ArabicNewSplits5_FineTuningAraBERT_run1_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: 0.8903
• Qwk: 0.5826
• Mse: 0.8903
• Rmse: 0.9436

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	0.0606	2	5.2166	-0.0138	5.2166	2.2840
No log	0.1212	4	3.2613	0.0710	3.2613	1.8059
No log	0.1818	6	2.1905	0.0427	2.1905	1.4800
No log	0.2424	8	1.5376	0.1504	1.5376	1.2400
No log	0.3030	10	1.4516	0.1197	1.4516	1.2048
No log	0.3636	12	1.3179	0.2209	1.3179	1.1480
No log	0.4242	14	1.2852	0.2549	1.2852	1.1337
No log	0.4848	16	1.2898	0.2979	1.2898	1.1357
No log	0.5455	18	1.4806	0.1466	1.4806	1.2168
No log	0.6061	20	1.5007	0.1215	1.5007	1.2250
No log	0.6667	22	1.5892	0.1026	1.5892	1.2606
No log	0.7273	24	1.5446	0.1625	1.5446	1.2428
No log	0.7879	26	1.4007	0.2686	1.4007	1.1835
No log	0.8485	28	1.4015	0.3332	1.4015	1.1838
No log	0.9091	30	1.2115	0.3893	1.2115	1.1007
No log	0.9697	32	1.0328	0.4178	1.0328	1.0163
No log	1.0303	34	1.0294	0.4676	1.0294	1.0146
No log	1.0909	36	1.0846	0.4337	1.0846	1.0414
No log	1.1515	38	1.1566	0.4586	1.1566	1.0754
No log	1.2121	40	1.2136	0.4342	1.2136	1.1016
No log	1.2727	42	1.4292	0.3392	1.4292	1.1955
No log	1.3333	44	1.5661	0.3208	1.5661	1.2515
No log	1.3939	46	1.6473	0.3349	1.6473	1.2835
No log	1.4545	48	1.2493	0.3540	1.2493	1.1177
No log	1.5152	50	1.0140	0.4423	1.0140	1.0070
No log	1.5758	52	0.9603	0.4389	0.9603	0.9799
No log	1.6364	54	0.9540	0.4067	0.9540	0.9767
No log	1.6970	56	0.9756	0.5233	0.9756	0.9877
No log	1.7576	58	1.0211	0.4995	1.0211	1.0105
No log	1.8182	60	1.0593	0.4790	1.0593	1.0292
No log	1.8788	62	1.1793	0.4374	1.1793	1.0860
No log	1.9394	64	1.1368	0.4415	1.1368	1.0662
No log	2.0	66	1.0395	0.4694	1.0395	1.0195
No log	2.0606	68	0.9485	0.4769	0.9485	0.9739
No log	2.1212	70	0.9566	0.4423	0.9566	0.9781
No log	2.1818	72	0.9647	0.4440	0.9647	0.9822
No log	2.2424	74	1.0662	0.3369	1.0662	1.0326
No log	2.3030	76	1.1820	0.3743	1.1820	1.0872
No log	2.3636	78	1.2616	0.3285	1.2616	1.1232
No log	2.4242	80	1.2923	0.3558	1.2923	1.1368
No log	2.4848	82	1.2058	0.4057	1.2058	1.0981
No log	2.5455	84	1.0274	0.4245	1.0274	1.0136
No log	2.6061	86	0.9689	0.5346	0.9689	0.9843
No log	2.6667	88	0.9716	0.5196	0.9716	0.9857
No log	2.7273	90	1.0410	0.4567	1.0410	1.0203
No log	2.7879	92	1.0647	0.4635	1.0647	1.0319
No log	2.8485	94	1.0745	0.4639	1.0745	1.0366
No log	2.9091	96	1.1404	0.4390	1.1404	1.0679
No log	2.9697	98	1.1632	0.4416	1.1632	1.0785
No log	3.0303	100	1.0348	0.4645	1.0348	1.0173
No log	3.0909	102	0.9534	0.5369	0.9534	0.9764
No log	3.1515	104	0.8940	0.5378	0.8940	0.9455
No log	3.2121	106	0.8629	0.6157	0.8629	0.9289
No log	3.2727	108	0.8800	0.6285	0.8800	0.9381
No log	3.3333	110	0.9247	0.5546	0.9247	0.9616
No log	3.3939	112	0.9527	0.5183	0.9527	0.9761
No log	3.4545	114	0.8658	0.6149	0.8658	0.9305
No log	3.5152	116	0.7852	0.6373	0.7852	0.8861
No log	3.5758	118	0.7767	0.6152	0.7767	0.8813
No log	3.6364	120	0.7998	0.5696	0.7998	0.8943
No log	3.6970	122	0.7982	0.6336	0.7982	0.8934
No log	3.7576	124	0.7999	0.6151	0.7999	0.8944
No log	3.8182	126	0.8351	0.6350	0.8351	0.9138
No log	3.8788	128	0.8315	0.6515	0.8315	0.9119
No log	3.9394	130	0.8047	0.6322	0.8047	0.8970
No log	4.0	132	0.7857	0.6380	0.7857	0.8864
No log	4.0606	134	0.7715	0.6380	0.7715	0.8784
No log	4.1212	136	0.7630	0.6332	0.7630	0.8735
No log	4.1818	138	0.7653	0.6245	0.7653	0.8748
No log	4.2424	140	0.7700	0.6279	0.7700	0.8775
No log	4.3030	142	0.7973	0.5969	0.7973	0.8929
No log	4.3636	144	0.8336	0.6231	0.8336	0.9130
No log	4.4242	146	0.8464	0.6288	0.8464	0.9200
No log	4.4848	148	0.8042	0.6322	0.8042	0.8968
No log	4.5455	150	0.7518	0.6489	0.7518	0.8670
No log	4.6061	152	0.7487	0.6237	0.7487	0.8653
No log	4.6667	154	0.7667	0.6337	0.7667	0.8756
No log	4.7273	156	0.7965	0.6224	0.7965	0.8925
No log	4.7879	158	0.8421	0.5902	0.8421	0.9177
No log	4.8485	160	0.8621	0.5880	0.8621	0.9285
No log	4.9091	162	0.8809	0.6075	0.8809	0.9385
No log	4.9697	164	0.8805	0.5809	0.8805	0.9384
No log	5.0303	166	0.9081	0.5806	0.9081	0.9530
No log	5.0909	168	0.9285	0.5720	0.9285	0.9636
No log	5.1515	170	0.9290	0.5485	0.9290	0.9639
No log	5.2121	172	0.9397	0.5282	0.9397	0.9694
No log	5.2727	174	0.9128	0.5696	0.9128	0.9554
No log	5.3333	176	0.8574	0.5988	0.8574	0.9260
No log	5.3939	178	0.8370	0.6127	0.8370	0.9149
No log	5.4545	180	0.7928	0.6456	0.7928	0.8904
No log	5.5152	182	0.7858	0.5931	0.7858	0.8864
No log	5.5758	184	0.7816	0.5955	0.7816	0.8841
No log	5.6364	186	0.8038	0.6442	0.8038	0.8965
No log	5.6970	188	0.8496	0.5883	0.8496	0.9217
No log	5.7576	190	0.9202	0.5951	0.9202	0.9593
No log	5.8182	192	0.9820	0.5066	0.9820	0.9910
No log	5.8788	194	0.9991	0.5111	0.9991	0.9996
No log	5.9394	196	0.9572	0.5160	0.9572	0.9784
No log	6.0	198	0.8777	0.5967	0.8777	0.9369
No log	6.0606	200	0.8088	0.6030	0.8088	0.8993
No log	6.1212	202	0.7870	0.6039	0.7870	0.8871
No log	6.1818	204	0.7963	0.6254	0.7963	0.8924
No log	6.2424	206	0.8153	0.6332	0.8153	0.9029
No log	6.3030	208	0.7997	0.6388	0.7997	0.8943
No log	6.3636	210	0.8114	0.6147	0.8114	0.9008
No log	6.4242	212	0.8251	0.5942	0.8251	0.9084
No log	6.4848	214	0.8619	0.5667	0.8619	0.9284
No log	6.5455	216	0.9152	0.5836	0.9152	0.9567
No log	6.6061	218	0.9890	0.5247	0.9890	0.9945
No log	6.6667	220	1.0010	0.5280	1.0010	1.0005
No log	6.7273	222	0.9653	0.5627	0.9653	0.9825
No log	6.7879	224	0.9027	0.5804	0.9027	0.9501
No log	6.8485	226	0.8508	0.6195	0.8508	0.9224
No log	6.9091	228	0.8305	0.6074	0.8305	0.9113
No log	6.9697	230	0.8323	0.6079	0.8323	0.9123
No log	7.0303	232	0.8477	0.6200	0.8477	0.9207
No log	7.0909	234	0.8737	0.6041	0.8737	0.9347
No log	7.1515	236	0.8903	0.5974	0.8903	0.9436
No log	7.2121	238	0.8927	0.5890	0.8927	0.9448
No log	7.2727	240	0.9066	0.5863	0.9066	0.9521
No log	7.3333	242	0.9005	0.5913	0.9005	0.9490
No log	7.3939	244	0.8800	0.5945	0.8800	0.9381
No log	7.4545	246	0.8444	0.6179	0.8444	0.9189
No log	7.5152	248	0.8219	0.6308	0.8219	0.9066
No log	7.5758	250	0.8168	0.6022	0.8168	0.9038
No log	7.6364	252	0.8206	0.6229	0.8206	0.9059
No log	7.6970	254	0.8314	0.6484	0.8314	0.9118
No log	7.7576	256	0.8395	0.6484	0.8395	0.9162
No log	7.8182	258	0.8446	0.6484	0.8446	0.9190
No log	7.8788	260	0.8588	0.6215	0.8588	0.9267
No log	7.9394	262	0.8769	0.5807	0.8769	0.9364
No log	8.0	264	0.9094	0.6033	0.9094	0.9536
No log	8.0606	266	0.9459	0.5567	0.9459	0.9726
No log	8.1212	268	0.9566	0.5531	0.9566	0.9780
No log	8.1818	270	0.9505	0.5420	0.9505	0.9750
No log	8.2424	272	0.9352	0.5691	0.9352	0.9670
No log	8.3030	274	0.9254	0.5633	0.9254	0.9620
No log	8.3636	276	0.9189	0.5941	0.9189	0.9586
No log	8.4242	278	0.9245	0.5795	0.9245	0.9615
No log	8.4848	280	0.9227	0.5857	0.9227	0.9606
No log	8.5455	282	0.9098	0.5687	0.9098	0.9538
No log	8.6061	284	0.8887	0.5922	0.8887	0.9427
No log	8.6667	286	0.8659	0.5991	0.8659	0.9305
No log	8.7273	288	0.8474	0.6197	0.8474	0.9206
No log	8.7879	290	0.8287	0.6026	0.8287	0.9103
No log	8.8485	292	0.8181	0.6055	0.8181	0.9045
No log	8.9091	294	0.8169	0.6118	0.8169	0.9039
No log	8.9697	296	0.8228	0.6104	0.8228	0.9071
No log	9.0303	298	0.8322	0.6146	0.8322	0.9123
No log	9.0909	300	0.8420	0.6221	0.8420	0.9176
No log	9.1515	302	0.8470	0.6221	0.8470	0.9203
No log	9.2121	304	0.8544	0.6221	0.8544	0.9243
No log	9.2727	306	0.8534	0.6152	0.8534	0.9238
No log	9.3333	308	0.8538	0.6081	0.8538	0.9240
No log	9.3939	310	0.8575	0.6081	0.8575	0.9260
No log	9.4545	312	0.8677	0.5972	0.8677	0.9315
No log	9.5152	314	0.8739	0.5900	0.8739	0.9348
No log	9.5758	316	0.8739	0.5900	0.8739	0.9348
No log	9.6364	318	0.8762	0.5729	0.8762	0.9361
No log	9.6970	320	0.8788	0.5909	0.8788	0.9374
No log	9.7576	322	0.8816	0.5826	0.8816	0.9389
No log	9.8182	324	0.8855	0.5826	0.8855	0.9410
No log	9.8788	326	0.8881	0.5826	0.8881	0.9424
No log	9.9394	328	0.8897	0.5826	0.8897	0.9433
No log	10.0	330	0.8903	0.5826	0.8903	0.9436

Framework versions

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