ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k9_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: 0.6589
• Qwk: 0.7351
• Mse: 0.6589
• Rmse: 0.8117

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	0.0435	2	5.1826	-0.0348	5.1826	2.2765
No log	0.0870	4	3.0093	0.0379	3.0093	1.7347
No log	0.1304	6	2.1685	-0.0053	2.1685	1.4726
No log	0.1739	8	1.4897	0.0903	1.4897	1.2205
No log	0.2174	10	1.3050	0.0848	1.3050	1.1424
No log	0.2609	12	1.2551	0.2067	1.2551	1.1203
No log	0.3043	14	1.2422	0.2224	1.2422	1.1145
No log	0.3478	16	1.2685	0.1718	1.2685	1.1263
No log	0.3913	18	1.2586	0.1600	1.2586	1.1219
No log	0.4348	20	1.3015	0.1551	1.3015	1.1408
No log	0.4783	22	1.1135	0.2580	1.1135	1.0552
No log	0.5217	24	1.0484	0.2010	1.0484	1.0239
No log	0.5652	26	1.1526	0.3438	1.1526	1.0736
No log	0.6087	28	1.0568	0.3568	1.0568	1.0280
No log	0.6522	30	1.0946	0.4049	1.0946	1.0463
No log	0.6957	32	1.5655	0.2999	1.5655	1.2512
No log	0.7391	34	1.9116	0.2526	1.9116	1.3826
No log	0.7826	36	2.1278	0.1944	2.1278	1.4587
No log	0.8261	38	1.8664	0.2481	1.8664	1.3661
No log	0.8696	40	1.9055	0.2318	1.9055	1.3804
No log	0.9130	42	1.7699	0.2482	1.7699	1.3304
No log	0.9565	44	2.0493	0.1891	2.0493	1.4315
No log	1.0	46	1.7898	0.2388	1.7898	1.3378
No log	1.0435	48	1.0896	0.3693	1.0896	1.0438
No log	1.0870	50	0.8718	0.5038	0.8718	0.9337
No log	1.1304	52	0.8445	0.5150	0.8445	0.9190
No log	1.1739	54	0.8782	0.4157	0.8782	0.9371
No log	1.2174	56	0.9990	0.3907	0.9990	0.9995
No log	1.2609	58	1.2425	0.3096	1.2425	1.1147
No log	1.3043	60	1.5277	0.2513	1.5277	1.2360
No log	1.3478	62	1.5846	0.2766	1.5846	1.2588
No log	1.3913	64	1.4206	0.3429	1.4206	1.1919
No log	1.4348	66	1.3003	0.4021	1.3003	1.1403
No log	1.4783	68	1.1414	0.4345	1.1414	1.0684
No log	1.5217	70	0.9021	0.5608	0.9021	0.9498
No log	1.5652	72	0.7419	0.5790	0.7419	0.8614
No log	1.6087	74	0.7328	0.5964	0.7328	0.8560
No log	1.6522	76	0.8630	0.5959	0.8630	0.9290
No log	1.6957	78	0.8269	0.6129	0.8269	0.9094
No log	1.7391	80	0.8394	0.5993	0.8394	0.9162
No log	1.7826	82	0.7756	0.6077	0.7756	0.8807
No log	1.8261	84	0.7663	0.5872	0.7663	0.8754
No log	1.8696	86	0.7654	0.5674	0.7654	0.8749
No log	1.9130	88	0.7360	0.5805	0.7360	0.8579
No log	1.9565	90	0.7395	0.6006	0.7395	0.8599
No log	2.0	92	0.8306	0.5841	0.8306	0.9114
No log	2.0435	94	0.9708	0.5385	0.9708	0.9853
No log	2.0870	96	0.9687	0.5526	0.9687	0.9842
No log	2.1304	98	0.8452	0.5628	0.8452	0.9193
No log	2.1739	100	0.7496	0.5878	0.7496	0.8658
No log	2.2174	102	0.7459	0.6150	0.7459	0.8637
No log	2.2609	104	0.7644	0.6172	0.7644	0.8743
No log	2.3043	106	0.7906	0.5934	0.7906	0.8891
No log	2.3478	108	0.7884	0.5985	0.7884	0.8879
No log	2.3913	110	0.8149	0.6067	0.8149	0.9027
No log	2.4348	112	0.7621	0.6125	0.7621	0.8730
No log	2.4783	114	0.6835	0.6263	0.6835	0.8267
No log	2.5217	116	0.6696	0.6717	0.6696	0.8183
No log	2.5652	118	0.6549	0.6861	0.6549	0.8093
No log	2.6087	120	0.6368	0.6984	0.6368	0.7980
No log	2.6522	122	0.6446	0.7112	0.6446	0.8029
No log	2.6957	124	0.6892	0.6787	0.6892	0.8302
No log	2.7391	126	0.8489	0.6510	0.8489	0.9214
No log	2.7826	128	0.9203	0.6174	0.9203	0.9593
No log	2.8261	130	0.7667	0.6462	0.7667	0.8756
No log	2.8696	132	0.6605	0.7070	0.6605	0.8127
No log	2.9130	134	0.7191	0.6930	0.7191	0.8480
No log	2.9565	136	0.7031	0.7106	0.7031	0.8385
No log	3.0	138	0.6408	0.6869	0.6408	0.8005
No log	3.0435	140	0.7594	0.6570	0.7594	0.8714
No log	3.0870	142	1.0115	0.5039	1.0115	1.0057
No log	3.1304	144	1.0686	0.5221	1.0686	1.0337
No log	3.1739	146	0.9486	0.5720	0.9486	0.9739
No log	3.2174	148	0.7692	0.6229	0.7692	0.8770
No log	3.2609	150	0.6397	0.6963	0.6397	0.7998
No log	3.3043	152	0.6176	0.7125	0.6176	0.7859
No log	3.3478	154	0.6680	0.6854	0.6680	0.8173
No log	3.3913	156	0.7303	0.7123	0.7303	0.8545
No log	3.4348	158	0.7099	0.7103	0.7099	0.8426
No log	3.4783	160	0.6447	0.7181	0.6447	0.8029
No log	3.5217	162	0.6082	0.7285	0.6082	0.7799
No log	3.5652	164	0.6233	0.7176	0.6233	0.7895
No log	3.6087	166	0.6133	0.7278	0.6133	0.7831
No log	3.6522	168	0.6038	0.7265	0.6038	0.7771
No log	3.6957	170	0.6464	0.7188	0.6464	0.8040
No log	3.7391	172	0.6852	0.6929	0.6852	0.8278
No log	3.7826	174	0.6742	0.7192	0.6742	0.8211
No log	3.8261	176	0.6290	0.7233	0.6290	0.7931
No log	3.8696	178	0.6198	0.7007	0.6198	0.7873
No log	3.9130	180	0.6719	0.7068	0.6719	0.8197
No log	3.9565	182	0.6546	0.7092	0.6546	0.8091
No log	4.0	184	0.6214	0.7391	0.6214	0.7883
No log	4.0435	186	0.6271	0.7174	0.6271	0.7919
No log	4.0870	188	0.6207	0.7192	0.6207	0.7878
No log	4.1304	190	0.6121	0.7155	0.6121	0.7824
No log	4.1739	192	0.6078	0.7198	0.6078	0.7796
No log	4.2174	194	0.6226	0.7342	0.6226	0.7891
No log	4.2609	196	0.6375	0.7048	0.6375	0.7984
No log	4.3043	198	0.6499	0.7026	0.6499	0.8061
No log	4.3478	200	0.6238	0.7002	0.6238	0.7898
No log	4.3913	202	0.5985	0.7232	0.5985	0.7736
No log	4.4348	204	0.5989	0.7242	0.5989	0.7739
No log	4.4783	206	0.6086	0.7056	0.6086	0.7801
No log	4.5217	208	0.6264	0.7150	0.6264	0.7914
No log	4.5652	210	0.6411	0.7184	0.6411	0.8007
No log	4.6087	212	0.7421	0.7226	0.7421	0.8614
No log	4.6522	214	0.8321	0.6799	0.8321	0.9122
No log	4.6957	216	0.7720	0.6974	0.7720	0.8786
No log	4.7391	218	0.6704	0.7188	0.6704	0.8188
No log	4.7826	220	0.6162	0.7242	0.6162	0.7850
No log	4.8261	222	0.5968	0.7413	0.5968	0.7726
No log	4.8696	224	0.6136	0.7365	0.6136	0.7833
No log	4.9130	226	0.6165	0.7224	0.6165	0.7852
No log	4.9565	228	0.6320	0.7195	0.6320	0.7950
No log	5.0	230	0.6241	0.7129	0.6241	0.7900
No log	5.0435	232	0.6101	0.7295	0.6101	0.7811
No log	5.0870	234	0.6032	0.7337	0.6032	0.7767
No log	5.1304	236	0.6106	0.7279	0.6106	0.7814
No log	5.1739	238	0.6305	0.7462	0.6305	0.7940
No log	5.2174	240	0.6478	0.7365	0.6478	0.8048
No log	5.2609	242	0.6364	0.7189	0.6364	0.7978
No log	5.3043	244	0.6620	0.7075	0.6620	0.8137
No log	5.3478	246	0.7124	0.7150	0.7124	0.8441
No log	5.3913	248	0.6973	0.7002	0.6973	0.8350
No log	5.4348	250	0.6572	0.7055	0.6572	0.8107
No log	5.4783	252	0.6342	0.7024	0.6342	0.7964
No log	5.5217	254	0.6129	0.7152	0.6129	0.7829
No log	5.5652	256	0.6011	0.7050	0.6011	0.7753
No log	5.6087	258	0.6005	0.7073	0.6005	0.7749
No log	5.6522	260	0.6336	0.6856	0.6336	0.7960
No log	5.6957	262	0.6814	0.6605	0.6814	0.8255
No log	5.7391	264	0.6563	0.6507	0.6563	0.8101
No log	5.7826	266	0.6175	0.6956	0.6175	0.7858
No log	5.8261	268	0.5904	0.7091	0.5904	0.7684
No log	5.8696	270	0.5770	0.7208	0.5770	0.7596
No log	5.9130	272	0.5882	0.7166	0.5882	0.7669
No log	5.9565	274	0.6279	0.7295	0.6279	0.7924
No log	6.0	276	0.6739	0.7281	0.6739	0.8209
No log	6.0435	278	0.6948	0.7251	0.6948	0.8335
No log	6.0870	280	0.7457	0.7218	0.7457	0.8635
No log	6.1304	282	0.8306	0.6619	0.8306	0.9114
No log	6.1739	284	0.9032	0.6456	0.9032	0.9504
No log	6.2174	286	0.8705	0.6346	0.8705	0.9330
No log	6.2609	288	0.7813	0.6570	0.7813	0.8839
No log	6.3043	290	0.7012	0.6965	0.7012	0.8374
No log	6.3478	292	0.6416	0.7331	0.6416	0.8010
No log	6.3913	294	0.6386	0.7257	0.6386	0.7991
No log	6.4348	296	0.6320	0.7289	0.6320	0.7950
No log	6.4783	298	0.6294	0.7375	0.6294	0.7933
No log	6.5217	300	0.6314	0.7375	0.6314	0.7946
No log	6.5652	302	0.6193	0.7240	0.6193	0.7870
No log	6.6087	304	0.6232	0.7347	0.6232	0.7894
No log	6.6522	306	0.6280	0.7292	0.6280	0.7924
No log	6.6957	308	0.6483	0.7270	0.6483	0.8052
No log	6.7391	310	0.6575	0.7084	0.6575	0.8109
No log	6.7826	312	0.6512	0.7402	0.6512	0.8070
No log	6.8261	314	0.6622	0.7218	0.6622	0.8137
No log	6.8696	316	0.6842	0.7131	0.6842	0.8272
No log	6.9130	318	0.7038	0.7035	0.7038	0.8389
No log	6.9565	320	0.6886	0.7035	0.6886	0.8298
No log	7.0	322	0.6915	0.7042	0.6915	0.8316
No log	7.0435	324	0.6833	0.7018	0.6833	0.8266
No log	7.0870	326	0.7051	0.6845	0.7051	0.8397
No log	7.1304	328	0.7531	0.6473	0.7531	0.8678
No log	7.1739	330	0.7585	0.6398	0.7585	0.8709
No log	7.2174	332	0.7687	0.6502	0.7687	0.8768
No log	7.2609	334	0.7255	0.6473	0.7255	0.8517
No log	7.3043	336	0.6844	0.7242	0.6844	0.8273
No log	7.3478	338	0.6564	0.7255	0.6564	0.8102
No log	7.3913	340	0.6341	0.7257	0.6341	0.7963
No log	7.4348	342	0.6362	0.7257	0.6362	0.7976
No log	7.4783	344	0.6646	0.7224	0.6646	0.8152
No log	7.5217	346	0.7336	0.6797	0.7336	0.8565
No log	7.5652	348	0.8247	0.6395	0.8247	0.9081
No log	7.6087	350	0.8565	0.6323	0.8565	0.9255
No log	7.6522	352	0.8285	0.6395	0.8285	0.9102
No log	7.6957	354	0.7862	0.6541	0.7862	0.8867
No log	7.7391	356	0.7405	0.6652	0.7405	0.8605
No log	7.7826	358	0.6943	0.6998	0.6943	0.8332
No log	7.8261	360	0.6769	0.7225	0.6769	0.8228
No log	7.8696	362	0.6728	0.7225	0.6728	0.8203
No log	7.9130	364	0.6605	0.7269	0.6605	0.8127
No log	7.9565	366	0.6529	0.7260	0.6529	0.8080
No log	8.0	368	0.6385	0.7434	0.6385	0.7991
No log	8.0435	370	0.6271	0.7298	0.6271	0.7919
No log	8.0870	372	0.6256	0.7260	0.6256	0.7910
No log	8.1304	374	0.6209	0.7282	0.6209	0.7880
No log	8.1739	376	0.6200	0.7321	0.6200	0.7874
No log	8.2174	378	0.6250	0.7231	0.6250	0.7906
No log	8.2609	380	0.6283	0.7269	0.6283	0.7926
No log	8.3043	382	0.6309	0.7285	0.6309	0.7943
No log	8.3478	384	0.6370	0.7240	0.6370	0.7981
No log	8.3913	386	0.6472	0.7279	0.6472	0.8045
No log	8.4348	388	0.6548	0.7335	0.6548	0.8092
No log	8.4783	390	0.6480	0.7279	0.6480	0.8050
No log	8.5217	392	0.6343	0.7224	0.6343	0.7964
No log	8.5652	394	0.6294	0.7337	0.6294	0.7933
No log	8.6087	396	0.6270	0.7298	0.6270	0.7919
No log	8.6522	398	0.6342	0.7337	0.6342	0.7964
No log	8.6957	400	0.6431	0.7413	0.6431	0.8020
No log	8.7391	402	0.6564	0.7341	0.6564	0.8102
No log	8.7826	404	0.6796	0.7224	0.6796	0.8244
No log	8.8261	406	0.7021	0.6936	0.7021	0.8379
No log	8.8696	408	0.7252	0.6686	0.7252	0.8516
No log	8.9130	410	0.7367	0.6662	0.7367	0.8583
No log	8.9565	412	0.7301	0.6749	0.7301	0.8545
No log	9.0	414	0.7263	0.6686	0.7263	0.8522
No log	9.0435	416	0.7152	0.6755	0.7152	0.8457
No log	9.0870	418	0.7008	0.6755	0.7008	0.8372
No log	9.1304	420	0.6934	0.6755	0.6934	0.8327
No log	9.1739	422	0.6821	0.7120	0.6821	0.8259
No log	9.2174	424	0.6743	0.7351	0.6743	0.8212
No log	9.2609	426	0.6655	0.7351	0.6655	0.8158
No log	9.3043	428	0.6609	0.7351	0.6609	0.8130
No log	9.3478	430	0.6594	0.7351	0.6594	0.8120
No log	9.3913	432	0.6562	0.7351	0.6562	0.8100
No log	9.4348	434	0.6526	0.7358	0.6526	0.8078
No log	9.4783	436	0.6462	0.7296	0.6462	0.8039
No log	9.5217	438	0.6411	0.7286	0.6411	0.8007
No log	9.5652	440	0.6407	0.7286	0.6407	0.8004
No log	9.6087	442	0.6422	0.7286	0.6422	0.8014
No log	9.6522	444	0.6417	0.7286	0.6417	0.8011
No log	9.6957	446	0.6428	0.7286	0.6428	0.8018
No log	9.7391	448	0.6453	0.7302	0.6453	0.8033
No log	9.7826	450	0.6481	0.7296	0.6481	0.8050
No log	9.8261	452	0.6511	0.7251	0.6511	0.8069
No log	9.8696	454	0.6543	0.7374	0.6543	0.8089
No log	9.9130	456	0.6569	0.7374	0.6569	0.8105
No log	9.9565	458	0.6583	0.7351	0.6583	0.8113
No log	10.0	460	0.6589	0.7351	0.6589	0.8117

Framework versions

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