ASAP_FineTuningBERT_AugV3_k15_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: 0.8505
• Qwk: 0.0676
• Mse: 0.8505
• Rmse: 0.9222

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	0.0011	2	10.0047	0.0	10.0047	3.1630
No log	0.0023	4	8.9454	0.0	8.9454	2.9909
No log	0.0034	6	7.6345	0.0082	7.6345	2.7631
No log	0.0045	8	6.4765	0.0069	6.4765	2.5449
No log	0.0056	10	5.1755	0.0037	5.1755	2.2750
No log	0.0068	12	4.2966	0.0	4.2966	2.0728
No log	0.0079	14	3.4764	0.0614	3.4764	1.8645
No log	0.0090	16	2.7420	0.0253	2.7420	1.6559
No log	0.0101	18	2.1923	0.0079	2.1923	1.4806
No log	0.0113	20	2.6331	0.0340	2.6331	1.6227
No log	0.0124	22	2.5181	0.0253	2.5181	1.5868
No log	0.0135	24	1.4859	0.0039	1.4859	1.2190
No log	0.0147	26	1.4553	0.0024	1.4553	1.2063
No log	0.0158	28	2.0731	0.0	2.0731	1.4398
No log	0.0169	30	2.3882	0.0	2.3882	1.5454
No log	0.0180	32	2.8720	-0.0009	2.8720	1.6947
No log	0.0192	34	2.2022	0.0	2.2022	1.4840
No log	0.0203	36	2.1363	0.0	2.1363	1.4616
No log	0.0214	38	2.3261	0.0	2.3261	1.5252
No log	0.0225	40	2.1542	0.0	2.1542	1.4677
No log	0.0237	42	1.7925	0.0	1.7925	1.3388
No log	0.0248	44	1.7598	0.0	1.7598	1.3266
No log	0.0259	46	1.7037	0.0	1.7037	1.3053
No log	0.0271	48	1.8133	0.0	1.8133	1.3466
No log	0.0282	50	2.4095	0.0	2.4095	1.5523
No log	0.0293	52	2.2750	0.0	2.2750	1.5083
No log	0.0304	54	1.8373	0.0	1.8373	1.3555
No log	0.0316	56	1.7890	0.0	1.7890	1.3375
No log	0.0327	58	1.7752	0.0	1.7752	1.3324
No log	0.0338	60	1.9470	0.0	1.9470	1.3954
No log	0.0349	62	2.3749	0.0	2.3749	1.5411
No log	0.0361	64	2.5639	0.0	2.5639	1.6012
No log	0.0372	66	2.3363	0.0	2.3363	1.5285
No log	0.0383	68	2.0901	0.0	2.0901	1.4457
No log	0.0395	70	1.8142	0.0	1.8142	1.3469
No log	0.0406	72	1.5811	0.0	1.5811	1.2574
No log	0.0417	74	1.6051	0.0	1.6051	1.2669
No log	0.0428	76	1.9364	0.0	1.9364	1.3915
No log	0.0440	78	2.7479	0.0	2.7479	1.6577
No log	0.0451	80	3.1647	0.0	3.1647	1.7790
No log	0.0462	82	2.9378	0.0	2.9378	1.7140
No log	0.0474	84	2.3250	0.0	2.3250	1.5248
No log	0.0485	86	1.9022	0.0	1.9022	1.3792
No log	0.0496	88	1.9596	0.0	1.9596	1.3999
No log	0.0507	90	2.0232	0.0	2.0232	1.4224
No log	0.0519	92	2.1708	0.0	2.1708	1.4734
No log	0.0530	94	2.1052	0.0	2.1052	1.4509
No log	0.0541	96	1.7352	0.0	1.7352	1.3173
No log	0.0552	98	1.6309	0.0	1.6309	1.2771
No log	0.0564	100	1.5875	-0.0010	1.5875	1.2600
No log	0.0575	102	1.5852	0.0	1.5852	1.2590
No log	0.0586	104	1.6687	0.0	1.6687	1.2918
No log	0.0598	106	1.7366	0.0	1.7366	1.3178
No log	0.0609	108	1.8360	0.0	1.8360	1.3550
No log	0.0620	110	1.8293	0.0	1.8293	1.3525
No log	0.0631	112	2.0746	0.0	2.0746	1.4403
No log	0.0643	114	2.4498	0.0	2.4498	1.5652
No log	0.0654	116	2.5572	0.0	2.5572	1.5991
No log	0.0665	118	2.1713	0.0	2.1713	1.4735
No log	0.0676	120	2.0996	0.0	2.0996	1.4490
No log	0.0688	122	2.0345	0.0	2.0345	1.4263
No log	0.0699	124	2.0377	0.0	2.0377	1.4275
No log	0.0710	126	2.0398	0.0	2.0398	1.4282
No log	0.0722	128	1.8206	0.0	1.8206	1.3493
No log	0.0733	130	1.6920	0.0	1.6920	1.3008
No log	0.0744	132	1.6918	0.0	1.6918	1.3007
No log	0.0755	134	1.7606	0.0	1.7606	1.3269
No log	0.0767	136	1.8214	0.0	1.8214	1.3496
No log	0.0778	138	1.9290	0.0	1.9290	1.3889
No log	0.0789	140	2.0099	0.0	2.0099	1.4177
No log	0.0800	142	2.2602	0.0	2.2602	1.5034
No log	0.0812	144	2.3509	0.0	2.3509	1.5333
No log	0.0823	146	2.2748	0.0	2.2748	1.5082
No log	0.0834	148	2.2192	0.0	2.2192	1.4897
No log	0.0846	150	2.2036	0.0	2.2036	1.4845
No log	0.0857	152	2.0851	0.0	2.0851	1.4440
No log	0.0868	154	1.9277	0.0	1.9277	1.3884
No log	0.0879	156	1.9318	0.0	1.9318	1.3899
No log	0.0891	158	1.9771	0.0	1.9771	1.4061
No log	0.0902	160	2.0224	0.0	2.0224	1.4221
No log	0.0913	162	1.9576	0.0	1.9576	1.3991
No log	0.0924	164	1.7850	0.0	1.7850	1.3360
No log	0.0936	166	1.7255	0.0	1.7255	1.3136
No log	0.0947	168	1.8145	0.0	1.8145	1.3470
No log	0.0958	170	1.9883	0.0	1.9883	1.4101
No log	0.0970	172	2.1711	0.0	2.1711	1.4735
No log	0.0981	174	2.2092	0.0	2.2092	1.4863
No log	0.0992	176	2.2816	0.0	2.2816	1.5105
No log	0.1003	178	2.3667	0.0	2.3667	1.5384
No log	0.1015	180	2.4460	0.0	2.4460	1.5640
No log	0.1026	182	2.3247	0.0	2.3247	1.5247
No log	0.1037	184	2.1933	0.0	2.1933	1.4810
No log	0.1048	186	2.1068	0.0	2.1068	1.4515
No log	0.1060	188	1.8973	0.0	1.8973	1.3774
No log	0.1071	190	1.8338	0.0	1.8338	1.3542
No log	0.1082	192	1.9527	0.0	1.9527	1.3974
No log	0.1094	194	2.0163	0.0	2.0163	1.4200
No log	0.1105	196	2.1862	0.0	2.1862	1.4786
No log	0.1116	198	2.4934	0.0	2.4934	1.5791
No log	0.1127	200	2.3538	0.0	2.3538	1.5342
No log	0.1139	202	2.1314	0.0	2.1314	1.4599
No log	0.1150	204	2.0276	0.0	2.0276	1.4239
No log	0.1161	206	2.1921	0.0	2.1921	1.4806
No log	0.1172	208	2.3520	0.0	2.3520	1.5336
No log	0.1184	210	2.6467	0.0	2.6467	1.6269
No log	0.1195	212	2.4306	0.0	2.4306	1.5590
No log	0.1206	214	1.9017	0.0	1.9017	1.3790
No log	0.1218	216	1.4978	-0.0139	1.4978	1.2238
No log	0.1229	218	1.4043	-0.0359	1.4043	1.1851
No log	0.1240	220	1.5060	-0.0076	1.5060	1.2272
No log	0.1251	222	1.8336	0.0	1.8336	1.3541
No log	0.1263	224	2.3565	0.0	2.3565	1.5351
No log	0.1274	226	2.6620	0.0	2.6620	1.6316
No log	0.1285	228	2.7252	0.0	2.7252	1.6508
No log	0.1297	230	2.3642	0.0	2.3642	1.5376
No log	0.1308	232	2.0187	0.0	2.0187	1.4208
No log	0.1319	234	1.8010	0.0	1.8009	1.3420
No log	0.1330	236	1.6997	0.0	1.6997	1.3037
No log	0.1342	238	1.7753	0.0	1.7753	1.3324
No log	0.1353	240	1.9195	0.0	1.9195	1.3855
No log	0.1364	242	1.9717	0.0	1.9717	1.4042
No log	0.1375	244	2.0455	0.0	2.0455	1.4302
No log	0.1387	246	1.9000	0.0	1.9000	1.3784
No log	0.1398	248	1.7286	0.0	1.7286	1.3148
No log	0.1409	250	1.6931	0.0	1.6931	1.3012
No log	0.1421	252	1.7974	0.0	1.7974	1.3407
No log	0.1432	254	1.9091	0.0	1.9091	1.3817
No log	0.1443	256	1.9390	0.0	1.9390	1.3925
No log	0.1454	258	1.8604	0.0	1.8604	1.3640
No log	0.1466	260	1.7518	0.0	1.7518	1.3235
No log	0.1477	262	1.7268	0.0	1.7268	1.3141
No log	0.1488	264	1.8238	0.0	1.8238	1.3505
No log	0.1499	266	1.7855	0.0	1.7855	1.3362
No log	0.1511	268	1.5833	0.0029	1.5833	1.2583
No log	0.1522	270	1.3473	0.0710	1.3473	1.1607
No log	0.1533	272	1.2441	0.0647	1.2441	1.1154
No log	0.1545	274	1.2623	0.0819	1.2623	1.1235
No log	0.1556	276	1.4108	0.0665	1.4108	1.1878
No log	0.1567	278	1.5740	0.0034	1.5740	1.2546
No log	0.1578	280	1.6837	0.0	1.6837	1.2976
No log	0.1590	282	1.6330	0.0005	1.6330	1.2779
No log	0.1601	284	1.4988	0.0325	1.4988	1.2242
No log	0.1612	286	1.3547	0.0838	1.3547	1.1639
No log	0.1623	288	1.3265	0.0914	1.3265	1.1517
No log	0.1635	290	1.4357	0.0428	1.4357	1.1982
No log	0.1646	292	1.4758	0.0331	1.4758	1.2148
No log	0.1657	294	1.4023	0.0635	1.4023	1.1842
No log	0.1669	296	1.3553	0.0747	1.3553	1.1642
No log	0.1680	298	1.3463	0.0827	1.3463	1.1603
No log	0.1691	300	1.3060	0.0862	1.3060	1.1428
No log	0.1702	302	1.3442	0.0716	1.3442	1.1594
No log	0.1714	304	1.4507	0.0430	1.4507	1.2045
No log	0.1725	306	1.5142	0.0119	1.5142	1.2305
No log	0.1736	308	1.6687	0.0	1.6687	1.2918
No log	0.1747	310	1.8485	0.0	1.8485	1.3596
No log	0.1759	312	1.9351	0.0	1.9351	1.3911
No log	0.1770	314	1.8345	0.0	1.8345	1.3544
No log	0.1781	316	1.5906	0.0	1.5906	1.2612
No log	0.1793	318	1.3406	0.1048	1.3406	1.1579
No log	0.1804	320	1.2384	0.0921	1.2384	1.1128
No log	0.1815	322	1.2328	0.0921	1.2328	1.1103
No log	0.1826	324	1.2713	0.1197	1.2713	1.1275
No log	0.1838	326	1.3517	0.0968	1.3517	1.1626
No log	0.1849	328	1.3799	0.0757	1.3799	1.1747
No log	0.1860	330	1.4759	0.0031	1.4759	1.2149
No log	0.1871	332	1.5380	-0.0005	1.5380	1.2402
No log	0.1883	334	1.5357	-0.0005	1.5357	1.2392
No log	0.1894	336	1.5078	0.0104	1.5078	1.2279
No log	0.1905	338	1.4953	0.0244	1.4953	1.2228
No log	0.1917	340	1.3762	0.1089	1.3762	1.1731
No log	0.1928	342	1.2525	0.1360	1.2525	1.1191
No log	0.1939	344	1.1876	0.1121	1.1876	1.0898
No log	0.1950	346	1.1763	0.1041	1.1763	1.0846
No log	0.1962	348	1.1523	0.0868	1.1523	1.0735
No log	0.1973	350	1.1415	0.0977	1.1415	1.0684
No log	0.1984	352	1.1644	0.1094	1.1644	1.0791
No log	0.1995	354	1.2059	0.1110	1.2059	1.0981
No log	0.2007	356	1.2484	0.1179	1.2484	1.1173
No log	0.2018	358	1.1463	0.1075	1.1463	1.0707
No log	0.2029	360	1.0586	0.1045	1.0586	1.0289
No log	0.2041	362	1.0035	0.0744	1.0035	1.0018
No log	0.2052	364	0.9864	0.0467	0.9864	0.9932
No log	0.2063	366	0.9696	0.0467	0.9696	0.9847
No log	0.2074	368	0.9763	0.0600	0.9763	0.9881
No log	0.2086	370	1.0467	0.1014	1.0467	1.0231
No log	0.2097	372	1.1056	0.1060	1.1056	1.0515
No log	0.2108	374	1.0847	0.1060	1.0847	1.0415
No log	0.2120	376	1.0379	0.1053	1.0379	1.0188
No log	0.2131	378	0.9986	0.0995	0.9986	0.9993
No log	0.2142	380	0.9677	0.0766	0.9677	0.9837
No log	0.2153	382	0.9596	0.0766	0.9596	0.9796
No log	0.2165	384	0.9779	0.0905	0.9779	0.9889
No log	0.2176	386	0.9829	0.0981	0.9829	0.9914
No log	0.2187	388	0.9945	0.1014	0.9945	0.9972
No log	0.2198	390	1.0299	0.1053	1.0299	1.0148
No log	0.2210	392	1.1083	0.1082	1.1083	1.0528
No log	0.2221	394	1.1971	0.1177	1.1971	1.0941
No log	0.2232	396	1.2446	0.1237	1.2446	1.1156
No log	0.2244	398	1.1894	0.1229	1.1894	1.0906
No log	0.2255	400	1.1429	0.1082	1.1429	1.0691
No log	0.2266	402	1.1032	0.1056	1.1032	1.0504
No log	0.2277	404	1.0770	0.1034	1.0770	1.0378
No log	0.2289	406	1.0586	0.1010	1.0586	1.0289
No log	0.2300	408	1.0146	0.1010	1.0146	1.0073
No log	0.2311	410	0.9658	0.0860	0.9658	0.9827
No log	0.2322	412	0.9344	0.0843	0.9344	0.9666
No log	0.2334	414	0.9266	0.0860	0.9266	0.9626
No log	0.2345	416	0.9202	0.0881	0.9202	0.9593
No log	0.2356	418	0.9121	0.0743	0.9121	0.9550
No log	0.2368	420	0.9162	0.0600	0.9162	0.9572
No log	0.2379	422	0.9287	0.0365	0.9287	0.9637
No log	0.2390	424	0.9378	0.0365	0.9378	0.9684
No log	0.2401	426	0.9444	0.0390	0.9444	0.9718
No log	0.2413	428	0.9574	0.0390	0.9574	0.9785
No log	0.2424	430	0.9799	0.0676	0.9799	0.9899
No log	0.2435	432	1.0149	0.0896	1.0149	1.0074
No log	0.2446	434	1.0818	0.1010	1.0818	1.0401
No log	0.2458	436	1.1287	0.1029	1.1287	1.0624
No log	0.2469	438	1.1481	0.1014	1.1481	1.0715
No log	0.2480	440	1.0856	0.1010	1.0856	1.0419
No log	0.2492	442	1.0272	0.1010	1.0272	1.0135
No log	0.2503	444	0.9721	0.1010	0.9721	0.9860
No log	0.2514	446	0.9233	0.0881	0.9233	0.9609
No log	0.2525	448	0.9006	0.0870	0.9006	0.9490
No log	0.2537	450	0.8903	0.0991	0.8903	0.9435
No log	0.2548	452	0.8821	0.1025	0.8821	0.9392
No log	0.2559	454	0.8696	0.0910	0.8696	0.9325
No log	0.2570	456	0.8643	0.0773	0.8643	0.9297
No log	0.2582	458	0.8634	0.0594	0.8634	0.9292
No log	0.2593	460	0.8694	0.0816	0.8694	0.9324
No log	0.2604	462	0.8815	0.0816	0.8815	0.9389
No log	0.2616	464	0.8725	0.0837	0.8725	0.9341
No log	0.2627	466	0.8627	0.0843	0.8627	0.9288
No log	0.2638	468	0.8663	0.1010	0.8663	0.9307
No log	0.2649	470	0.8768	0.1010	0.8768	0.9364
No log	0.2661	472	0.8781	0.1010	0.8781	0.9371
No log	0.2672	474	0.8797	0.0751	0.8797	0.9379
No log	0.2683	476	0.8855	0.0262	0.8855	0.9410
No log	0.2694	478	0.8942	0.0262	0.8942	0.9456
No log	0.2706	480	0.8976	0.0262	0.8976	0.9474
No log	0.2717	482	0.9092	0.0262	0.9092	0.9535
No log	0.2728	484	0.9344	0.0875	0.9344	0.9667
No log	0.2740	486	0.9357	0.1029	0.9357	0.9673
No log	0.2751	488	0.9024	0.0868	0.9024	0.9499
No log	0.2762	490	0.8768	0.0586	0.8768	0.9364
No log	0.2773	492	0.8709	0.0477	0.8709	0.9332
No log	0.2785	494	0.8631	0.0390	0.8631	0.9290
No log	0.2796	496	0.8588	0.0262	0.8588	0.9267
No log	0.2807	498	0.8553	0.0400	0.8553	0.9248
1.4812	0.2818	500	0.8579	0.0766	0.8579	0.9262
1.4812	0.2830	502	0.8671	0.0936	0.8671	0.9312
1.4812	0.2841	504	0.8662	0.1001	0.8662	0.9307
1.4812	0.2852	506	0.8568	0.0915	0.8568	0.9256
1.4812	0.2864	508	0.8493	0.0810	0.8493	0.9216
1.4812	0.2875	510	0.8484	0.0810	0.8484	0.9211
1.4812	0.2886	512	0.8479	0.0794	0.8479	0.9208
1.4812	0.2897	514	0.8465	0.0895	0.8465	0.9200
1.4812	0.2909	516	0.8435	0.0801	0.8435	0.9184
1.4812	0.2920	518	0.8416	0.0900	0.8416	0.9174
1.4812	0.2931	520	0.8502	0.1010	0.8502	0.9221
1.4812	0.2943	522	0.8573	0.1010	0.8573	0.9259
1.4812	0.2954	524	0.8657	0.1010	0.8657	0.9304
1.4812	0.2965	526	0.8681	0.1010	0.8681	0.9317
1.4812	0.2976	528	0.8639	0.0991	0.8639	0.9294
1.4812	0.2988	530	0.8535	0.0822	0.8535	0.9238
1.4812	0.2999	532	0.8371	0.0728	0.8371	0.9149
1.4812	0.3010	534	0.8221	0.0822	0.8221	0.9067
1.4812	0.3021	536	0.8138	0.0721	0.8138	0.9021
1.4812	0.3033	538	0.8160	0.0721	0.8160	0.9033
1.4812	0.3044	540	0.8282	0.0721	0.8282	0.9100
1.4812	0.3055	542	0.8334	0.0721	0.8334	0.9129
1.4812	0.3067	544	0.8242	0.0890	0.8242	0.9078
1.4812	0.3078	546	0.8199	0.0916	0.8199	0.9055
1.4812	0.3089	548	0.8210	0.0756	0.8210	0.9061
1.4812	0.3100	550	0.8246	0.0706	0.8246	0.9081
1.4812	0.3112	552	0.8281	0.0706	0.8281	0.9100
1.4812	0.3123	554	0.8334	0.0916	0.8334	0.9129
1.4812	0.3134	556	0.8293	0.0890	0.8293	0.9107
1.4812	0.3145	558	0.8222	0.0896	0.8222	0.9067
1.4812	0.3157	560	0.8224	0.0890	0.8224	0.9069
1.4812	0.3168	562	0.8322	0.0885	0.8322	0.9122
1.4812	0.3179	564	0.8381	0.0916	0.8381	0.9155
1.4812	0.3191	566	0.8413	0.0901	0.8413	0.9172
1.4812	0.3202	568	0.8561	0.0901	0.8561	0.9253
1.4812	0.3213	570	0.8643	0.0783	0.8643	0.9297
1.4812	0.3224	572	0.8744	0.0706	0.8744	0.9351
1.4812	0.3236	574	0.8842	0.0684	0.8842	0.9403
1.4812	0.3247	576	0.8750	0.0539	0.8750	0.9354
1.4812	0.3258	578	0.8662	0.0571	0.8662	0.9307
1.4812	0.3269	580	0.8505	0.0676	0.8505	0.9222

Framework versions

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