ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k7_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: 0.8509
• Qwk: 0.6617
• Mse: 0.8509
• Rmse: 0.9225

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	0.1111	2	7.8350	-0.0494	7.8350	2.7991
No log	0.2222	4	5.5484	-0.0378	5.5484	2.3555
No log	0.3333	6	4.0058	0.0318	4.0058	2.0014
No log	0.4444	8	3.0570	0.0840	3.0570	1.7484
No log	0.5556	10	2.3152	0.1518	2.3152	1.5216
No log	0.6667	12	1.7919	0.1676	1.7919	1.3386
No log	0.7778	14	1.5273	0.1668	1.5273	1.2358
No log	0.8889	16	1.2965	0.1524	1.2965	1.1386
No log	1.0	18	1.1203	0.3153	1.1203	1.0584
No log	1.1111	20	1.0568	0.3619	1.0568	1.0280
No log	1.2222	22	1.1006	0.4577	1.1006	1.0491
No log	1.3333	24	1.1938	0.3592	1.1938	1.0926
No log	1.4444	26	1.2428	0.3094	1.2428	1.1148
No log	1.5556	28	1.1193	0.3741	1.1193	1.0580
No log	1.6667	30	0.9819	0.4921	0.9819	0.9909
No log	1.7778	32	0.9220	0.4897	0.9220	0.9602
No log	1.8889	34	0.8935	0.4823	0.8935	0.9452
No log	2.0	36	0.8246	0.4665	0.8246	0.9081
No log	2.1111	38	0.7881	0.4702	0.7881	0.8877
No log	2.2222	40	0.7885	0.4788	0.7885	0.8880
No log	2.3333	42	0.7767	0.5	0.7767	0.8813
No log	2.4444	44	0.7851	0.4979	0.7851	0.8861
No log	2.5556	46	0.8930	0.5597	0.8930	0.9450
No log	2.6667	48	1.0267	0.4958	1.0267	1.0133
No log	2.7778	50	1.0801	0.5062	1.0801	1.0393
No log	2.8889	52	0.9751	0.5222	0.9751	0.9875
No log	3.0	54	0.8980	0.5761	0.8980	0.9476
No log	3.1111	56	0.8966	0.5892	0.8966	0.9469
No log	3.2222	58	0.8040	0.6027	0.8040	0.8967
No log	3.3333	60	0.7848	0.6074	0.7848	0.8859
No log	3.4444	62	0.7750	0.6049	0.7750	0.8803
No log	3.5556	64	0.8168	0.5982	0.8168	0.9038
No log	3.6667	66	0.8142	0.5917	0.8142	0.9023
No log	3.7778	68	0.8688	0.5760	0.8688	0.9321
No log	3.8889	70	0.8823	0.6103	0.8823	0.9393
No log	4.0	72	0.7690	0.6398	0.7690	0.8769
No log	4.1111	74	0.7257	0.6456	0.7257	0.8519
No log	4.2222	76	0.6835	0.6521	0.6835	0.8267
No log	4.3333	78	0.6261	0.7143	0.6261	0.7913
No log	4.4444	80	0.6231	0.7201	0.6231	0.7893
No log	4.5556	82	0.6249	0.7211	0.6249	0.7905
No log	4.6667	84	0.7206	0.6763	0.7206	0.8489
No log	4.7778	86	0.7951	0.6533	0.7951	0.8917
No log	4.8889	88	0.7695	0.6712	0.7695	0.8772
No log	5.0	90	0.7583	0.6779	0.7583	0.8708
No log	5.1111	92	0.7955	0.6508	0.7955	0.8919
No log	5.2222	94	0.6989	0.6956	0.6989	0.8360
No log	5.3333	96	0.6289	0.7158	0.6289	0.7930
No log	5.4444	98	0.6291	0.7072	0.6291	0.7931
No log	5.5556	100	0.6950	0.6890	0.6950	0.8337
No log	5.6667	102	0.7962	0.6533	0.7962	0.8923
No log	5.7778	104	0.7557	0.6573	0.7557	0.8693
No log	5.8889	106	0.6321	0.6784	0.6321	0.7951
No log	6.0	108	0.5882	0.6998	0.5882	0.7669
No log	6.1111	110	0.5939	0.6968	0.5939	0.7707
No log	6.2222	112	0.6124	0.7029	0.6124	0.7825
No log	6.3333	114	0.5949	0.7239	0.5949	0.7713
No log	6.4444	116	0.6333	0.6881	0.6333	0.7958
No log	6.5556	118	0.8097	0.6562	0.8097	0.8998
No log	6.6667	120	0.9344	0.6176	0.9344	0.9666
No log	6.7778	122	0.8692	0.6484	0.8692	0.9323
No log	6.8889	124	0.8105	0.6685	0.8105	0.9003
No log	7.0	126	0.7821	0.6787	0.7821	0.8843
No log	7.1111	128	0.7285	0.7145	0.7285	0.8535
No log	7.2222	130	0.6529	0.7447	0.6529	0.8080
No log	7.3333	132	0.6455	0.7378	0.6455	0.8035
No log	7.4444	134	0.6516	0.7210	0.6516	0.8072
No log	7.5556	136	0.6663	0.7087	0.6663	0.8163
No log	7.6667	138	0.7848	0.6944	0.7848	0.8859
No log	7.7778	140	0.8830	0.6494	0.8830	0.9397
No log	7.8889	142	0.8150	0.6721	0.8150	0.9028
No log	8.0	144	0.6768	0.6947	0.6768	0.8227
No log	8.1111	146	0.6442	0.6923	0.6442	0.8026
No log	8.2222	148	0.6427	0.7365	0.6427	0.8017
No log	8.3333	150	0.6435	0.7342	0.6435	0.8022
No log	8.4444	152	0.6466	0.7326	0.6466	0.8041
No log	8.5556	154	0.6585	0.7367	0.6585	0.8115
No log	8.6667	156	0.6631	0.7278	0.6631	0.8143
No log	8.7778	158	0.6756	0.7200	0.6756	0.8219
No log	8.8889	160	0.6897	0.7258	0.6897	0.8305
No log	9.0	162	0.6989	0.7247	0.6989	0.8360
No log	9.1111	164	0.7277	0.7116	0.7277	0.8530
No log	9.2222	166	0.7539	0.7175	0.7539	0.8683
No log	9.3333	168	0.7362	0.7322	0.7362	0.8580
No log	9.4444	170	0.7332	0.7394	0.7332	0.8563
No log	9.5556	172	0.7366	0.7175	0.7366	0.8582
No log	9.6667	174	0.7189	0.7322	0.7189	0.8479
No log	9.7778	176	0.7093	0.6776	0.7093	0.8422
No log	9.8889	178	0.7135	0.6383	0.7135	0.8447
No log	10.0	180	0.7005	0.6803	0.7005	0.8369
No log	10.1111	182	0.6867	0.7028	0.6867	0.8287
No log	10.2222	184	0.6968	0.6914	0.6968	0.8347
No log	10.3333	186	0.7097	0.6914	0.7097	0.8424
No log	10.4444	188	0.7429	0.6699	0.7429	0.8619
No log	10.5556	190	0.7909	0.6624	0.7909	0.8893
No log	10.6667	192	0.8509	0.6447	0.8509	0.9224
No log	10.7778	194	0.7956	0.6817	0.7956	0.8920
No log	10.8889	196	0.8167	0.6446	0.8167	0.9037
No log	11.0	198	0.8796	0.6228	0.8796	0.9378
No log	11.1111	200	0.8381	0.6494	0.8381	0.9155
No log	11.2222	202	0.8123	0.6896	0.8123	0.9013
No log	11.3333	204	0.9050	0.6403	0.9050	0.9513
No log	11.4444	206	0.9674	0.5776	0.9674	0.9835
No log	11.5556	208	0.8623	0.6679	0.8623	0.9286
No log	11.6667	210	0.7743	0.6685	0.7743	0.8800
No log	11.7778	212	0.7485	0.6566	0.7485	0.8652
No log	11.8889	214	0.7347	0.6611	0.7347	0.8571
No log	12.0	216	0.7600	0.6731	0.7600	0.8718
No log	12.1111	218	0.8835	0.6475	0.8835	0.9399
No log	12.2222	220	0.9478	0.5979	0.9478	0.9736
No log	12.3333	222	0.9172	0.6246	0.9172	0.9577
No log	12.4444	224	0.7683	0.6658	0.7683	0.8765
No log	12.5556	226	0.7035	0.7042	0.7035	0.8387
No log	12.6667	228	0.7802	0.6687	0.7802	0.8833
No log	12.7778	230	0.8104	0.6518	0.8104	0.9002
No log	12.8889	232	0.7262	0.7070	0.7262	0.8522
No log	13.0	234	0.6609	0.7282	0.6609	0.8129
No log	13.1111	236	0.6599	0.6990	0.6599	0.8123
No log	13.2222	238	0.6735	0.7035	0.6735	0.8206
No log	13.3333	240	0.6782	0.7231	0.6782	0.8235
No log	13.4444	242	0.7149	0.7160	0.7149	0.8455
No log	13.5556	244	0.7335	0.6963	0.7335	0.8565
No log	13.6667	246	0.7149	0.7112	0.7149	0.8455
No log	13.7778	248	0.7730	0.6616	0.7730	0.8792
No log	13.8889	250	0.7917	0.6295	0.7917	0.8898
No log	14.0	252	0.7324	0.6815	0.7324	0.8558
No log	14.1111	254	0.7339	0.7125	0.7339	0.8567
No log	14.2222	256	0.7398	0.6874	0.7398	0.8601
No log	14.3333	258	0.7713	0.6424	0.7713	0.8782
No log	14.4444	260	0.7395	0.6632	0.7395	0.8599
No log	14.5556	262	0.7069	0.6755	0.7069	0.8408
No log	14.6667	264	0.7295	0.6817	0.7295	0.8541
No log	14.7778	266	0.7239	0.6944	0.7239	0.8508
No log	14.8889	268	0.7410	0.6590	0.7410	0.8608
No log	15.0	270	0.7526	0.6610	0.7526	0.8675
No log	15.1111	272	0.7499	0.6608	0.7499	0.8660
No log	15.2222	274	0.7535	0.6632	0.7535	0.8680
No log	15.3333	276	0.8136	0.6588	0.8136	0.9020
No log	15.4444	278	0.8384	0.6663	0.8384	0.9157
No log	15.5556	280	0.7874	0.6522	0.7874	0.8874
No log	15.6667	282	0.7899	0.6625	0.7899	0.8887
No log	15.7778	284	0.8179	0.6809	0.8179	0.9044
No log	15.8889	286	0.7979	0.6932	0.7979	0.8933
No log	16.0	288	0.7672	0.6673	0.7672	0.8759
No log	16.1111	290	0.7737	0.6518	0.7737	0.8796
No log	16.2222	292	0.7771	0.6624	0.7771	0.8815
No log	16.3333	294	0.7264	0.6663	0.7264	0.8523
No log	16.4444	296	0.7197	0.7105	0.7197	0.8483
No log	16.5556	298	0.7203	0.7123	0.7203	0.8487
No log	16.6667	300	0.7474	0.6926	0.7474	0.8645
No log	16.7778	302	0.8021	0.6803	0.8021	0.8956
No log	16.8889	304	0.7777	0.6961	0.7777	0.8819
No log	17.0	306	0.7573	0.6465	0.7573	0.8702
No log	17.1111	308	0.7765	0.6606	0.7765	0.8812
No log	17.2222	310	0.7637	0.6528	0.7637	0.8739
No log	17.3333	312	0.8270	0.6556	0.8270	0.9094
No log	17.4444	314	0.9000	0.6457	0.9000	0.9487
No log	17.5556	316	0.8527	0.6535	0.8527	0.9234
No log	17.6667	318	0.7582	0.6828	0.7582	0.8707
No log	17.7778	320	0.7566	0.6796	0.7566	0.8698
No log	17.8889	322	0.7438	0.6814	0.7438	0.8625
No log	18.0	324	0.7215	0.6675	0.7215	0.8494
No log	18.1111	326	0.7344	0.7000	0.7344	0.8570
No log	18.2222	328	0.7568	0.7145	0.7568	0.8699
No log	18.3333	330	0.7350	0.6952	0.7350	0.8573
No log	18.4444	332	0.7494	0.6713	0.7494	0.8657
No log	18.5556	334	0.7745	0.6458	0.7745	0.8800
No log	18.6667	336	0.7508	0.6727	0.7508	0.8665
No log	18.7778	338	0.7369	0.6921	0.7369	0.8584
No log	18.8889	340	0.7724	0.7239	0.7724	0.8789
No log	19.0	342	0.7666	0.7202	0.7666	0.8756
No log	19.1111	344	0.7486	0.6633	0.7486	0.8652
No log	19.2222	346	0.7657	0.6584	0.7657	0.8750
No log	19.3333	348	0.7798	0.6554	0.7798	0.8831
No log	19.4444	350	0.7662	0.6614	0.7662	0.8753
No log	19.5556	352	0.7788	0.6678	0.7788	0.8825
No log	19.6667	354	0.7941	0.7105	0.7941	0.8911
No log	19.7778	356	0.7834	0.7011	0.7834	0.8851
No log	19.8889	358	0.7659	0.6781	0.7659	0.8752
No log	20.0	360	0.7657	0.6630	0.7657	0.8751
No log	20.1111	362	0.7712	0.6750	0.7712	0.8782
No log	20.2222	364	0.7730	0.6775	0.7730	0.8792
No log	20.3333	366	0.7771	0.6617	0.7771	0.8815
No log	20.4444	368	0.7846	0.6486	0.7846	0.8858
No log	20.5556	370	0.8081	0.6507	0.8081	0.8990
No log	20.6667	372	0.8108	0.6561	0.8108	0.9004
No log	20.7778	374	0.8044	0.6594	0.8044	0.8969
No log	20.8889	376	0.8481	0.6807	0.8481	0.9209
No log	21.0	378	0.8535	0.6749	0.8535	0.9239
No log	21.1111	380	0.8476	0.6796	0.8476	0.9207
No log	21.2222	382	0.8230	0.6791	0.8230	0.9072
No log	21.3333	384	0.8148	0.6837	0.8148	0.9026
No log	21.4444	386	0.8090	0.6883	0.8090	0.8995
No log	21.5556	388	0.8095	0.7102	0.8095	0.8997
No log	21.6667	390	0.7742	0.7010	0.7742	0.8799
No log	21.7778	392	0.7605	0.6609	0.7605	0.8721
No log	21.8889	394	0.7710	0.6518	0.7710	0.8781
No log	22.0	396	0.7744	0.6641	0.7744	0.8800
No log	22.1111	398	0.8166	0.7102	0.8166	0.9037
No log	22.2222	400	0.8384	0.6666	0.8384	0.9157
No log	22.3333	402	0.8123	0.7066	0.8123	0.9013
No log	22.4444	404	0.7867	0.6786	0.7867	0.8869
No log	22.5556	406	0.7857	0.6735	0.7857	0.8864
No log	22.6667	408	0.7820	0.6709	0.7820	0.8843
No log	22.7778	410	0.7753	0.6767	0.7753	0.8805
No log	22.8889	412	0.7691	0.7024	0.7691	0.8770
No log	23.0	414	0.7573	0.6813	0.7573	0.8702
No log	23.1111	416	0.7536	0.6768	0.7536	0.8681
No log	23.2222	418	0.7603	0.6889	0.7603	0.8719
No log	23.3333	420	0.7610	0.6859	0.7610	0.8723
No log	23.4444	422	0.7593	0.6859	0.7593	0.8714
No log	23.5556	424	0.7604	0.6761	0.7604	0.8720
No log	23.6667	426	0.7528	0.6785	0.7529	0.8677
No log	23.7778	428	0.7599	0.6749	0.7599	0.8717
No log	23.8889	430	0.7694	0.6749	0.7694	0.8772
No log	24.0	432	0.8156	0.6931	0.8156	0.9031
No log	24.1111	434	0.9290	0.6658	0.9290	0.9639
No log	24.2222	436	0.9395	0.6494	0.9395	0.9693
No log	24.3333	438	0.8413	0.6793	0.8413	0.9172
No log	24.4444	440	0.7658	0.6682	0.7658	0.8751
No log	24.5556	442	0.7698	0.6605	0.7698	0.8774
No log	24.6667	444	0.7582	0.6685	0.7582	0.8707
No log	24.7778	446	0.7910	0.6992	0.7910	0.8894
No log	24.8889	448	0.8242	0.6737	0.8242	0.9079
No log	25.0	450	0.7909	0.6857	0.7909	0.8893
No log	25.1111	452	0.7633	0.6749	0.7633	0.8737
No log	25.2222	454	0.7668	0.6685	0.7668	0.8757
No log	25.3333	456	0.7798	0.6823	0.7798	0.8830
No log	25.4444	458	0.8218	0.6414	0.8218	0.9065
No log	25.5556	460	0.8503	0.6449	0.8503	0.9221
No log	25.6667	462	0.8730	0.6397	0.8730	0.9343
No log	25.7778	464	0.8246	0.6656	0.8246	0.9081
No log	25.8889	466	0.8147	0.6656	0.8147	0.9026
No log	26.0	468	0.8178	0.6719	0.8178	0.9043
No log	26.1111	470	0.8364	0.6616	0.8364	0.9145
No log	26.2222	472	0.8347	0.6557	0.8347	0.9136
No log	26.3333	474	0.8010	0.6883	0.8010	0.8950
No log	26.4444	476	0.7996	0.6739	0.7996	0.8942
No log	26.5556	478	0.7717	0.6673	0.7717	0.8785
No log	26.6667	480	0.7737	0.6680	0.7737	0.8796
No log	26.7778	482	0.7834	0.6756	0.7834	0.8851
No log	26.8889	484	0.7787	0.6703	0.7787	0.8824
No log	27.0	486	0.7807	0.6555	0.7807	0.8836
No log	27.1111	488	0.7867	0.6564	0.7867	0.8870
No log	27.2222	490	0.7941	0.6766	0.7941	0.8911
No log	27.3333	492	0.8006	0.6506	0.8006	0.8948
No log	27.4444	494	0.8076	0.6367	0.8076	0.8987
No log	27.5556	496	0.7969	0.6601	0.7969	0.8927
No log	27.6667	498	0.8194	0.6850	0.8194	0.9052
0.541	27.7778	500	0.8218	0.6624	0.8218	0.9065
0.541	27.8889	502	0.7854	0.6830	0.7854	0.8862
0.541	28.0	504	0.7685	0.6518	0.7685	0.8766
0.541	28.1111	506	0.7652	0.6273	0.7652	0.8747
0.541	28.2222	508	0.7459	0.6594	0.7459	0.8637
0.541	28.3333	510	0.7441	0.6864	0.7441	0.8626
0.541	28.4444	512	0.7711	0.6752	0.7711	0.8781
0.541	28.5556	514	0.7926	0.6552	0.7926	0.8903
0.541	28.6667	516	0.7838	0.6927	0.7838	0.8853
0.541	28.7778	518	0.8053	0.6617	0.8053	0.8974
0.541	28.8889	520	0.8374	0.6593	0.8374	0.9151
0.541	29.0	522	0.8772	0.6526	0.8772	0.9366
0.541	29.1111	524	0.8694	0.6623	0.8694	0.9324
0.541	29.2222	526	0.8509	0.6617	0.8509	0.9225

Framework versions

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