ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k4_task1_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: 0.7449
• Qwk: 0.6631
• Mse: 0.7449
• Rmse: 0.8631

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: 16
• eval_batch_size: 16
• 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	7.8631	-0.0508	7.8631	2.8041
No log	0.3333	4	5.4577	-0.0378	5.4577	2.3362
No log	0.5	6	3.8171	0.0260	3.8171	1.9537
No log	0.6667	8	2.9852	0.1234	2.9852	1.7278
No log	0.8333	10	2.2701	0.1808	2.2701	1.5067
No log	1.0	12	1.6877	0.1409	1.6877	1.2991
No log	1.1667	14	1.4271	0.2581	1.4271	1.1946
No log	1.3333	16	1.2764	0.2359	1.2764	1.1298
No log	1.5	18	1.1819	0.2646	1.1819	1.0872
No log	1.6667	20	1.0952	0.4482	1.0952	1.0465
No log	1.8333	22	1.0495	0.4881	1.0495	1.0244
No log	2.0	24	1.0164	0.4764	1.0164	1.0082
No log	2.1667	26	0.9934	0.4890	0.9934	0.9967
No log	2.3333	28	0.9932	0.4915	0.9932	0.9966
No log	2.5	30	1.0176	0.4891	1.0176	1.0088
No log	2.6667	32	1.1478	0.4356	1.1478	1.0713
No log	2.8333	34	1.2805	0.4095	1.2805	1.1316
No log	3.0	36	1.1791	0.4305	1.1791	1.0859
No log	3.1667	38	0.9782	0.5128	0.9782	0.9890
No log	3.3333	40	0.8510	0.5784	0.8510	0.9225
No log	3.5	42	0.8110	0.5673	0.8110	0.9006
No log	3.6667	44	0.8021	0.5777	0.8021	0.8956
No log	3.8333	46	0.8620	0.5593	0.8620	0.9284
No log	4.0	48	1.1053	0.4737	1.1053	1.0513
No log	4.1667	50	1.3113	0.4429	1.3113	1.1451
No log	4.3333	52	1.2536	0.4416	1.2536	1.1196
No log	4.5	54	1.1698	0.4530	1.1698	1.0816
No log	4.6667	56	0.9535	0.5275	0.9535	0.9765
No log	4.8333	58	0.7446	0.6462	0.7446	0.8629
No log	5.0	60	0.6795	0.6473	0.6795	0.8243
No log	5.1667	62	0.6581	0.6505	0.6581	0.8112
No log	5.3333	64	0.6706	0.6877	0.6706	0.8189
No log	5.5	66	0.7653	0.6390	0.7653	0.8748
No log	5.6667	68	0.9527	0.5494	0.9527	0.9760
No log	5.8333	70	1.1047	0.4984	1.1047	1.0510
No log	6.0	72	1.0599	0.5022	1.0599	1.0295
No log	6.1667	74	0.9275	0.5870	0.9275	0.9631
No log	6.3333	76	0.7587	0.6657	0.7587	0.8711
No log	6.5	78	0.6920	0.6889	0.6920	0.8318
No log	6.6667	80	0.6728	0.6936	0.6728	0.8202
No log	6.8333	82	0.6791	0.6644	0.6791	0.8240
No log	7.0	84	0.6910	0.6623	0.6910	0.8313
No log	7.1667	86	0.6992	0.6605	0.6992	0.8362
No log	7.3333	88	0.7629	0.6877	0.7629	0.8734
No log	7.5	90	0.8587	0.6309	0.8587	0.9267
No log	7.6667	92	0.8118	0.6631	0.8118	0.9010
No log	7.8333	94	0.8012	0.6640	0.8012	0.8951
No log	8.0	96	0.7825	0.6708	0.7825	0.8846
No log	8.1667	98	0.7954	0.6513	0.7954	0.8919
No log	8.3333	100	0.7540	0.6889	0.7540	0.8683
No log	8.5	102	0.7541	0.6889	0.7541	0.8684
No log	8.6667	104	0.7469	0.6824	0.7469	0.8642
No log	8.8333	106	0.7782	0.6716	0.7782	0.8822
No log	9.0	108	0.8699	0.6295	0.8699	0.9327
No log	9.1667	110	0.8135	0.6553	0.8135	0.9019
No log	9.3333	112	0.7268	0.6846	0.7268	0.8525
No log	9.5	114	0.6710	0.7131	0.6710	0.8192
No log	9.6667	116	0.6859	0.6960	0.6859	0.8282
No log	9.8333	118	0.7304	0.6898	0.7304	0.8547
No log	10.0	120	0.7268	0.6872	0.7268	0.8525
No log	10.1667	122	0.6803	0.6851	0.6803	0.8248
No log	10.3333	124	0.6418	0.7324	0.6418	0.8011
No log	10.5	126	0.6406	0.7183	0.6406	0.8004
No log	10.6667	128	0.6499	0.7387	0.6499	0.8062
No log	10.8333	130	0.6488	0.7166	0.6488	0.8055
No log	11.0	132	0.7150	0.6556	0.7150	0.8455
No log	11.1667	134	0.7670	0.6320	0.7670	0.8758
No log	11.3333	136	0.7416	0.6677	0.7416	0.8612
No log	11.5	138	0.7072	0.6732	0.7072	0.8410
No log	11.6667	140	0.6868	0.7177	0.6868	0.8287
No log	11.8333	142	0.6957	0.7073	0.6957	0.8341
No log	12.0	144	0.6969	0.6964	0.6969	0.8348
No log	12.1667	146	0.7037	0.7084	0.7037	0.8389
No log	12.3333	148	0.7297	0.6928	0.7297	0.8542
No log	12.5	150	0.8477	0.6689	0.8477	0.9207
No log	12.6667	152	0.9085	0.6306	0.9085	0.9532
No log	12.8333	154	0.8106	0.6871	0.8106	0.9003
No log	13.0	156	0.7074	0.6884	0.7074	0.8410
No log	13.1667	158	0.6937	0.6911	0.6937	0.8329
No log	13.3333	160	0.7008	0.7007	0.7008	0.8371
No log	13.5	162	0.7235	0.6872	0.7235	0.8506
No log	13.6667	164	0.7206	0.6860	0.7206	0.8489
No log	13.8333	166	0.6986	0.6863	0.6986	0.8358
No log	14.0	168	0.6784	0.6948	0.6784	0.8236
No log	14.1667	170	0.6769	0.7144	0.6769	0.8227
No log	14.3333	172	0.6800	0.7131	0.6800	0.8246
No log	14.5	174	0.6614	0.7112	0.6614	0.8133
No log	14.6667	176	0.7030	0.6599	0.7030	0.8385
No log	14.8333	178	0.7505	0.6709	0.7505	0.8663
No log	15.0	180	0.7133	0.6687	0.7133	0.8446
No log	15.1667	182	0.6659	0.6994	0.6659	0.8160
No log	15.3333	184	0.6457	0.6942	0.6457	0.8036
No log	15.5	186	0.6493	0.7255	0.6493	0.8058
No log	15.6667	188	0.6553	0.6888	0.6553	0.8095
No log	15.8333	190	0.6699	0.6771	0.6699	0.8184
No log	16.0	192	0.6772	0.6716	0.6772	0.8229
No log	16.1667	194	0.6821	0.7098	0.6821	0.8259
No log	16.3333	196	0.7212	0.6798	0.7212	0.8492
No log	16.5	198	0.7140	0.6841	0.7140	0.8450
No log	16.6667	200	0.6947	0.7058	0.6947	0.8335
No log	16.8333	202	0.6889	0.7078	0.6889	0.8300
No log	17.0	204	0.6848	0.6998	0.6848	0.8275
No log	17.1667	206	0.6955	0.6715	0.6955	0.8340
No log	17.3333	208	0.7112	0.6777	0.7112	0.8433
No log	17.5	210	0.6976	0.7189	0.6976	0.8352
No log	17.6667	212	0.7708	0.6680	0.7708	0.8779
No log	17.8333	214	0.8495	0.6671	0.8495	0.9217
No log	18.0	216	0.8065	0.6615	0.8065	0.8980
No log	18.1667	218	0.7205	0.7121	0.7205	0.8488
No log	18.3333	220	0.7490	0.6988	0.7490	0.8654
No log	18.5	222	0.7617	0.6529	0.7617	0.8727
No log	18.6667	224	0.7250	0.6805	0.7250	0.8515
No log	18.8333	226	0.7601	0.6785	0.7601	0.8719
No log	19.0	228	0.8122	0.6615	0.8122	0.9012
No log	19.1667	230	0.7915	0.6580	0.7915	0.8897
No log	19.3333	232	0.7121	0.7057	0.7121	0.8439
No log	19.5	234	0.6933	0.6822	0.6933	0.8327
No log	19.6667	236	0.6884	0.6760	0.6884	0.8297
No log	19.8333	238	0.6759	0.7003	0.6759	0.8221
No log	20.0	240	0.6818	0.6982	0.6818	0.8257
No log	20.1667	242	0.7080	0.6870	0.7080	0.8414
No log	20.3333	244	0.6995	0.6877	0.6995	0.8364
No log	20.5	246	0.6712	0.6768	0.6712	0.8193
No log	20.6667	248	0.6829	0.6889	0.6829	0.8264
No log	20.8333	250	0.6850	0.6844	0.6850	0.8277
No log	21.0	252	0.6922	0.6845	0.6922	0.8320
No log	21.1667	254	0.7079	0.6787	0.7079	0.8414
No log	21.3333	256	0.7157	0.7024	0.7157	0.8460
No log	21.5	258	0.7290	0.7077	0.7290	0.8538
No log	21.6667	260	0.7178	0.7037	0.7178	0.8472
No log	21.8333	262	0.7197	0.6900	0.7197	0.8484
No log	22.0	264	0.7307	0.6774	0.7307	0.8548
No log	22.1667	266	0.7266	0.7045	0.7266	0.8524
No log	22.3333	268	0.7499	0.7165	0.7499	0.8659
No log	22.5	270	0.8155	0.6337	0.8155	0.9030
No log	22.6667	272	0.8727	0.6402	0.8727	0.9342
No log	22.8333	274	0.8293	0.6508	0.8293	0.9106
No log	23.0	276	0.7581	0.6861	0.7581	0.8707
No log	23.1667	278	0.7203	0.7039	0.7203	0.8487
No log	23.3333	280	0.7152	0.6991	0.7152	0.8457
No log	23.5	282	0.7051	0.6788	0.7051	0.8397
No log	23.6667	284	0.7213	0.6949	0.7213	0.8493
No log	23.8333	286	0.7250	0.6919	0.7250	0.8515
No log	24.0	288	0.7494	0.6821	0.7494	0.8657
No log	24.1667	290	0.7316	0.6839	0.7316	0.8554
No log	24.3333	292	0.6913	0.7014	0.6913	0.8315
No log	24.5	294	0.7258	0.6693	0.7258	0.8519
No log	24.6667	296	0.7382	0.6693	0.7382	0.8592
No log	24.8333	298	0.7081	0.6989	0.7081	0.8415
No log	25.0	300	0.7397	0.6827	0.7397	0.8601
No log	25.1667	302	0.8026	0.6077	0.8026	0.8959
No log	25.3333	304	0.7984	0.6555	0.7984	0.8935
No log	25.5	306	0.7428	0.6689	0.7428	0.8619
No log	25.6667	308	0.7427	0.6521	0.7427	0.8618
No log	25.8333	310	0.7361	0.6680	0.7361	0.8580
No log	26.0	312	0.7467	0.6826	0.7467	0.8641
No log	26.1667	314	0.7457	0.6877	0.7457	0.8635
No log	26.3333	316	0.7315	0.6784	0.7315	0.8553
No log	26.5	318	0.7696	0.6834	0.7696	0.8773
No log	26.6667	320	0.7958	0.6469	0.7958	0.8921
No log	26.8333	322	0.7524	0.6863	0.7524	0.8674
No log	27.0	324	0.7309	0.7110	0.7309	0.8549
No log	27.1667	326	0.7254	0.7055	0.7254	0.8517
No log	27.3333	328	0.7047	0.7151	0.7047	0.8394
No log	27.5	330	0.6990	0.6940	0.6990	0.8361
No log	27.6667	332	0.6980	0.7054	0.6980	0.8355
No log	27.8333	334	0.7238	0.6700	0.7238	0.8508
No log	28.0	336	0.7369	0.6766	0.7369	0.8584
No log	28.1667	338	0.7275	0.6866	0.7275	0.8530
No log	28.3333	340	0.7008	0.6750	0.7008	0.8371
No log	28.5	342	0.6981	0.6435	0.6981	0.8355
No log	28.6667	344	0.6956	0.6606	0.6956	0.8340
No log	28.8333	346	0.6881	0.6778	0.6881	0.8295
No log	29.0	348	0.6932	0.6839	0.6932	0.8326
No log	29.1667	350	0.7324	0.6791	0.7324	0.8558
No log	29.3333	352	0.7527	0.6802	0.7527	0.8676
No log	29.5	354	0.7449	0.6846	0.7449	0.8631
No log	29.6667	356	0.7451	0.6839	0.7451	0.8632
No log	29.8333	358	0.7483	0.6885	0.7483	0.8650
No log	30.0	360	0.7462	0.6956	0.7462	0.8638
No log	30.1667	362	0.7310	0.6957	0.7310	0.8550
No log	30.3333	364	0.7071	0.7022	0.7071	0.8409
No log	30.5	366	0.7000	0.7035	0.7000	0.8367
No log	30.6667	368	0.6961	0.6973	0.6961	0.8343
No log	30.8333	370	0.7063	0.6838	0.7063	0.8404
No log	31.0	372	0.7038	0.6774	0.7038	0.8389
No log	31.1667	374	0.6992	0.6792	0.6992	0.8362
No log	31.3333	376	0.6955	0.6678	0.6955	0.8339
No log	31.5	378	0.7008	0.6756	0.7008	0.8372
No log	31.6667	380	0.7112	0.6661	0.7112	0.8433
No log	31.8333	382	0.7252	0.6681	0.7252	0.8516
No log	32.0	384	0.7354	0.6727	0.7354	0.8576
No log	32.1667	386	0.7595	0.6802	0.7595	0.8715
No log	32.3333	388	0.7743	0.6744	0.7743	0.8800
No log	32.5	390	0.7646	0.6798	0.7646	0.8744
No log	32.6667	392	0.7241	0.6698	0.7241	0.8509
No log	32.8333	394	0.7297	0.6609	0.7297	0.8542
No log	33.0	396	0.7294	0.6463	0.7294	0.8541
No log	33.1667	398	0.7185	0.6481	0.7185	0.8477
No log	33.3333	400	0.7207	0.6815	0.7207	0.8489
No log	33.5	402	0.7702	0.6892	0.7702	0.8776
No log	33.6667	404	0.8046	0.6787	0.8046	0.8970
No log	33.8333	406	0.7833	0.6953	0.7833	0.8851
No log	34.0	408	0.7296	0.6815	0.7296	0.8542
No log	34.1667	410	0.7191	0.6745	0.7191	0.8480
No log	34.3333	412	0.7222	0.6866	0.7222	0.8498
No log	34.5	414	0.7608	0.6751	0.7608	0.8723
No log	34.6667	416	0.8002	0.6830	0.8002	0.8945
No log	34.8333	418	0.7986	0.7007	0.7986	0.8937
No log	35.0	420	0.7706	0.6700	0.7706	0.8779
No log	35.1667	422	0.7538	0.6795	0.7538	0.8682
No log	35.3333	424	0.7496	0.6813	0.7496	0.8658
No log	35.5	426	0.7406	0.6776	0.7406	0.8606
No log	35.6667	428	0.7322	0.6820	0.7322	0.8557
No log	35.8333	430	0.7263	0.6907	0.7263	0.8522
No log	36.0	432	0.7237	0.6914	0.7237	0.8507
No log	36.1667	434	0.7267	0.6956	0.7267	0.8525
No log	36.3333	436	0.7184	0.6852	0.7184	0.8476
No log	36.5	438	0.7134	0.6909	0.7134	0.8446
No log	36.6667	440	0.7207	0.6939	0.7207	0.8490
No log	36.8333	442	0.7675	0.6973	0.7675	0.8761
No log	37.0	444	0.8006	0.6797	0.8006	0.8948
No log	37.1667	446	0.8073	0.6797	0.8073	0.8985
No log	37.3333	448	0.8007	0.6814	0.8007	0.8948
No log	37.5	450	0.7928	0.6857	0.7928	0.8904
No log	37.6667	452	0.7567	0.7041	0.7567	0.8699
No log	37.8333	454	0.7623	0.6846	0.7623	0.8731
No log	38.0	456	0.7785	0.6828	0.7785	0.8823
No log	38.1667	458	0.7996	0.6874	0.7996	0.8942
No log	38.3333	460	0.8329	0.6515	0.8329	0.9126
No log	38.5	462	0.8313	0.6432	0.8313	0.9118
No log	38.6667	464	0.8248	0.6377	0.8248	0.9082
No log	38.8333	466	0.7918	0.6709	0.7918	0.8898
No log	39.0	468	0.7557	0.6848	0.7557	0.8693
No log	39.1667	470	0.7389	0.6687	0.7389	0.8596
No log	39.3333	472	0.7274	0.6786	0.7274	0.8529
No log	39.5	474	0.7239	0.6804	0.7239	0.8508
No log	39.6667	476	0.7367	0.6852	0.7367	0.8583
No log	39.8333	478	0.8009	0.6574	0.8009	0.8949
No log	40.0	480	0.8581	0.6552	0.8581	0.9263
No log	40.1667	482	0.8430	0.6552	0.8430	0.9182
No log	40.3333	484	0.7736	0.6788	0.7736	0.8795
No log	40.5	486	0.7241	0.6877	0.7241	0.8509
No log	40.6667	488	0.7174	0.6678	0.7174	0.8470
No log	40.8333	490	0.7245	0.6877	0.7245	0.8511
No log	41.0	492	0.7756	0.6700	0.7756	0.8807
No log	41.1667	494	0.8228	0.6489	0.8228	0.9071
No log	41.3333	496	0.7964	0.6650	0.7964	0.8924
No log	41.5	498	0.7392	0.6920	0.7392	0.8597
0.5282	41.6667	500	0.7299	0.6868	0.7299	0.8544
0.5282	41.8333	502	0.7424	0.6783	0.7424	0.8616
0.5282	42.0	504	0.7783	0.6690	0.7783	0.8822
0.5282	42.1667	506	0.7995	0.6683	0.7995	0.8941
0.5282	42.3333	508	0.8015	0.6683	0.8015	0.8953
0.5282	42.5	510	0.7626	0.6937	0.7626	0.8732
0.5282	42.6667	512	0.7344	0.6685	0.7344	0.8570
0.5282	42.8333	514	0.7288	0.6618	0.7288	0.8537
0.5282	43.0	516	0.7326	0.6666	0.7326	0.8559
0.5282	43.1667	518	0.7486	0.6852	0.7486	0.8652
0.5282	43.3333	520	0.7449	0.6631	0.7449	0.8631

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1