ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k8_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: 0.7867
• Qwk: 0.6692
• Mse: 0.7867
• Rmse: 0.8870

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0385	2	5.1387	-0.0452	5.1387	2.2669
No log	0.0769	4	3.4926	-0.0038	3.4926	1.8688
No log	0.1154	6	2.3563	-0.0850	2.3563	1.5350
No log	0.1538	8	2.2318	-0.1016	2.2318	1.4939
No log	0.1923	10	2.2862	-0.0624	2.2862	1.5120
No log	0.2308	12	1.9411	-0.0151	1.9411	1.3932
No log	0.2692	14	1.8161	0.0471	1.8161	1.3476
No log	0.3077	16	1.9320	0.1246	1.9320	1.3900
No log	0.3462	18	2.1705	0.1389	2.1705	1.4733
No log	0.3846	20	2.4562	0.1095	2.4562	1.5672
No log	0.4231	22	2.2968	0.1410	2.2968	1.5155
No log	0.4615	24	1.9695	0.1744	1.9695	1.4034
No log	0.5	26	1.7390	0.2621	1.7390	1.3187
No log	0.5385	28	1.8925	0.2440	1.8925	1.3757
No log	0.5769	30	2.1225	0.2425	2.1225	1.4569
No log	0.6154	32	1.6052	0.3450	1.6052	1.2670
No log	0.6538	34	1.3422	0.3690	1.3422	1.1585
No log	0.6923	36	1.0448	0.4775	1.0448	1.0222
No log	0.7308	38	0.9715	0.4634	0.9715	0.9857
No log	0.7692	40	0.9993	0.4517	0.9993	0.9996
No log	0.8077	42	1.0228	0.4573	1.0228	1.0113
No log	0.8462	44	1.1646	0.3937	1.1646	1.0792
No log	0.8846	46	1.4801	0.2752	1.4801	1.2166
No log	0.9231	48	1.8118	0.2561	1.8118	1.3460
No log	0.9615	50	2.0057	0.2301	2.0057	1.4162
No log	1.0	52	2.2562	0.2077	2.2562	1.5021
No log	1.0385	54	2.0900	0.2122	2.0900	1.4457
No log	1.0769	56	1.5666	0.3100	1.5666	1.2517
No log	1.1154	58	1.2755	0.3832	1.2755	1.1294
No log	1.1538	60	1.2105	0.4043	1.2105	1.1002
No log	1.1923	62	1.1892	0.4636	1.1892	1.0905
No log	1.2308	64	1.2868	0.4047	1.2868	1.1344
No log	1.2692	66	1.4071	0.3652	1.4071	1.1862
No log	1.3077	68	1.4496	0.3795	1.4496	1.2040
No log	1.3462	70	1.5844	0.3486	1.5844	1.2587
No log	1.3846	72	1.6676	0.3380	1.6676	1.2914
No log	1.4231	74	1.5114	0.4005	1.5114	1.2294
No log	1.4615	76	1.2817	0.4511	1.2817	1.1321
No log	1.5	78	1.0774	0.4666	1.0774	1.0380
No log	1.5385	80	0.9774	0.4683	0.9774	0.9886
No log	1.5769	82	0.9830	0.4329	0.9830	0.9915
No log	1.6154	84	1.0236	0.4387	1.0236	1.0117
No log	1.6538	86	1.1622	0.4441	1.1622	1.0780
No log	1.6923	88	1.4432	0.3767	1.4432	1.2013
No log	1.7308	90	1.5273	0.3680	1.5273	1.2359
No log	1.7692	92	1.4098	0.4110	1.4098	1.1873
No log	1.8077	94	1.1813	0.4176	1.1813	1.0869
No log	1.8462	96	1.0361	0.4577	1.0361	1.0179
No log	1.8846	98	1.0286	0.4345	1.0286	1.0142
No log	1.9231	100	0.9686	0.4630	0.9686	0.9842
No log	1.9615	102	0.9819	0.5069	0.9819	0.9909
No log	2.0	104	0.9968	0.5111	0.9968	0.9984
No log	2.0385	106	1.1093	0.5028	1.1093	1.0532
No log	2.0769	108	1.1744	0.4900	1.1744	1.0837
No log	2.1154	110	1.1418	0.5028	1.1418	1.0686
No log	2.1538	112	0.9381	0.5877	0.9381	0.9685
No log	2.1923	114	0.8390	0.6557	0.8390	0.9159
No log	2.2308	116	0.9010	0.5516	0.9010	0.9492
No log	2.2692	118	0.9170	0.5731	0.9170	0.9576
No log	2.3077	120	0.8329	0.6492	0.8329	0.9126
No log	2.3462	122	0.7660	0.6530	0.7660	0.8752
No log	2.3846	124	0.7629	0.6262	0.7629	0.8735
No log	2.4231	126	0.7728	0.6348	0.7728	0.8791
No log	2.4615	128	0.7827	0.6416	0.7827	0.8847
No log	2.5	130	0.8105	0.6072	0.8105	0.9003
No log	2.5385	132	0.8299	0.5983	0.8299	0.9110
No log	2.5769	134	0.8194	0.6154	0.8194	0.9052
No log	2.6154	136	0.8478	0.5927	0.8478	0.9207
No log	2.6538	138	0.8252	0.6054	0.8252	0.9084
No log	2.6923	140	0.7598	0.6727	0.7598	0.8717
No log	2.7308	142	0.7639	0.7124	0.7639	0.8740
No log	2.7692	144	0.7329	0.6818	0.7329	0.8561
No log	2.8077	146	0.7337	0.7015	0.7337	0.8566
No log	2.8462	148	0.7918	0.6756	0.7918	0.8899
No log	2.8846	150	0.8225	0.6635	0.8225	0.9069
No log	2.9231	152	0.7871	0.7011	0.7871	0.8872
No log	2.9615	154	0.7563	0.6644	0.7563	0.8697
No log	3.0	156	0.7672	0.6738	0.7672	0.8759
No log	3.0385	158	0.7600	0.6749	0.7600	0.8718
No log	3.0769	160	0.7247	0.6589	0.7247	0.8513
No log	3.1154	162	0.7554	0.6869	0.7554	0.8691
No log	3.1538	164	0.8459	0.6065	0.8459	0.9197
No log	3.1923	166	0.8508	0.6074	0.8508	0.9224
No log	3.2308	168	0.8286	0.6395	0.8286	0.9103
No log	3.2692	170	0.8284	0.6410	0.8284	0.9101
No log	3.3077	172	0.8534	0.6106	0.8534	0.9238
No log	3.3462	174	0.8825	0.6052	0.8825	0.9394
No log	3.3846	176	0.9209	0.5953	0.9209	0.9596
No log	3.4231	178	0.8885	0.5865	0.8885	0.9426
No log	3.4615	180	0.8066	0.6432	0.8066	0.8981
No log	3.5	182	0.8376	0.6431	0.8376	0.9152
No log	3.5385	184	0.8333	0.6583	0.8333	0.9128
No log	3.5769	186	0.8171	0.6807	0.8171	0.9039
No log	3.6154	188	0.8080	0.6685	0.8080	0.8989
No log	3.6538	190	0.8351	0.6301	0.8351	0.9139
No log	3.6923	192	0.8607	0.6118	0.8607	0.9278
No log	3.7308	194	0.8379	0.6564	0.8379	0.9154
No log	3.7692	196	0.8263	0.6464	0.8263	0.9090
No log	3.8077	198	0.7990	0.6577	0.7990	0.8939
No log	3.8462	200	0.7626	0.7089	0.7626	0.8733
No log	3.8846	202	0.7336	0.6831	0.7336	0.8565
No log	3.9231	204	0.7278	0.6639	0.7278	0.8531
No log	3.9615	206	0.7041	0.6730	0.7041	0.8391
No log	4.0	208	0.7019	0.7001	0.7019	0.8378
No log	4.0385	210	0.7895	0.6821	0.7895	0.8885
No log	4.0769	212	0.9209	0.6033	0.9209	0.9596
No log	4.1154	214	0.9378	0.5993	0.9378	0.9684
No log	4.1538	216	0.9109	0.6162	0.9109	0.9544
No log	4.1923	218	0.8235	0.6472	0.8235	0.9074
No log	4.2308	220	0.7465	0.7031	0.7465	0.8640
No log	4.2692	222	0.7508	0.6889	0.7508	0.8665
No log	4.3077	224	0.7976	0.6803	0.7976	0.8931
No log	4.3462	226	0.8140	0.6521	0.8140	0.9022
No log	4.3846	228	0.7892	0.6737	0.7892	0.8884
No log	4.4231	230	0.7788	0.6831	0.7788	0.8825
No log	4.4615	232	0.7856	0.6824	0.7856	0.8864
No log	4.5	234	0.8097	0.6620	0.8097	0.8998
No log	4.5385	236	0.8226	0.6556	0.8226	0.9070
No log	4.5769	238	0.8101	0.6633	0.8101	0.9000
No log	4.6154	240	0.7985	0.6757	0.7985	0.8936
No log	4.6538	242	0.7945	0.6842	0.7945	0.8914
No log	4.6923	244	0.7843	0.6778	0.7843	0.8856
No log	4.7308	246	0.7868	0.7004	0.7868	0.8870
No log	4.7692	248	0.8130	0.6449	0.8130	0.9017
No log	4.8077	250	0.8118	0.6449	0.8118	0.9010
No log	4.8462	252	0.7812	0.6692	0.7812	0.8838
No log	4.8846	254	0.7916	0.6765	0.7916	0.8897
No log	4.9231	256	0.8054	0.6739	0.8054	0.8974
No log	4.9615	258	0.7722	0.6754	0.7722	0.8788
No log	5.0	260	0.7534	0.6561	0.7534	0.8680
No log	5.0385	262	0.7621	0.6492	0.7621	0.8730
No log	5.0769	264	0.7613	0.6442	0.7613	0.8725
No log	5.1154	266	0.7901	0.6861	0.7901	0.8889
No log	5.1538	268	0.8928	0.5961	0.8928	0.9449
No log	5.1923	270	0.9757	0.5485	0.9757	0.9878
No log	5.2308	272	0.9821	0.5397	0.9821	0.9910
No log	5.2692	274	0.9144	0.5587	0.9144	0.9563
No log	5.3077	276	0.8067	0.6451	0.8067	0.8982
No log	5.3462	278	0.7493	0.6602	0.7493	0.8656
No log	5.3846	280	0.7382	0.6430	0.7382	0.8592
No log	5.4231	282	0.7443	0.6412	0.7443	0.8627
No log	5.4615	284	0.7657	0.6587	0.7657	0.8751
No log	5.5	286	0.7872	0.6656	0.7872	0.8873
No log	5.5385	288	0.8032	0.6566	0.8032	0.8962
No log	5.5769	290	0.8039	0.6725	0.8039	0.8966
No log	5.6154	292	0.8217	0.6409	0.8217	0.9065
No log	5.6538	294	0.8342	0.6218	0.8342	0.9133
No log	5.6923	296	0.8206	0.6121	0.8206	0.9059
No log	5.7308	298	0.7966	0.6668	0.7966	0.8925
No log	5.7692	300	0.7856	0.6526	0.7856	0.8864
No log	5.8077	302	0.8331	0.6197	0.8331	0.9127
No log	5.8462	304	0.9353	0.5741	0.9353	0.9671
No log	5.8846	306	0.9748	0.5424	0.9748	0.9873
No log	5.9231	308	0.9230	0.5842	0.9230	0.9608
No log	5.9615	310	0.8684	0.6054	0.8684	0.9319
No log	6.0	312	0.7961	0.5727	0.7961	0.8922
No log	6.0385	314	0.7571	0.5984	0.7571	0.8701
No log	6.0769	316	0.7319	0.6564	0.7319	0.8555
No log	6.1154	318	0.7176	0.6750	0.7176	0.8471
No log	6.1538	320	0.7230	0.6607	0.7230	0.8503
No log	6.1923	322	0.7301	0.6570	0.7301	0.8544
No log	6.2308	324	0.7445	0.6757	0.7445	0.8628
No log	6.2692	326	0.7730	0.6854	0.7730	0.8792
No log	6.3077	328	0.8303	0.6607	0.8303	0.9112
No log	6.3462	330	0.8752	0.6234	0.8752	0.9355
No log	6.3846	332	0.9060	0.6209	0.9060	0.9519
No log	6.4231	334	0.9515	0.6210	0.9515	0.9754
No log	6.4615	336	0.9656	0.6091	0.9656	0.9826
No log	6.5	338	0.9355	0.6229	0.9355	0.9672
No log	6.5385	340	0.9240	0.6229	0.9240	0.9612
No log	6.5769	342	0.9204	0.6303	0.9204	0.9594
No log	6.6154	344	0.9316	0.6303	0.9316	0.9652
No log	6.6538	346	0.8993	0.6332	0.8993	0.9483
No log	6.6923	348	0.8783	0.6266	0.8783	0.9372
No log	6.7308	350	0.8828	0.6280	0.8828	0.9396
No log	6.7692	352	0.8440	0.6475	0.8440	0.9187
No log	6.8077	354	0.7916	0.6408	0.7916	0.8897
No log	6.8462	356	0.7583	0.6644	0.7583	0.8708
No log	6.8846	358	0.7405	0.6815	0.7405	0.8605
No log	6.9231	360	0.7357	0.6815	0.7357	0.8577
No log	6.9615	362	0.7543	0.6881	0.7543	0.8685
No log	7.0	364	0.7742	0.6641	0.7742	0.8799
No log	7.0385	366	0.7955	0.6598	0.7955	0.8919
No log	7.0769	368	0.8190	0.6446	0.8190	0.9050
No log	7.1154	370	0.8129	0.6446	0.8129	0.9016
No log	7.1538	372	0.7920	0.6636	0.7920	0.8899
No log	7.1923	374	0.7607	0.6669	0.7607	0.8722
No log	7.2308	376	0.7469	0.6835	0.7469	0.8642
No log	7.2692	378	0.7475	0.6835	0.7475	0.8646
No log	7.3077	380	0.7531	0.6881	0.7531	0.8678
No log	7.3462	382	0.7587	0.6952	0.7587	0.8710
No log	7.3846	384	0.7653	0.6952	0.7653	0.8748
No log	7.4231	386	0.7819	0.6951	0.7819	0.8843
No log	7.4615	388	0.8094	0.6736	0.8094	0.8996
No log	7.5	390	0.8264	0.6674	0.8264	0.9091
No log	7.5385	392	0.8167	0.6674	0.8167	0.9037
No log	7.5769	394	0.7912	0.6828	0.7912	0.8895
No log	7.6154	396	0.7713	0.6763	0.7713	0.8782
No log	7.6538	398	0.7694	0.6763	0.7694	0.8772
No log	7.6923	400	0.7899	0.6717	0.7899	0.8888
No log	7.7308	402	0.8226	0.6499	0.8226	0.9070
No log	7.7692	404	0.8460	0.6491	0.8460	0.9198
No log	7.8077	406	0.8517	0.6483	0.8517	0.9229
No log	7.8462	408	0.8503	0.6483	0.8503	0.9221
No log	7.8846	410	0.8225	0.6783	0.8225	0.9069
No log	7.9231	412	0.7956	0.6816	0.7956	0.8920
No log	7.9615	414	0.7857	0.6977	0.7857	0.8864
No log	8.0	416	0.7935	0.6931	0.7935	0.8908
No log	8.0385	418	0.8126	0.6943	0.8126	0.9014
No log	8.0769	420	0.8201	0.6924	0.8201	0.9056
No log	8.1154	422	0.8190	0.6924	0.8190	0.9050
No log	8.1538	424	0.8024	0.6880	0.8024	0.8958
No log	8.1923	426	0.7870	0.6899	0.7870	0.8871
No log	8.2308	428	0.7790	0.6899	0.7790	0.8826
No log	8.2692	430	0.7853	0.6764	0.7853	0.8862
No log	8.3077	432	0.7896	0.6674	0.7896	0.8886
No log	8.3462	434	0.7989	0.6674	0.7989	0.8938
No log	8.3846	436	0.8007	0.6674	0.8007	0.8948
No log	8.4231	438	0.7875	0.6813	0.7875	0.8874
No log	8.4615	440	0.7763	0.6813	0.7763	0.8811
No log	8.5	442	0.7675	0.6813	0.7675	0.8761
No log	8.5385	444	0.7543	0.6747	0.7543	0.8685
No log	8.5769	446	0.7370	0.6750	0.7370	0.8585
No log	8.6154	448	0.7306	0.6702	0.7306	0.8548
No log	8.6538	450	0.7274	0.6823	0.7274	0.8529
No log	8.6923	452	0.7257	0.6823	0.7257	0.8519
No log	8.7308	454	0.7321	0.6932	0.7321	0.8556
No log	8.7692	456	0.7466	0.6816	0.7466	0.8641
No log	8.8077	458	0.7681	0.6873	0.7681	0.8764
No log	8.8462	460	0.7971	0.6674	0.7971	0.8928
No log	8.8846	462	0.8231	0.6629	0.8231	0.9073
No log	8.9231	464	0.8466	0.6348	0.8466	0.9201
No log	8.9615	466	0.8536	0.6348	0.8536	0.9239
No log	9.0	468	0.8561	0.6340	0.8561	0.9253
No log	9.0385	470	0.8545	0.6385	0.8545	0.9244
No log	9.0769	472	0.8418	0.6385	0.8418	0.9175
No log	9.1154	474	0.8213	0.6674	0.8213	0.9063
No log	9.1538	476	0.8021	0.6674	0.8021	0.8956
No log	9.1923	478	0.7798	0.6692	0.7798	0.8830
No log	9.2308	480	0.7682	0.6747	0.7682	0.8765
No log	9.2692	482	0.7592	0.6747	0.7592	0.8713
No log	9.3077	484	0.7511	0.6866	0.7511	0.8667
No log	9.3462	486	0.7493	0.6866	0.7493	0.8656
No log	9.3846	488	0.7522	0.6866	0.7522	0.8673
No log	9.4231	490	0.7520	0.6866	0.7520	0.8672
No log	9.4615	492	0.7521	0.6866	0.7521	0.8673
No log	9.5	494	0.7516	0.6866	0.7516	0.8670
No log	9.5385	496	0.7529	0.6793	0.7529	0.8677
No log	9.5769	498	0.7582	0.6747	0.7582	0.8708
0.4125	9.6154	500	0.7644	0.6625	0.7644	0.8743
0.4125	9.6538	502	0.7703	0.6692	0.7703	0.8777
0.4125	9.6923	504	0.7751	0.6692	0.7751	0.8804
0.4125	9.7308	506	0.7803	0.6692	0.7803	0.8833
0.4125	9.7692	508	0.7840	0.6692	0.7840	0.8854
0.4125	9.8077	510	0.7861	0.6730	0.7861	0.8866
0.4125	9.8462	512	0.7867	0.6692	0.7867	0.8870
0.4125	9.8846	514	0.7877	0.6692	0.7877	0.8875
0.4125	9.9231	516	0.7875	0.6692	0.7875	0.8874
0.4125	9.9615	518	0.7869	0.6692	0.7869	0.8871
0.4125	10.0	520	0.7867	0.6692	0.7867	0.8870

Framework versions

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