ArabicNewSplits5_FineTuningAraBERT_run1_AugV5_k7_task5_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: 0.7968
• Qwk: 0.7076
• Mse: 0.7968
• Rmse: 0.8927

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	0.0571	2	2.3729	0.0341	2.3729	1.5404
No log	0.1143	4	1.6247	0.1087	1.6247	1.2746
No log	0.1714	6	1.4872	0.2058	1.4872	1.2195
No log	0.2286	8	1.2191	0.3251	1.2191	1.1041
No log	0.2857	10	1.1893	0.2176	1.1893	1.0905
No log	0.3429	12	1.2210	0.1762	1.2210	1.1050
No log	0.4	14	1.2482	0.1682	1.2482	1.1172
No log	0.4571	16	1.2496	0.1628	1.2496	1.1179
No log	0.5143	18	1.2180	0.2183	1.2180	1.1036
No log	0.5714	20	1.1925	0.2253	1.1925	1.0920
No log	0.6286	22	1.1573	0.2818	1.1573	1.0758
No log	0.6857	24	1.1577	0.3336	1.1577	1.0759
No log	0.7429	26	1.3986	0.1936	1.3986	1.1826
No log	0.8	28	1.5191	0.1301	1.5191	1.2325
No log	0.8571	30	1.5832	0.1055	1.5832	1.2583
No log	0.9143	32	1.4728	0.1695	1.4728	1.2136
No log	0.9714	34	1.2937	0.2619	1.2937	1.1374
No log	1.0286	36	1.1933	0.2709	1.1933	1.0924
No log	1.0857	38	1.0945	0.3978	1.0945	1.0462
No log	1.1429	40	1.0360	0.3639	1.0360	1.0178
No log	1.2	42	1.0683	0.3515	1.0683	1.0336
No log	1.2571	44	1.0851	0.3777	1.0851	1.0417
No log	1.3143	46	1.1705	0.3794	1.1705	1.0819
No log	1.3714	48	1.1287	0.3660	1.1287	1.0624
No log	1.4286	50	1.0361	0.3855	1.0361	1.0179
No log	1.4857	52	1.0458	0.3693	1.0458	1.0227
No log	1.5429	54	1.0247	0.4208	1.0247	1.0123
No log	1.6	56	1.0344	0.4472	1.0344	1.0170
No log	1.6571	58	1.0277	0.4377	1.0277	1.0137
No log	1.7143	60	1.0486	0.3526	1.0486	1.0240
No log	1.7714	62	1.0104	0.3879	1.0104	1.0052
No log	1.8286	64	0.9982	0.4803	0.9982	0.9991
No log	1.8857	66	1.0189	0.4680	1.0189	1.0094
No log	1.9429	68	0.9576	0.5129	0.9576	0.9786
No log	2.0	70	0.9258	0.5286	0.9258	0.9622
No log	2.0571	72	0.9162	0.5226	0.9162	0.9572
No log	2.1143	74	0.9239	0.5150	0.9239	0.9612
No log	2.1714	76	0.9175	0.4877	0.9175	0.9578
No log	2.2286	78	0.9221	0.4963	0.9221	0.9603
No log	2.2857	80	0.9353	0.4729	0.9353	0.9671
No log	2.3429	82	0.9952	0.4664	0.9952	0.9976
No log	2.4	84	1.0913	0.4281	1.0913	1.0447
No log	2.4571	86	1.2651	0.3900	1.2651	1.1248
No log	2.5143	88	1.1858	0.4321	1.1858	1.0889
No log	2.5714	90	1.0928	0.4411	1.0928	1.0454
No log	2.6286	92	0.9523	0.5328	0.9523	0.9759
No log	2.6857	94	0.8882	0.5747	0.8882	0.9424
No log	2.7429	96	0.8912	0.4934	0.8912	0.9440
No log	2.8	98	0.9913	0.4844	0.9913	0.9957
No log	2.8571	100	1.1866	0.4762	1.1866	1.0893
No log	2.9143	102	1.4332	0.4273	1.4332	1.1972
No log	2.9714	104	1.2971	0.4632	1.2971	1.1389
No log	3.0286	106	1.0419	0.5286	1.0419	1.0208
No log	3.0857	108	0.8708	0.5653	0.8708	0.9332
No log	3.1429	110	0.8570	0.5761	0.8570	0.9257
No log	3.2	112	0.8808	0.5712	0.8808	0.9385
No log	3.2571	114	1.1222	0.5249	1.1222	1.0593
No log	3.3143	116	1.3758	0.5208	1.3758	1.1729
No log	3.3714	118	1.4073	0.4926	1.4073	1.1863
No log	3.4286	120	1.1518	0.5703	1.1518	1.0732
No log	3.4857	122	0.8678	0.6357	0.8678	0.9316
No log	3.5429	124	0.7818	0.6034	0.7818	0.8842
No log	3.6	126	0.7758	0.5973	0.7758	0.8808
No log	3.6571	128	0.7695	0.6061	0.7695	0.8772
No log	3.7143	130	0.7591	0.6185	0.7591	0.8713
No log	3.7714	132	0.7873	0.6306	0.7873	0.8873
No log	3.8286	134	0.8231	0.6043	0.8231	0.9073
No log	3.8857	136	0.8443	0.6417	0.8443	0.9189
No log	3.9429	138	0.8703	0.6344	0.8703	0.9329
No log	4.0	140	0.8849	0.6459	0.8849	0.9407
No log	4.0571	142	0.9692	0.6232	0.9692	0.9845
No log	4.1143	144	0.9012	0.6396	0.9012	0.9493
No log	4.1714	146	0.8165	0.6340	0.8165	0.9036
No log	4.2286	148	0.7507	0.6919	0.7507	0.8664
No log	4.2857	150	0.7272	0.6598	0.7272	0.8528
No log	4.3429	152	0.7363	0.7101	0.7363	0.8581
No log	4.4	154	0.7974	0.6684	0.7974	0.8930
No log	4.4571	156	0.7732	0.7031	0.7732	0.8793
No log	4.5143	158	0.7610	0.7208	0.7610	0.8723
No log	4.5714	160	0.7596	0.7164	0.7596	0.8715
No log	4.6286	162	0.7608	0.7164	0.7608	0.8722
No log	4.6857	164	0.7698	0.6906	0.7698	0.8774
No log	4.7429	166	0.8397	0.6677	0.8397	0.9163
No log	4.8	168	0.9027	0.6514	0.9027	0.9501
No log	4.8571	170	1.0630	0.5953	1.0630	1.0310
No log	4.9143	172	1.2227	0.5626	1.2227	1.1058
No log	4.9714	174	1.2145	0.5706	1.2145	1.1020
No log	5.0286	176	1.0350	0.6123	1.0350	1.0173
No log	5.0857	178	0.8390	0.6942	0.8390	0.9160
No log	5.1429	180	0.7611	0.7030	0.7611	0.8724
No log	5.2	182	0.7751	0.7271	0.7751	0.8804
No log	5.2571	184	0.8359	0.6501	0.8359	0.9143
No log	5.3143	186	0.9008	0.6415	0.9008	0.9491
No log	5.3714	188	0.8889	0.6428	0.8889	0.9428
No log	5.4286	190	0.8941	0.6489	0.8941	0.9456
No log	5.4857	192	0.8385	0.6428	0.8385	0.9157
No log	5.5429	194	0.7702	0.6399	0.7702	0.8776
No log	5.6	196	0.7303	0.6588	0.7303	0.8546
No log	5.6571	198	0.7231	0.6743	0.7231	0.8504
No log	5.7143	200	0.7570	0.6780	0.7570	0.8700
No log	5.7714	202	0.8448	0.6767	0.8448	0.9191
No log	5.8286	204	0.9542	0.6362	0.9542	0.9768
No log	5.8857	206	0.9229	0.6355	0.9229	0.9607
No log	5.9429	208	0.7889	0.6892	0.7889	0.8882
No log	6.0	210	0.7277	0.7096	0.7277	0.8531
No log	6.0571	212	0.7244	0.7096	0.7244	0.8511
No log	6.1143	214	0.7488	0.7030	0.7488	0.8653
No log	6.1714	216	0.8276	0.6982	0.8276	0.9097
No log	6.2286	218	1.0069	0.6313	1.0069	1.0035
No log	6.2857	220	1.1191	0.5953	1.1191	1.0579
No log	6.3429	222	1.0850	0.6101	1.0850	1.0416
No log	6.4	224	0.9623	0.6250	0.9623	0.9810
No log	6.4571	226	0.8038	0.6784	0.8038	0.8966
No log	6.5143	228	0.7533	0.6876	0.7533	0.8679
No log	6.5714	230	0.7645	0.6618	0.7645	0.8744
No log	6.6286	232	0.7678	0.6940	0.7678	0.8763
No log	6.6857	234	0.8287	0.6631	0.8287	0.9103
No log	6.7429	236	0.9170	0.6175	0.9170	0.9576
No log	6.8	238	0.9332	0.6254	0.9332	0.9660
No log	6.8571	240	0.9101	0.6311	0.9101	0.9540
No log	6.9143	242	0.8262	0.6902	0.8262	0.9089
No log	6.9714	244	0.7769	0.7152	0.7769	0.8814
No log	7.0286	246	0.7805	0.7189	0.7805	0.8835
No log	7.0857	248	0.8314	0.6812	0.8314	0.9118
No log	7.1429	250	0.9216	0.6053	0.9216	0.9600
No log	7.2	252	1.0006	0.6001	1.0006	1.0003
No log	7.2571	254	1.0360	0.6034	1.0360	1.0178
No log	7.3143	256	1.0332	0.6034	1.0332	1.0165
No log	7.3714	258	0.9637	0.6119	0.9637	0.9817
No log	7.4286	260	0.9027	0.6325	0.9027	0.9501
No log	7.4857	262	0.8879	0.6325	0.8879	0.9423
No log	7.5429	264	0.8966	0.6368	0.8966	0.9469
No log	7.6	266	0.8478	0.6773	0.8478	0.9208
No log	7.6571	268	0.8010	0.7218	0.8010	0.8950
No log	7.7143	270	0.7684	0.7270	0.7684	0.8766
No log	7.7714	272	0.7656	0.7270	0.7656	0.8750
No log	7.8286	274	0.7907	0.7309	0.7907	0.8892
No log	7.8857	276	0.8067	0.6966	0.8067	0.8981
No log	7.9429	278	0.8092	0.7004	0.8092	0.8995
No log	8.0	280	0.8101	0.6999	0.8101	0.9000
No log	8.0571	282	0.8428	0.6604	0.8428	0.9180
No log	8.1143	284	0.8855	0.6182	0.8855	0.9410
No log	8.1714	286	0.8995	0.6247	0.8995	0.9484
No log	8.2286	288	0.9249	0.6127	0.9249	0.9617
No log	8.2857	290	0.9117	0.6218	0.9117	0.9548
No log	8.3429	292	0.8601	0.6500	0.8601	0.9274
No log	8.4	294	0.8069	0.7096	0.8069	0.8983
No log	8.4571	296	0.7622	0.7189	0.7622	0.8731
No log	8.5143	298	0.7548	0.7189	0.7548	0.8688
No log	8.5714	300	0.7716	0.7189	0.7716	0.8784
No log	8.6286	302	0.8087	0.7203	0.8086	0.8992
No log	8.6857	304	0.8464	0.7165	0.8464	0.9200
No log	8.7429	306	0.8642	0.7019	0.8642	0.9296
No log	8.8	308	0.8504	0.7165	0.8504	0.9222
No log	8.8571	310	0.8203	0.7280	0.8203	0.9057
No log	8.9143	312	0.7950	0.7202	0.7950	0.8916
No log	8.9714	314	0.7845	0.7220	0.7845	0.8857
No log	9.0286	316	0.7741	0.7124	0.7741	0.8798
No log	9.0857	318	0.7724	0.7345	0.7724	0.8789
No log	9.1429	320	0.7788	0.7220	0.7788	0.8825
No log	9.2	322	0.7902	0.7199	0.7902	0.8889
No log	9.2571	324	0.7910	0.7199	0.7910	0.8894
No log	9.3143	326	0.7985	0.7201	0.7985	0.8936
No log	9.3714	328	0.8084	0.6919	0.8084	0.8991
No log	9.4286	330	0.8033	0.7039	0.8033	0.8963
No log	9.4857	332	0.7991	0.7036	0.7991	0.8939
No log	9.5429	334	0.8034	0.7036	0.8034	0.8963
No log	9.6	336	0.8041	0.7036	0.8041	0.8967
No log	9.6571	338	0.8055	0.7036	0.8055	0.8975
No log	9.7143	340	0.8034	0.7079	0.8034	0.8963
No log	9.7714	342	0.8011	0.7079	0.8011	0.8950
No log	9.8286	344	0.8012	0.7079	0.8012	0.8951
No log	9.8857	346	0.7992	0.7079	0.7992	0.8940
No log	9.9429	348	0.7976	0.7076	0.7976	0.8931
No log	10.0	350	0.7968	0.7076	0.7968	0.8927

Framework versions

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