ArabicNewSplits7_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: 0.5893
• Qwk: 0.7586
• Mse: 0.5893
• Rmse: 0.7676

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	0.0526	2	6.7183	0.0308	6.7183	2.5920
No log	0.1053	4	4.4910	0.0769	4.4910	2.1192
No log	0.1579	6	2.9818	0.0755	2.9818	1.7268
No log	0.2105	8	2.1320	0.1667	2.1320	1.4601
No log	0.2632	10	1.9275	0.2276	1.9275	1.3883
No log	0.3158	12	1.6295	0.1524	1.6295	1.2765
No log	0.3684	14	1.7337	0.1165	1.7337	1.3167
No log	0.4211	16	2.0118	0.1538	2.0118	1.4184
No log	0.4737	18	2.3278	-0.1311	2.3278	1.5257
No log	0.5263	20	2.3231	-0.1240	2.3231	1.5242
No log	0.5789	22	2.3805	-0.0438	2.3805	1.5429
No log	0.6316	24	2.3232	-0.0584	2.3232	1.5242
No log	0.6842	26	2.1576	0.0672	2.1576	1.4689
No log	0.7368	28	2.0893	0.1391	2.0893	1.4455
No log	0.7895	30	1.9538	0.1622	1.9538	1.3978
No log	0.8421	32	1.9058	0.2087	1.9058	1.3805
No log	0.8947	34	1.9260	0.3226	1.9260	1.3878
No log	0.9474	36	1.9703	0.3053	1.9703	1.4037
No log	1.0	38	1.9111	0.3182	1.9111	1.3824
No log	1.0526	40	1.6929	0.3387	1.6929	1.3011
No log	1.1053	42	1.4474	0.2321	1.4474	1.2031
No log	1.1579	44	1.5634	0.1905	1.5634	1.2504
No log	1.2105	46	1.8872	0.1154	1.8872	1.3738
No log	1.2632	48	1.9241	0.0741	1.9241	1.3871
No log	1.3158	50	1.6497	0.1887	1.6497	1.2844
No log	1.3684	52	1.4681	0.2523	1.4681	1.2116
No log	1.4211	54	1.4327	0.4426	1.4327	1.1970
No log	1.4737	56	1.3152	0.4034	1.3152	1.1468
No log	1.5263	58	1.1805	0.4237	1.1805	1.0865
No log	1.5789	60	1.1025	0.4138	1.1025	1.0500
No log	1.6316	62	1.1199	0.4918	1.1199	1.0583
No log	1.6842	64	1.1655	0.5625	1.1655	1.0796
No log	1.7368	66	1.0034	0.5041	1.0034	1.0017
No log	1.7895	68	1.0261	0.5410	1.0261	1.0130
No log	1.8421	70	1.4298	0.4274	1.4298	1.1957
No log	1.8947	72	1.3500	0.4878	1.3500	1.1619
No log	1.9474	74	1.0744	0.6047	1.0744	1.0365
No log	2.0	76	0.9750	0.56	0.9750	0.9874
No log	2.0526	78	1.0426	0.5528	1.0426	1.0211
No log	2.1053	80	1.0255	0.5124	1.0255	1.0127
No log	2.1579	82	1.0535	0.5781	1.0535	1.0264
No log	2.2105	84	1.1496	0.5649	1.1496	1.0722
No log	2.2632	86	1.1099	0.5970	1.1099	1.0535
No log	2.3158	88	0.8840	0.6212	0.8840	0.9402
No log	2.3684	90	0.7405	0.6866	0.7405	0.8605
No log	2.4211	92	0.6767	0.7397	0.6767	0.8226
No log	2.4737	94	0.6694	0.7586	0.6694	0.8182
No log	2.5263	96	0.6298	0.7534	0.6298	0.7936
No log	2.5789	98	0.8204	0.6853	0.8204	0.9058
No log	2.6316	100	1.1912	0.5037	1.1912	1.0914
No log	2.6842	102	1.1953	0.5139	1.1953	1.0933
No log	2.7368	104	0.8412	0.6759	0.8412	0.9171
No log	2.7895	106	0.5116	0.8133	0.5116	0.7152
No log	2.8421	108	0.5269	0.7552	0.5269	0.7259
No log	2.8947	110	0.6204	0.7568	0.6204	0.7877
No log	2.9474	112	1.1692	0.5455	1.1692	1.0813
No log	3.0	114	1.4233	0.4444	1.4233	1.1930
No log	3.0526	116	1.2554	0.4925	1.2554	1.1204
No log	3.1053	118	0.9357	0.6618	0.9357	0.9673
No log	3.1579	120	0.7960	0.6901	0.7960	0.8922
No log	3.2105	122	0.7475	0.7092	0.7475	0.8646
No log	3.2632	124	0.7405	0.7	0.7405	0.8605
No log	3.3158	126	0.7416	0.7092	0.7416	0.8611
No log	3.3684	128	0.7034	0.7042	0.7034	0.8387
No log	3.4211	130	0.6658	0.7733	0.6658	0.8160
No log	3.4737	132	0.6794	0.7368	0.6794	0.8243
No log	3.5263	134	0.7144	0.7152	0.7144	0.8452
No log	3.5789	136	0.7999	0.7027	0.7999	0.8944
No log	3.6316	138	0.8455	0.7027	0.8455	0.9195
No log	3.6842	140	0.8761	0.6980	0.8761	0.9360
No log	3.7368	142	0.9485	0.6447	0.9485	0.9739
No log	3.7895	144	0.9046	0.6755	0.9046	0.9511
No log	3.8421	146	0.9335	0.6755	0.9335	0.9662
No log	3.8947	148	0.8809	0.6933	0.8809	0.9385
No log	3.9474	150	0.7465	0.7417	0.7465	0.8640
No log	4.0	152	0.6538	0.7632	0.6538	0.8086
No log	4.0526	154	0.5729	0.8258	0.5729	0.7569
No log	4.1053	156	0.6172	0.8052	0.6172	0.7856
No log	4.1579	158	0.5800	0.8153	0.5800	0.7616
No log	4.2105	160	0.5946	0.8079	0.5946	0.7711
No log	4.2632	162	0.7757	0.6759	0.7757	0.8807
No log	4.3158	164	0.8057	0.6575	0.8057	0.8976
No log	4.3684	166	0.7268	0.7114	0.7268	0.8525
No log	4.4211	168	0.6952	0.8	0.6952	0.8338
No log	4.4737	170	0.7128	0.7703	0.7128	0.8443
No log	4.5263	172	0.8439	0.6806	0.8439	0.9186
No log	4.5789	174	1.0026	0.6154	1.0026	1.0013
No log	4.6316	176	0.9909	0.6241	0.9909	0.9954
No log	4.6842	178	0.8743	0.6761	0.8743	0.9350
No log	4.7368	180	0.7486	0.7347	0.7486	0.8652
No log	4.7895	182	0.7096	0.7651	0.7096	0.8424
No log	4.8421	184	0.7118	0.7651	0.7118	0.8437
No log	4.8947	186	0.7995	0.7383	0.7995	0.8941
No log	4.9474	188	1.0029	0.5972	1.0029	1.0014
No log	5.0	190	1.0410	0.5972	1.0410	1.0203
No log	5.0526	192	0.9043	0.6522	0.9043	0.9509
No log	5.1053	194	0.7775	0.7429	0.7775	0.8818
No log	5.1579	196	0.7513	0.7222	0.7513	0.8668
No log	5.2105	198	0.6895	0.7703	0.6895	0.8304
No log	5.2632	200	0.6568	0.7785	0.6568	0.8104
No log	5.3158	202	0.6529	0.7867	0.6529	0.8080
No log	5.3684	204	0.6615	0.7785	0.6615	0.8133
No log	5.4211	206	0.6871	0.7838	0.6871	0.8289
No log	5.4737	208	0.6894	0.7838	0.6894	0.8303
No log	5.5263	210	0.6860	0.7568	0.6860	0.8282
No log	5.5789	212	0.7313	0.7632	0.7313	0.8551
No log	5.6316	214	0.7900	0.7211	0.7900	0.8888
No log	5.6842	216	0.8276	0.6667	0.8276	0.9097
No log	5.7368	218	0.8061	0.7101	0.8061	0.8978
No log	5.7895	220	0.7270	0.7101	0.7270	0.8526
No log	5.8421	222	0.6889	0.7361	0.6889	0.8300
No log	5.8947	224	0.7233	0.7324	0.7233	0.8505
No log	5.9474	226	0.8559	0.6667	0.8559	0.9251
No log	6.0	228	0.8738	0.6667	0.8738	0.9348
No log	6.0526	230	0.8234	0.6950	0.8234	0.9074
No log	6.1053	232	0.7010	0.7123	0.7010	0.8373
No log	6.1579	234	0.6801	0.7260	0.6801	0.8247
No log	6.2105	236	0.7102	0.7568	0.7102	0.8427
No log	6.2632	238	0.7200	0.7347	0.7200	0.8485
No log	6.3158	240	0.7470	0.7260	0.7470	0.8643
No log	6.3684	242	0.7259	0.7568	0.7259	0.8520
No log	6.4211	244	0.7074	0.7467	0.7074	0.8411
No log	6.4737	246	0.7069	0.7568	0.7069	0.8407
No log	6.5263	248	0.7168	0.7432	0.7168	0.8466
No log	6.5789	250	0.7238	0.7310	0.7238	0.8508
No log	6.6316	252	0.6824	0.7568	0.6824	0.8261
No log	6.6842	254	0.6645	0.7532	0.6645	0.8151
No log	6.7368	256	0.7296	0.7407	0.7296	0.8542
No log	6.7895	258	0.7476	0.7515	0.7476	0.8646
No log	6.8421	260	0.7248	0.7296	0.7248	0.8514
No log	6.8947	262	0.6686	0.7613	0.6686	0.8177
No log	6.9474	264	0.6030	0.76	0.6030	0.7765
No log	7.0	266	0.5928	0.8133	0.5928	0.7699
No log	7.0526	268	0.6451	0.7534	0.6451	0.8032
No log	7.1053	270	0.6604	0.76	0.6604	0.8127
No log	7.1579	272	0.6331	0.76	0.6331	0.7957
No log	7.2105	274	0.6456	0.7613	0.6456	0.8035
No log	7.2632	276	0.6624	0.7952	0.6624	0.8139
No log	7.3158	278	0.6237	0.8144	0.6237	0.7898
No log	7.3684	280	0.5184	0.8280	0.5184	0.7200
No log	7.4211	282	0.4798	0.8182	0.4798	0.6927
No log	7.4737	284	0.5081	0.8105	0.5081	0.7128
No log	7.5263	286	0.5514	0.8182	0.5514	0.7426
No log	7.5789	288	0.6315	0.7517	0.6315	0.7947
No log	7.6316	290	0.6702	0.7273	0.6702	0.8187
No log	7.6842	292	0.6046	0.7815	0.6046	0.7776
No log	7.7368	294	0.5542	0.8026	0.5542	0.7445
No log	7.7895	296	0.5623	0.8026	0.5623	0.7499
No log	7.8421	298	0.6107	0.7922	0.6107	0.7814
No log	7.8947	300	0.6983	0.7582	0.6983	0.8356
No log	7.9474	302	0.6619	0.7517	0.6619	0.8136
No log	8.0	304	0.6685	0.7517	0.6685	0.8176
No log	8.0526	306	0.6637	0.7733	0.6637	0.8147
No log	8.1053	308	0.6430	0.8133	0.6430	0.8019
No log	8.1579	310	0.6446	0.7919	0.6446	0.8029
No log	8.2105	312	0.6289	0.7763	0.6289	0.7930
No log	8.2632	314	0.5883	0.8026	0.5883	0.7670
No log	8.3158	316	0.6703	0.7733	0.6703	0.8187
No log	8.3684	318	0.7149	0.7123	0.7149	0.8455
No log	8.4211	320	0.6856	0.7397	0.6856	0.8280
No log	8.4737	322	0.6167	0.7619	0.6167	0.7853
No log	8.5263	324	0.6307	0.75	0.6307	0.7941
No log	8.5789	326	0.5817	0.7973	0.5817	0.7627
No log	8.6316	328	0.5827	0.7973	0.5827	0.7634
No log	8.6842	330	0.6051	0.7815	0.6051	0.7779
No log	8.7368	332	0.6230	0.7891	0.6230	0.7893
No log	8.7895	334	0.6691	0.7808	0.6691	0.8180
No log	8.8421	336	0.7757	0.6906	0.7757	0.8807
No log	8.8947	338	0.7860	0.7123	0.7860	0.8866
No log	8.9474	340	0.7360	0.7383	0.7360	0.8579
No log	9.0	342	0.6417	0.7742	0.6417	0.8011
No log	9.0526	344	0.5793	0.7843	0.5793	0.7611
No log	9.1053	346	0.5681	0.7922	0.5681	0.7537
No log	9.1579	348	0.6054	0.7742	0.6054	0.7781
No log	9.2105	350	0.6931	0.7547	0.6931	0.8325
No log	9.2632	352	0.6761	0.7712	0.6761	0.8223
No log	9.3158	354	0.5852	0.7975	0.5852	0.7650
No log	9.3684	356	0.5590	0.8205	0.5590	0.7476
No log	9.4211	358	0.5872	0.8280	0.5872	0.7663
No log	9.4737	360	0.5812	0.8205	0.5812	0.7624
No log	9.5263	362	0.5694	0.8182	0.5694	0.7546
No log	9.5789	364	0.6145	0.7763	0.6145	0.7839
No log	9.6316	366	0.6345	0.7763	0.6345	0.7966
No log	9.6842	368	0.5940	0.7763	0.5940	0.7707
No log	9.7368	370	0.5505	0.8105	0.5505	0.7419
No log	9.7895	372	0.4991	0.8354	0.4991	0.7065
No log	9.8421	374	0.4920	0.8323	0.4920	0.7014
No log	9.8947	376	0.5385	0.8025	0.5385	0.7339
No log	9.9474	378	0.6117	0.7947	0.6117	0.7821
No log	10.0	380	0.6379	0.7947	0.6379	0.7987
No log	10.0526	382	0.6346	0.8026	0.6346	0.7966
No log	10.1053	384	0.6169	0.8235	0.6169	0.7855
No log	10.1579	386	0.6141	0.7582	0.6141	0.7837
No log	10.2105	388	0.6124	0.7613	0.6124	0.7825
No log	10.2632	390	0.5637	0.7821	0.5637	0.7508
No log	10.3158	392	0.5179	0.8125	0.5179	0.7197
No log	10.3684	394	0.5782	0.8052	0.5782	0.7604
No log	10.4211	396	0.6054	0.8025	0.6054	0.7781
No log	10.4737	398	0.6363	0.8098	0.6363	0.7977
No log	10.5263	400	0.6197	0.8025	0.6197	0.7872
No log	10.5789	402	0.5761	0.7974	0.5761	0.7590
No log	10.6316	404	0.5694	0.8079	0.5694	0.7546
No log	10.6842	406	0.5983	0.7947	0.5983	0.7735
No log	10.7368	408	0.6151	0.7778	0.6151	0.7843
No log	10.7895	410	0.6051	0.7692	0.6051	0.7779
No log	10.8421	412	0.5910	0.7724	0.5910	0.7688
No log	10.8947	414	0.5657	0.8026	0.5657	0.7521
No log	10.9474	416	0.6079	0.7682	0.6079	0.7797
No log	11.0	418	0.6433	0.7483	0.6433	0.8021
No log	11.0526	420	0.6608	0.7413	0.6608	0.8129
No log	11.1053	422	0.6409	0.7465	0.6409	0.8006
No log	11.1579	424	0.6583	0.7376	0.6583	0.8113
No log	11.2105	426	0.6499	0.7376	0.6499	0.8062
No log	11.2632	428	0.6339	0.7626	0.6339	0.7962
No log	11.3158	430	0.6319	0.7429	0.6319	0.7949
No log	11.3684	432	0.6317	0.7286	0.6317	0.7948
No log	11.4211	434	0.6209	0.7286	0.6209	0.7880
No log	11.4737	436	0.6118	0.7518	0.6118	0.7822
No log	11.5263	438	0.6320	0.7429	0.6320	0.7950
No log	11.5789	440	0.6513	0.7626	0.6513	0.8070
No log	11.6316	442	0.6588	0.7391	0.6588	0.8117
No log	11.6842	444	0.6484	0.7101	0.6484	0.8052
No log	11.7368	446	0.6736	0.75	0.6736	0.8207
No log	11.7895	448	0.6914	0.7143	0.6914	0.8315
No log	11.8421	450	0.6511	0.7143	0.6511	0.8069
No log	11.8947	452	0.5615	0.7568	0.5615	0.7493
No log	11.9474	454	0.4835	0.7867	0.4835	0.6954
No log	12.0	456	0.4514	0.8153	0.4514	0.6719
No log	12.0526	458	0.4381	0.825	0.4381	0.6619
No log	12.1053	460	0.4673	0.8364	0.4673	0.6836
No log	12.1579	462	0.5140	0.8075	0.5140	0.7169
No log	12.2105	464	0.5377	0.7871	0.5377	0.7333
No log	12.2632	466	0.5606	0.7785	0.5606	0.7487
No log	12.3158	468	0.5823	0.7974	0.5823	0.7631
No log	12.3684	470	0.6694	0.7755	0.6694	0.8182
No log	12.4211	472	0.7291	0.7333	0.7291	0.8539
No log	12.4737	474	0.6997	0.7651	0.6997	0.8365
No log	12.5263	476	0.6441	0.7550	0.6441	0.8025
No log	12.5789	478	0.6264	0.7843	0.6264	0.7914
No log	12.6316	480	0.6248	0.7871	0.6248	0.7905
No log	12.6842	482	0.6041	0.7683	0.6041	0.7772
No log	12.7368	484	0.5885	0.7758	0.5885	0.7672
No log	12.7895	486	0.5988	0.7805	0.5988	0.7738
No log	12.8421	488	0.5901	0.7692	0.5901	0.7682
No log	12.8947	490	0.6125	0.7733	0.6125	0.7826
No log	12.9474	492	0.6391	0.7448	0.6391	0.7994
No log	13.0	494	0.6523	0.7448	0.6523	0.8077
No log	13.0526	496	0.6661	0.7534	0.6661	0.8161
No log	13.1053	498	0.6577	0.7815	0.6577	0.8110
0.4188	13.1579	500	0.6235	0.7692	0.6235	0.7896
0.4188	13.2105	502	0.5979	0.7742	0.5979	0.7733
0.4188	13.2632	504	0.5771	0.7848	0.5771	0.7596
0.4188	13.3158	506	0.5616	0.7848	0.5616	0.7494
0.4188	13.3684	508	0.5517	0.7848	0.5517	0.7428
0.4188	13.4211	510	0.5576	0.7771	0.5576	0.7467
0.4188	13.4737	512	0.5859	0.7975	0.5859	0.7654
0.4188	13.5263	514	0.6430	0.7898	0.6430	0.8019
0.4188	13.5789	516	0.6873	0.7771	0.6873	0.8290
0.4188	13.6316	518	0.6934	0.7821	0.6934	0.8327
0.4188	13.6842	520	0.6372	0.7682	0.6372	0.7983
0.4188	13.7368	522	0.6360	0.75	0.6360	0.7975
0.4188	13.7895	524	0.6473	0.7755	0.6473	0.8046
0.4188	13.8421	526	0.6208	0.7552	0.6208	0.7879
0.4188	13.8947	528	0.5978	0.7838	0.5978	0.7732
0.4188	13.9474	530	0.5940	0.7619	0.5940	0.7707
0.4188	14.0	532	0.5944	0.7619	0.5944	0.7710
0.4188	14.0526	534	0.6083	0.76	0.6083	0.7799
0.4188	14.1053	536	0.6126	0.7582	0.6126	0.7827
0.4188	14.1579	538	0.5893	0.7586	0.5893	0.7676

Framework versions

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