ArabicNewSplits6_FineTuningAraBERTFreeze_run3_AugV5_k5_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: 0.7125
• Qwk: 0.6806
• Mse: 0.7125
• Rmse: 0.8441

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	0.1429	2	7.8577	-0.0515	7.8577	2.8032
No log	0.2857	4	5.5560	-0.0349	5.5560	2.3571
No log	0.4286	6	3.9159	0.0341	3.9159	1.9789
No log	0.5714	8	2.9540	0.0900	2.9540	1.7187
No log	0.7143	10	2.1926	0.1674	2.1926	1.4807
No log	0.8571	12	1.6822	0.1296	1.6822	1.2970
No log	1.0	14	1.3847	0.2771	1.3847	1.1767
No log	1.1429	16	1.2068	0.3744	1.2068	1.0985
No log	1.2857	18	1.1004	0.4753	1.1004	1.0490
No log	1.4286	20	0.9972	0.4542	0.9972	0.9986
No log	1.5714	22	0.9433	0.4908	0.9433	0.9713
No log	1.7143	24	0.9399	0.5096	0.9399	0.9695
No log	1.8571	26	0.9696	0.5070	0.9696	0.9847
No log	2.0	28	0.9673	0.5152	0.9673	0.9835
No log	2.1429	30	0.8704	0.5405	0.8704	0.9329
No log	2.2857	32	0.7619	0.5679	0.7619	0.8729
No log	2.4286	34	0.7421	0.5565	0.7421	0.8615
No log	2.5714	36	0.7483	0.5876	0.7483	0.8650
No log	2.7143	38	0.8430	0.6089	0.8430	0.9182
No log	2.8571	40	0.9771	0.5256	0.9771	0.9885
No log	3.0	42	1.0624	0.5153	1.0624	1.0307
No log	3.1429	44	0.9791	0.5722	0.9791	0.9895
No log	3.2857	46	0.7935	0.6393	0.7935	0.8908
No log	3.4286	48	0.7191	0.6294	0.7191	0.8480
No log	3.5714	50	0.7436	0.6321	0.7436	0.8623
No log	3.7143	52	0.8514	0.6113	0.8514	0.9227
No log	3.8571	54	0.9391	0.5725	0.9391	0.9691
No log	4.0	56	0.9783	0.5820	0.9783	0.9891
No log	4.1429	58	0.9430	0.6072	0.9430	0.9711
No log	4.2857	60	0.7927	0.6472	0.7927	0.8904
No log	4.4286	62	0.6937	0.6722	0.6937	0.8329
No log	4.5714	64	0.6885	0.6780	0.6885	0.8298
No log	4.7143	66	0.7883	0.6613	0.7883	0.8879
No log	4.8571	68	1.1261	0.5283	1.1261	1.0612
No log	5.0	70	1.3798	0.4240	1.3798	1.1746
No log	5.1429	72	1.3033	0.4665	1.3033	1.1416
No log	5.2857	74	1.0166	0.5826	1.0166	1.0082
No log	5.4286	76	0.7594	0.6807	0.7594	0.8714
No log	5.5714	78	0.6879	0.6770	0.6879	0.8294
No log	5.7143	80	0.7303	0.7009	0.7303	0.8546
No log	5.8571	82	0.8186	0.6889	0.8186	0.9047
No log	6.0	84	0.8022	0.6881	0.8022	0.8956
No log	6.1429	86	0.7856	0.6848	0.7856	0.8864
No log	6.2857	88	0.7204	0.7137	0.7204	0.8488
No log	6.4286	90	0.6482	0.7111	0.6482	0.8051
No log	6.5714	92	0.6361	0.7111	0.6361	0.7976
No log	6.7143	94	0.6533	0.7111	0.6533	0.8082
No log	6.8571	96	0.6561	0.7111	0.6561	0.8100
No log	7.0	98	0.6733	0.7004	0.6733	0.8206
No log	7.1429	100	0.7190	0.6769	0.7190	0.8479
No log	7.2857	102	0.7116	0.6722	0.7116	0.8436
No log	7.4286	104	0.7710	0.6876	0.7710	0.8780
No log	7.5714	106	0.8729	0.6477	0.8729	0.9343
No log	7.7143	108	0.8786	0.6414	0.8786	0.9373
No log	7.8571	110	0.7496	0.6680	0.7496	0.8658
No log	8.0	112	0.6691	0.6967	0.6691	0.8180
No log	8.1429	114	0.6792	0.6645	0.6792	0.8241
No log	8.2857	116	0.7825	0.6853	0.7825	0.8846
No log	8.4286	118	0.8468	0.6559	0.8468	0.9202
No log	8.5714	120	0.8508	0.6646	0.8508	0.9224
No log	8.7143	122	0.7766	0.6713	0.7766	0.8812
No log	8.8571	124	0.7113	0.6786	0.7113	0.8434
No log	9.0	126	0.7335	0.6811	0.7335	0.8565
No log	9.1429	128	0.7291	0.6770	0.7291	0.8539
No log	9.2857	130	0.6815	0.6960	0.6815	0.8255
No log	9.4286	132	0.6398	0.7231	0.6398	0.7999
No log	9.5714	134	0.6558	0.6908	0.6558	0.8098
No log	9.7143	136	0.7583	0.6814	0.7583	0.8708
No log	9.8571	138	0.8343	0.6529	0.8343	0.9134
No log	10.0	140	0.9277	0.6468	0.9277	0.9632
No log	10.1429	142	0.8407	0.6549	0.8407	0.9169
No log	10.2857	144	0.7119	0.6858	0.7119	0.8437
No log	10.4286	146	0.6824	0.7382	0.6824	0.8261
No log	10.5714	148	0.7162	0.7287	0.7162	0.8463
No log	10.7143	150	0.6812	0.7236	0.6812	0.8254
No log	10.8571	152	0.6625	0.6978	0.6625	0.8139
No log	11.0	154	0.6552	0.6927	0.6552	0.8094
No log	11.1429	156	0.6290	0.6781	0.6290	0.7931
No log	11.2857	158	0.6312	0.7314	0.6312	0.7945
No log	11.4286	160	0.6661	0.7258	0.6661	0.8162
No log	11.5714	162	0.6361	0.7500	0.6361	0.7976
No log	11.7143	164	0.6225	0.6985	0.6225	0.7890
No log	11.8571	166	0.6841	0.6909	0.6841	0.8271
No log	12.0	168	0.8008	0.6597	0.8008	0.8949
No log	12.1429	170	0.8680	0.6493	0.8680	0.9317
No log	12.2857	172	0.7785	0.6458	0.7785	0.8823
No log	12.4286	174	0.7165	0.6602	0.7165	0.8465
No log	12.5714	176	0.6721	0.6807	0.6721	0.8198
No log	12.7143	178	0.6766	0.6795	0.6766	0.8225
No log	12.8571	180	0.6983	0.6660	0.6983	0.8357
No log	13.0	182	0.7266	0.6583	0.7266	0.8524
No log	13.1429	184	0.8397	0.6301	0.8397	0.9163
No log	13.2857	186	0.8653	0.6242	0.8653	0.9302
No log	13.4286	188	0.7677	0.6307	0.7677	0.8762
No log	13.5714	190	0.7507	0.7024	0.7507	0.8664
No log	13.7143	192	0.7490	0.7082	0.7490	0.8654
No log	13.8571	194	0.7379	0.6701	0.7379	0.8590
No log	14.0	196	0.7448	0.6435	0.7448	0.8630
No log	14.1429	198	0.7375	0.6608	0.7375	0.8588
No log	14.2857	200	0.6977	0.6695	0.6977	0.8353
No log	14.4286	202	0.6815	0.7241	0.6815	0.8255
No log	14.5714	204	0.7421	0.7194	0.7421	0.8615
No log	14.7143	206	0.7193	0.6995	0.7193	0.8481
No log	14.8571	208	0.6969	0.6932	0.6969	0.8348
No log	15.0	210	0.7295	0.6647	0.7295	0.8541
No log	15.1429	212	0.7730	0.6373	0.7730	0.8792
No log	15.2857	214	0.7465	0.6354	0.7465	0.8640
No log	15.4286	216	0.7195	0.7093	0.7195	0.8483
No log	15.5714	218	0.7315	0.7114	0.7315	0.8553
No log	15.7143	220	0.7088	0.7110	0.7088	0.8419
No log	15.8571	222	0.7140	0.6975	0.7140	0.8450
No log	16.0	224	0.7274	0.6838	0.7274	0.8529
No log	16.1429	226	0.7521	0.7159	0.7521	0.8672
No log	16.2857	228	0.7781	0.7183	0.7781	0.8821
No log	16.4286	230	0.7432	0.6935	0.7432	0.8621
No log	16.5714	232	0.7476	0.6524	0.7476	0.8646
No log	16.7143	234	0.7356	0.6851	0.7356	0.8577
No log	16.8571	236	0.7373	0.6892	0.7373	0.8586
No log	17.0	238	0.8401	0.6650	0.8401	0.9166
No log	17.1429	240	0.8919	0.6466	0.8919	0.9444
No log	17.2857	242	0.8027	0.7199	0.8027	0.8959
No log	17.4286	244	0.7480	0.7065	0.7480	0.8648
No log	17.5714	246	0.7130	0.7028	0.7130	0.8444
No log	17.7143	248	0.7138	0.6957	0.7138	0.8449
No log	17.8571	250	0.6989	0.6924	0.6989	0.8360
No log	18.0	252	0.7007	0.6773	0.7007	0.8371
No log	18.1429	254	0.7064	0.6861	0.7064	0.8405
No log	18.2857	256	0.7195	0.6842	0.7195	0.8482
No log	18.4286	258	0.7351	0.6740	0.7351	0.8574
No log	18.5714	260	0.7539	0.6825	0.7539	0.8683
No log	18.7143	262	0.7607	0.6816	0.7607	0.8722
No log	18.8571	264	0.7760	0.6814	0.7760	0.8809
No log	19.0	266	0.7863	0.7077	0.7863	0.8867
No log	19.1429	268	0.7794	0.6814	0.7794	0.8829
No log	19.2857	270	0.8086	0.6595	0.8086	0.8992
No log	19.4286	272	0.8386	0.6595	0.8386	0.9158
No log	19.5714	274	0.7805	0.6583	0.7805	0.8835
No log	19.7143	276	0.7518	0.6814	0.7518	0.8670
No log	19.8571	278	0.7943	0.6984	0.7943	0.8912
No log	20.0	280	0.7835	0.7121	0.7835	0.8852
No log	20.1429	282	0.7438	0.6944	0.7438	0.8624
No log	20.2857	284	0.7196	0.6644	0.7196	0.8483
No log	20.4286	286	0.7191	0.6614	0.7191	0.8480
No log	20.5714	288	0.7096	0.6599	0.7096	0.8424
No log	20.7143	290	0.7154	0.6588	0.7154	0.8458
No log	20.8571	292	0.7289	0.6815	0.7289	0.8537
No log	21.0	294	0.7345	0.6681	0.7345	0.8570
No log	21.1429	296	0.7277	0.6683	0.7277	0.8530
No log	21.2857	298	0.7329	0.6625	0.7329	0.8561
No log	21.4286	300	0.7606	0.6689	0.7606	0.8721
No log	21.5714	302	0.7759	0.6549	0.7759	0.8809
No log	21.7143	304	0.7605	0.6687	0.7605	0.8720
No log	21.8571	306	0.7748	0.6821	0.7748	0.8802
No log	22.0	308	0.8000	0.6885	0.8000	0.8944
No log	22.1429	310	0.8344	0.6802	0.8344	0.9135
No log	22.2857	312	0.8004	0.6869	0.8004	0.8947
No log	22.4286	314	0.8041	0.6810	0.8041	0.8967
No log	22.5714	316	0.8609	0.7003	0.8609	0.9278
No log	22.7143	318	0.8942	0.6721	0.8942	0.9456
No log	22.8571	320	0.8347	0.6819	0.8347	0.9136
No log	23.0	322	0.7959	0.6634	0.7959	0.8921
No log	23.1429	324	0.7955	0.6434	0.7955	0.8919
No log	23.2857	326	0.7938	0.6666	0.7938	0.8910
No log	23.4286	328	0.8001	0.6712	0.8001	0.8945
No log	23.5714	330	0.8133	0.6661	0.8133	0.9018
No log	23.7143	332	0.8127	0.6661	0.8127	0.9015
No log	23.8571	334	0.8136	0.6731	0.8136	0.9020
No log	24.0	336	0.8669	0.6772	0.8669	0.9311
No log	24.1429	338	0.8837	0.6774	0.8837	0.9401
No log	24.2857	340	0.8054	0.6793	0.8054	0.8975
No log	24.4286	342	0.7906	0.6738	0.7906	0.8892
No log	24.5714	344	0.7799	0.6596	0.7799	0.8831
No log	24.7143	346	0.7877	0.6725	0.7877	0.8875
No log	24.8571	348	0.8139	0.6841	0.8139	0.9022
No log	25.0	350	0.8100	0.6695	0.8100	0.9000
No log	25.1429	352	0.8065	0.6646	0.8065	0.8980
No log	25.2857	354	0.8103	0.6456	0.8103	0.9002
No log	25.4286	356	0.8340	0.6347	0.8340	0.9132
No log	25.5714	358	0.8053	0.6492	0.8053	0.8974
No log	25.7143	360	0.8456	0.6895	0.8456	0.9196
No log	25.8571	362	0.9814	0.6070	0.9814	0.9907
No log	26.0	364	1.0432	0.5794	1.0432	1.0214
No log	26.1429	366	0.9597	0.6244	0.9597	0.9796
No log	26.2857	368	0.8341	0.6757	0.8341	0.9133
No log	26.4286	370	0.8121	0.6461	0.8121	0.9012
No log	26.5714	372	0.8011	0.6482	0.8011	0.8951
No log	26.7143	374	0.8409	0.6597	0.8409	0.9170
No log	26.8571	376	0.8872	0.6753	0.8872	0.9419
No log	27.0	378	0.8642	0.6760	0.8642	0.9296
No log	27.1429	380	0.7905	0.6708	0.7905	0.8891
No log	27.2857	382	0.7839	0.6260	0.7839	0.8854
No log	27.4286	384	0.7791	0.6540	0.7791	0.8827
No log	27.5714	386	0.8029	0.6717	0.8029	0.8961
No log	27.7143	388	0.9046	0.6855	0.9046	0.9511
No log	27.8571	390	0.8970	0.6911	0.8970	0.9471
No log	28.0	392	0.8454	0.6986	0.8454	0.9195
No log	28.1429	394	0.7938	0.6828	0.7938	0.8910
No log	28.2857	396	0.8368	0.6036	0.8368	0.9148
No log	28.4286	398	0.8428	0.5996	0.8428	0.9180
No log	28.5714	400	0.7739	0.6448	0.7739	0.8797
No log	28.7143	402	0.7827	0.6864	0.7827	0.8847
No log	28.8571	404	0.8797	0.6971	0.8797	0.9379
No log	29.0	406	0.8839	0.6857	0.8839	0.9401
No log	29.1429	408	0.8143	0.6820	0.8143	0.9024
No log	29.2857	410	0.7673	0.6688	0.7673	0.8760
No log	29.4286	412	0.7802	0.6501	0.7802	0.8833
No log	29.5714	414	0.7652	0.6587	0.7652	0.8748
No log	29.7143	416	0.7532	0.6835	0.7532	0.8678
No log	29.8571	418	0.7624	0.7191	0.7624	0.8731
No log	30.0	420	0.8855	0.6253	0.8855	0.9410
No log	30.1429	422	0.9705	0.5868	0.9705	0.9851
No log	30.2857	424	0.9198	0.6066	0.9198	0.9591
No log	30.4286	426	0.7830	0.6868	0.7830	0.8849
No log	30.5714	428	0.7174	0.6948	0.7174	0.8470
No log	30.7143	430	0.7444	0.6784	0.7444	0.8628
No log	30.8571	432	0.7472	0.6653	0.7472	0.8644
No log	31.0	434	0.7343	0.6993	0.7343	0.8569
No log	31.1429	436	0.7583	0.7081	0.7583	0.8708
No log	31.2857	438	0.7690	0.6981	0.7690	0.8769
No log	31.4286	440	0.7506	0.7022	0.7506	0.8664
No log	31.5714	442	0.7539	0.6751	0.7539	0.8683
No log	31.7143	444	0.7587	0.6658	0.7587	0.8710
No log	31.8571	446	0.7577	0.6769	0.7577	0.8705
No log	32.0	448	0.7725	0.6775	0.7725	0.8789
No log	32.1429	450	0.8099	0.7068	0.8099	0.9000
No log	32.2857	452	0.8285	0.6868	0.8285	0.9102
No log	32.4286	454	0.8262	0.6806	0.8262	0.9090
No log	32.5714	456	0.7796	0.6875	0.7796	0.8830
No log	32.7143	458	0.7729	0.6538	0.7729	0.8792
No log	32.8571	460	0.7855	0.6270	0.7855	0.8863
No log	33.0	462	0.7838	0.6551	0.7838	0.8853
No log	33.1429	464	0.7921	0.6512	0.7921	0.8900
No log	33.2857	466	0.8356	0.6882	0.8356	0.9141
No log	33.4286	468	0.8678	0.6850	0.8678	0.9315
No log	33.5714	470	0.8282	0.6882	0.8282	0.9100
No log	33.7143	472	0.7937	0.6239	0.7937	0.8909
No log	33.8571	474	0.8042	0.6129	0.8042	0.8968
No log	34.0	476	0.7899	0.6359	0.7899	0.8888
No log	34.1429	478	0.8002	0.6845	0.8002	0.8945
No log	34.2857	480	0.8125	0.6938	0.8125	0.9014
No log	34.4286	482	0.8039	0.6981	0.8039	0.8966
No log	34.5714	484	0.7933	0.6882	0.7933	0.8906
No log	34.7143	486	0.8145	0.6832	0.8145	0.9025
No log	34.8571	488	0.8227	0.6832	0.8227	0.9070
No log	35.0	490	0.7948	0.7024	0.7948	0.8915
No log	35.1429	492	0.7911	0.7064	0.7911	0.8894
No log	35.2857	494	0.7795	0.7033	0.7795	0.8829
No log	35.4286	496	0.8007	0.7018	0.8007	0.8948
No log	35.5714	498	0.8053	0.7018	0.8053	0.8974
0.5125	35.7143	500	0.7758	0.6871	0.7758	0.8808
0.5125	35.8571	502	0.7709	0.6486	0.7709	0.8780
0.5125	36.0	504	0.7765	0.6470	0.7765	0.8812
0.5125	36.1429	506	0.8237	0.7049	0.8237	0.9076
0.5125	36.2857	508	0.8661	0.6632	0.8661	0.9306
0.5125	36.4286	510	0.8624	0.6649	0.8624	0.9286
0.5125	36.5714	512	0.8145	0.6894	0.8145	0.9025
0.5125	36.7143	514	0.8158	0.6120	0.8158	0.9032
0.5125	36.8571	516	0.8572	0.5652	0.8572	0.9259
0.5125	37.0	518	0.8226	0.6068	0.8226	0.9070
0.5125	37.1429	520	0.7894	0.6486	0.7894	0.8885
0.5125	37.2857	522	0.8588	0.6873	0.8588	0.9267
0.5125	37.4286	524	1.0279	0.5784	1.0279	1.0138
0.5125	37.5714	526	1.0620	0.5649	1.0620	1.0305
0.5125	37.7143	528	0.9529	0.6439	0.9529	0.9761
0.5125	37.8571	530	0.7943	0.7055	0.7943	0.8912
0.5125	38.0	532	0.7332	0.6821	0.7332	0.8563
0.5125	38.1429	534	0.7369	0.6615	0.7369	0.8584
0.5125	38.2857	536	0.7371	0.6615	0.7371	0.8586
0.5125	38.4286	538	0.7473	0.6991	0.7473	0.8645
0.5125	38.5714	540	0.7968	0.7036	0.7968	0.8927
0.5125	38.7143	542	0.8079	0.7036	0.8079	0.8989
0.5125	38.8571	544	0.8374	0.6756	0.8374	0.9151
0.5125	39.0	546	0.8293	0.6832	0.8293	0.9106
0.5125	39.1429	548	0.7880	0.6981	0.7880	0.8877
0.5125	39.2857	550	0.7746	0.6908	0.7746	0.8801
0.5125	39.4286	552	0.7520	0.6845	0.7520	0.8672
0.5125	39.5714	554	0.7301	0.6671	0.7301	0.8544
0.5125	39.7143	556	0.7377	0.6625	0.7377	0.8589
0.5125	39.8571	558	0.7201	0.6621	0.7201	0.8486
0.5125	40.0	560	0.7125	0.6806	0.7125	0.8441

Framework versions

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