ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k7_task3_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: 0.7802
• Qwk: 0.2566
• Mse: 0.7802
• Rmse: 0.8833

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	0.0588	2	3.4084	-0.0160	3.4084	1.8462
No log	0.1176	4	1.9830	-0.0370	1.9830	1.4082
No log	0.1765	6	0.9549	0.0118	0.9549	0.9772
No log	0.2353	8	0.6996	0.0538	0.6996	0.8364
No log	0.2941	10	0.6901	-0.0435	0.6901	0.8307
No log	0.3529	12	0.7332	-0.1358	0.7332	0.8563
No log	0.4118	14	0.7616	0.0538	0.7616	0.8727
No log	0.4706	16	0.8147	0.0042	0.8147	0.9026
No log	0.5294	18	0.9201	0.0078	0.9201	0.9592
No log	0.5882	20	0.8778	0.0476	0.8778	0.9369
No log	0.6471	22	0.8897	0.0476	0.8897	0.9432
No log	0.7059	24	0.8932	0.0745	0.8932	0.9451
No log	0.7647	26	0.8650	0.1000	0.8650	0.9301
No log	0.8235	28	0.7986	0.0164	0.7986	0.8936
No log	0.8824	30	0.8206	0.0303	0.8206	0.9058
No log	0.9412	32	0.8444	0.0196	0.8444	0.9189
No log	1.0	34	0.7907	0.0196	0.7907	0.8892
No log	1.0588	36	0.7767	0.1515	0.7767	0.8813
No log	1.1176	38	0.7006	-0.0133	0.7006	0.8370
No log	1.1765	40	0.6874	-0.0435	0.6874	0.8291
No log	1.2353	42	0.7221	-0.0667	0.7221	0.8498
No log	1.2941	44	0.7658	0.0601	0.7658	0.8751
No log	1.3529	46	0.8570	0.1174	0.8570	0.9257
No log	1.4118	48	0.9045	0.0427	0.9045	0.9510
No log	1.4706	50	0.7663	-0.0149	0.7663	0.8754
No log	1.5294	52	0.6181	0.0222	0.6181	0.7862
No log	1.5882	54	0.6768	0.1407	0.6768	0.8227
No log	1.6471	56	0.7012	0.1278	0.7012	0.8374
No log	1.7059	58	0.6276	-0.0159	0.6276	0.7922
No log	1.7647	60	0.6347	0.1795	0.6347	0.7967
No log	1.8235	62	1.4366	0.0984	1.4366	1.1986
No log	1.8824	64	1.8974	0.0968	1.8974	1.3775
No log	1.9412	66	1.2339	0.1172	1.2339	1.1108
No log	2.0	68	0.6724	0.0850	0.6724	0.8200
No log	2.0588	70	0.6658	-0.0303	0.6658	0.8159
No log	2.1176	72	0.6924	-0.0435	0.6924	0.8321
No log	2.1765	74	0.7285	-0.1156	0.7285	0.8535
No log	2.2353	76	0.7723	0.0345	0.7723	0.8788
No log	2.2941	78	0.7675	0.0282	0.7675	0.8760
No log	2.3529	80	0.7423	0.0061	0.7423	0.8616
No log	2.4118	82	0.8165	0.0	0.8165	0.9036
No log	2.4706	84	0.8639	0.0588	0.8639	0.9295
No log	2.5294	86	0.9948	0.1111	0.9948	0.9974
No log	2.5882	88	0.8067	0.1238	0.8067	0.8982
No log	2.6471	90	0.8213	0.0918	0.8213	0.9062
No log	2.7059	92	1.1715	0.0229	1.1715	1.0824
No log	2.7647	94	1.2742	-0.0149	1.2742	1.1288
No log	2.8235	96	0.8984	0.1304	0.8984	0.9478
No log	2.8824	98	0.7292	0.1209	0.7292	0.8539
No log	2.9412	100	0.7247	0.0909	0.7247	0.8513
No log	3.0	102	0.7491	0.1648	0.7491	0.8655
No log	3.0588	104	0.8133	0.125	0.8133	0.9018
No log	3.1176	106	0.8501	0.1590	0.8501	0.9220
No log	3.1765	108	0.7620	0.1753	0.7620	0.8729
No log	3.2353	110	0.7321	0.2273	0.7321	0.8556
No log	3.2941	112	0.7282	0.2265	0.7282	0.8533
No log	3.3529	114	0.7749	0.2000	0.7749	0.8803
No log	3.4118	116	0.8747	0.1469	0.8747	0.9353
No log	3.4706	118	0.8334	0.1610	0.8334	0.9129
No log	3.5294	120	0.8292	0.1304	0.8292	0.9106
No log	3.5882	122	0.8075	0.1527	0.8075	0.8986
No log	3.6471	124	0.7862	0.1456	0.7862	0.8867
No log	3.7059	126	0.8239	0.1336	0.8239	0.9077
No log	3.7647	128	0.8130	0.1921	0.8130	0.9017
No log	3.8235	130	0.8935	0.2803	0.8935	0.9452
No log	3.8824	132	1.0457	0.2375	1.0457	1.0226
No log	3.9412	134	1.2035	0.2000	1.2035	1.0971
No log	4.0	136	0.9246	0.1864	0.9246	0.9616
No log	4.0588	138	0.7216	0.2897	0.7216	0.8494
No log	4.1176	140	0.7156	0.24	0.7156	0.8459
No log	4.1765	142	0.6568	0.2821	0.6568	0.8105
No log	4.2353	144	0.6467	0.3433	0.6467	0.8042
No log	4.2941	146	0.6552	0.2842	0.6552	0.8094
No log	4.3529	148	0.7578	0.1923	0.7578	0.8705
No log	4.4118	150	0.7331	0.2165	0.7331	0.8562
No log	4.4706	152	0.6224	0.3402	0.6224	0.7889
No log	4.5294	154	0.6844	0.2079	0.6844	0.8273
No log	4.5882	156	0.7334	0.3091	0.7334	0.8564
No log	4.6471	158	0.8204	0.2146	0.8204	0.9057
No log	4.7059	160	0.9271	0.1807	0.9271	0.9629
No log	4.7647	162	0.9042	0.2327	0.9042	0.9509
No log	4.8235	164	0.8737	0.1790	0.8737	0.9347
No log	4.8824	166	0.8987	0.2881	0.8987	0.9480
No log	4.9412	168	0.9969	0.2066	0.9969	0.9985
No log	5.0	170	0.9633	0.2941	0.9633	0.9815
No log	5.0588	172	0.9178	0.2203	0.9178	0.9580
No log	5.1176	174	0.9372	0.2131	0.9372	0.9681
No log	5.1765	176	0.9239	0.1741	0.9239	0.9612
No log	5.2353	178	0.9878	0.2787	0.9878	0.9939
No log	5.2941	180	0.9729	0.2727	0.9729	0.9863
No log	5.3529	182	0.9284	0.1571	0.9284	0.9636
No log	5.4118	184	0.9462	0.2069	0.9462	0.9727
No log	5.4706	186	0.8845	0.1554	0.8845	0.9405
No log	5.5294	188	0.8466	0.2212	0.8466	0.9201
No log	5.5882	190	0.8011	0.2000	0.8011	0.8951
No log	5.6471	192	0.8310	0.1786	0.8310	0.9116
No log	5.7059	194	0.8261	0.1786	0.8261	0.9089
No log	5.7647	196	0.7675	0.2744	0.7675	0.8761
No log	5.8235	198	0.7677	0.2523	0.7677	0.8762
No log	5.8824	200	0.8045	0.3247	0.8045	0.8969
No log	5.9412	202	0.8469	0.3147	0.8469	0.9203
No log	6.0	204	0.7848	0.3247	0.7848	0.8859
No log	6.0588	206	0.7615	0.2661	0.7615	0.8726
No log	6.1176	208	0.7394	0.2661	0.7394	0.8599
No log	6.1765	210	0.7779	0.3527	0.7779	0.8820
No log	6.2353	212	0.9127	0.2520	0.9127	0.9554
No log	6.2941	214	0.9204	0.2520	0.9204	0.9594
No log	6.3529	216	0.7922	0.3115	0.7922	0.8901
No log	6.4118	218	0.7576	0.2579	0.7576	0.8704
No log	6.4706	220	0.7672	0.2356	0.7672	0.8759
No log	6.5294	222	0.8115	0.1928	0.8115	0.9008
No log	6.5882	224	0.7800	0.2364	0.7800	0.8832
No log	6.6471	226	0.7759	0.3000	0.7759	0.8809
No log	6.7059	228	0.9786	0.1873	0.9786	0.9893
No log	6.7647	230	1.0667	0.1635	1.0667	1.0328
No log	6.8235	232	0.9889	0.2131	0.9889	0.9944
No log	6.8824	234	0.8669	0.3156	0.8669	0.9311
No log	6.9412	236	0.8827	0.2423	0.8827	0.9395
No log	7.0	238	0.9375	0.2469	0.9375	0.9683
No log	7.0588	240	0.9005	0.2275	0.9005	0.9489
No log	7.1176	242	0.8564	0.2258	0.8564	0.9254
No log	7.1765	244	0.9361	0.2126	0.9361	0.9675
No log	7.2353	246	0.9925	0.2327	0.9925	0.9963
No log	7.2941	248	0.9034	0.2531	0.9034	0.9505
No log	7.3529	250	0.7945	0.1781	0.7945	0.8913
No log	7.4118	252	0.7882	0.2074	0.7882	0.8878
No log	7.4706	254	0.7946	0.1636	0.7946	0.8914
No log	7.5294	256	0.7912	0.1781	0.7912	0.8895
No log	7.5882	258	0.8665	0.2743	0.8665	0.9308
No log	7.6471	260	0.9197	0.2531	0.9197	0.9590
No log	7.7059	262	0.9231	0.2459	0.9231	0.9608
No log	7.7647	264	0.8663	0.2340	0.8663	0.9307
No log	7.8235	266	0.8156	0.1781	0.8156	0.9031
No log	7.8824	268	0.8086	0.1636	0.8086	0.8992
No log	7.9412	270	0.8055	0.1636	0.8055	0.8975
No log	8.0	272	0.7995	0.1469	0.7995	0.8942
No log	8.0588	274	0.8213	0.1636	0.8213	0.9063
No log	8.1176	276	0.8317	0.1705	0.8317	0.9120
No log	8.1765	278	0.7930	0.1628	0.7930	0.8905
No log	8.2353	280	0.7576	0.2000	0.7576	0.8704
No log	8.2941	282	0.7475	0.2727	0.7475	0.8646
No log	8.3529	284	0.7613	0.2000	0.7613	0.8725
No log	8.4118	286	0.8037	0.1776	0.8037	0.8965
No log	8.4706	288	0.8066	0.1781	0.8066	0.8981
No log	8.5294	290	0.7948	0.2150	0.7948	0.8915
No log	8.5882	292	0.7639	0.2079	0.7639	0.8740
No log	8.6471	294	0.7407	0.1845	0.7407	0.8606
No log	8.7059	296	0.7422	0.2157	0.7422	0.8615
No log	8.7647	298	0.7538	0.2157	0.7538	0.8682
No log	8.8235	300	0.7680	0.2157	0.7680	0.8764
No log	8.8824	302	0.7818	0.2511	0.7818	0.8842
No log	8.9412	304	0.7946	0.3138	0.7946	0.8914
No log	9.0	306	0.8020	0.2960	0.8020	0.8955
No log	9.0588	308	0.8145	0.2960	0.8145	0.9025
No log	9.1176	310	0.8326	0.2685	0.8326	0.9124
No log	9.1765	312	0.8455	0.2846	0.8455	0.9195
No log	9.2353	314	0.8609	0.3518	0.8609	0.9278
No log	9.2941	316	0.8622	0.3280	0.8622	0.9285
No log	9.3529	318	0.8435	0.3437	0.8435	0.9184
No log	9.4118	320	0.8246	0.2846	0.8246	0.9081
No log	9.4706	322	0.8067	0.2713	0.8067	0.8982
No log	9.5294	324	0.8007	0.2881	0.8007	0.8948
No log	9.5882	326	0.7959	0.2881	0.7959	0.8921
No log	9.6471	328	0.7927	0.2881	0.7927	0.8904
No log	9.7059	330	0.7851	0.2554	0.7851	0.8860
No log	9.7647	332	0.7810	0.2554	0.7810	0.8837
No log	9.8235	334	0.7783	0.2566	0.7783	0.8822
No log	9.8824	336	0.7787	0.2566	0.7787	0.8824
No log	9.9412	338	0.7800	0.2566	0.7800	0.8832
No log	10.0	340	0.7802	0.2566	0.7802	0.8833

Framework versions

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