ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_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: 0.7559
• Qwk: 0.4469
• Mse: 0.7559
• Rmse: 0.8694

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	4.1593	-0.0228	4.1593	2.0394
No log	0.1429	4	2.1598	0.0043	2.1598	1.4696
No log	0.2143	6	1.3269	0.0048	1.3269	1.1519
No log	0.2857	8	0.9564	0.0572	0.9564	0.9779
No log	0.3571	10	0.9769	-0.0210	0.9769	0.9884
No log	0.4286	12	1.2247	0.0262	1.2247	1.1067
No log	0.5	14	1.1861	0.0469	1.1861	1.0891
No log	0.5714	16	0.8378	0.2582	0.8378	0.9153
No log	0.6429	18	0.7382	0.2883	0.7382	0.8592
No log	0.7143	20	0.7602	0.2862	0.7602	0.8719
No log	0.7857	22	0.8478	0.2354	0.8478	0.9208
No log	0.8571	24	0.9453	0.2219	0.9453	0.9722
No log	0.9286	26	1.3071	0.0622	1.3071	1.1433
No log	1.0	28	1.3621	0.0573	1.3621	1.1671
No log	1.0714	30	1.3474	0.0697	1.3474	1.1608
No log	1.1429	32	1.0976	0.0888	1.0976	1.0477
No log	1.2143	34	1.0354	0.0848	1.0354	1.0175
No log	1.2857	36	0.8457	0.2624	0.8457	0.9196
No log	1.3571	38	0.8137	0.2879	0.8137	0.9021
No log	1.4286	40	0.9247	0.2267	0.9247	0.9616
No log	1.5	42	1.0332	0.1818	1.0332	1.0165
No log	1.5714	44	1.2912	0.1781	1.2912	1.1363
No log	1.6429	46	1.3734	0.1326	1.3734	1.1719
No log	1.7143	48	1.3638	0.0769	1.3638	1.1678
No log	1.7857	50	1.1421	0.0887	1.1421	1.0687
No log	1.8571	52	0.8793	0.2368	0.8793	0.9377
No log	1.9286	54	0.6616	0.3230	0.6616	0.8134
No log	2.0	56	0.6470	0.3613	0.6470	0.8043
No log	2.0714	58	0.6884	0.3883	0.6884	0.8297
No log	2.1429	60	0.7424	0.3683	0.7424	0.8616
No log	2.2143	62	0.9312	0.2472	0.9312	0.9650
No log	2.2857	64	1.2590	0.2372	1.2590	1.1220
No log	2.3571	66	1.3449	0.1646	1.3449	1.1597
No log	2.4286	68	1.0633	0.1850	1.0633	1.0311
No log	2.5	70	0.8954	0.2653	0.8954	0.9463
No log	2.5714	72	1.0334	0.2049	1.0334	1.0166
No log	2.6429	74	0.9250	0.2010	0.9250	0.9617
No log	2.7143	76	0.6773	0.3951	0.6773	0.8230
No log	2.7857	78	0.6300	0.4692	0.6300	0.7937
No log	2.8571	80	0.6010	0.4902	0.6010	0.7752
No log	2.9286	82	0.6287	0.4980	0.6287	0.7929
No log	3.0	84	0.5682	0.5591	0.5682	0.7538
No log	3.0714	86	0.5863	0.5491	0.5863	0.7657
No log	3.1429	88	0.5998	0.5381	0.5998	0.7745
No log	3.2143	90	0.6655	0.4857	0.6655	0.8158
No log	3.2857	92	0.6123	0.5396	0.6123	0.7825
No log	3.3571	94	0.5311	0.5011	0.5311	0.7288
No log	3.4286	96	0.5472	0.5372	0.5472	0.7397
No log	3.5	98	0.5464	0.5114	0.5464	0.7392
No log	3.5714	100	0.6435	0.5804	0.6435	0.8022
No log	3.6429	102	0.7764	0.5025	0.7764	0.8811
No log	3.7143	104	0.6779	0.5846	0.6779	0.8234
No log	3.7857	106	0.7053	0.5656	0.7053	0.8398
No log	3.8571	108	0.8183	0.4916	0.8183	0.9046
No log	3.9286	110	0.7384	0.5085	0.7384	0.8593
No log	4.0	112	0.7708	0.5115	0.7708	0.8779
No log	4.0714	114	0.9794	0.4040	0.9794	0.9896
No log	4.1429	116	1.2303	0.3288	1.2303	1.1092
No log	4.2143	118	0.8766	0.4014	0.8766	0.9363
No log	4.2857	120	0.6909	0.4891	0.6909	0.8312
No log	4.3571	122	0.5858	0.5515	0.5858	0.7654
No log	4.4286	124	0.6197	0.4932	0.6197	0.7872
No log	4.5	126	0.8154	0.4649	0.8154	0.9030
No log	4.5714	128	0.7935	0.5097	0.7935	0.8908
No log	4.6429	130	0.6746	0.5483	0.6746	0.8213
No log	4.7143	132	0.7185	0.5552	0.7185	0.8476
No log	4.7857	134	0.7687	0.5151	0.7687	0.8768
No log	4.8571	136	0.6742	0.5303	0.6742	0.8211
No log	4.9286	138	0.6277	0.5009	0.6277	0.7923
No log	5.0	140	0.6511	0.4898	0.6512	0.8069
No log	5.0714	142	0.6840	0.4734	0.6840	0.8270
No log	5.1429	144	0.6321	0.4525	0.6321	0.7950
No log	5.2143	146	0.6461	0.5123	0.6461	0.8038
No log	5.2857	148	0.6773	0.5004	0.6773	0.8230
No log	5.3571	150	0.8295	0.4600	0.8295	0.9108
No log	5.4286	152	0.9573	0.4506	0.9573	0.9784
No log	5.5	154	0.7958	0.4887	0.7958	0.8921
No log	5.5714	156	0.6858	0.5622	0.6858	0.8281
No log	5.6429	158	0.6716	0.5083	0.6716	0.8195
No log	5.7143	160	0.7871	0.4725	0.7871	0.8872
No log	5.7857	162	0.7952	0.4831	0.7952	0.8917
No log	5.8571	164	0.6591	0.5152	0.6591	0.8118
No log	5.9286	166	0.6177	0.5531	0.6177	0.7859
No log	6.0	168	0.6514	0.4940	0.6514	0.8071
No log	6.0714	170	0.9421	0.3754	0.9421	0.9706
No log	6.1429	172	1.1738	0.2841	1.1738	1.0834
No log	6.2143	174	1.0141	0.3187	1.0141	1.0070
No log	6.2857	176	0.6629	0.5560	0.6629	0.8142
No log	6.3571	178	0.5937	0.5414	0.5937	0.7706
No log	6.4286	180	0.6127	0.5379	0.6127	0.7827
No log	6.5	182	0.7320	0.4691	0.7320	0.8555
No log	6.5714	184	0.7497	0.4893	0.7497	0.8658
No log	6.6429	186	0.7482	0.5500	0.7482	0.8650
No log	6.7143	188	0.6558	0.5347	0.6558	0.8098
No log	6.7857	190	0.6395	0.4986	0.6395	0.7997
No log	6.8571	192	0.6639	0.4686	0.6639	0.8148
No log	6.9286	194	0.7456	0.5474	0.7456	0.8635
No log	7.0	196	0.8644	0.4289	0.8644	0.9297
No log	7.0714	198	0.7391	0.5568	0.7391	0.8597
No log	7.1429	200	0.6460	0.5153	0.6460	0.8037
No log	7.2143	202	0.6627	0.4896	0.6627	0.8141
No log	7.2857	204	0.6451	0.4945	0.6451	0.8032
No log	7.3571	206	0.6771	0.4857	0.6771	0.8229
No log	7.4286	208	0.7933	0.4474	0.7933	0.8907
No log	7.5	210	0.7990	0.4367	0.7990	0.8938
No log	7.5714	212	0.6717	0.5038	0.6717	0.8196
No log	7.6429	214	0.6229	0.4373	0.6229	0.7893
No log	7.7143	216	0.6649	0.4415	0.6649	0.8154
No log	7.7857	218	0.6493	0.4689	0.6493	0.8058
No log	7.8571	220	0.7624	0.4274	0.7624	0.8732
No log	7.9286	222	1.0327	0.3565	1.0327	1.0162
No log	8.0	224	1.2454	0.2731	1.2454	1.1160
No log	8.0714	226	1.1975	0.2714	1.1975	1.0943
No log	8.1429	228	0.9038	0.3750	0.9038	0.9507
No log	8.2143	230	0.7154	0.4549	0.7154	0.8458
No log	8.2857	232	0.6691	0.4236	0.6691	0.8180
No log	8.3571	234	0.6419	0.4217	0.6419	0.8012
No log	8.4286	236	0.6417	0.4395	0.6417	0.8011
No log	8.5	238	0.6648	0.4704	0.6648	0.8154
No log	8.5714	240	0.6488	0.4613	0.6488	0.8055
No log	8.6429	242	0.6583	0.4337	0.6583	0.8113
No log	8.7143	244	0.6694	0.4168	0.6694	0.8182
No log	8.7857	246	0.6807	0.4754	0.6807	0.8251
No log	8.8571	248	0.6966	0.4969	0.6966	0.8346
No log	8.9286	250	0.7216	0.4694	0.7216	0.8494
No log	9.0	252	0.7315	0.5096	0.7315	0.8553
No log	9.0714	254	0.6740	0.4715	0.6740	0.8210
No log	9.1429	256	0.6537	0.5005	0.6537	0.8085
No log	9.2143	258	0.6398	0.5018	0.6398	0.7999
No log	9.2857	260	0.6505	0.4948	0.6505	0.8066
No log	9.3571	262	0.7071	0.5194	0.7071	0.8409
No log	9.4286	264	0.6983	0.4930	0.6983	0.8356
No log	9.5	266	0.6684	0.4878	0.6684	0.8176
No log	9.5714	268	0.7331	0.4646	0.7331	0.8562
No log	9.6429	270	0.7766	0.4687	0.7766	0.8813
No log	9.7143	272	0.6957	0.4870	0.6957	0.8341
No log	9.7857	274	0.6554	0.4549	0.6554	0.8096
No log	9.8571	276	0.6555	0.4790	0.6555	0.8096
No log	9.9286	278	0.6396	0.4572	0.6396	0.7997
No log	10.0	280	0.6351	0.4367	0.6351	0.7969
No log	10.0714	282	0.6492	0.4676	0.6492	0.8057
No log	10.1429	284	0.6745	0.4844	0.6745	0.8213
No log	10.2143	286	0.7145	0.5232	0.7145	0.8453
No log	10.2857	288	0.8973	0.4677	0.8973	0.9473
No log	10.3571	290	1.0052	0.3941	1.0052	1.0026
No log	10.4286	292	0.8630	0.4614	0.8630	0.9290
No log	10.5	294	0.6842	0.5238	0.6842	0.8272
No log	10.5714	296	0.6658	0.4670	0.6658	0.8160
No log	10.6429	298	0.6920	0.4730	0.6920	0.8319
No log	10.7143	300	0.6280	0.4354	0.6280	0.7924
No log	10.7857	302	0.6002	0.5265	0.6002	0.7747
No log	10.8571	304	0.6108	0.5580	0.6108	0.7815
No log	10.9286	306	0.6127	0.5396	0.6127	0.7828
No log	11.0	308	0.6292	0.4557	0.6292	0.7932
No log	11.0714	310	0.7055	0.4839	0.7055	0.8399
No log	11.1429	312	0.6865	0.4845	0.6865	0.8285
No log	11.2143	314	0.6383	0.4830	0.6383	0.7989
No log	11.2857	316	0.6368	0.4909	0.6368	0.7980
No log	11.3571	318	0.6390	0.4909	0.6390	0.7994
No log	11.4286	320	0.6535	0.4812	0.6535	0.8084
No log	11.5	322	0.6265	0.4383	0.6265	0.7915
No log	11.5714	324	0.6078	0.4865	0.6078	0.7796
No log	11.6429	326	0.6256	0.5504	0.6256	0.7910
No log	11.7143	328	0.6251	0.5527	0.6251	0.7907
No log	11.7857	330	0.6388	0.5489	0.6388	0.7992
No log	11.8571	332	0.6750	0.5369	0.6750	0.8216
No log	11.9286	334	0.7540	0.4936	0.7540	0.8683
No log	12.0	336	0.7801	0.4611	0.7801	0.8832
No log	12.0714	338	0.7023	0.4713	0.7023	0.8380
No log	12.1429	340	0.6443	0.5063	0.6443	0.8027
No log	12.2143	342	0.6551	0.5005	0.6551	0.8094
No log	12.2857	344	0.6362	0.4954	0.6362	0.7976
No log	12.3571	346	0.6266	0.4940	0.6266	0.7916
No log	12.4286	348	0.6250	0.4739	0.6250	0.7906
No log	12.5	350	0.6449	0.5156	0.6449	0.8031
No log	12.5714	352	0.6755	0.5082	0.6755	0.8219
No log	12.6429	354	0.6559	0.4834	0.6559	0.8099
No log	12.7143	356	0.6827	0.5066	0.6827	0.8263
No log	12.7857	358	0.7062	0.5111	0.7062	0.8403
No log	12.8571	360	0.6883	0.4878	0.6883	0.8297
No log	12.9286	362	0.6740	0.4767	0.6740	0.8210
No log	13.0	364	0.6703	0.4673	0.6703	0.8187
No log	13.0714	366	0.6685	0.4792	0.6685	0.8176
No log	13.1429	368	0.6605	0.4491	0.6605	0.8127
No log	13.2143	370	0.6652	0.4677	0.6652	0.8156
No log	13.2857	372	0.6813	0.4775	0.6813	0.8254
No log	13.3571	374	0.6669	0.4802	0.6669	0.8166
No log	13.4286	376	0.6588	0.4869	0.6588	0.8117
No log	13.5	378	0.6295	0.5352	0.6295	0.7934
No log	13.5714	380	0.6847	0.4672	0.6847	0.8275
No log	13.6429	382	0.7197	0.4500	0.7197	0.8483
No log	13.7143	384	0.6628	0.4926	0.6628	0.8142
No log	13.7857	386	0.6650	0.5646	0.6650	0.8155
No log	13.8571	388	0.7618	0.4767	0.7618	0.8728
No log	13.9286	390	0.7741	0.4922	0.7741	0.8798
No log	14.0	392	0.7838	0.4997	0.7838	0.8853
No log	14.0714	394	0.8116	0.4753	0.8116	0.9009
No log	14.1429	396	0.7701	0.4934	0.7701	0.8775
No log	14.2143	398	0.7419	0.5059	0.7419	0.8613
No log	14.2857	400	0.6618	0.5538	0.6618	0.8135
No log	14.3571	402	0.6218	0.5403	0.6218	0.7885
No log	14.4286	404	0.6434	0.5538	0.6434	0.8021
No log	14.5	406	0.6150	0.5729	0.6150	0.7842
No log	14.5714	408	0.5943	0.5132	0.5943	0.7709
No log	14.6429	410	0.6112	0.5646	0.6112	0.7818
No log	14.7143	412	0.6099	0.5312	0.6099	0.7810
No log	14.7857	414	0.6323	0.5555	0.6323	0.7952
No log	14.8571	416	0.6967	0.5251	0.6967	0.8347
No log	14.9286	418	0.7958	0.5023	0.7958	0.8921
No log	15.0	420	0.7822	0.4981	0.7822	0.8844
No log	15.0714	422	0.7544	0.5158	0.7544	0.8686
No log	15.1429	424	0.6841	0.5261	0.6841	0.8271
No log	15.2143	426	0.6847	0.5469	0.6847	0.8275
No log	15.2857	428	0.7058	0.5182	0.7058	0.8401
No log	15.3571	430	0.6550	0.4960	0.6550	0.8093
No log	15.4286	432	0.6205	0.5365	0.6205	0.7877
No log	15.5	434	0.6053	0.5118	0.6053	0.7780
No log	15.5714	436	0.6128	0.5396	0.6128	0.7828
No log	15.6429	438	0.6272	0.4991	0.6272	0.7919
No log	15.7143	440	0.6217	0.5641	0.6217	0.7885
No log	15.7857	442	0.6288	0.4868	0.6288	0.7929
No log	15.8571	444	0.6378	0.5006	0.6378	0.7986
No log	15.9286	446	0.6218	0.5161	0.6218	0.7885
No log	16.0	448	0.6248	0.5069	0.6248	0.7904
No log	16.0714	450	0.6389	0.5024	0.6389	0.7993
No log	16.1429	452	0.6511	0.5024	0.6511	0.8069
No log	16.2143	454	0.6510	0.5024	0.6510	0.8069
No log	16.2857	456	0.6527	0.4820	0.6527	0.8079
No log	16.3571	458	0.6811	0.5542	0.6811	0.8253
No log	16.4286	460	0.6544	0.5625	0.6544	0.8090
No log	16.5	462	0.6228	0.4984	0.6228	0.7892
No log	16.5714	464	0.6455	0.5242	0.6455	0.8034
No log	16.6429	466	0.6620	0.5408	0.6620	0.8136
No log	16.7143	468	0.6792	0.5239	0.6792	0.8242
No log	16.7857	470	0.6858	0.5333	0.6858	0.8281
No log	16.8571	472	0.7191	0.5327	0.7191	0.8480
No log	16.9286	474	0.6999	0.5305	0.6999	0.8366
No log	17.0	476	0.6634	0.5378	0.6634	0.8145
No log	17.0714	478	0.6407	0.5254	0.6407	0.8004
No log	17.1429	480	0.6331	0.5088	0.6331	0.7957
No log	17.2143	482	0.6203	0.5473	0.6203	0.7876
No log	17.2857	484	0.6176	0.5178	0.6176	0.7859
No log	17.3571	486	0.6442	0.5354	0.6442	0.8026
No log	17.4286	488	0.6433	0.5245	0.6433	0.8020
No log	17.5	490	0.6366	0.5357	0.6366	0.7979
No log	17.5714	492	0.6372	0.5288	0.6372	0.7982
No log	17.6429	494	0.6348	0.5408	0.6348	0.7968
No log	17.7143	496	0.6461	0.5358	0.6461	0.8038
No log	17.7857	498	0.6529	0.5176	0.6529	0.8080
0.3235	17.8571	500	0.6651	0.5097	0.6651	0.8155
0.3235	17.9286	502	0.6966	0.5119	0.6966	0.8346
0.3235	18.0	504	0.7478	0.5071	0.7478	0.8647
0.3235	18.0714	506	0.7675	0.5129	0.7675	0.8761
0.3235	18.1429	508	0.6929	0.4991	0.6929	0.8324
0.3235	18.2143	510	0.6470	0.5618	0.6470	0.8044
0.3235	18.2857	512	0.6581	0.5228	0.6581	0.8113
0.3235	18.3571	514	0.6532	0.5386	0.6532	0.8082
0.3235	18.4286	516	0.6507	0.5293	0.6507	0.8067
0.3235	18.5	518	0.6412	0.5172	0.6412	0.8008
0.3235	18.5714	520	0.6679	0.5454	0.6679	0.8172
0.3235	18.6429	522	0.6832	0.5132	0.6832	0.8266
0.3235	18.7143	524	0.6752	0.5476	0.6752	0.8217
0.3235	18.7857	526	0.6675	0.5111	0.6675	0.8170
0.3235	18.8571	528	0.6613	0.5135	0.6613	0.8132
0.3235	18.9286	530	0.6710	0.5106	0.6710	0.8191
0.3235	19.0	532	0.7103	0.5343	0.7103	0.8428
0.3235	19.0714	534	0.7103	0.5217	0.7103	0.8428
0.3235	19.1429	536	0.6637	0.5614	0.6637	0.8147
0.3235	19.2143	538	0.6281	0.5048	0.6281	0.7925
0.3235	19.2857	540	0.6242	0.5069	0.6242	0.7901
0.3235	19.3571	542	0.6401	0.5155	0.6401	0.8001
0.3235	19.4286	544	0.6865	0.5373	0.6865	0.8286
0.3235	19.5	546	0.7035	0.5199	0.7035	0.8388
0.3235	19.5714	548	0.6893	0.5117	0.6893	0.8302
0.3235	19.6429	550	0.6841	0.5203	0.6841	0.8271
0.3235	19.7143	552	0.6912	0.5203	0.6912	0.8314
0.3235	19.7857	554	0.7249	0.5197	0.7249	0.8514
0.3235	19.8571	556	0.7686	0.4605	0.7686	0.8767
0.3235	19.9286	558	0.7789	0.4690	0.7789	0.8825
0.3235	20.0	560	0.7347	0.4516	0.7347	0.8572
0.3235	20.0714	562	0.7703	0.4489	0.7703	0.8777
0.3235	20.1429	564	0.7559	0.4469	0.7559	0.8694

Framework versions

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