ArabicNewSplits7_FineTuningAraBERT_run2_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: 0.7208
• Qwk: 0.7260
• Mse: 0.7208
• Rmse: 0.8490

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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	0.0588	2	6.9735	0.0056	6.9735	2.6407
No log	0.1176	4	4.3746	0.0769	4.3746	2.0916
No log	0.1765	6	2.8700	0.0633	2.8700	1.6941
No log	0.2353	8	2.1075	0.125	2.1075	1.4517
No log	0.2941	10	1.7950	0.1905	1.7950	1.3398
No log	0.3529	12	1.8416	0.2000	1.8416	1.3571
No log	0.4118	14	1.8567	0.1321	1.8567	1.3626
No log	0.4706	16	1.8165	0.0962	1.8165	1.3478
No log	0.5294	18	1.8647	0.0762	1.8647	1.3656
No log	0.5882	20	1.8476	0.1468	1.8476	1.3593
No log	0.6471	22	2.0458	0.1760	2.0458	1.4303
No log	0.7059	24	1.9897	0.2381	1.9897	1.4106
No log	0.7647	26	1.7253	0.2975	1.7253	1.3135
No log	0.8235	28	1.6325	0.3871	1.6325	1.2777
No log	0.8824	30	1.6435	0.4186	1.6435	1.2820
No log	0.9412	32	1.3749	0.4094	1.3749	1.1726
No log	1.0	34	1.2316	0.5039	1.2316	1.1098
No log	1.0588	36	1.1604	0.5512	1.1604	1.0772
No log	1.1176	38	1.0932	0.6	1.0932	1.0456
No log	1.1765	40	1.3027	0.5532	1.3027	1.1414
No log	1.2353	42	1.2583	0.5180	1.2583	1.1217
No log	1.2941	44	1.1397	0.5507	1.1397	1.0676
No log	1.3529	46	0.9802	0.6222	0.9802	0.9900
No log	1.4118	48	1.6090	0.3438	1.6090	1.2685
No log	1.4706	50	2.3697	-0.0320	2.3697	1.5394
No log	1.5294	52	2.3959	-0.0310	2.3959	1.5479
No log	1.5882	54	1.4223	0.4118	1.4223	1.1926
No log	1.6471	56	0.8602	0.7417	0.8602	0.9275
No log	1.7059	58	0.8228	0.7211	0.8228	0.9071
No log	1.7647	60	0.8407	0.6573	0.8407	0.9169
No log	1.8235	62	0.8267	0.6809	0.8267	0.9092
No log	1.8824	64	0.7667	0.6944	0.7667	0.8756
No log	1.9412	66	0.7627	0.6944	0.7627	0.8734
No log	2.0	68	0.6820	0.7568	0.6820	0.8258
No log	2.0588	70	0.6808	0.7568	0.6808	0.8251
No log	2.1176	72	0.8158	0.7020	0.8158	0.9032
No log	2.1765	74	0.8018	0.7020	0.8018	0.8954
No log	2.2353	76	0.6660	0.7702	0.6660	0.8161
No log	2.2941	78	0.7504	0.7952	0.7504	0.8663
No log	2.3529	80	0.6967	0.7927	0.6967	0.8347
No log	2.4118	82	0.8168	0.7613	0.8168	0.9038
No log	2.4706	84	0.9448	0.6711	0.9448	0.9720
No log	2.5294	86	0.7011	0.7898	0.7011	0.8373
No log	2.5882	88	0.7170	0.7673	0.7170	0.8467
No log	2.6471	90	0.8725	0.7	0.8725	0.9341
No log	2.7059	92	0.7087	0.7484	0.7087	0.8418
No log	2.7647	94	0.6411	0.7632	0.6411	0.8007
No log	2.8235	96	1.0670	0.6301	1.0670	1.0330
No log	2.8824	98	1.2259	0.5362	1.2259	1.1072
No log	2.9412	100	1.0030	0.5735	1.0030	1.0015
No log	3.0	102	0.7783	0.6667	0.7783	0.8822
No log	3.0588	104	0.7049	0.7286	0.7049	0.8396
No log	3.1176	106	0.7734	0.7	0.7734	0.8794
No log	3.1765	108	0.7456	0.7260	0.7456	0.8635
No log	3.2353	110	0.6291	0.7517	0.6291	0.7932
No log	3.2941	112	0.6335	0.7742	0.6335	0.7959
No log	3.3529	114	0.6444	0.7722	0.6444	0.8027
No log	3.4118	116	0.6810	0.7927	0.6810	0.8252
No log	3.4706	118	0.6957	0.7799	0.6957	0.8341
No log	3.5294	120	0.8241	0.6892	0.8241	0.9078
No log	3.5882	122	0.8689	0.6849	0.8689	0.9321
No log	3.6471	124	0.8661	0.7234	0.8661	0.9306
No log	3.7059	126	0.9004	0.6176	0.9004	0.9489
No log	3.7647	128	0.9543	0.5481	0.9543	0.9769
No log	3.8235	130	0.9078	0.5865	0.9078	0.9528
No log	3.8824	132	0.8598	0.6260	0.8598	0.9273
No log	3.9412	134	0.7676	0.7310	0.7676	0.8761
No log	4.0	136	0.7432	0.7297	0.7432	0.8621
No log	4.0588	138	0.7763	0.6939	0.7763	0.8811
No log	4.1176	140	0.8251	0.6939	0.8251	0.9083
No log	4.1765	142	0.7559	0.6939	0.7559	0.8694
No log	4.2353	144	0.6913	0.7632	0.6913	0.8315
No log	4.2941	146	0.7775	0.7237	0.7775	0.8818
No log	4.3529	148	0.7477	0.7333	0.7477	0.8647
No log	4.4118	150	0.6550	0.7671	0.6550	0.8093
No log	4.4706	152	0.6428	0.7432	0.6428	0.8017
No log	4.5294	154	0.5808	0.7417	0.5808	0.7621
No log	4.5882	156	0.5691	0.7857	0.5691	0.7544
No log	4.6471	158	0.7064	0.7485	0.7064	0.8405
No log	4.7059	160	0.6080	0.7738	0.6080	0.7797
No log	4.7647	162	0.6416	0.76	0.6416	0.8010
No log	4.8235	164	0.7479	0.7027	0.7479	0.8648
No log	4.8824	166	0.6493	0.7724	0.6493	0.8058
No log	4.9412	168	0.7841	0.7013	0.7841	0.8855
No log	5.0	170	1.2366	0.5375	1.2366	1.1120
No log	5.0588	172	1.2098	0.5350	1.2098	1.0999
No log	5.1176	174	0.8891	0.6338	0.8891	0.9429
No log	5.1765	176	0.8558	0.7007	0.8558	0.9251
No log	5.2353	178	0.9119	0.6866	0.9119	0.9549
No log	5.2941	180	0.8074	0.75	0.8074	0.8986
No log	5.3529	182	0.6681	0.7815	0.6681	0.8174
No log	5.4118	184	0.6146	0.8026	0.6146	0.7839
No log	5.4706	186	0.6893	0.7712	0.6893	0.8302
No log	5.5294	188	0.7428	0.6849	0.7428	0.8619
No log	5.5882	190	0.6805	0.7483	0.6805	0.8249
No log	5.6471	192	0.6827	0.7483	0.6827	0.8262
No log	5.7059	194	0.6906	0.7483	0.6906	0.8310
No log	5.7647	196	0.6012	0.7867	0.6012	0.7754
No log	5.8235	198	0.5874	0.7919	0.5874	0.7664
No log	5.8824	200	0.6483	0.7671	0.6483	0.8052
No log	5.9412	202	0.6492	0.7671	0.6492	0.8058
No log	6.0	204	0.5891	0.7919	0.5891	0.7675
No log	6.0588	206	0.5571	0.7927	0.5571	0.7464
No log	6.1176	208	0.5581	0.7879	0.5581	0.7471
No log	6.1765	210	0.5428	0.8025	0.5428	0.7368
No log	6.2353	212	0.6171	0.7724	0.6171	0.7856
No log	6.2941	214	0.6298	0.7724	0.6298	0.7936
No log	6.3529	216	0.6219	0.7778	0.6219	0.7886
No log	6.4118	218	0.6057	0.7973	0.6057	0.7783
No log	6.4706	220	0.6325	0.7891	0.6325	0.7953
No log	6.5294	222	0.6528	0.7891	0.6528	0.8080
No log	6.5882	224	0.7220	0.7467	0.7220	0.8497
No log	6.6471	226	0.8677	0.6345	0.8677	0.9315
No log	6.7059	228	0.8361	0.7027	0.8361	0.9144
No log	6.7647	230	0.7424	0.7895	0.7424	0.8616
No log	6.8235	232	0.7955	0.7403	0.7955	0.8919
No log	6.8824	234	0.8038	0.7484	0.8038	0.8965
No log	6.9412	236	0.7095	0.7821	0.7095	0.8423
No log	7.0	238	0.7437	0.7355	0.7437	0.8624
No log	7.0588	240	0.9827	0.6275	0.9827	0.9913
No log	7.1176	242	1.2333	0.5733	1.2333	1.1105
No log	7.1765	244	1.2114	0.56	1.2114	1.1006
No log	7.2353	246	0.9929	0.6575	0.9929	0.9965
No log	7.2941	248	0.7797	0.7260	0.7797	0.8830
No log	7.3529	250	0.8507	0.6846	0.8507	0.9224
No log	7.4118	252	0.9083	0.6531	0.9083	0.9530
No log	7.4706	254	0.8009	0.72	0.8009	0.8949
No log	7.5294	256	0.6975	0.7273	0.6975	0.8352
No log	7.5882	258	0.8294	0.6968	0.8294	0.9107
No log	7.6471	260	0.8652	0.6824	0.8652	0.9302
No log	7.7059	262	0.7115	0.7595	0.7115	0.8435
No log	7.7647	264	0.6415	0.7643	0.6415	0.8009
No log	7.8235	266	0.7403	0.7342	0.7403	0.8604
No log	7.8824	268	0.7424	0.7152	0.7424	0.8616
No log	7.9412	270	0.7086	0.7586	0.7086	0.8418
No log	8.0	272	0.6852	0.7778	0.6852	0.8278
No log	8.0588	274	0.6323	0.7862	0.6323	0.7951
No log	8.1176	276	0.6087	0.7613	0.6087	0.7802
No log	8.1765	278	0.6315	0.7662	0.6315	0.7947
No log	8.2353	280	0.5640	0.7771	0.5640	0.7510
No log	8.2941	282	0.5728	0.8108	0.5728	0.7568
No log	8.3529	284	0.6500	0.8	0.6500	0.8062
No log	8.4118	286	0.6506	0.7867	0.6506	0.8066
No log	8.4706	288	0.6333	0.8	0.6333	0.7958
No log	8.5294	290	0.6098	0.8108	0.6098	0.7809
No log	8.5882	292	0.6214	0.8054	0.6214	0.7883
No log	8.6471	294	0.6174	0.8108	0.6174	0.7858
No log	8.7059	296	0.6608	0.8	0.6608	0.8129
No log	8.7647	298	0.7728	0.6939	0.7728	0.8791
No log	8.8235	300	0.7798	0.7123	0.7798	0.8831
No log	8.8824	302	0.7187	0.7027	0.7187	0.8478
No log	8.9412	304	0.7331	0.7297	0.7331	0.8562
No log	9.0	306	0.8372	0.6944	0.8372	0.9150
No log	9.0588	308	0.8787	0.6857	0.8787	0.9374
No log	9.1176	310	0.7722	0.6993	0.7722	0.8787
No log	9.1765	312	0.6981	0.76	0.6981	0.8355
No log	9.2353	314	0.7290	0.7285	0.7290	0.8538
No log	9.2941	316	0.6976	0.7383	0.6976	0.8352
No log	9.3529	318	0.6743	0.75	0.6743	0.8212
No log	9.4118	320	0.6550	0.7724	0.6550	0.8093
No log	9.4706	322	0.6134	0.7724	0.6134	0.7832
No log	9.5294	324	0.5792	0.7785	0.5792	0.7611
No log	9.5882	326	0.5704	0.7755	0.5704	0.7553
No log	9.6471	328	0.5691	0.8188	0.5691	0.7544
No log	9.7059	330	0.5892	0.7947	0.5892	0.7676
No log	9.7647	332	0.5772	0.8221	0.5772	0.7598
No log	9.8235	334	0.6252	0.75	0.6252	0.7907
No log	9.8824	336	0.6462	0.7574	0.6462	0.8039
No log	9.9412	338	0.6127	0.7730	0.6127	0.7827
No log	10.0	340	0.5936	0.8205	0.5936	0.7705
No log	10.0588	342	0.6425	0.7838	0.6425	0.8016
No log	10.1176	344	0.6670	0.7639	0.6670	0.8167
No log	10.1765	346	0.6470	0.7808	0.6470	0.8044
No log	10.2353	348	0.6762	0.7703	0.6762	0.8223
No log	10.2941	350	0.6478	0.7517	0.6478	0.8049
No log	10.3529	352	0.6051	0.7808	0.6051	0.7779
No log	10.4118	354	0.6910	0.7285	0.6910	0.8312
No log	10.4706	356	0.7560	0.7114	0.7560	0.8695
No log	10.5294	358	0.7342	0.6986	0.7342	0.8569
No log	10.5882	360	0.6623	0.7534	0.6623	0.8138
No log	10.6471	362	0.6617	0.7619	0.6617	0.8134
No log	10.7059	364	0.6546	0.7792	0.6546	0.8091
No log	10.7647	366	0.6289	0.7771	0.6289	0.7930
No log	10.8235	368	0.6052	0.8025	0.6052	0.7780
No log	10.8824	370	0.5845	0.8095	0.5845	0.7645
No log	10.9412	372	0.6038	0.8118	0.6038	0.7771
No log	11.0	374	0.6273	0.7654	0.6273	0.7920
No log	11.0588	376	0.6199	0.7682	0.6199	0.7873
No log	11.1176	378	0.6226	0.7671	0.6226	0.7890
No log	11.1765	380	0.5908	0.7785	0.5908	0.7686
No log	11.2353	382	0.5644	0.7692	0.5644	0.7513
No log	11.2941	384	0.5917	0.7421	0.5917	0.7692
No log	11.3529	386	0.6066	0.7421	0.6066	0.7789
No log	11.4118	388	0.6937	0.6968	0.6937	0.8329
No log	11.4706	390	0.7402	0.7105	0.7402	0.8603
No log	11.5294	392	0.6844	0.7586	0.6844	0.8273
No log	11.5882	394	0.6446	0.7586	0.6446	0.8029
No log	11.6471	396	0.6247	0.7586	0.6247	0.7904
No log	11.7059	398	0.6566	0.7517	0.6566	0.8103
No log	11.7647	400	0.6430	0.7517	0.6430	0.8019
No log	11.8235	402	0.5467	0.8354	0.5467	0.7394
No log	11.8824	404	0.5357	0.8025	0.5357	0.7319
No log	11.9412	406	0.5462	0.8	0.5462	0.7391
No log	12.0	408	0.5575	0.8025	0.5575	0.7466
No log	12.0588	410	0.5525	0.8101	0.5525	0.7433
No log	12.1176	412	0.5685	0.8105	0.5685	0.7540
No log	12.1765	414	0.5759	0.8105	0.5759	0.7588
No log	12.2353	416	0.5318	0.8153	0.5318	0.7292
No log	12.2941	418	0.4926	0.8148	0.4926	0.7019
No log	12.3529	420	0.5130	0.7831	0.5130	0.7162
No log	12.4118	422	0.5112	0.7904	0.5112	0.7150
No log	12.4706	424	0.4833	0.7929	0.4833	0.6952
No log	12.5294	426	0.4890	0.8242	0.4890	0.6993
No log	12.5882	428	0.5078	0.8242	0.5078	0.7126
No log	12.6471	430	0.5239	0.8193	0.5239	0.7238
No log	12.7059	432	0.5254	0.8166	0.5254	0.7248
No log	12.7647	434	0.5283	0.8263	0.5283	0.7269
No log	12.8235	436	0.5505	0.8129	0.5505	0.7420
No log	12.8824	438	0.6074	0.8129	0.6074	0.7793
No log	12.9412	440	0.6175	0.8025	0.6175	0.7858
No log	13.0	442	0.6030	0.8025	0.6030	0.7765
No log	13.0588	444	0.5967	0.8025	0.5967	0.7724
No log	13.1176	446	0.5656	0.8129	0.5656	0.7520
No log	13.1765	448	0.5639	0.8289	0.5639	0.7509
No log	13.2353	450	0.6081	0.8212	0.6081	0.7798
No log	13.2941	452	0.6451	0.7482	0.6451	0.8032
No log	13.3529	454	0.6389	0.7482	0.6389	0.7993
No log	13.4118	456	0.5936	0.7867	0.5936	0.7704
No log	13.4706	458	0.5860	0.7821	0.5860	0.7655
No log	13.5294	460	0.6160	0.7848	0.6160	0.7849
No log	13.5882	462	0.6026	0.7712	0.6026	0.7763
No log	13.6471	464	0.6241	0.7682	0.6241	0.7900
No log	13.7059	466	0.6687	0.7246	0.6687	0.8178
No log	13.7647	468	0.7020	0.7111	0.7020	0.8379
No log	13.8235	470	0.7149	0.7015	0.7149	0.8455
No log	13.8824	472	0.6944	0.7111	0.6944	0.8333
No log	13.9412	474	0.6678	0.7724	0.6678	0.8172
No log	14.0	476	0.7076	0.7413	0.7076	0.8412
No log	14.0588	478	0.7461	0.6950	0.7461	0.8638
No log	14.1176	480	0.7012	0.75	0.7012	0.8374
No log	14.1765	482	0.6701	0.75	0.6701	0.8186
No log	14.2353	484	0.6909	0.7465	0.6909	0.8312
No log	14.2941	486	0.7524	0.6957	0.7524	0.8674
No log	14.3529	488	0.7628	0.6957	0.7628	0.8734
No log	14.4118	490	0.7242	0.7324	0.7242	0.8510
No log	14.4706	492	0.6916	0.7361	0.6916	0.8316
No log	14.5294	494	0.6876	0.7347	0.6876	0.8292
No log	14.5882	496	0.6660	0.7483	0.6660	0.8161
No log	14.6471	498	0.6949	0.7534	0.6949	0.8336
0.3771	14.7059	500	0.7507	0.7324	0.7507	0.8664
0.3771	14.7647	502	0.7592	0.7324	0.7592	0.8713
0.3771	14.8235	504	0.7193	0.7448	0.7193	0.8481
0.3771	14.8824	506	0.7196	0.6667	0.7196	0.8483
0.3771	14.9412	508	0.7293	0.7172	0.7293	0.8540
0.3771	15.0	510	0.6907	0.7222	0.6907	0.8311
0.3771	15.0588	512	0.6704	0.7568	0.6704	0.8188
0.3771	15.1176	514	0.7148	0.7468	0.7148	0.8455
0.3771	15.1765	516	0.7636	0.7195	0.7636	0.8738
0.3771	15.2353	518	0.7413	0.7342	0.7413	0.8610
0.3771	15.2941	520	0.7226	0.7417	0.7226	0.8501
0.3771	15.3529	522	0.7116	0.7568	0.7116	0.8436
0.3771	15.4118	524	0.7266	0.7619	0.7266	0.8524
0.3771	15.4706	526	0.7212	0.7619	0.7212	0.8493
0.3771	15.5294	528	0.7114	0.7286	0.7114	0.8435
0.3771	15.5882	530	0.7169	0.7286	0.7169	0.8467
0.3771	15.6471	532	0.6960	0.7286	0.6960	0.8343
0.3771	15.7059	534	0.6557	0.7606	0.6557	0.8097
0.3771	15.7647	536	0.6349	0.7606	0.6349	0.7968
0.3771	15.8235	538	0.6274	0.7639	0.6274	0.7921
0.3771	15.8824	540	0.6163	0.7692	0.6163	0.7851
0.3771	15.9412	542	0.6778	0.7456	0.6778	0.8233
0.3771	16.0	544	0.8217	0.7458	0.8217	0.9065
0.3771	16.0588	546	0.9062	0.7241	0.9062	0.9520
0.3771	16.1176	548	0.9424	0.6335	0.9424	0.9708
0.3771	16.1765	550	0.8750	0.6712	0.8750	0.9354
0.3771	16.2353	552	0.7942	0.7222	0.7942	0.8912
0.3771	16.2941	554	0.7208	0.7260	0.7208	0.8490

Framework versions

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