ASAP_FineTuningBERT_AugV3_k1_task1_organization_fold1

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5283
• Qwk: 0.6259
• Mse: 0.5283
• Rmse: 0.7268

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: 32
• eval_batch_size: 32
• 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	0.0133	2	13.6607	0.0	13.6607	3.6960
No log	0.0267	4	11.4024	0.0	11.4024	3.3767
No log	0.04	6	9.0075	0.0002	9.0075	3.0013
No log	0.0533	8	6.9717	0.0197	6.9717	2.6404
No log	0.0667	10	5.3280	0.0018	5.3280	2.3083
No log	0.08	12	3.9704	0.0059	3.9704	1.9926
No log	0.0933	14	2.9815	0.0227	2.9815	1.7267
No log	0.1067	16	2.0925	0.0079	2.0925	1.4465
No log	0.12	18	1.5854	0.0	1.5854	1.2591
No log	0.1333	20	1.6292	-0.0203	1.6292	1.2764
No log	0.1467	22	2.8454	-0.0067	2.8454	1.6868
No log	0.16	24	1.7662	-0.0394	1.7662	1.3290
No log	0.1733	26	1.2483	0.0262	1.2483	1.1173
No log	0.1867	28	1.3990	-0.0333	1.3990	1.1828
No log	0.2	30	1.4747	-0.0322	1.4747	1.2144
No log	0.2133	32	1.7462	0.0005	1.7462	1.3214
No log	0.2267	34	1.9636	0.0	1.9636	1.4013
No log	0.24	36	1.6157	-0.0242	1.6157	1.2711
No log	0.2533	38	1.2023	0.0119	1.2023	1.0965
No log	0.2667	40	1.3781	0.0206	1.3781	1.1739
No log	0.28	42	1.7386	-0.0025	1.7386	1.3186
No log	0.2933	44	1.8883	0.0	1.8883	1.3742
No log	0.3067	46	1.9045	0.0	1.9045	1.3800
No log	0.32	48	1.5870	-0.0219	1.5870	1.2598
No log	0.3333	50	1.5983	-0.0131	1.5983	1.2643
No log	0.3467	52	1.2697	0.0872	1.2697	1.1268
No log	0.36	54	1.3287	0.0578	1.3287	1.1527
No log	0.3733	56	1.8440	0.0	1.8440	1.3580
No log	0.3867	58	2.0378	0.0	2.0378	1.4275
No log	0.4	60	1.6476	0.0002	1.6476	1.2836
No log	0.4133	62	1.2087	0.1017	1.2087	1.0994
No log	0.4267	64	1.2976	0.1205	1.2976	1.1391
No log	0.44	66	1.3959	0.0728	1.3959	1.1815
No log	0.4533	68	1.2259	0.0773	1.2259	1.1072
No log	0.4667	70	1.1469	0.0481	1.1469	1.0709
No log	0.48	72	1.3156	0.0323	1.3156	1.1470
No log	0.4933	74	1.3391	0.0079	1.3391	1.1572
No log	0.5067	76	1.3619	-0.0034	1.3619	1.1670
No log	0.52	78	0.9937	0.0359	0.9937	0.9968
No log	0.5333	80	0.9656	0.0	0.9656	0.9827
No log	0.5467	82	0.9602	0.0	0.9602	0.9799
No log	0.56	84	0.9467	0.0299	0.9467	0.9730
No log	0.5733	86	0.9373	0.0362	0.9373	0.9681
No log	0.5867	88	0.9194	0.0106	0.9194	0.9589
No log	0.6	90	0.9714	0.0	0.9714	0.9856
No log	0.6133	92	0.9797	0.0013	0.9797	0.9898
No log	0.6267	94	0.9337	0.0	0.9337	0.9663
No log	0.64	96	0.8742	0.0198	0.8742	0.9350
No log	0.6533	98	1.0278	0.0817	1.0278	1.0138
No log	0.6667	100	1.2888	0.0542	1.2888	1.1353
No log	0.68	102	1.1874	0.0900	1.1874	1.0897
No log	0.6933	104	0.9632	0.0877	0.9632	0.9814
No log	0.7067	106	0.8459	0.0804	0.8459	0.9197
No log	0.72	108	0.8715	0.0262	0.8715	0.9335
No log	0.7333	110	0.8509	0.0262	0.8509	0.9224
No log	0.7467	112	0.8169	0.0262	0.8169	0.9038
No log	0.76	114	0.8022	0.0794	0.8022	0.8957
No log	0.7733	116	0.8223	0.1068	0.8223	0.9068
No log	0.7867	118	0.8124	0.1483	0.8124	0.9013
No log	0.8	120	0.7972	0.1950	0.7972	0.8929
No log	0.8133	122	0.8444	0.2650	0.8444	0.9189
No log	0.8267	124	0.8818	0.2225	0.8818	0.9390
No log	0.84	126	0.8455	0.2507	0.8455	0.9195
No log	0.8533	128	0.7698	0.2662	0.7698	0.8774
No log	0.8667	130	0.7102	0.0986	0.7102	0.8428
No log	0.88	132	0.7021	0.1149	0.7021	0.8379
No log	0.8933	134	0.6666	0.1783	0.6666	0.8165
No log	0.9067	136	0.7221	0.4623	0.7221	0.8498
No log	0.92	138	0.9050	0.3256	0.9050	0.9513
No log	0.9333	140	1.0062	0.2022	1.0062	1.0031
No log	0.9467	142	1.0037	0.1509	1.0037	1.0018
No log	0.96	144	0.9015	0.2819	0.9015	0.9495
No log	0.9733	146	0.7667	0.5085	0.7667	0.8756
No log	0.9867	148	0.6534	0.4043	0.6534	0.8083
No log	1.0	150	0.6199	0.2859	0.6199	0.7874
No log	1.0133	152	0.6219	0.3743	0.6219	0.7886
No log	1.0267	154	0.6510	0.4890	0.6510	0.8069
No log	1.04	156	0.6692	0.5044	0.6692	0.8181
No log	1.0533	158	0.6923	0.5255	0.6923	0.8321
No log	1.0667	160	0.6044	0.4359	0.6044	0.7775
No log	1.08	162	0.6206	0.2743	0.6206	0.7878
No log	1.0933	164	0.6720	0.2421	0.6720	0.8198
No log	1.1067	166	0.6995	0.2524	0.6995	0.8363
No log	1.12	168	0.5703	0.3129	0.5703	0.7552
No log	1.1333	170	0.5657	0.5241	0.5657	0.7521
No log	1.1467	172	0.6678	0.5110	0.6678	0.8172
No log	1.16	174	0.6599	0.3255	0.6599	0.8123
No log	1.1733	176	0.6527	0.4577	0.6527	0.8079
No log	1.1867	178	0.6420	0.5451	0.6420	0.8013
No log	1.2	180	0.5411	0.5304	0.5411	0.7356
No log	1.2133	182	0.5195	0.5425	0.5195	0.7208
No log	1.2267	184	0.6062	0.5588	0.6062	0.7786
No log	1.24	186	0.7488	0.5106	0.7488	0.8653
No log	1.2533	188	0.7183	0.5007	0.7183	0.8475
No log	1.2667	190	0.6929	0.4438	0.6929	0.8324
No log	1.28	192	0.6114	0.3173	0.6114	0.7819
No log	1.2933	194	0.5500	0.4633	0.5500	0.7416
No log	1.3067	196	0.5456	0.5531	0.5456	0.7386
No log	1.32	198	0.6125	0.5361	0.6125	0.7826
No log	1.3333	200	0.8416	0.4671	0.8416	0.9174
No log	1.3467	202	0.9776	0.4037	0.9776	0.9887
No log	1.3600	204	0.9236	0.4434	0.9236	0.9610
No log	1.3733	206	0.7034	0.5240	0.7034	0.8387
No log	1.3867	208	0.4751	0.4884	0.4751	0.6893
No log	1.4	210	0.6308	0.3232	0.6308	0.7942
No log	1.4133	212	0.5651	0.3538	0.5651	0.7518
No log	1.4267	214	0.4852	0.4687	0.4852	0.6965
No log	1.44	216	0.5241	0.5591	0.5241	0.7240
No log	1.4533	218	0.6890	0.4925	0.6890	0.8301
No log	1.4667	220	0.7531	0.5031	0.7531	0.8678
No log	1.48	222	0.8139	0.4833	0.8139	0.9021
No log	1.4933	224	0.7569	0.5387	0.7569	0.8700
No log	1.5067	226	0.6993	0.5719	0.6993	0.8363
No log	1.52	228	0.5344	0.5959	0.5344	0.7310
No log	1.5333	230	0.4724	0.5802	0.4724	0.6873
No log	1.5467	232	0.4614	0.5422	0.4614	0.6792
No log	1.56	234	0.5188	0.4791	0.5188	0.7203
No log	1.5733	236	0.5657	0.4535	0.5657	0.7521
No log	1.5867	238	0.4609	0.5268	0.4609	0.6789
No log	1.6	240	0.7844	0.5351	0.7844	0.8856
No log	1.6133	242	1.0155	0.4675	1.0155	1.0077
No log	1.6267	244	0.9082	0.4917	0.9082	0.9530
No log	1.6400	246	0.6510	0.5671	0.6510	0.8069
No log	1.6533	248	0.4579	0.5930	0.4579	0.6767
No log	1.6667	250	0.4944	0.5908	0.4944	0.7031
No log	1.6800	252	0.6008	0.6111	0.6008	0.7751
No log	1.6933	254	0.7151	0.6023	0.7151	0.8456
No log	1.7067	256	0.6071	0.6150	0.6071	0.7791
No log	1.72	258	0.4522	0.6347	0.4522	0.6724
No log	1.7333	260	0.4300	0.5616	0.4300	0.6557
No log	1.7467	262	0.5877	0.4731	0.5877	0.7666
No log	1.76	264	0.4636	0.5324	0.4636	0.6809
No log	1.7733	266	0.4516	0.6245	0.4516	0.6720
No log	1.7867	268	0.8260	0.5727	0.8260	0.9088
No log	1.8	270	0.7748	0.5791	0.7748	0.8802
No log	1.8133	272	0.5748	0.5830	0.5748	0.7582
No log	1.8267	274	0.5550	0.3998	0.5550	0.7450
No log	1.8400	276	0.5573	0.3398	0.5573	0.7465
No log	1.8533	278	0.5278	0.3837	0.5278	0.7265
No log	1.8667	280	0.4964	0.4299	0.4964	0.7045
No log	1.88	282	0.4874	0.5943	0.4874	0.6981
No log	1.8933	284	0.5837	0.6126	0.5837	0.7640
No log	1.9067	286	0.6567	0.5843	0.6567	0.8103
No log	1.92	288	0.7005	0.5705	0.7005	0.8369
No log	1.9333	290	0.5721	0.6018	0.5721	0.7564
No log	1.9467	292	0.5149	0.6117	0.5149	0.7175
No log	1.96	294	0.4167	0.5780	0.4167	0.6455
No log	1.9733	296	0.5122	0.4741	0.5122	0.7157
No log	1.9867	298	0.7100	0.3920	0.7100	0.8426
No log	2.0	300	0.6533	0.4098	0.6533	0.8082
No log	2.0133	302	0.4450	0.5163	0.4450	0.6671
No log	2.0267	304	0.4557	0.6081	0.4557	0.6751
No log	2.04	306	0.6023	0.6022	0.6023	0.7761
No log	2.0533	308	0.6382	0.5859	0.6382	0.7989
No log	2.0667	310	0.5929	0.5785	0.5929	0.7700
No log	2.08	312	0.5009	0.5664	0.5009	0.7078
No log	2.0933	314	0.4361	0.5427	0.4361	0.6604
No log	2.1067	316	0.4363	0.5059	0.4363	0.6605
No log	2.12	318	0.4384	0.5007	0.4384	0.6621
No log	2.1333	320	0.4424	0.5470	0.4424	0.6651
No log	2.1467	322	0.4814	0.5673	0.4814	0.6939
No log	2.16	324	0.5074	0.5647	0.5074	0.7123
No log	2.1733	326	0.4990	0.5861	0.4990	0.7064
No log	2.1867	328	0.4723	0.5914	0.4723	0.6872
No log	2.2	330	0.5080	0.6044	0.5080	0.7127
No log	2.2133	332	0.5593	0.6253	0.5593	0.7478
No log	2.2267	334	0.5771	0.6188	0.5771	0.7597
No log	2.24	336	0.5825	0.6210	0.5825	0.7632
No log	2.2533	338	0.5303	0.6299	0.5303	0.7282
No log	2.2667	340	0.5931	0.6118	0.5931	0.7701
No log	2.2800	342	0.6771	0.5736	0.6771	0.8228
No log	2.2933	344	0.6141	0.6024	0.6141	0.7836
No log	2.3067	346	0.4795	0.6209	0.4795	0.6925
No log	2.32	348	0.4231	0.5401	0.4231	0.6504
No log	2.3333	350	0.5592	0.4250	0.5592	0.7478
No log	2.3467	352	0.6445	0.3922	0.6445	0.8028
No log	2.36	354	0.4704	0.5114	0.4704	0.6859
No log	2.3733	356	0.4104	0.6144	0.4104	0.6406
No log	2.3867	358	0.7089	0.5992	0.7089	0.8420
No log	2.4	360	1.0714	0.4654	1.0714	1.0351
No log	2.4133	362	0.9958	0.4903	0.9958	0.9979
No log	2.4267	364	0.6707	0.5648	0.6707	0.8189
No log	2.44	366	0.4229	0.5966	0.4229	0.6503
No log	2.4533	368	0.3941	0.5613	0.3941	0.6277
No log	2.4667	370	0.3901	0.5999	0.3901	0.6246
No log	2.48	372	0.4340	0.6131	0.4340	0.6588
No log	2.4933	374	0.5223	0.6265	0.5223	0.7227
No log	2.5067	376	0.5950	0.6102	0.5950	0.7714
No log	2.52	378	0.5608	0.6150	0.5608	0.7489
No log	2.5333	380	0.5132	0.6129	0.5132	0.7164
No log	2.5467	382	0.4301	0.5903	0.4301	0.6559
No log	2.56	384	0.4054	0.5422	0.4054	0.6367
No log	2.5733	386	0.4438	0.4964	0.4438	0.6662
No log	2.5867	388	0.4267	0.5116	0.4267	0.6532
No log	2.6	390	0.3917	0.5939	0.3917	0.6259
No log	2.6133	392	0.4122	0.6066	0.4122	0.6420
No log	2.6267	394	0.4555	0.6189	0.4555	0.6749
No log	2.64	396	0.4924	0.6298	0.4924	0.7017
No log	2.6533	398	0.4955	0.6384	0.4955	0.7039
No log	2.6667	400	0.4552	0.6266	0.4552	0.6747
No log	2.68	402	0.4194	0.6288	0.4194	0.6476
No log	2.6933	404	0.4172	0.6279	0.4172	0.6459
No log	2.7067	406	0.4454	0.6435	0.4454	0.6674
No log	2.7200	408	0.4752	0.6488	0.4752	0.6893
No log	2.7333	410	0.4424	0.6298	0.4424	0.6651
No log	2.7467	412	0.4134	0.6152	0.4134	0.6429
No log	2.76	414	0.4379	0.5607	0.4379	0.6617
No log	2.7733	416	0.4419	0.5536	0.4419	0.6648
No log	2.7867	418	0.4197	0.6145	0.4197	0.6478
No log	2.8	420	0.5071	0.6475	0.5071	0.7121
No log	2.8133	422	0.7675	0.5908	0.7675	0.8761
No log	2.8267	424	0.9000	0.5335	0.9000	0.9487
No log	2.84	426	0.8978	0.5147	0.8978	0.9475
No log	2.8533	428	0.7941	0.5618	0.7941	0.8911
No log	2.8667	430	0.5661	0.6378	0.5661	0.7524
No log	2.88	432	0.4789	0.6309	0.4789	0.6920
No log	2.8933	434	0.4568	0.6212	0.4568	0.6759
No log	2.9067	436	0.4859	0.6341	0.4859	0.6971
No log	2.92	438	0.4651	0.6231	0.4651	0.6820
No log	2.9333	440	0.4128	0.6251	0.4128	0.6425
No log	2.9467	442	0.3943	0.6019	0.3943	0.6279
No log	2.96	444	0.3860	0.6041	0.3860	0.6213
No log	2.9733	446	0.3867	0.6028	0.3867	0.6219
No log	2.9867	448	0.4134	0.6165	0.4134	0.6430
No log	3.0	450	0.4792	0.6343	0.4792	0.6922
No log	3.0133	452	0.5320	0.6439	0.5320	0.7294
No log	3.0267	454	0.5605	0.6356	0.5605	0.7486
No log	3.04	456	0.5636	0.6359	0.5636	0.7507
No log	3.0533	458	0.5792	0.6269	0.5792	0.7611
No log	3.0667	460	0.5075	0.6302	0.5075	0.7124
No log	3.08	462	0.4535	0.6304	0.4535	0.6734
No log	3.0933	464	0.3937	0.6223	0.3937	0.6274
No log	3.1067	466	0.3670	0.5794	0.3670	0.6058
No log	3.12	468	0.3696	0.6121	0.3696	0.6080
No log	3.1333	470	0.4022	0.6331	0.4022	0.6342
No log	3.1467	472	0.4401	0.6435	0.4401	0.6634
No log	3.16	474	0.4523	0.6446	0.4523	0.6725
No log	3.1733	476	0.4315	0.6316	0.4315	0.6569
No log	3.1867	478	0.3965	0.6201	0.3965	0.6297
No log	3.2	480	0.3898	0.6066	0.3898	0.6243
No log	3.2133	482	0.4003	0.6210	0.4003	0.6327
No log	3.2267	484	0.4149	0.6330	0.4149	0.6441
No log	3.24	486	0.4145	0.6311	0.4145	0.6438
No log	3.2533	488	0.3959	0.6291	0.3959	0.6292
No log	3.2667	490	0.3923	0.6279	0.3923	0.6263
No log	3.2800	492	0.4228	0.6153	0.4228	0.6502
No log	3.2933	494	0.5010	0.6399	0.5010	0.7078
No log	3.3067	496	0.5594	0.6382	0.5594	0.7479
No log	3.32	498	0.4876	0.6404	0.4876	0.6983
1.369	3.3333	500	0.3859	0.6319	0.3859	0.6212
1.369	3.3467	502	0.3831	0.6259	0.3831	0.6190
1.369	3.36	504	0.3784	0.6147	0.3784	0.6151
1.369	3.3733	506	0.3968	0.6338	0.3968	0.6299
1.369	3.3867	508	0.5116	0.6370	0.5116	0.7153
1.369	3.4	510	0.6528	0.6333	0.6528	0.8080
1.369	3.4133	512	0.6505	0.6292	0.6505	0.8066
1.369	3.4267	514	0.6021	0.6340	0.6021	0.7760
1.369	3.44	516	0.4691	0.6342	0.4691	0.6849
1.369	3.4533	518	0.3851	0.6177	0.3851	0.6206
1.369	3.4667	520	0.3668	0.6158	0.3668	0.6056
1.369	3.48	522	0.3623	0.6081	0.3623	0.6019
1.369	3.4933	524	0.3645	0.6085	0.3645	0.6037
1.369	3.5067	526	0.4368	0.6350	0.4368	0.6609
1.369	3.52	528	0.5696	0.6149	0.5696	0.7547
1.369	3.5333	530	0.6137	0.6207	0.6137	0.7834
1.369	3.5467	532	0.6059	0.6315	0.6059	0.7784
1.369	3.56	534	0.5445	0.6249	0.5445	0.7379
1.369	3.5733	536	0.5283	0.6259	0.5283	0.7268

Framework versions

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