2857	120	1.0658	0.3142	1.0658	1.0324
No log	4.3571	122	0.8280	0.4047	0.8280	0.9100
No log	4.4286	124	0.7323	0.4265	0.7323	0.8557
No log	4.5	126	0.8413	0.4118	0.8413	0.9172
No log	4.5714	128	0.7063	0.3975	0.7063	0.8404
No log	4.6429	130	0.7445	0.4369	0.7445	0.8628
No log	4.7143	132	0.9785	0.3911	0.9785	0.9892
No log	4.7857	134	0.7663	0.4187	0.7663	0.8754
No log	4.8571	136	0.6539	0.4648	0.6539	0.8086
No log	4.9286	138	0.6576	0.4248	0.6576	0.8109
No log	5.0	140	0.8555	0.4149	0.8555	0.9249
No log	5.0714	142	1.0966	0.3446	1.0966	1.0472
No log	5.1429	144	0.8819	0.4024	0.8819	0.9391
No log	5.2143	146	0.6973	0.4613	0.6973	0.8350
No log	5.2857	148	0.6690	0.4401	0.6690	0.8180
No log	5.3571	150	0.6531	0.4205	0.6531	0.8081
No log	5.4286	152	0.6849	0.4377	0.6849	0.8276
No log	5.5	154	0.7091	0.3727	0.7091	0.8421
No log	5.5714	156	0.6374	0.4216	0.6374	0.7984
No log	5.6429	158	0.6440	0.4459	0.6440	0.8025
No log	5.7143	160	0.6382	0.4091	0.6382	0.7989
No log	5.7857	162	0.8013	0.4156	0.8013	0.8952
No log	5.8571	164	0.9811	0.4253	0.9811	0.9905
No log	5.9286	166	0.9489	0.4058	0.9489	0.9741
No log	6.0	168	0.6798	0.4973	0.6798	0.8245
No log	6.0714	170	0.6487	0.4814	0.6487	0.8054
No log	6.1429	172	0.6560	0.4585	0.6560	0.8099
No log	6.2143	174	0.6669	0.5131	0.6669	0.8167
No log	6.2857	176	0.9472	0.4076	0.9472	0.9733
No log	6.3571	178	1.1587	0.3453	1.1587	1.0764
No log	6.4286	180	1.0226	0.3789	1.0226	1.0112
No log	6.5	182	1.0239	0.3856	1.0239	1.0119
No log	6.5714	184	0.9542	0.3849	0.9542	0.9768
No log	6.6429	186	0.7795	0.4196	0.7795	0.8829
No log	6.7143	188	0.6866	0.4718	0.6866	0.8286
No log	6.7857	190	0.6936	0.4580	0.6936	0.8329
No log	6.8571	192	0.6729	0.4978	0.6729	0.8203
No log	6.9286	194	0.6418	0.4747	0.6418	0.8011
No log	7.0	196	0.6559	0.3976	0.6559	0.8098
No log	7.0714	198	0.6489	0.3945	0.6489	0.8056
No log	7.1429	200	0.6202	0.3970	0.6202	0.7876
No log	7.2143	202	0.6720	0.4869	0.6720	0.8197
No log	7.2857	204	0.8470	0.4026	0.8470	0.9203
No log	7.3571	206	0.8917	0.4225	0.8917	0.9443
No log	7.4286	208	0.7803	0.4881	0.7803	0.8833
No log	7.5	210	0.7174	0.5355	0.7174	0.8470
No log	7.5714	212	0.6864	0.5145	0.6864	0.8285
No log	7.6429	214	0.6989	0.4627	0.6989	0.8360
No log	7.7143	216	0.6700	0.4507	0.6700	0.8186
No log	7.7857	218	0.6470	0.4742	0.6470	0.8043
No log	7.8571	220	0.6667	0.4816	0.6667	0.8165
No log	7.9286	222	0.6776	0.4671	0.6776	0.8231
No log	8.0	224	0.8075	0.4333	0.8075	0.8986
No log	8.0714	226	0.9416	0.3962	0.9416	0.9704
No log	8.1429	228	0.8205	0.4502	0.8205	0.9058
No log	8.2143	230	0.6541	0.4759	0.6541	0.8088
No log	8.2857	232	0.6473	0.4321	0.6473	0.8046
No log	8.3571	234	0.6442	0.4383	0.6442	0.8026
No log	8.4286	236	0.7273	0.4362	0.7273	0.8528
No log	8.5	238	0.7053	0.4291	0.7053	0.8398
No log	8.5714	240	0.6295	0.4528	0.6295	0.7934
No log	8.6429	242	0.6259	0.4580	0.6259	0.7911
No log	8.7143	244	0.6422	0.4320	0.6422	0.8014
No log	8.7857	246	0.6746	0.4385	0.6746	0.8214
No log	8.8571	248	0.6468	0.4684	0.6468	0.8042
No log	8.9286	250	0.6153	0.4543	0.6153	0.7844
No log	9.0	252	0.6190	0.4302	0.6190	0.7868
No log	9.0714	254	0.6017	0.4420	0.6017	0.7757
No log	9.1429	256	0.5984	0.5389	0.5984	0.7735
No log	9.2143	258	0.6010	0.5006	0.6010	0.7753
No log	9.2857	260	0.5931	0.4930	0.5931	0.7701
No log	9.3571	262	0.6448	0.4639	0.6448	0.8030
No log	9.4286	264	0.7430	0.3591	0.7430	0.8620
No log	9.5	266	0.7766	0.3874	0.7766	0.8812
No log	9.5714	268	0.6360	0.4997	0.6360	0.7975
No log	9.6429	270	0.6511	0.4704	0.6511	0.8069
No log	9.7143	272	0.7006	0.4928	0.7006	0.8370
No log	9.7857	274	0.6191	0.4679	0.6191	0.7868
No log	9.8571	276	0.6693	0.4541	0.6693	0.8181
No log	9.9286	278	0.6787	0.4458	0.6787	0.8238
No log	10.0	280	0.6100	0.4760	0.6100	0.7810
No log	10.0714	282	0.7237	0.4172	0.7237	0.8507
No log	10.1429	284	0.7966	0.4238	0.7966	0.8925
No log	10.2143	286	0.6937	0.4281	0.6937	0.8329
No log	10.2857	288	0.6085	0.4281	0.6085	0.7801
No log	10.3571	290	0.6624	0.3738	0.6624	0.8139
No log	10.4286	292	0.7890	0.4517	0.7890	0.8882
No log	10.5	294	0.7908	0.4344	0.7908	0.8893
No log	10.5714	296	0.8306	0.4549	0.8306	0.9114
No log	10.6429	298	0.7796	0.4793	0.7796	0.8829
No log	10.7143	300	0.7129	0.4497	0.7129	0.8443
No log	10.7857	302	0.6798	0.4157	0.6798	0.8245
No log	10.8571	304	0.6794	0.4164	0.6794	0.8243
No log	10.9286	306	0.6764	0.4467	0.6764	0.8224
No log	11.0	308	0.6716	0.4616	0.6716	0.8195
No log	11.0714	310	0.7146	0.4936	0.7146	0.8453
No log	11.1429	312	0.7190	0.5112	0.7190	0.8480
No log	11.2143	314	0.7019	0.4962	0.7019	0.8378
No log	11.2857	316	0.6734	0.4823	0.6734	0.8206
No log	11.3571	318	0.6452	0.4571	0.6452	0.8033
No log	11.4286	320	0.6412	0.4711	0.6412	0.8008
No log	11.5	322	0.6858	0.5098	0.6858	0.8281
No log	11.5714	324	0.6815	0.4462	0.6815	0.8256
No log	11.6429	326	0.6291	0.4180	0.6291	0.7931
No log	11.7143	328	0.6219	0.4182	0.6219	0.7886
No log	11.7857	330	0.7184	0.4797	0.7184	0.8476
No log	11.8571	332	0.7973	0.4784	0.7973	0.8929
No log	11.9286	334	0.7037	0.4214	0.7037	0.8389
No log	12.0	336	0.6514	0.4916	0.6514	0.8071
No log	12.0714	338	0.6764	0.5529	0.6764	0.8224
No log	12.1429	340	0.6872	0.5211	0.6872	0.8290
No log	12.2143	342	0.6497	0.5229	0.6497	0.8060
No log	12.2857	344	0.6170	0.4443	0.6170	0.7855
No log	12.3571	346	0.6121	0.4506	0.6121	0.7824
No log	12.4286	348	0.6210	0.4520	0.6210	0.7880
No log	12.5	350	0.6268	0.4382	0.6268	0.7917
No log	12.5714	352	0.6604	0.4611	0.6604	0.8127
No log	12.6429	354	0.6719	0.4861	0.6719	0.8197
No log	12.7143	356	0.6599	0.4835	0.6599	0.8123
No log	12.7857	358	0.6873	0.4715	0.6873	0.8290
No log	12.8571	360	0.6646	0.4511	0.6646	0.8152
No log	12.9286	362	0.6131	0.4598	0.6131	0.7830
No log	13.0	364	0.6050	0.4688	0.6050	0.7778
No log	13.0714	366	0.6055	0.4818	0.6055	0.7781
No log	13.1429	368	0.6372	0.4563	0.6372	0.7983
No log	13.2143	370	0.6257	0.4550	0.6257	0.7910
No log	13.2857	372	0.6223	0.4284	0.6223	0.7888
No log	13.3571	374	0.6338	0.4543	0.6338	0.7961
No log	13.4286	376	0.6219	0.4325	0.6219	0.7886
No log	13.5	378	0.6301	0.4660	0.6301	0.7938
No log	13.5714	380	0.6402	0.4497	0.6402	0.8001
No log	13.6429	382	0.6897	0.4380	0.6897	0.8305
No log	13.7143	384	0.7978	0.4739	0.7978	0.8932
No log	13.7857	386	0.7358	0.4876	0.7358	0.8578
No log	13.8571	388	0.6945	0.4823	0.6945	0.8334
No log	13.9286	390	0.7143	0.4801	0.7143	0.8451
No log	14.0	392	0.6816	0.4818	0.6816	0.8256
No log	14.0714	394	0.6700	0.4628	0.6700	0.8185
No log	14.1429	396	0.6428	0.4474	0.6428	0.8018
No log	14.2143	398	0.6225	0.4537	0.6225	0.7890
No log	14.2857	400	0.6212	0.4467	0.6212	0.7881
No log	14.3571	402	0.6117	0.4818	0.6117	0.7821
No log	14.4286	404	0.6254	0.4554	0.6254	0.7908
No log	14.5	406	0.6707	0.4503	0.6707	0.8189
No log	14.5714	408	0.6510	0.4398	0.6510	0.8069
No log	14.6429	410	0.6302	0.5162	0.6302	0.7939
No log	14.7143	412	0.6342	0.5200	0.6342	0.7964
No log	14.7857	414	0.6489	0.5088	0.6489	0.8056
No log	14.8571	416	0.6506	0.5088	0.6506	0.8066
No log	14.9286	418	0.6616	0.4881	0.6616	0.8134
No log	15.0	420	0.6460	0.5051	0.6460	0.8038
No log	15.0714	422	0.6372	0.4940	0.6372	0.7982
No log	15.1429	424	0.6493	0.5017	0.6493	0.8058
No log	15.2143	426	0.6549	0.5036	0.6549	0.8093
No log	15.2857	428	0.6939	0.4817	0.6939	0.8330
No log	15.3571	430	0.8088	0.4136	0.8088	0.8994
No log	15.4286	432	0.7922	0.4279	0.7922	0.8901
No log	15.5	434	0.6687	0.4419	0.6687	0.8178
No log	15.5714	436	0.6410	0.4535	0.6410	0.8006
No log	15.6429	438	0.8183	0.4482	0.8183	0.9046
No log	15.7143	440	1.0072	0.3850	1.0072	1.0036
No log	15.7857	442	0.9522	0.4182	0.9522	0.9758
No log	15.8571	444	0.7315	0.4439	0.7315	0.8553
No log	15.9286	446	0.6559	0.5332	0.6559	0.8099
No log	16.0	448	0.6633	0.5030	0.6633	0.8144
No log	16.0714	450	0.6572	0.5210	0.6572	0.8107
No log	16.1429	452	0.7159	0.4879	0.7159	0.8461
No log	16.2143	454	0.7942	0.4310	0.7942	0.8912
No log	16.2857	456	0.7896	0.4455	0.7896	0.8886
No log	16.3571	458	0.6789	0.4173	0.6789	0.8240
No log	16.4286	460	0.6355	0.5059	0.6355	0.7972
No log	16.5	462	0.6427	0.4691	0.6427	0.8017
No log	16.5714	464	0.6406	0.4951	0.6406	0.8004
No log	16.6429	466	0.6846	0.4282	0.6846	0.8274
No log	16.7143	468	0.8297	0.4047	0.8297	0.9109
No log	16.7857	470	0.9675	0.3710	0.9675	0.9836
No log	16.8571	472	0.8866	0.3950	0.8866	0.9416
No log	16.9286	474	0.7567	0.3791	0.7567	0.8699
No log	17.0	476	0.7043	0.3758	0.7043	0.8392
No log	17.0714	478	0.6844	0.3969	0.6844	0.8273
No log	17.1429	480	0.7187	0.3833	0.7187	0.8478
No log	17.2143	482	0.7271	0.3833	0.7271	0.8527
No log	17.2857	484	0.7073	0.4043	0.7073	0.8410
No log	17.3571	486	0.6310	0.4343	0.6310	0.7944
No log	17.4286	488	0.6216	0.4188	0.6216	0.7884
No log	17.5	490	0.6196	0.4030	0.6196	0.7872
No log	17.5714	492	0.6287	0.4349	0.6287	0.7929
No log	17.6429	494	0.7145	0.4290	0.7145	0.8453
No log	17.7143	496	0.8001	0.3944	0.8001	0.8945
No log	17.7857	498	0.7747	0.4482	0.7747	0.8802
0.3271	17.8571	500	0.6940	0.4942	0.6940	0.8330
0.3271	17.9286	502	0.6764	0.5313	0.6764	0.8225
0.3271	18.0	504	0.6735	0.5225	0.6735	0.8207
0.3271	18.0714	506	0.6962	0.4997	0.6962	0.8344
0.3271	18.1429	508	0.7602	0.4576	0.7602	0.8719
0.3271	18.2143	510	0.7356	0.4564	0.7356	0.8576
0.3271	18.2857	512	0.6617	0.4489	0.6617	0.8135
0.3271	18.3571	514	0.6334	0.4544	0.6334	0.7959
0.3271	18.4286	516	0.6296	0.4601	0.6296	0.7935

Framework versions

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