ArabicNewSplits6_FineTuningAraBERT_run1_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: 0.6133
• Qwk: 0.7407
• Mse: 0.6133
• Rmse: 0.7831

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	0.0476	2	5.2713	-0.0207	5.2713	2.2959
No log	0.0952	4	3.5714	0.0421	3.5714	1.8898
No log	0.1429	6	2.5823	-0.0764	2.5823	1.6070
No log	0.1905	8	1.5770	0.0868	1.5770	1.2558
No log	0.2381	10	1.4454	0.1390	1.4454	1.2022
No log	0.2857	12	1.3163	0.3012	1.3163	1.1473
No log	0.3333	14	1.0874	0.4270	1.0874	1.0428
No log	0.3810	16	1.0749	0.4407	1.0749	1.0368
No log	0.4286	18	1.2599	0.3680	1.2599	1.1225
No log	0.4762	20	1.8611	0.2061	1.8611	1.3642
No log	0.5238	22	2.6725	0.1711	2.6725	1.6348
No log	0.5714	24	2.3578	0.2171	2.3578	1.5355
No log	0.6190	26	1.3650	0.3313	1.3650	1.1683
No log	0.6667	28	0.8807	0.4240	0.8807	0.9385
No log	0.7143	30	0.8639	0.3497	0.8639	0.9295
No log	0.7619	32	0.8712	0.4055	0.8712	0.9334
No log	0.8095	34	0.8425	0.4262	0.8425	0.9179
No log	0.8571	36	1.1426	0.4533	1.1426	1.0689
No log	0.9048	38	2.0424	0.2816	2.0424	1.4291
No log	0.9524	40	2.3622	0.2323	2.3622	1.5369
No log	1.0	42	1.9053	0.3004	1.9053	1.3803
No log	1.0476	44	1.2420	0.4176	1.2420	1.1145
No log	1.0952	46	0.9624	0.5035	0.9624	0.9810
No log	1.1429	48	0.9453	0.5080	0.9453	0.9722
No log	1.1905	50	1.1317	0.4123	1.1317	1.0638
No log	1.2381	52	1.4247	0.2719	1.4247	1.1936
No log	1.2857	54	1.6310	0.3019	1.6310	1.2771
No log	1.3333	56	1.6660	0.2984	1.6660	1.2907
No log	1.3810	58	1.3654	0.3746	1.3654	1.1685
No log	1.4286	60	0.8795	0.5938	0.8795	0.9378
No log	1.4762	62	0.7171	0.6309	0.7171	0.8468
No log	1.5238	64	0.6654	0.6147	0.6654	0.8157
No log	1.5714	66	0.6714	0.6407	0.6714	0.8194
No log	1.6190	68	0.6589	0.6524	0.6589	0.8117
No log	1.6667	70	0.7549	0.6408	0.7549	0.8689
No log	1.7143	72	0.9385	0.5702	0.9385	0.9688
No log	1.7619	74	0.9792	0.5865	0.9792	0.9895
No log	1.8095	76	0.8311	0.6305	0.8311	0.9116
No log	1.8571	78	0.7320	0.6725	0.7320	0.8555
No log	1.9048	80	0.6727	0.7032	0.6727	0.8202
No log	1.9524	82	0.5851	0.7425	0.5851	0.7649
No log	2.0	84	0.5824	0.7431	0.5824	0.7632
No log	2.0476	86	0.6025	0.6846	0.6025	0.7762
No log	2.0952	88	0.7209	0.6315	0.7209	0.8491
No log	2.1429	90	0.9678	0.5907	0.9678	0.9838
No log	2.1905	92	0.9953	0.5824	0.9953	0.9976
No log	2.2381	94	0.7881	0.6099	0.7881	0.8878
No log	2.2857	96	0.6881	0.6093	0.6881	0.8295
No log	2.3333	98	0.7113	0.4886	0.7113	0.8434
No log	2.3810	100	0.7414	0.5202	0.7414	0.8610
No log	2.4286	102	0.6973	0.5925	0.6973	0.8351
No log	2.4762	104	0.6373	0.5997	0.6373	0.7983
No log	2.5238	106	0.6976	0.6263	0.6976	0.8352
No log	2.5714	108	0.8219	0.6201	0.8219	0.9066
No log	2.6190	110	0.8430	0.5987	0.8430	0.9181
No log	2.6667	112	0.7046	0.6474	0.7046	0.8394
No log	2.7143	114	0.6386	0.6938	0.6386	0.7991
No log	2.7619	116	0.7802	0.6787	0.7802	0.8833
No log	2.8095	118	0.9054	0.6024	0.9054	0.9515
No log	2.8571	120	0.8989	0.5896	0.8989	0.9481
No log	2.9048	122	0.7688	0.6572	0.7688	0.8768
No log	2.9524	124	0.6630	0.6542	0.6630	0.8142
No log	3.0	126	0.6360	0.6817	0.6360	0.7975
No log	3.0476	128	0.7368	0.6418	0.7368	0.8584
No log	3.0952	130	0.7528	0.6420	0.7528	0.8677
No log	3.1429	132	0.7025	0.6535	0.7025	0.8381
No log	3.1905	134	0.6424	0.6648	0.6424	0.8015
No log	3.2381	136	0.5949	0.7076	0.5949	0.7713
No log	3.2857	138	0.5907	0.6795	0.5907	0.7686
No log	3.3333	140	0.5924	0.6870	0.5924	0.7697
No log	3.3810	142	0.5942	0.7089	0.5942	0.7708
No log	3.4286	144	0.5925	0.6889	0.5925	0.7697
No log	3.4762	146	0.5829	0.7089	0.5829	0.7635
No log	3.5238	148	0.5747	0.7354	0.5747	0.7581
No log	3.5714	150	0.6170	0.7182	0.6170	0.7855
No log	3.6190	152	0.6453	0.6883	0.6453	0.8033
No log	3.6667	154	0.7045	0.6530	0.7045	0.8393
No log	3.7143	156	0.7608	0.6465	0.7608	0.8722
No log	3.7619	158	0.6780	0.7051	0.6780	0.8234
No log	3.8095	160	0.6702	0.7051	0.6702	0.8186
No log	3.8571	162	0.7835	0.6392	0.7835	0.8851
No log	3.9048	164	0.8199	0.6157	0.8199	0.9055
No log	3.9524	166	0.6975	0.6397	0.6975	0.8352
No log	4.0	168	0.6028	0.7302	0.6028	0.7764
No log	4.0476	170	0.6041	0.7555	0.6041	0.7772
No log	4.0952	172	0.6029	0.7327	0.6029	0.7764
No log	4.1429	174	0.6077	0.6858	0.6077	0.7795
No log	4.1905	176	0.6872	0.6482	0.6872	0.8290
No log	4.2381	178	0.7379	0.6291	0.7379	0.8590
No log	4.2857	180	0.6761	0.6592	0.6761	0.8222
No log	4.3333	182	0.5902	0.7538	0.5902	0.7682
No log	4.3810	184	0.6029	0.7311	0.6029	0.7765
No log	4.4286	186	0.6784	0.7102	0.6784	0.8236
No log	4.4762	188	0.6705	0.7247	0.6705	0.8188
No log	4.5238	190	0.6075	0.7560	0.6075	0.7794
No log	4.5714	192	0.5919	0.7649	0.5919	0.7694
No log	4.6190	194	0.5869	0.7448	0.5869	0.7661
No log	4.6667	196	0.5837	0.7386	0.5837	0.7640
No log	4.7143	198	0.6102	0.7043	0.6102	0.7811
No log	4.7619	200	0.6254	0.7050	0.6254	0.7908
No log	4.8095	202	0.6078	0.7343	0.6078	0.7796
No log	4.8571	204	0.5977	0.7485	0.5977	0.7731
No log	4.9048	206	0.5976	0.7570	0.5976	0.7730
No log	4.9524	208	0.6060	0.7631	0.6060	0.7784
No log	5.0	210	0.6072	0.7539	0.6072	0.7792
No log	5.0476	212	0.6247	0.7233	0.6247	0.7904
No log	5.0952	214	0.6761	0.6926	0.6761	0.8223
No log	5.1429	216	0.6705	0.6735	0.6705	0.8188
No log	5.1905	218	0.6376	0.6819	0.6376	0.7985
No log	5.2381	220	0.5931	0.7255	0.5931	0.7701
No log	5.2857	222	0.5911	0.7322	0.5911	0.7688
No log	5.3333	224	0.6003	0.7559	0.6003	0.7748
No log	5.3810	226	0.6038	0.7405	0.6038	0.7771
No log	5.4286	228	0.6051	0.7437	0.6051	0.7779
No log	5.4762	230	0.6058	0.7484	0.6058	0.7783
No log	5.5238	232	0.6121	0.7387	0.6121	0.7824
No log	5.5714	234	0.6138	0.7555	0.6138	0.7835
No log	5.6190	236	0.6330	0.7165	0.6330	0.7956
No log	5.6667	238	0.6694	0.7276	0.6694	0.8182
No log	5.7143	240	0.6677	0.7292	0.6677	0.8171
No log	5.7619	242	0.6494	0.7334	0.6494	0.8058
No log	5.8095	244	0.6069	0.7353	0.6069	0.7790
No log	5.8571	246	0.5995	0.7318	0.5995	0.7743
No log	5.9048	248	0.6548	0.6525	0.6548	0.8092
No log	5.9524	250	0.6815	0.6442	0.6815	0.8255
No log	6.0	252	0.6543	0.6678	0.6543	0.8089
No log	6.0476	254	0.6163	0.7181	0.6163	0.7850
No log	6.0952	256	0.6378	0.7352	0.6378	0.7986
No log	6.1429	258	0.6759	0.7356	0.6759	0.8221
No log	6.1905	260	0.7092	0.6990	0.7092	0.8421
No log	6.2381	262	0.6974	0.7109	0.6974	0.8351
No log	6.2857	264	0.6880	0.7329	0.6880	0.8295
No log	6.3333	266	0.6709	0.7319	0.6709	0.8191
No log	6.3810	268	0.6508	0.7368	0.6508	0.8067
No log	6.4286	270	0.6389	0.7108	0.6389	0.7993
No log	6.4762	272	0.6407	0.6917	0.6407	0.8005
No log	6.5238	274	0.6437	0.6869	0.6437	0.8023
No log	6.5714	276	0.6450	0.6917	0.6450	0.8031
No log	6.6190	278	0.6400	0.6917	0.6400	0.8000
No log	6.6667	280	0.6345	0.6821	0.6345	0.7965
No log	6.7143	282	0.6330	0.6889	0.6330	0.7956
No log	6.7619	284	0.6306	0.6923	0.6306	0.7941
No log	6.8095	286	0.6305	0.6923	0.6305	0.7941
No log	6.8571	288	0.6346	0.6985	0.6346	0.7966
No log	6.9048	290	0.6707	0.6896	0.6707	0.8189
No log	6.9524	292	0.6834	0.6543	0.6834	0.8267
No log	7.0	294	0.6608	0.6896	0.6608	0.8129
No log	7.0476	296	0.6227	0.7094	0.6227	0.7891
No log	7.0952	298	0.6169	0.7393	0.6169	0.7854
No log	7.1429	300	0.6246	0.7434	0.6246	0.7903
No log	7.1905	302	0.6172	0.7477	0.6172	0.7856
No log	7.2381	304	0.6078	0.7393	0.6078	0.7796
No log	7.2857	306	0.6049	0.7496	0.6049	0.7778
No log	7.3333	308	0.6067	0.7481	0.6067	0.7789
No log	7.3810	310	0.6075	0.7564	0.6075	0.7794
No log	7.4286	312	0.6072	0.7513	0.6072	0.7792
No log	7.4762	314	0.6092	0.7488	0.6092	0.7805
No log	7.5238	316	0.6127	0.7497	0.6127	0.7827
No log	7.5714	318	0.6096	0.7569	0.6096	0.7808
No log	7.6190	320	0.6043	0.7622	0.6043	0.7773
No log	7.6667	322	0.6023	0.7564	0.6023	0.7761
No log	7.7143	324	0.6030	0.7509	0.6030	0.7765
No log	7.7619	326	0.6128	0.7480	0.6128	0.7828
No log	7.8095	328	0.6198	0.7480	0.6198	0.7873
No log	7.8571	330	0.6174	0.7447	0.6174	0.7857
No log	7.9048	332	0.6199	0.7709	0.6199	0.7873
No log	7.9524	334	0.6263	0.7405	0.6263	0.7914
No log	8.0	336	0.6353	0.7062	0.6353	0.7971
No log	8.0476	338	0.6431	0.7062	0.6431	0.8019
No log	8.0952	340	0.6433	0.7069	0.6433	0.8021
No log	8.1429	342	0.6337	0.7062	0.6337	0.7961
No log	8.1905	344	0.6240	0.7534	0.6240	0.7899
No log	8.2381	346	0.6224	0.7387	0.6224	0.7889
No log	8.2857	348	0.6237	0.7441	0.6237	0.7897
No log	8.3333	350	0.6297	0.7436	0.6297	0.7936
No log	8.3810	352	0.6255	0.7418	0.6255	0.7909
No log	8.4286	354	0.6155	0.7473	0.6155	0.7845
No log	8.4762	356	0.6109	0.7647	0.6109	0.7816
No log	8.5238	358	0.6103	0.7548	0.6103	0.7812
No log	8.5714	360	0.6101	0.7548	0.6101	0.7811
No log	8.6190	362	0.6091	0.7517	0.6091	0.7805
No log	8.6667	364	0.6092	0.7517	0.6092	0.7805
No log	8.7143	366	0.6131	0.7462	0.6131	0.7830
No log	8.7619	368	0.6145	0.7462	0.6145	0.7839
No log	8.8095	370	0.6104	0.7529	0.6104	0.7813
No log	8.8571	372	0.6077	0.7548	0.6077	0.7796
No log	8.9048	374	0.6087	0.7459	0.6087	0.7802
No log	8.9524	376	0.6060	0.7503	0.6060	0.7785
No log	9.0	378	0.6053	0.7503	0.6053	0.7780
No log	9.0476	380	0.6060	0.7485	0.6060	0.7785
No log	9.0952	382	0.6087	0.7462	0.6087	0.7802
No log	9.1429	384	0.6123	0.7462	0.6123	0.7825
No log	9.1905	386	0.6128	0.7462	0.6128	0.7828
No log	9.2381	388	0.6137	0.7445	0.6137	0.7834
No log	9.2857	390	0.6127	0.7332	0.6127	0.7828
No log	9.3333	392	0.6129	0.7236	0.6129	0.7829
No log	9.3810	394	0.6131	0.7222	0.6131	0.7830
No log	9.4286	396	0.6127	0.7349	0.6127	0.7827
No log	9.4762	398	0.6121	0.7392	0.6121	0.7824
No log	9.5238	400	0.6122	0.7392	0.6122	0.7824
No log	9.5714	402	0.6121	0.7392	0.6121	0.7824
No log	9.6190	404	0.6121	0.7307	0.6121	0.7824
No log	9.6667	406	0.6121	0.7264	0.6121	0.7824
No log	9.7143	408	0.6119	0.7279	0.6119	0.7822
No log	9.7619	410	0.6116	0.7430	0.6116	0.7821
No log	9.8095	412	0.6120	0.7430	0.6120	0.7823
No log	9.8571	414	0.6124	0.7430	0.6124	0.7826
No log	9.9048	416	0.6131	0.7407	0.6131	0.7830
No log	9.9524	418	0.6132	0.7407	0.6132	0.7831
No log	10.0	420	0.6133	0.7407	0.6133	0.7831

Framework versions

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