ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_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: 0.6511
• Qwk: 0.6282
• Mse: 0.6511
• Rmse: 0.8069

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	3.9762	-0.0215	3.9762	1.9940
No log	0.8	4	2.2024	0.0364	2.2024	1.4841
No log	1.2	6	1.4057	-0.0032	1.4057	1.1856
No log	1.6	8	1.0561	0.2492	1.0561	1.0277
No log	2.0	10	1.0800	0.1954	1.0800	1.0392
No log	2.4	12	1.2103	0.1740	1.2103	1.1001
No log	2.8	14	1.1838	0.1549	1.1838	1.0880
No log	3.2	16	1.1883	0.0581	1.1883	1.0901
No log	3.6	18	1.1096	0.0970	1.1096	1.0534
No log	4.0	20	0.9699	0.2217	0.9699	0.9848
No log	4.4	22	0.8842	0.2991	0.8842	0.9403
No log	4.8	24	0.8356	0.3548	0.8356	0.9141
No log	5.2	26	0.8785	0.3665	0.8785	0.9373
No log	5.6	28	0.8865	0.4224	0.8865	0.9415
No log	6.0	30	1.1173	0.4167	1.1173	1.0570
No log	6.4	32	1.2503	0.4228	1.2503	1.1182
No log	6.8	34	0.8260	0.5362	0.8260	0.9088
No log	7.2	36	0.7337	0.6263	0.7337	0.8565
No log	7.6	38	0.7135	0.6435	0.7135	0.8447
No log	8.0	40	0.7085	0.6044	0.7085	0.8417
No log	8.4	42	0.7487	0.6062	0.7487	0.8653
No log	8.8	44	0.6951	0.5969	0.6951	0.8337
No log	9.2	46	0.6975	0.6167	0.6975	0.8351
No log	9.6	48	0.8367	0.5141	0.8367	0.9147
No log	10.0	50	0.9321	0.4609	0.9321	0.9654
No log	10.4	52	0.7445	0.5438	0.7445	0.8628
No log	10.8	54	0.8091	0.5304	0.8091	0.8995
No log	11.2	56	1.0223	0.5150	1.0223	1.0111
No log	11.6	58	0.8966	0.5705	0.8966	0.9469
No log	12.0	60	0.7220	0.6095	0.7220	0.8497
No log	12.4	62	0.9668	0.4777	0.9668	0.9833
No log	12.8	64	0.9772	0.4976	0.9772	0.9885
No log	13.2	66	0.7478	0.5418	0.7478	0.8648
No log	13.6	68	0.7346	0.5787	0.7346	0.8571
No log	14.0	70	0.8888	0.5697	0.8888	0.9427
No log	14.4	72	0.8498	0.6057	0.8498	0.9219
No log	14.8	74	0.6658	0.6365	0.6658	0.8159
No log	15.2	76	0.6726	0.5513	0.6726	0.8201
No log	15.6	78	0.6504	0.5909	0.6504	0.8065
No log	16.0	80	0.6412	0.6001	0.6412	0.8007
No log	16.4	82	0.6583	0.5487	0.6583	0.8114
No log	16.8	84	0.6990	0.5093	0.6990	0.8361
No log	17.2	86	0.6921	0.5548	0.6921	0.8320
No log	17.6	88	0.6598	0.5735	0.6598	0.8123
No log	18.0	90	0.6587	0.6094	0.6587	0.8116
No log	18.4	92	0.6448	0.5923	0.6448	0.8030
No log	18.8	94	0.7203	0.5665	0.7203	0.8487
No log	19.2	96	0.8682	0.4957	0.8682	0.9318
No log	19.6	98	0.7489	0.5560	0.7489	0.8654
No log	20.0	100	0.6650	0.5865	0.6650	0.8154
No log	20.4	102	0.6413	0.5923	0.6413	0.8008
No log	20.8	104	0.6670	0.5856	0.6670	0.8167
No log	21.2	106	0.7162	0.5219	0.7162	0.8463
No log	21.6	108	0.7238	0.4984	0.7238	0.8508
No log	22.0	110	0.6787	0.5505	0.6787	0.8239
No log	22.4	112	0.7410	0.6047	0.7410	0.8608
No log	22.8	114	0.7715	0.5989	0.7715	0.8783
No log	23.2	116	0.7061	0.5842	0.7061	0.8403
No log	23.6	118	0.7142	0.5300	0.7142	0.8451
No log	24.0	120	0.7270	0.4736	0.7270	0.8527
No log	24.4	122	0.6905	0.5747	0.6905	0.8310
No log	24.8	124	0.6932	0.5809	0.6932	0.8326
No log	25.2	126	0.6898	0.5809	0.6898	0.8305
No log	25.6	128	0.6799	0.5713	0.6799	0.8246
No log	26.0	130	0.6886	0.6049	0.6886	0.8298
No log	26.4	132	0.6991	0.6060	0.6991	0.8361
No log	26.8	134	0.6791	0.5796	0.6791	0.8241
No log	27.2	136	0.6829	0.5975	0.6829	0.8264
No log	27.6	138	0.6917	0.5774	0.6917	0.8317
No log	28.0	140	0.6872	0.5898	0.6872	0.8290
No log	28.4	142	0.7203	0.5080	0.7203	0.8487
No log	28.8	144	0.7219	0.4947	0.7219	0.8497
No log	29.2	146	0.7094	0.6096	0.7094	0.8423
No log	29.6	148	0.7171	0.5734	0.7171	0.8468
No log	30.0	150	0.7056	0.5622	0.7056	0.8400
No log	30.4	152	0.7090	0.5517	0.7090	0.8420
No log	30.8	154	0.7024	0.5714	0.7024	0.8381
No log	31.2	156	0.7289	0.6144	0.7289	0.8537
No log	31.6	158	0.7446	0.5826	0.7446	0.8629
No log	32.0	160	0.7022	0.6246	0.7022	0.8380
No log	32.4	162	0.6788	0.6237	0.6788	0.8239
No log	32.8	164	0.6709	0.6177	0.6709	0.8191
No log	33.2	166	0.6971	0.6337	0.6971	0.8349
No log	33.6	168	0.7086	0.5959	0.7086	0.8418
No log	34.0	170	0.6878	0.5844	0.6878	0.8293
No log	34.4	172	0.6568	0.5932	0.6568	0.8104
No log	34.8	174	0.6410	0.6054	0.6410	0.8006
No log	35.2	176	0.6491	0.5315	0.6491	0.8057
No log	35.6	178	0.6484	0.6065	0.6484	0.8052
No log	36.0	180	0.6809	0.5986	0.6809	0.8252
No log	36.4	182	0.7011	0.5959	0.7011	0.8373
No log	36.8	184	0.6779	0.6187	0.6779	0.8233
No log	37.2	186	0.6562	0.6011	0.6562	0.8101
No log	37.6	188	0.6623	0.6278	0.6623	0.8138
No log	38.0	190	0.6644	0.6278	0.6644	0.8151
No log	38.4	192	0.6595	0.5939	0.6595	0.8121
No log	38.8	194	0.6593	0.5955	0.6593	0.8120
No log	39.2	196	0.6572	0.5735	0.6572	0.8107
No log	39.6	198	0.6429	0.6427	0.6429	0.8018
No log	40.0	200	0.6329	0.6470	0.6329	0.7956
No log	40.4	202	0.6357	0.6610	0.6357	0.7973
No log	40.8	204	0.6229	0.6237	0.6229	0.7892
No log	41.2	206	0.6525	0.6125	0.6525	0.8078
No log	41.6	208	0.6579	0.6278	0.6579	0.8111
No log	42.0	210	0.6346	0.6049	0.6346	0.7966
No log	42.4	212	0.6258	0.6097	0.6258	0.7911
No log	42.8	214	0.6264	0.6296	0.6264	0.7914
No log	43.2	216	0.6668	0.6315	0.6668	0.8166
No log	43.6	218	0.7135	0.6319	0.7135	0.8447
No log	44.0	220	0.6943	0.6567	0.6943	0.8332
No log	44.4	222	0.6326	0.6488	0.6326	0.7954
No log	44.8	224	0.6283	0.6049	0.6283	0.7926
No log	45.2	226	0.6348	0.6049	0.6348	0.7967
No log	45.6	228	0.6342	0.6658	0.6342	0.7964
No log	46.0	230	0.6525	0.6634	0.6525	0.8078
No log	46.4	232	0.6503	0.6634	0.6503	0.8064
No log	46.8	234	0.6429	0.6154	0.6429	0.8018
No log	47.2	236	0.6446	0.6049	0.6446	0.8028
No log	47.6	238	0.6463	0.6658	0.6463	0.8039
No log	48.0	240	0.6556	0.5954	0.6556	0.8097
No log	48.4	242	0.6574	0.6055	0.6574	0.8108
No log	48.8	244	0.6462	0.5980	0.6462	0.8039
No log	49.2	246	0.6392	0.6547	0.6392	0.7995
No log	49.6	248	0.6408	0.6118	0.6408	0.8005
No log	50.0	250	0.6440	0.5902	0.6440	0.8025
No log	50.4	252	0.6757	0.5944	0.6757	0.8220
No log	50.8	254	0.7011	0.6064	0.7011	0.8373
No log	51.2	256	0.6975	0.6296	0.6975	0.8352
No log	51.6	258	0.6626	0.5866	0.6626	0.8140
No log	52.0	260	0.6481	0.6118	0.6481	0.8051
No log	52.4	262	0.6529	0.5771	0.6529	0.8080
No log	52.8	264	0.6501	0.6087	0.6501	0.8063
No log	53.2	266	0.6486	0.6164	0.6486	0.8053
No log	53.6	268	0.6595	0.6066	0.6595	0.8121
No log	54.0	270	0.6594	0.5877	0.6594	0.8120
No log	54.4	272	0.6472	0.6154	0.6472	0.8045
No log	54.8	274	0.6413	0.6307	0.6413	0.8008
No log	55.2	276	0.6400	0.6307	0.6400	0.8000
No log	55.6	278	0.6423	0.6307	0.6423	0.8015
No log	56.0	280	0.6438	0.6307	0.6438	0.8024
No log	56.4	282	0.6442	0.6307	0.6442	0.8026
No log	56.8	284	0.6459	0.6307	0.6459	0.8037
No log	57.2	286	0.6474	0.6307	0.6474	0.8046
No log	57.6	288	0.6591	0.6054	0.6591	0.8118
No log	58.0	290	0.6571	0.5943	0.6571	0.8106
No log	58.4	292	0.6480	0.6307	0.6480	0.8050
No log	58.8	294	0.6564	0.5771	0.6564	0.8102
No log	59.2	296	0.6680	0.5650	0.6680	0.8173
No log	59.6	298	0.6583	0.5650	0.6583	0.8114
No log	60.0	300	0.6412	0.6307	0.6412	0.8008
No log	60.4	302	0.6565	0.6301	0.6565	0.8102
No log	60.8	304	0.7007	0.6218	0.7007	0.8371
No log	61.2	306	0.7337	0.6218	0.7337	0.8566
No log	61.6	308	0.7267	0.6218	0.7267	0.8525
No log	62.0	310	0.6945	0.6063	0.6945	0.8334
No log	62.4	312	0.6680	0.5866	0.6680	0.8173
No log	62.8	314	0.6570	0.5980	0.6570	0.8106
No log	63.2	316	0.6535	0.6007	0.6535	0.8084
No log	63.6	318	0.6558	0.5980	0.6558	0.8098
No log	64.0	320	0.6680	0.6138	0.6680	0.8173
No log	64.4	322	0.6808	0.6028	0.6808	0.8251
No log	64.8	324	0.6747	0.5954	0.6747	0.8214
No log	65.2	326	0.6593	0.6177	0.6593	0.8120
No log	65.6	328	0.6524	0.6076	0.6524	0.8077
No log	66.0	330	0.6529	0.6144	0.6529	0.8080
No log	66.4	332	0.6547	0.6330	0.6547	0.8091
No log	66.8	334	0.6565	0.6330	0.6565	0.8103
No log	67.2	336	0.6610	0.6157	0.6610	0.8130
No log	67.6	338	0.6701	0.6048	0.6701	0.8186
No log	68.0	340	0.6827	0.6365	0.6827	0.8262
No log	68.4	342	0.6852	0.6365	0.6852	0.8278
No log	68.8	344	0.6751	0.6032	0.6751	0.8217
No log	69.2	346	0.6710	0.6058	0.6710	0.8192
No log	69.6	348	0.6770	0.6535	0.6770	0.8228
No log	70.0	350	0.6981	0.6225	0.6981	0.8355
No log	70.4	352	0.7189	0.5618	0.7189	0.8479
No log	70.8	354	0.7100	0.6025	0.7100	0.8426
No log	71.2	356	0.6840	0.6225	0.6840	0.8271
No log	71.6	358	0.6582	0.6374	0.6582	0.8113
No log	72.0	360	0.6521	0.6144	0.6521	0.8075
No log	72.4	362	0.6596	0.6129	0.6596	0.8122
No log	72.8	364	0.6682	0.6493	0.6682	0.8174
No log	73.2	366	0.6669	0.6356	0.6669	0.8166
No log	73.6	368	0.6559	0.6307	0.6559	0.8099
No log	74.0	370	0.6515	0.6175	0.6515	0.8071
No log	74.4	372	0.6565	0.5988	0.6565	0.8103
No log	74.8	374	0.6631	0.5988	0.6631	0.8143
No log	75.2	376	0.6614	0.5988	0.6614	0.8133
No log	75.6	378	0.6535	0.6409	0.6535	0.8084
No log	76.0	380	0.6515	0.6517	0.6515	0.8072
No log	76.4	382	0.6522	0.6374	0.6522	0.8076
No log	76.8	384	0.6524	0.6374	0.6524	0.8077
No log	77.2	386	0.6519	0.6374	0.6519	0.8074
No log	77.6	388	0.6536	0.6049	0.6536	0.8085
No log	78.0	390	0.6582	0.6078	0.6582	0.8113
No log	78.4	392	0.6716	0.5542	0.6716	0.8195
No log	78.8	394	0.6792	0.5542	0.6792	0.8241
No log	79.2	396	0.6718	0.5542	0.6718	0.8196
No log	79.6	398	0.6575	0.6049	0.6575	0.8109
No log	80.0	400	0.6496	0.6049	0.6496	0.8060
No log	80.4	402	0.6475	0.6049	0.6475	0.8047
No log	80.8	404	0.6463	0.6049	0.6463	0.8040
No log	81.2	406	0.6463	0.6049	0.6463	0.8040
No log	81.6	408	0.6457	0.6049	0.6457	0.8035
No log	82.0	410	0.6468	0.6097	0.6468	0.8042
No log	82.4	412	0.6498	0.6097	0.6498	0.8061
No log	82.8	414	0.6494	0.6097	0.6494	0.8059
No log	83.2	416	0.6464	0.6437	0.6464	0.8040
No log	83.6	418	0.6459	0.6437	0.6459	0.8037
No log	84.0	420	0.6448	0.6409	0.6448	0.8030
No log	84.4	422	0.6455	0.6409	0.6455	0.8034
No log	84.8	424	0.6459	0.6517	0.6459	0.8037
No log	85.2	426	0.6471	0.6479	0.6471	0.8044
No log	85.6	428	0.6489	0.6584	0.6489	0.8055
No log	86.0	430	0.6507	0.6584	0.6507	0.8067
No log	86.4	432	0.6500	0.6584	0.6500	0.8063
No log	86.8	434	0.6486	0.6479	0.6486	0.8053
No log	87.2	436	0.6478	0.6479	0.6478	0.8049
No log	87.6	438	0.6491	0.6409	0.6491	0.8057
No log	88.0	440	0.6509	0.6409	0.6509	0.8068
No log	88.4	442	0.6507	0.6409	0.6507	0.8066
No log	88.8	444	0.6492	0.6517	0.6492	0.8057
No log	89.2	446	0.6483	0.6517	0.6483	0.8052
No log	89.6	448	0.6493	0.6584	0.6493	0.8058
No log	90.0	450	0.6511	0.6433	0.6511	0.8069
No log	90.4	452	0.6519	0.6433	0.6519	0.8074
No log	90.8	454	0.6532	0.6433	0.6532	0.8082
No log	91.2	456	0.6531	0.6433	0.6531	0.8081
No log	91.6	458	0.6522	0.6433	0.6522	0.8076
No log	92.0	460	0.6507	0.6282	0.6507	0.8066
No log	92.4	462	0.6500	0.6282	0.6500	0.8062
No log	92.8	464	0.6503	0.6282	0.6503	0.8064
No log	93.2	466	0.6505	0.6282	0.6505	0.8065
No log	93.6	468	0.6507	0.6282	0.6507	0.8067
No log	94.0	470	0.6508	0.6282	0.6508	0.8067
No log	94.4	472	0.6508	0.6175	0.6508	0.8067
No log	94.8	474	0.6508	0.6175	0.6508	0.8067
No log	95.2	476	0.6507	0.6175	0.6507	0.8066
No log	95.6	478	0.6503	0.6517	0.6503	0.8064
No log	96.0	480	0.6501	0.6517	0.6501	0.8063
No log	96.4	482	0.6500	0.6175	0.6500	0.8062
No log	96.8	484	0.6501	0.6175	0.6501	0.8063
No log	97.2	486	0.6503	0.6175	0.6503	0.8064
No log	97.6	488	0.6506	0.6282	0.6506	0.8066
No log	98.0	490	0.6510	0.6282	0.6510	0.8069
No log	98.4	492	0.6511	0.6282	0.6511	0.8069
No log	98.8	494	0.6511	0.6282	0.6511	0.8069
No log	99.2	496	0.6511	0.6282	0.6511	0.8069
No log	99.6	498	0.6511	0.6282	0.6511	0.8069
0.1601	100.0	500	0.6511	0.6282	0.6511	0.8069

Framework versions

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