ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k3_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: 0.6935
• Qwk: 0.6208
• Mse: 0.6935
• Rmse: 0.8328

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	0.1667	2	4.6705	0.0010	4.6705	2.1611
No log	0.3333	4	2.6941	0.0215	2.6941	1.6414
No log	0.5	6	1.7015	0.0372	1.7015	1.3044
No log	0.6667	8	1.3518	0.0811	1.3518	1.1627
No log	0.8333	10	1.1885	0.1857	1.1885	1.0902
No log	1.0	12	1.2404	0.0802	1.2404	1.1137
No log	1.1667	14	1.2829	0.0802	1.2829	1.1326
No log	1.3333	16	1.2515	0.1247	1.2515	1.1187
No log	1.5	18	1.5618	-0.0149	1.5618	1.2497
No log	1.6667	20	1.8265	0.0227	1.8265	1.3515
No log	1.8333	22	1.6318	0.0	1.6318	1.2774
No log	2.0	24	1.3089	0.0	1.3089	1.1441
No log	2.1667	26	1.1603	0.3565	1.1603	1.0772
No log	2.3333	28	1.0788	0.3965	1.0788	1.0387
No log	2.5	30	1.0864	0.3441	1.0864	1.0423
No log	2.6667	32	1.2526	0.1346	1.2526	1.1192
No log	2.8333	34	1.2017	0.1472	1.2017	1.0962
No log	3.0	36	1.3830	0.1552	1.3830	1.1760
No log	3.1667	38	1.3496	0.1552	1.3496	1.1617
No log	3.3333	40	1.1004	0.2386	1.1004	1.0490
No log	3.5	42	1.0507	0.2938	1.0507	1.0250
No log	3.6667	44	1.0208	0.3095	1.0208	1.0103
No log	3.8333	46	1.0269	0.2520	1.0269	1.0133
No log	4.0	48	1.0172	0.2556	1.0172	1.0086
No log	4.1667	50	1.1643	0.2220	1.1643	1.0790
No log	4.3333	52	1.2629	0.2919	1.2629	1.1238
No log	4.5	54	1.0573	0.3012	1.0573	1.0283
No log	4.6667	56	0.9597	0.3854	0.9597	0.9796
No log	4.8333	58	1.0472	0.3978	1.0472	1.0233
No log	5.0	60	0.9315	0.4078	0.9315	0.9651
No log	5.1667	62	1.0528	0.4640	1.0528	1.0261
No log	5.3333	64	1.3060	0.3949	1.3060	1.1428
No log	5.5	66	1.0021	0.5185	1.0021	1.0010
No log	5.6667	68	0.8255	0.5198	0.8255	0.9086
No log	5.8333	70	0.7848	0.5922	0.7848	0.8859
No log	6.0	72	0.8002	0.5869	0.8002	0.8945
No log	6.1667	74	0.7996	0.5439	0.7996	0.8942
No log	6.3333	76	0.7988	0.5621	0.7988	0.8938
No log	6.5	78	0.7880	0.5738	0.7880	0.8877
No log	6.6667	80	0.7812	0.5951	0.7812	0.8839
No log	6.8333	82	0.7683	0.5938	0.7683	0.8765
No log	7.0	84	0.8295	0.5933	0.8295	0.9108
No log	7.1667	86	0.9499	0.4941	0.9499	0.9747
No log	7.3333	88	0.8851	0.5554	0.8851	0.9408
No log	7.5	90	0.7631	0.6205	0.7631	0.8735
No log	7.6667	92	0.7434	0.5754	0.7434	0.8622
No log	7.8333	94	0.7397	0.6053	0.7397	0.8601
No log	8.0	96	0.8409	0.5352	0.8409	0.9170
No log	8.1667	98	0.9545	0.4739	0.9545	0.9770
No log	8.3333	100	0.9355	0.4794	0.9355	0.9672
No log	8.5	102	0.8160	0.5476	0.8160	0.9033
No log	8.6667	104	0.8500	0.5875	0.8500	0.9220
No log	8.8333	106	0.9036	0.5380	0.9036	0.9506
No log	9.0	108	0.9523	0.5352	0.9523	0.9759
No log	9.1667	110	1.0154	0.4573	1.0154	1.0076
No log	9.3333	112	0.9520	0.5441	0.9520	0.9757
No log	9.5	114	1.0822	0.4840	1.0822	1.0403
No log	9.6667	116	1.2880	0.4246	1.2880	1.1349
No log	9.8333	118	1.2118	0.4407	1.2118	1.1008
No log	10.0	120	0.9838	0.4372	0.9838	0.9919
No log	10.1667	122	0.9111	0.3874	0.9111	0.9545
No log	10.3333	124	0.9725	0.3567	0.9725	0.9862
No log	10.5	126	0.9601	0.3390	0.9601	0.9799
No log	10.6667	128	0.9199	0.3929	0.9199	0.9591
No log	10.8333	130	0.9145	0.4866	0.9145	0.9563
No log	11.0	132	0.8731	0.5186	0.8731	0.9344
No log	11.1667	134	0.8296	0.4313	0.8296	0.9108
No log	11.3333	136	0.8172	0.5339	0.8172	0.9040
No log	11.5	138	0.7993	0.6404	0.7993	0.8940
No log	11.6667	140	0.7909	0.5811	0.7909	0.8893
No log	11.8333	142	0.9133	0.4910	0.9133	0.9557
No log	12.0	144	0.9369	0.4730	0.9369	0.9679
No log	12.1667	146	0.7750	0.5793	0.7750	0.8803
No log	12.3333	148	0.7103	0.6257	0.7103	0.8428
No log	12.5	150	0.7033	0.6257	0.7033	0.8386
No log	12.6667	152	0.7010	0.6431	0.7010	0.8373
No log	12.8333	154	0.7129	0.5985	0.7129	0.8443
No log	13.0	156	0.7340	0.6057	0.7340	0.8568
No log	13.1667	158	0.7447	0.6346	0.7447	0.8629
No log	13.3333	160	0.7520	0.6308	0.7520	0.8672
No log	13.5	162	0.7510	0.5756	0.7510	0.8666
No log	13.6667	164	0.8431	0.5455	0.8431	0.9182
No log	13.8333	166	0.8688	0.5133	0.8688	0.9321
No log	14.0	168	0.7929	0.4527	0.7929	0.8905
No log	14.1667	170	0.8034	0.4482	0.8034	0.8964
No log	14.3333	172	0.8949	0.4186	0.8949	0.9460
No log	14.5	174	0.8812	0.4440	0.8812	0.9387
No log	14.6667	176	0.8151	0.3998	0.8151	0.9028
No log	14.8333	178	0.8773	0.4439	0.8773	0.9367
No log	15.0	180	0.8439	0.4657	0.8439	0.9186
No log	15.1667	182	0.7823	0.4828	0.7823	0.8845
No log	15.3333	184	0.8243	0.5287	0.8243	0.9079
No log	15.5	186	0.8045	0.4507	0.8045	0.8969
No log	15.6667	188	0.7540	0.5528	0.7540	0.8683
No log	15.8333	190	0.7472	0.5342	0.7472	0.8644
No log	16.0	192	0.7510	0.5120	0.7510	0.8666
No log	16.1667	194	0.7463	0.5455	0.7463	0.8639
No log	16.3333	196	0.7549	0.5451	0.7549	0.8689
No log	16.5	198	0.7866	0.6365	0.7866	0.8869
No log	16.6667	200	0.8376	0.6307	0.8376	0.9152
No log	16.8333	202	0.7908	0.6019	0.7908	0.8893
No log	17.0	204	0.7629	0.6127	0.7629	0.8734
No log	17.1667	206	0.7483	0.6251	0.7483	0.8650
No log	17.3333	208	0.7471	0.6258	0.7471	0.8644
No log	17.5	210	0.7011	0.6328	0.7011	0.8373
No log	17.6667	212	0.7054	0.6333	0.7054	0.8399
No log	17.8333	214	0.7037	0.6424	0.7037	0.8388
No log	18.0	216	0.7048	0.6054	0.7048	0.8395
No log	18.1667	218	0.7926	0.5511	0.7926	0.8903
No log	18.3333	220	0.8095	0.5511	0.8095	0.8997
No log	18.5	222	0.6910	0.6340	0.6910	0.8313
No log	18.6667	224	0.7524	0.4929	0.7524	0.8674
No log	18.8333	226	0.9355	0.5357	0.9355	0.9672
No log	19.0	228	0.9030	0.5222	0.9030	0.9502
No log	19.1667	230	0.7386	0.4841	0.7386	0.8594
No log	19.3333	232	0.7347	0.4690	0.7347	0.8571
No log	19.5	234	0.8451	0.5113	0.8451	0.9193
No log	19.6667	236	0.8783	0.5098	0.8783	0.9372
No log	19.8333	238	0.7865	0.5071	0.7865	0.8868
No log	20.0	240	0.7216	0.5672	0.7216	0.8495
No log	20.1667	242	0.7684	0.6022	0.7684	0.8766
No log	20.3333	244	0.7589	0.6022	0.7589	0.8711
No log	20.5	246	0.7206	0.5672	0.7206	0.8489
No log	20.6667	248	0.7611	0.5996	0.7611	0.8724
No log	20.8333	250	0.9018	0.5255	0.9018	0.9496
No log	21.0	252	0.9368	0.5421	0.9368	0.9679
No log	21.1667	254	0.8421	0.5781	0.8421	0.9177
No log	21.3333	256	0.7100	0.6089	0.7100	0.8426
No log	21.5	258	0.6912	0.5659	0.6912	0.8314
No log	21.6667	260	0.6992	0.5811	0.6992	0.8362
No log	21.8333	262	0.6885	0.5755	0.6885	0.8298
No log	22.0	264	0.6983	0.6217	0.6983	0.8357
No log	22.1667	266	0.7266	0.6249	0.7266	0.8524
No log	22.3333	268	0.7422	0.6215	0.7422	0.8615
No log	22.5	270	0.7131	0.6304	0.7131	0.8445
No log	22.6667	272	0.7016	0.5633	0.7016	0.8376
No log	22.8333	274	0.6986	0.5633	0.6986	0.8358
No log	23.0	276	0.6998	0.6287	0.6998	0.8365
No log	23.1667	278	0.7334	0.6453	0.7334	0.8564
No log	23.3333	280	0.7706	0.5553	0.7706	0.8778
No log	23.5	282	0.7215	0.5921	0.7215	0.8494
No log	23.6667	284	0.6885	0.5878	0.6885	0.8298
No log	23.8333	286	0.7252	0.5500	0.7252	0.8516
No log	24.0	288	0.7914	0.5642	0.7914	0.8896
No log	24.1667	290	0.7686	0.5642	0.7686	0.8767
No log	24.3333	292	0.6855	0.5993	0.6855	0.8280
No log	24.5	294	0.7817	0.6151	0.7817	0.8842
No log	24.6667	296	0.9145	0.5433	0.9145	0.9563
No log	24.8333	298	0.9259	0.5781	0.9259	0.9622
No log	25.0	300	0.8333	0.5724	0.8333	0.9128
No log	25.1667	302	0.7283	0.6195	0.7283	0.8534
No log	25.3333	304	0.7126	0.6404	0.7126	0.8442
No log	25.5	306	0.7032	0.6196	0.7032	0.8386
No log	25.6667	308	0.7390	0.6300	0.7390	0.8596
No log	25.8333	310	0.7991	0.5412	0.7991	0.8939
No log	26.0	312	0.7602	0.6029	0.7602	0.8719
No log	26.1667	314	0.7510	0.6029	0.7510	0.8666
No log	26.3333	316	0.7593	0.6059	0.7593	0.8714
No log	26.5	318	0.7284	0.6089	0.7284	0.8535
No log	26.6667	320	0.7105	0.5611	0.7105	0.8429
No log	26.8333	322	0.7046	0.5408	0.7046	0.8394
No log	27.0	324	0.7000	0.5089	0.7000	0.8367
No log	27.1667	326	0.7075	0.5220	0.7075	0.8412
No log	27.3333	328	0.7716	0.5637	0.7716	0.8784
No log	27.5	330	0.7961	0.5614	0.7961	0.8922
No log	27.6667	332	0.7734	0.5637	0.7734	0.8794
No log	27.8333	334	0.6983	0.6059	0.6983	0.8357
No log	28.0	336	0.6600	0.6230	0.6600	0.8124
No log	28.1667	338	0.6497	0.6288	0.6497	0.8060
No log	28.3333	340	0.6472	0.6423	0.6472	0.8045
No log	28.5	342	0.6455	0.6368	0.6455	0.8035
No log	28.6667	344	0.6586	0.6287	0.6586	0.8116
No log	28.8333	346	0.6878	0.6453	0.6878	0.8294
No log	29.0	348	0.6957	0.6453	0.6957	0.8341
No log	29.1667	350	0.6659	0.6565	0.6659	0.8160
No log	29.3333	352	0.6675	0.5382	0.6675	0.8170
No log	29.5	354	0.6825	0.5526	0.6825	0.8261
No log	29.6667	356	0.6808	0.5200	0.6808	0.8251
No log	29.8333	358	0.6605	0.6199	0.6605	0.8127
No log	30.0	360	0.6561	0.6106	0.6561	0.8100
No log	30.1667	362	0.6606	0.6106	0.6606	0.8128
No log	30.3333	364	0.6712	0.5729	0.6712	0.8193
No log	30.5	366	0.6861	0.5790	0.6861	0.8283
No log	30.6667	368	0.7004	0.5479	0.7004	0.8369
No log	30.8333	370	0.7132	0.5223	0.7132	0.8445
No log	31.0	372	0.7264	0.5223	0.7264	0.8523
No log	31.1667	374	0.7458	0.5184	0.7458	0.8636
No log	31.3333	376	0.7568	0.6385	0.7568	0.8700
No log	31.5	378	0.7343	0.6385	0.7343	0.8569
No log	31.6667	380	0.7041	0.5671	0.7041	0.8391
No log	31.8333	382	0.6861	0.6313	0.6861	0.8283
No log	32.0	384	0.6847	0.6139	0.6847	0.8274
No log	32.1667	386	0.6839	0.6525	0.6839	0.8270
No log	32.3333	388	0.6951	0.6388	0.6951	0.8337
No log	32.5	390	0.7279	0.6280	0.7279	0.8532
No log	32.6667	392	0.7729	0.5661	0.7729	0.8792
No log	32.8333	394	0.7995	0.5173	0.7995	0.8942
No log	33.0	396	0.7668	0.54	0.7668	0.8757
No log	33.1667	398	0.6988	0.6044	0.6988	0.8359
No log	33.3333	400	0.6673	0.6251	0.6673	0.8169
No log	33.5	402	0.6704	0.6304	0.6704	0.8188
No log	33.6667	404	0.6688	0.6304	0.6688	0.8178
No log	33.8333	406	0.6695	0.6304	0.6695	0.8183
No log	34.0	408	0.6812	0.6404	0.6812	0.8254
No log	34.1667	410	0.7436	0.5661	0.7436	0.8623
No log	34.3333	412	0.8091	0.5553	0.8091	0.8995
No log	34.5	414	0.8659	0.5342	0.8659	0.9305
No log	34.6667	416	0.9102	0.5055	0.9102	0.9540
No log	34.8333	418	0.9021	0.5055	0.9021	0.9498
No log	35.0	420	0.8536	0.5113	0.8536	0.9239
No log	35.1667	422	0.7655	0.54	0.7655	0.8749
No log	35.3333	424	0.7265	0.5650	0.7265	0.8523
No log	35.5	426	0.7177	0.5823	0.7177	0.8471
No log	35.6667	428	0.7444	0.6174	0.7444	0.8628
No log	35.8333	430	0.7524	0.6142	0.7524	0.8674
No log	36.0	432	0.7354	0.6417	0.7354	0.8575
No log	36.1667	434	0.6966	0.6817	0.6966	0.8346
No log	36.3333	436	0.6807	0.7143	0.6807	0.8250
No log	36.5	438	0.6829	0.6117	0.6829	0.8264
No log	36.6667	440	0.6907	0.5656	0.6907	0.8311
No log	36.8333	442	0.6719	0.6214	0.6719	0.8197
No log	37.0	444	0.6665	0.5891	0.6665	0.8164
No log	37.1667	446	0.6744	0.5905	0.6744	0.8212
No log	37.3333	448	0.6834	0.5810	0.6834	0.8267
No log	37.5	450	0.6788	0.5841	0.6788	0.8239
No log	37.6667	452	0.6849	0.5810	0.6849	0.8276
No log	37.8333	454	0.6899	0.6041	0.6899	0.8306
No log	38.0	456	0.6885	0.6218	0.6885	0.8298
No log	38.1667	458	0.7003	0.5870	0.7003	0.8368
No log	38.3333	460	0.7056	0.5870	0.7056	0.8400
No log	38.5	462	0.7045	0.5507	0.7045	0.8394
No log	38.6667	464	0.7228	0.6142	0.7228	0.8502
No log	38.8333	466	0.7300	0.6100	0.7300	0.8544
No log	39.0	468	0.7251	0.6280	0.7251	0.8515
No log	39.1667	470	0.7223	0.6350	0.7223	0.8499
No log	39.3333	472	0.7501	0.6350	0.7501	0.8661
No log	39.5	474	0.7347	0.6350	0.7347	0.8572
No log	39.6667	476	0.7043	0.6319	0.7043	0.8392
No log	39.8333	478	0.6982	0.6247	0.6982	0.8356
No log	40.0	480	0.7052	0.5922	0.7052	0.8397
No log	40.1667	482	0.7281	0.6228	0.7281	0.8533
No log	40.3333	484	0.7450	0.6066	0.7450	0.8631
No log	40.5	486	0.7672	0.6208	0.7672	0.8759
No log	40.6667	488	0.7652	0.6385	0.7652	0.8747
No log	40.8333	490	0.7740	0.6315	0.7740	0.8798
No log	41.0	492	0.7715	0.6131	0.7715	0.8784
No log	41.1667	494	0.7712	0.6131	0.7712	0.8782
No log	41.3333	496	0.7435	0.6266	0.7435	0.8623
No log	41.5	498	0.7197	0.6300	0.7197	0.8484
0.2693	41.6667	500	0.7229	0.6266	0.7229	0.8502
0.2693	41.8333	502	0.7136	0.6300	0.7136	0.8448
0.2693	42.0	504	0.7031	0.6385	0.7031	0.8385
0.2693	42.1667	506	0.7149	0.6350	0.7149	0.8455
0.2693	42.3333	508	0.7430	0.6350	0.7430	0.8619
0.2693	42.5	510	0.7325	0.6350	0.7325	0.8559
0.2693	42.6667	512	0.7181	0.6350	0.7181	0.8474
0.2693	42.8333	514	0.7293	0.6350	0.7293	0.8540
0.2693	43.0	516	0.7817	0.5954	0.7817	0.8841
0.2693	43.1667	518	0.8091	0.5660	0.8091	0.8995
0.2693	43.3333	520	0.7826	0.5954	0.7826	0.8847
0.2693	43.5	522	0.7225	0.6350	0.7225	0.8500
0.2693	43.6667	524	0.6860	0.6385	0.6860	0.8283
0.2693	43.8333	526	0.6599	0.6887	0.6599	0.8124
0.2693	44.0	528	0.6519	0.6487	0.6519	0.8074
0.2693	44.1667	530	0.6512	0.6735	0.6512	0.8070
0.2693	44.3333	532	0.6512	0.5978	0.6512	0.8070
0.2693	44.5	534	0.6637	0.6429	0.6637	0.8147
0.2693	44.6667	536	0.6786	0.6441	0.6786	0.8238
0.2693	44.8333	538	0.7086	0.6100	0.7086	0.8418
0.2693	45.0	540	0.7490	0.5962	0.7490	0.8655
0.2693	45.1667	542	0.7664	0.5962	0.7664	0.8754
0.2693	45.3333	544	0.7289	0.6100	0.7289	0.8538
0.2693	45.5	546	0.6935	0.6208	0.6935	0.8328

Framework versions

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