ASAP_FineTuningBERT_AugV3_k10_task1_organization_fold4

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: 1.0469
• Qwk: 0.2729
• Mse: 1.0469
• Rmse: 1.0232

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	0.0018	2	10.1358	0.0	10.1358	3.1837
No log	0.0035	4	8.6276	-0.0008	8.6276	2.9373
No log	0.0053	6	6.9215	0.0046	6.9215	2.6309
No log	0.0071	8	5.6596	0.0037	5.6596	2.3790
No log	0.0088	10	4.5407	0.0018	4.5407	2.1309
No log	0.0106	12	3.8128	0.0386	3.8128	1.9526
No log	0.0124	14	3.0074	0.0171	3.0074	1.7342
No log	0.0141	16	2.4403	0.0118	2.4403	1.5621
No log	0.0159	18	2.0293	0.0079	2.0293	1.4245
No log	0.0177	20	2.0828	0.0040	2.0828	1.4432
No log	0.0194	22	2.0659	0.0040	2.0659	1.4373
No log	0.0212	24	2.8098	0.0009	2.8098	1.6762
No log	0.0229	26	1.9749	0.0040	1.9749	1.4053
No log	0.0247	28	1.8910	0.0040	1.8910	1.3751
No log	0.0265	30	2.0246	0.0040	2.0246	1.4229
No log	0.0282	32	2.2142	0.0040	2.2142	1.4880
No log	0.0300	34	2.0493	0.0040	2.0493	1.4315
No log	0.0318	36	2.0142	0.0040	2.0142	1.4192
No log	0.0335	38	2.1019	0.0040	2.1019	1.4498
No log	0.0353	40	1.8828	0.0040	1.8828	1.3721
No log	0.0371	42	1.6868	0.0040	1.6868	1.2988
No log	0.0388	44	1.8783	0.0040	1.8783	1.3705
No log	0.0406	46	2.2277	0.0040	2.2277	1.4926
No log	0.0424	48	2.0631	0.0040	2.0631	1.4364
No log	0.0441	50	1.6913	0.0040	1.6913	1.3005
No log	0.0459	52	1.7121	0.0040	1.7121	1.3085
No log	0.0477	54	2.3189	0.0040	2.3189	1.5228
No log	0.0494	56	3.8606	-0.0441	3.8606	1.9648
No log	0.0512	58	3.5192	-0.0106	3.5192	1.8760
No log	0.0530	60	2.1302	0.0040	2.1302	1.4595
No log	0.0547	62	1.3246	0.0531	1.3246	1.1509
No log	0.0565	64	1.3379	0.0928	1.3379	1.1567
No log	0.0583	66	1.7814	0.0040	1.7814	1.3347
No log	0.0600	68	2.4056	0.0040	2.4056	1.5510
No log	0.0618	70	2.4932	0.0040	2.4932	1.5790
No log	0.0635	72	2.5985	0.0040	2.5985	1.6120
No log	0.0653	74	2.2520	0.0040	2.2520	1.5007
No log	0.0671	76	1.9323	0.0040	1.9323	1.3901
No log	0.0688	78	1.9150	0.0040	1.9150	1.3838
No log	0.0706	80	1.8036	0.0040	1.8036	1.3430
No log	0.0724	82	1.8962	0.0040	1.8962	1.3770
No log	0.0741	84	2.2944	0.0040	2.2944	1.5147
No log	0.0759	86	2.1044	0.0040	2.1044	1.4507
No log	0.0777	88	2.1024	0.0040	2.1024	1.4500
No log	0.0794	90	1.8947	0.0040	1.8947	1.3765
No log	0.0812	92	1.8874	0.0040	1.8874	1.3738
No log	0.0830	94	2.1713	0.0040	2.1713	1.4735
No log	0.0847	96	2.6252	0.0040	2.6252	1.6202
No log	0.0865	98	2.4772	0.0040	2.4772	1.5739
No log	0.0883	100	2.0223	0.0040	2.0223	1.4221
No log	0.0900	102	1.6999	0.0	1.6999	1.3038
No log	0.0918	104	1.6205	0.0	1.6205	1.2730
No log	0.0936	106	1.5650	0.0	1.5650	1.2510
No log	0.0953	108	1.6027	0.0	1.6027	1.2660
No log	0.0971	110	1.5240	0.0	1.5240	1.2345
No log	0.0989	112	1.5265	0.0	1.5265	1.2355
No log	0.1006	114	1.6190	0.0	1.6190	1.2724
No log	0.1024	116	1.7642	0.0040	1.7642	1.3282
No log	0.1041	118	1.8919	0.0040	1.8919	1.3755
No log	0.1059	120	1.8338	0.0040	1.8338	1.3542
No log	0.1077	122	1.7210	0.0040	1.7210	1.3119
No log	0.1094	124	1.5691	0.0040	1.5691	1.2526
No log	0.1112	126	1.4739	0.0232	1.4739	1.2141
No log	0.1130	128	1.4760	0.0237	1.4760	1.2149
No log	0.1147	130	1.5565	0.0092	1.5565	1.2476
No log	0.1165	132	1.6250	0.0040	1.6250	1.2747
No log	0.1183	134	1.5088	0.0182	1.5088	1.2283
No log	0.1200	136	1.4600	0.0458	1.4600	1.2083
No log	0.1218	138	1.3639	0.1056	1.3639	1.1678
No log	0.1236	140	1.3323	0.1223	1.3323	1.1543
No log	0.1253	142	1.3041	0.1417	1.3041	1.1420
No log	0.1271	144	1.2799	0.1463	1.2799	1.1313
No log	0.1289	146	1.2783	0.1399	1.2783	1.1306
No log	0.1306	148	1.1864	0.1363	1.1864	1.0892
No log	0.1324	150	1.0726	0.0676	1.0726	1.0357
No log	0.1342	152	1.0592	0.0560	1.0592	1.0292
No log	0.1359	154	1.1015	0.0544	1.1015	1.0495
No log	0.1377	156	1.1468	0.0797	1.1468	1.0709
No log	0.1395	158	1.2403	0.1240	1.2403	1.1137
No log	0.1412	160	1.2887	0.1334	1.2887	1.1352
No log	0.1430	162	1.2393	0.1095	1.2393	1.1132
No log	0.1447	164	1.1605	0.0654	1.1605	1.0773
No log	0.1465	166	1.0955	0.0622	1.0955	1.0467
No log	0.1483	168	1.0433	0.0602	1.0433	1.0214
No log	0.1500	170	1.0059	0.0592	1.0059	1.0030
No log	0.1518	172	0.9691	0.0544	0.9691	0.9844
No log	0.1536	174	0.9481	0.0497	0.9481	0.9737
No log	0.1553	176	0.9321	0.0497	0.9321	0.9655
No log	0.1571	178	0.9105	0.0560	0.9105	0.9542
No log	0.1589	180	0.9165	0.0609	0.9165	0.9573
No log	0.1606	182	0.9199	0.0808	0.9199	0.9591
No log	0.1624	184	0.9144	0.0808	0.9144	0.9562
No log	0.1642	186	0.9105	0.0808	0.9105	0.9542
No log	0.1659	188	0.9034	0.0808	0.9034	0.9505
No log	0.1677	190	0.9009	0.0830	0.9009	0.9492
No log	0.1695	192	0.8726	0.0652	0.8726	0.9341
No log	0.1712	194	0.8656	0.0619	0.8656	0.9304
No log	0.1730	196	0.8773	0.0666	0.8773	0.9366
No log	0.1748	198	0.9017	0.0585	0.9017	0.9496
No log	0.1765	200	0.9193	0.0522	0.9193	0.9588
No log	0.1783	202	0.9623	0.0668	0.9623	0.9810
No log	0.1801	204	0.9861	0.0759	0.9861	0.9930
No log	0.1818	206	0.9610	0.0672	0.9610	0.9803
No log	0.1836	208	0.9583	0.0560	0.9583	0.9789
No log	0.1853	210	0.9727	0.0560	0.9727	0.9862
No log	0.1871	212	1.0051	0.0633	1.0051	1.0025
No log	0.1889	214	1.0791	0.0723	1.0791	1.0388
No log	0.1906	216	1.1744	0.1136	1.1744	1.0837
No log	0.1924	218	1.2123	0.1198	1.2123	1.1010
No log	0.1942	220	1.1733	0.0813	1.1733	1.0832
No log	0.1959	222	1.1483	0.0726	1.1483	1.0716
No log	0.1977	224	1.1900	0.0726	1.1900	1.0909
No log	0.1995	226	1.2639	0.1183	1.2639	1.1242
No log	0.2012	228	1.3629	0.0805	1.3629	1.1675
No log	0.2030	230	1.3711	0.0799	1.3711	1.1709
No log	0.2048	232	1.3827	0.1026	1.3827	1.1759
No log	0.2065	234	1.3211	0.1141	1.3211	1.1494
No log	0.2083	236	1.2001	0.1088	1.2001	1.0955
No log	0.2101	238	1.0673	0.0632	1.0673	1.0331
No log	0.2118	240	1.0132	0.0662	1.0132	1.0066
No log	0.2136	242	1.0313	0.0632	1.0313	1.0155
No log	0.2154	244	1.1069	0.0884	1.1069	1.0521
No log	0.2171	246	1.1685	0.1223	1.1685	1.0810
No log	0.2189	248	1.2475	0.1365	1.2475	1.1169
No log	0.2207	250	1.2286	0.1359	1.2286	1.1084
No log	0.2224	252	1.0917	0.1121	1.0917	1.0448
No log	0.2242	254	0.9769	0.0673	0.9769	0.9884
No log	0.2259	256	0.8944	0.0632	0.8944	0.9457
No log	0.2277	258	0.8722	0.0609	0.8722	0.9339
No log	0.2295	260	0.8745	0.0560	0.8745	0.9352
No log	0.2312	262	0.8795	0.0629	0.8795	0.9378
No log	0.2330	264	0.8939	0.0632	0.8939	0.9455
No log	0.2348	266	0.9178	0.0745	0.9178	0.9580
No log	0.2365	268	0.9206	0.0891	0.9206	0.9595
No log	0.2383	270	0.9372	0.0999	0.9372	0.9681
No log	0.2401	272	0.9614	0.0999	0.9614	0.9805
No log	0.2418	274	0.9850	0.0891	0.9850	0.9925
No log	0.2436	276	1.0004	0.0632	1.0004	1.0002
No log	0.2454	278	1.0376	0.0612	1.0376	1.0186
No log	0.2471	280	1.1017	0.0612	1.1017	1.0496
No log	0.2489	282	1.1321	0.0514	1.1321	1.0640
No log	0.2507	284	1.1047	0.0632	1.1047	1.0510
No log	0.2524	286	1.1181	0.0632	1.1181	1.0574
No log	0.2542	288	1.1214	0.0632	1.1214	1.0590
No log	0.2560	290	0.9917	0.0632	0.9917	0.9958
No log	0.2577	292	0.8835	0.0632	0.8835	0.9400
No log	0.2595	294	0.8621	0.0632	0.8621	0.9285
No log	0.2613	296	0.8765	0.0632	0.8765	0.9362
No log	0.2630	298	0.9078	0.0619	0.9078	0.9528
No log	0.2648	300	0.9514	0.0641	0.9514	0.9754
No log	0.2665	302	0.9357	0.0654	0.9357	0.9673
No log	0.2683	304	0.8986	0.0649	0.8986	0.9480
No log	0.2701	306	0.8863	0.0649	0.8863	0.9414
No log	0.2718	308	0.9194	0.0654	0.9194	0.9589
No log	0.2736	310	0.9950	0.0996	0.9950	0.9975
No log	0.2754	312	0.9881	0.1365	0.9881	0.9940
No log	0.2771	314	0.9832	0.1485	0.9832	0.9916
No log	0.2789	316	0.9157	0.1215	0.9157	0.9569
No log	0.2807	318	0.8440	0.0995	0.8440	0.9187
No log	0.2824	320	0.8275	0.0723	0.8275	0.9097
No log	0.2842	322	0.8558	0.0602	0.8558	0.9251
No log	0.2860	324	0.8760	0.0544	0.8760	0.9359
No log	0.2877	326	0.8843	0.0544	0.8843	0.9404
No log	0.2895	328	0.8567	0.0544	0.8567	0.9256
No log	0.2913	330	0.8309	0.0555	0.8309	0.9115
No log	0.2930	332	0.8142	0.0579	0.8142	0.9023
No log	0.2948	334	0.7993	0.0649	0.7993	0.8941
No log	0.2966	336	0.7853	0.0626	0.7853	0.8861
No log	0.2983	338	0.7867	0.0592	0.7867	0.8870
No log	0.3001	340	0.8058	0.0568	0.8058	0.8976
No log	0.3019	342	0.8401	0.0568	0.8401	0.9166
No log	0.3036	344	0.8903	0.0626	0.8903	0.9436
No log	0.3054	346	0.8676	0.0632	0.8676	0.9314
No log	0.3071	348	0.8622	0.0632	0.8622	0.9285
No log	0.3089	350	0.8650	0.0677	0.8650	0.9301
No log	0.3107	352	0.8346	0.0792	0.8346	0.9135
No log	0.3124	354	0.7959	0.0632	0.7959	0.8921
No log	0.3142	356	0.7794	0.0632	0.7794	0.8828
No log	0.3160	358	0.7871	0.0667	0.7871	0.8872
No log	0.3177	360	0.8132	0.1278	0.8132	0.9018
No log	0.3195	362	0.8320	0.1834	0.8320	0.9122
No log	0.3213	364	0.8375	0.0534	0.8375	0.9151
No log	0.3230	366	0.8463	0.0451	0.8463	0.9200
No log	0.3248	368	0.8515	0.0453	0.8515	0.9228
No log	0.3266	370	0.8538	0.0576	0.8538	0.9240
No log	0.3283	372	0.8641	0.0725	0.8641	0.9296
No log	0.3301	374	0.8763	0.0786	0.8763	0.9361
No log	0.3319	376	0.8719	0.0717	0.8719	0.9338
No log	0.3336	378	0.8764	0.0717	0.8764	0.9362
No log	0.3354	380	0.8703	0.0717	0.8703	0.9329
No log	0.3372	382	0.8691	0.0600	0.8691	0.9323
No log	0.3389	384	0.8807	0.0649	0.8807	0.9384
No log	0.3407	386	0.8976	0.1097	0.8976	0.9474
No log	0.3425	388	0.9072	0.1065	0.9072	0.9525
No log	0.3442	390	0.8990	0.0947	0.8990	0.9482
No log	0.3460	392	0.8817	0.1155	0.8817	0.9390
No log	0.3477	394	0.8827	0.0959	0.8827	0.9395
No log	0.3495	396	0.8982	0.0730	0.8982	0.9477
No log	0.3513	398	0.9193	0.0632	0.9193	0.9588
No log	0.3530	400	0.9336	0.0723	0.9336	0.9662
No log	0.3548	402	0.9485	0.0723	0.9485	0.9739
No log	0.3566	404	0.9612	0.0632	0.9612	0.9804
No log	0.3583	406	0.9447	0.0597	0.9447	0.9720
No log	0.3601	408	0.8716	0.1459	0.8716	0.9336
No log	0.3619	410	0.9123	0.2408	0.9123	0.9551
No log	0.3636	412	0.9316	0.2476	0.9316	0.9652
No log	0.3654	414	0.9253	0.2624	0.9253	0.9619
No log	0.3672	416	0.9008	0.3161	0.9008	0.9491
No log	0.3689	418	0.8803	0.3231	0.8803	0.9382
No log	0.3707	420	0.8857	0.3333	0.8857	0.9411
No log	0.3725	422	0.9245	0.2759	0.9245	0.9615
No log	0.3742	424	0.9332	0.2812	0.9332	0.9660
No log	0.3760	426	0.9173	0.2844	0.9173	0.9578
No log	0.3778	428	0.8487	0.3556	0.8487	0.9213
No log	0.3795	430	0.7738	0.2517	0.7738	0.8797
No log	0.3813	432	0.7474	0.0669	0.7474	0.8645
No log	0.3831	434	0.7496	0.0656	0.7496	0.8658
No log	0.3848	436	0.7580	0.0726	0.7580	0.8706
No log	0.3866	438	0.7392	0.0656	0.7392	0.8597
No log	0.3883	440	0.7305	0.0656	0.7305	0.8547
No log	0.3901	442	0.7425	0.2193	0.7425	0.8617
No log	0.3919	444	0.7672	0.3560	0.7672	0.8759
No log	0.3936	446	0.7612	0.2994	0.7612	0.8724
No log	0.3954	448	0.7341	0.1934	0.7341	0.8568
No log	0.3972	450	0.7221	0.1030	0.7221	0.8498
No log	0.3989	452	0.7214	0.0705	0.7214	0.8494
No log	0.4007	454	0.7219	0.0658	0.7219	0.8496
No log	0.4025	456	0.7256	0.0722	0.7256	0.8518
No log	0.4042	458	0.7291	0.0668	0.7291	0.8539
No log	0.4060	460	0.7405	0.1215	0.7405	0.8605
No log	0.4078	462	0.7447	0.0888	0.7447	0.8630
No log	0.4095	464	0.7405	0.0607	0.7405	0.8605
No log	0.4113	466	0.7459	0.0677	0.7459	0.8637
No log	0.4131	468	0.7536	0.0689	0.7536	0.8681
No log	0.4148	470	0.7879	0.0940	0.7879	0.8876
No log	0.4166	472	0.7602	0.0918	0.7602	0.8719
No log	0.4184	474	0.7143	0.0767	0.7143	0.8452
No log	0.4201	476	0.6914	0.1580	0.6914	0.8315
No log	0.4219	478	0.7050	0.3562	0.7050	0.8396
No log	0.4237	480	0.7308	0.3592	0.7308	0.8549
No log	0.4254	482	0.7562	0.3968	0.7562	0.8696
No log	0.4272	484	0.8040	0.3756	0.8040	0.8966
No log	0.4289	486	0.8293	0.3345	0.8293	0.9107
No log	0.4307	488	0.8416	0.3297	0.8416	0.9174
No log	0.4325	490	0.8429	0.3488	0.8429	0.9181
No log	0.4342	492	0.8329	0.3523	0.8329	0.9126
No log	0.4360	494	0.8110	0.3297	0.8110	0.9005
No log	0.4378	496	0.8018	0.3105	0.8018	0.8954
No log	0.4395	498	0.7811	0.2803	0.7811	0.8838
1.4624	0.4413	500	0.7670	0.2859	0.7670	0.8758
1.4624	0.4431	502	0.7686	0.3640	0.7686	0.8767
1.4624	0.4448	504	0.7861	0.4008	0.7861	0.8866
1.4624	0.4466	506	0.7866	0.4047	0.7866	0.8869
1.4624	0.4484	508	0.7962	0.3981	0.7962	0.8923
1.4624	0.4501	510	0.8191	0.3494	0.8191	0.9050
1.4624	0.4519	512	0.8653	0.3383	0.8653	0.9302
1.4624	0.4537	514	0.9110	0.3224	0.9110	0.9544
1.4624	0.4554	516	0.9405	0.2933	0.9405	0.9698
1.4624	0.4572	518	0.8914	0.3367	0.8914	0.9441
1.4624	0.4590	520	0.8010	0.3867	0.8010	0.8950
1.4624	0.4607	522	0.7283	0.4199	0.7283	0.8534
1.4624	0.4625	524	0.6875	0.3180	0.6875	0.8291
1.4624	0.4643	526	0.6701	0.2529	0.6701	0.8186
1.4624	0.4660	528	0.6662	0.2008	0.6662	0.8162
1.4624	0.4678	530	0.6641	0.1922	0.6641	0.8149
1.4624	0.4695	532	0.6620	0.3157	0.6620	0.8136
1.4624	0.4713	534	0.6732	0.3776	0.6732	0.8205
1.4624	0.4731	536	0.6976	0.4309	0.6976	0.8352
1.4624	0.4748	538	0.7156	0.4359	0.7156	0.8459
1.4624	0.4766	540	0.7026	0.4356	0.7026	0.8382
1.4624	0.4784	542	0.6924	0.4399	0.6924	0.8321
1.4624	0.4801	544	0.6866	0.4266	0.6866	0.8286
1.4624	0.4819	546	0.6728	0.3934	0.6728	0.8202
1.4624	0.4837	548	0.6726	0.3878	0.6726	0.8201
1.4624	0.4854	550	0.6999	0.4347	0.6999	0.8366
1.4624	0.4872	552	0.7751	0.4153	0.7751	0.8804
1.4624	0.4890	554	0.8344	0.3860	0.8344	0.9135
1.4624	0.4907	556	0.8573	0.3828	0.8573	0.9259
1.4624	0.4925	558	0.9077	0.3646	0.9077	0.9527
1.4624	0.4943	560	0.9222	0.3660	0.9222	0.9603
1.4624	0.4960	562	0.9360	0.3355	0.9360	0.9675
1.4624	0.4978	564	0.9409	0.3323	0.9409	0.9700
1.4624	0.4996	566	0.9719	0.3051	0.9719	0.9859
1.4624	0.5013	568	1.0163	0.2800	1.0163	1.0081
1.4624	0.5031	570	1.0607	0.2543	1.0607	1.0299
1.4624	0.5049	572	1.1160	0.2234	1.1160	1.0564
1.4624	0.5066	574	1.1182	0.2234	1.1182	1.0575
1.4624	0.5084	576	1.0469	0.2729	1.0469	1.0232

Framework versions

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