ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k7_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: 0.6750
• Qwk: 0.7057
• Mse: 0.6750
• Rmse: 0.8216

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	0.0556	2	5.0740	-0.0012	5.0740	2.2526
No log	0.1111	4	3.0763	0.1174	3.0763	1.7539
No log	0.1667	6	2.6286	-0.1267	2.6286	1.6213
No log	0.2222	8	2.6262	-0.1794	2.6262	1.6206
No log	0.2778	10	1.8628	0.0233	1.8628	1.3649
No log	0.3333	12	1.2066	0.2736	1.2066	1.0984
No log	0.3889	14	1.1860	0.2909	1.1860	1.0890
No log	0.4444	16	1.5761	0.0640	1.5761	1.2554
No log	0.5	18	2.1874	0.0756	2.1874	1.4790
No log	0.5556	20	2.9529	-0.0354	2.9529	1.7184
No log	0.6111	22	2.5931	0.0981	2.5931	1.6103
No log	0.6667	24	1.6268	0.0811	1.6268	1.2755
No log	0.7222	26	1.0882	0.2867	1.0882	1.0431
No log	0.7778	28	1.0762	0.3459	1.0762	1.0374
No log	0.8333	30	1.1294	0.3351	1.1294	1.0627
No log	0.8889	32	1.2276	0.3090	1.2276	1.1080
No log	0.9444	34	1.4880	0.0364	1.4880	1.2198
No log	1.0	36	1.6250	0.1061	1.6250	1.2747
No log	1.0556	38	1.5243	0.1599	1.5243	1.2346
No log	1.1111	40	1.3236	0.3228	1.3236	1.1505
No log	1.1667	42	0.9493	0.4971	0.9493	0.9743
No log	1.2222	44	0.9206	0.5202	0.9206	0.9595
No log	1.2778	46	1.2748	0.4391	1.2748	1.1291
No log	1.3333	48	1.7703	0.3291	1.7703	1.3305
No log	1.3889	50	1.6556	0.3611	1.6556	1.2867
No log	1.4444	52	1.1626	0.5068	1.1626	1.0783
No log	1.5	54	0.9369	0.5673	0.9369	0.9679
No log	1.5556	56	0.7683	0.6305	0.7683	0.8765
No log	1.6111	58	0.7570	0.6243	0.7570	0.8700
No log	1.6667	60	0.8937	0.5744	0.8937	0.9454
No log	1.7222	62	1.3836	0.4116	1.3836	1.1763
No log	1.7778	64	1.6651	0.3342	1.6651	1.2904
No log	1.8333	66	1.7200	0.3143	1.7200	1.3115
No log	1.8889	68	1.5840	0.3737	1.5840	1.2586
No log	1.9444	70	1.2199	0.4333	1.2199	1.1045
No log	2.0	72	0.8924	0.6189	0.8924	0.9447
No log	2.0556	74	0.7861	0.6294	0.7861	0.8866
No log	2.1111	76	0.8195	0.6305	0.8195	0.9052
No log	2.1667	78	0.9699	0.5781	0.9699	0.9848
No log	2.2222	80	1.3322	0.4468	1.3322	1.1542
No log	2.2778	82	1.5452	0.4021	1.5452	1.2430
No log	2.3333	84	1.3126	0.4690	1.3126	1.1457
No log	2.3889	86	0.9183	0.6136	0.9183	0.9583
No log	2.4444	88	0.7806	0.6304	0.7806	0.8835
No log	2.5	90	0.6712	0.6620	0.6712	0.8193
No log	2.5556	92	0.6298	0.6988	0.6298	0.7936
No log	2.6111	94	0.6482	0.6981	0.6482	0.8051
No log	2.6667	96	0.7525	0.6921	0.7525	0.8675
No log	2.7222	98	0.7661	0.6718	0.7661	0.8753
No log	2.7778	100	0.6869	0.7054	0.6869	0.8288
No log	2.8333	102	0.6525	0.7256	0.6525	0.8078
No log	2.8889	104	0.7144	0.6802	0.7144	0.8452
No log	2.9444	106	0.7012	0.7026	0.7012	0.8374
No log	3.0	108	0.6807	0.7013	0.6807	0.8251
No log	3.0556	110	0.7928	0.6792	0.7928	0.8904
No log	3.1111	112	0.9421	0.6462	0.9421	0.9706
No log	3.1667	114	0.9097	0.6681	0.9097	0.9538
No log	3.2222	116	0.7788	0.6851	0.7788	0.8825
No log	3.2778	118	0.7515	0.6875	0.7515	0.8669
No log	3.3333	120	0.7483	0.6595	0.7483	0.8650
No log	3.3889	122	0.7083	0.6887	0.7083	0.8416
No log	3.4444	124	0.7320	0.6574	0.7320	0.8556
No log	3.5	126	0.9067	0.5653	0.9067	0.9522
No log	3.5556	128	0.9276	0.5724	0.9276	0.9631
No log	3.6111	130	0.7780	0.6659	0.7780	0.8820
No log	3.6667	132	0.6736	0.6817	0.6736	0.8207
No log	3.7222	134	0.6556	0.7021	0.6556	0.8097
No log	3.7778	136	0.6632	0.7141	0.6632	0.8144
No log	3.8333	138	0.7329	0.6778	0.7329	0.8561
No log	3.8889	140	0.7723	0.6821	0.7723	0.8788
No log	3.9444	142	0.7128	0.6979	0.7128	0.8443
No log	4.0	144	0.6686	0.7101	0.6686	0.8177
No log	4.0556	146	0.6972	0.6892	0.6972	0.8350
No log	4.1111	148	0.6845	0.6892	0.6845	0.8274
No log	4.1667	150	0.6646	0.7467	0.6646	0.8153
No log	4.2222	152	0.7463	0.6762	0.7463	0.8639
No log	4.2778	154	0.7768	0.6640	0.7768	0.8814
No log	4.3333	156	0.7395	0.6846	0.7395	0.8599
No log	4.3889	158	0.6811	0.6786	0.6811	0.8253
No log	4.4444	160	0.6756	0.6693	0.6756	0.8220
No log	4.5	162	0.7149	0.6719	0.7149	0.8455
No log	4.5556	164	0.8589	0.6050	0.8589	0.9268
No log	4.6111	166	1.1432	0.5169	1.1432	1.0692
No log	4.6667	168	1.3391	0.4197	1.3391	1.1572
No log	4.7222	170	1.2471	0.4450	1.2471	1.1167
No log	4.7778	172	0.9945	0.5586	0.9945	0.9972
No log	4.8333	174	0.7844	0.6469	0.7844	0.8857
No log	4.8889	176	0.7156	0.6782	0.7156	0.8460
No log	4.9444	178	0.7182	0.6715	0.7182	0.8474
No log	5.0	180	0.7614	0.6389	0.7614	0.8726
No log	5.0556	182	0.8606	0.6353	0.8606	0.9277
No log	5.1111	184	0.8664	0.6250	0.8664	0.9308
No log	5.1667	186	0.7847	0.6342	0.7847	0.8858
No log	5.2222	188	0.7373	0.6644	0.7373	0.8587
No log	5.2778	190	0.7381	0.6636	0.7381	0.8591
No log	5.3333	192	0.7914	0.6434	0.7914	0.8896
No log	5.3889	194	0.9592	0.5899	0.9592	0.9794
No log	5.4444	196	1.2003	0.5320	1.2003	1.0956
No log	5.5	198	1.2112	0.5285	1.2112	1.1006
No log	5.5556	200	1.0321	0.5446	1.0321	1.0159
No log	5.6111	202	0.8094	0.6558	0.8094	0.8996
No log	5.6667	204	0.7160	0.6856	0.7160	0.8462
No log	5.7222	206	0.6940	0.6829	0.6940	0.8331
No log	5.7778	208	0.7051	0.7085	0.7051	0.8397
No log	5.8333	210	0.7345	0.6785	0.7345	0.8570
No log	5.8889	212	0.7249	0.7054	0.7249	0.8514
No log	5.9444	214	0.6856	0.7054	0.6856	0.8280
No log	6.0	216	0.6617	0.6978	0.6617	0.8135
No log	6.0556	218	0.6585	0.6856	0.6585	0.8115
No log	6.1111	220	0.6562	0.6854	0.6562	0.8100
No log	6.1667	222	0.6557	0.7005	0.6557	0.8098
No log	6.2222	224	0.6645	0.7024	0.6645	0.8152
No log	6.2778	226	0.6912	0.7185	0.6912	0.8314
No log	6.3333	228	0.7703	0.6607	0.7703	0.8776
No log	6.3889	230	0.8055	0.6383	0.8055	0.8975
No log	6.4444	232	0.8212	0.6272	0.8212	0.9062
No log	6.5	234	0.7868	0.6436	0.7868	0.8870
No log	6.5556	236	0.7391	0.6647	0.7391	0.8597
No log	6.6111	238	0.7090	0.6824	0.7090	0.8420
No log	6.6667	240	0.6859	0.7019	0.6859	0.8282
No log	6.7222	242	0.6899	0.6980	0.6899	0.8306
No log	6.7778	244	0.7235	0.6733	0.7235	0.8506
No log	6.8333	246	0.8137	0.6458	0.8137	0.9021
No log	6.8889	248	0.9806	0.5666	0.9806	0.9902
No log	6.9444	250	1.1008	0.5632	1.1008	1.0492
No log	7.0	252	1.1325	0.5709	1.1325	1.0642
No log	7.0556	254	1.0395	0.5568	1.0395	1.0196
No log	7.1111	256	0.8895	0.6008	0.8895	0.9431
No log	7.1667	258	0.7629	0.6803	0.7629	0.8734
No log	7.2222	260	0.7130	0.6725	0.7130	0.8444
No log	7.2778	262	0.6930	0.7133	0.6930	0.8325
No log	7.3333	264	0.6827	0.6995	0.6827	0.8263
No log	7.3889	266	0.6810	0.6989	0.6810	0.8252
No log	7.4444	268	0.6815	0.6952	0.6815	0.8255
No log	7.5	270	0.6844	0.7133	0.6844	0.8273
No log	7.5556	272	0.7012	0.7197	0.7012	0.8374
No log	7.6111	274	0.7199	0.7043	0.7199	0.8484
No log	7.6667	276	0.7325	0.6949	0.7325	0.8559
No log	7.7222	278	0.7360	0.6856	0.7360	0.8579
No log	7.7778	280	0.7263	0.6917	0.7263	0.8522
No log	7.8333	282	0.7037	0.7257	0.7037	0.8389
No log	7.8889	284	0.6954	0.7413	0.6954	0.8339
No log	7.9444	286	0.6929	0.7310	0.6929	0.8324
No log	8.0	288	0.6961	0.7272	0.6961	0.8343
No log	8.0556	290	0.6961	0.7227	0.6961	0.8343
No log	8.1111	292	0.7005	0.7272	0.7005	0.8370
No log	8.1667	294	0.7023	0.7100	0.7023	0.8380
No log	8.2222	296	0.7086	0.7030	0.7086	0.8418
No log	8.2778	298	0.7235	0.6905	0.7235	0.8506
No log	8.3333	300	0.7443	0.6749	0.7443	0.8627
No log	8.3889	302	0.7442	0.6842	0.7442	0.8627
No log	8.4444	304	0.7281	0.6842	0.7281	0.8533
No log	8.5	306	0.7142	0.6905	0.7142	0.8451
No log	8.5556	308	0.7097	0.6779	0.7097	0.8424
No log	8.6111	310	0.7056	0.6779	0.7056	0.8400
No log	8.6667	312	0.7019	0.6842	0.7019	0.8378
No log	8.7222	314	0.7048	0.6967	0.7048	0.8395
No log	8.7778	316	0.7061	0.6967	0.7061	0.8403
No log	8.8333	318	0.7009	0.7065	0.7009	0.8372
No log	8.8889	320	0.6997	0.7065	0.6997	0.8365
No log	8.9444	322	0.6937	0.6976	0.6937	0.8329
No log	9.0	324	0.6942	0.6976	0.6942	0.8332
No log	9.0556	326	0.6950	0.7099	0.6950	0.8336
No log	9.1111	328	0.6904	0.6958	0.6904	0.8309
No log	9.1667	330	0.6876	0.6958	0.6876	0.8292
No log	9.2222	332	0.6839	0.6782	0.6839	0.8270
No log	9.2778	334	0.6802	0.7	0.6802	0.8247
No log	9.3333	336	0.6783	0.7118	0.6783	0.8236
No log	9.3889	338	0.6782	0.7238	0.6782	0.8235
No log	9.4444	340	0.6793	0.7276	0.6793	0.8242
No log	9.5	342	0.6804	0.7276	0.6804	0.8249
No log	9.5556	344	0.6797	0.7276	0.6797	0.8244
No log	9.6111	346	0.6791	0.7276	0.6791	0.8241
No log	9.6667	348	0.6784	0.7276	0.6784	0.8237
No log	9.7222	350	0.6773	0.7238	0.6773	0.8230
No log	9.7778	352	0.6761	0.7238	0.6761	0.8222
No log	9.8333	354	0.6753	0.7179	0.6753	0.8218
No log	9.8889	356	0.6749	0.7118	0.6749	0.8215
No log	9.9444	358	0.6749	0.7057	0.6749	0.8215
No log	10.0	360	0.6750	0.7057	0.6750	0.8216

Framework versions

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