ASAP_FineTuningBERT_AugV4_k4_task1_organization_fold0

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: 0.6338
• Qwk: 0.4989
• Mse: 0.6338
• Rmse: 0.7961

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	0.0048	2	9.7884	0.0036	9.7884	3.1286
No log	0.0097	4	8.3457	0.0	8.3457	2.8889
No log	0.0145	6	7.3232	0.0	7.3232	2.7061
No log	0.0193	8	6.6114	0.0	6.6114	2.5713
No log	0.0242	10	5.9011	0.0090	5.9011	2.4292
No log	0.0290	12	5.0913	0.0112	5.0913	2.2564
No log	0.0338	14	4.3007	0.0077	4.3007	2.0738
No log	0.0386	16	3.5755	0.0039	3.5755	1.8909
No log	0.0435	18	2.8540	0.0	2.8540	1.6894
No log	0.0483	20	2.2425	0.0742	2.2425	1.4975
No log	0.0531	22	1.7255	0.0382	1.7255	1.3136
No log	0.0580	24	1.3306	0.0316	1.3306	1.1535
No log	0.0628	26	1.0734	0.0316	1.0734	1.0361
No log	0.0676	28	0.8781	0.1273	0.8781	0.9370
No log	0.0725	30	0.8005	0.1169	0.8005	0.8947
No log	0.0773	32	0.7497	0.1076	0.7497	0.8659
No log	0.0821	34	0.8244	0.0689	0.8244	0.9080
No log	0.0870	36	0.8958	0.0521	0.8958	0.9465
No log	0.0918	38	0.9542	0.0348	0.9542	0.9769
No log	0.0966	40	1.1204	0.0348	1.1204	1.0585
No log	0.1014	42	1.1989	0.0174	1.1989	1.0949
No log	0.1063	44	1.0374	0.0174	1.0374	1.0185
No log	0.1111	46	0.9324	0.0174	0.9324	0.9656
No log	0.1159	48	0.9645	0.0174	0.9645	0.9821
No log	0.1208	50	1.1371	0.0174	1.1371	1.0663
No log	0.1256	52	1.0818	0.0174	1.0818	1.0401
No log	0.1304	54	1.1180	0.0174	1.1180	1.0573
No log	0.1353	56	1.0966	0.0	1.0966	1.0472
No log	0.1401	58	0.9594	0.0	0.9594	0.9795
No log	0.1449	60	0.8625	0.0	0.8625	0.9287
No log	0.1498	62	0.8699	0.0	0.8699	0.9327
No log	0.1546	64	0.9776	0.0	0.9776	0.9887
No log	0.1594	66	1.0314	0.0	1.0314	1.0156
No log	0.1643	68	0.8824	0.0174	0.8824	0.9393
No log	0.1691	70	0.8842	0.0174	0.8842	0.9403
No log	0.1739	72	1.0974	0.0	1.0974	1.0475
No log	0.1787	74	1.1630	0.0	1.1630	1.0784
No log	0.1836	76	0.9696	0.0	0.9696	0.9847
No log	0.1884	78	0.9355	0.0	0.9355	0.9672
No log	0.1932	80	1.0228	0.0	1.0228	1.0113
No log	0.1981	82	1.0875	0.0	1.0875	1.0428
No log	0.2029	84	1.0401	0.0	1.0401	1.0198
No log	0.2077	86	0.9557	0.0	0.9557	0.9776
No log	0.2126	88	0.9466	0.0	0.9466	0.9729
No log	0.2174	90	0.9541	0.0	0.9541	0.9768
No log	0.2222	92	0.9751	0.0	0.9751	0.9875
No log	0.2271	94	0.9317	0.0	0.9317	0.9652
No log	0.2319	96	0.8861	0.0	0.8861	0.9413
No log	0.2367	98	0.8846	0.0	0.8846	0.9405
No log	0.2415	100	0.9770	0.0	0.9770	0.9885
No log	0.2464	102	1.0583	0.0	1.0583	1.0287
No log	0.2512	104	0.9901	0.0	0.9901	0.9950
No log	0.2560	106	0.9516	0.0174	0.9516	0.9755
No log	0.2609	108	1.0214	0.0	1.0214	1.0106
No log	0.2657	110	0.9706	0.0	0.9706	0.9852
No log	0.2705	112	0.8449	0.0	0.8449	0.9192
No log	0.2754	114	0.7743	0.0049	0.7743	0.8799
No log	0.2802	116	0.7784	0.0147	0.7784	0.8823
No log	0.2850	118	0.8229	0.0	0.8229	0.9071
No log	0.2899	120	1.0002	0.1325	1.0002	1.0001
No log	0.2947	122	1.0582	0.1573	1.0582	1.0287
No log	0.2995	124	1.0952	0.1566	1.0952	1.0465
No log	0.3043	126	1.2585	0.1007	1.2585	1.1218
No log	0.3092	128	1.0667	0.2120	1.0667	1.0328
No log	0.3140	130	0.7665	0.1629	0.7665	0.8755
No log	0.3188	132	0.9435	0.2251	0.9435	0.9714
No log	0.3237	134	1.2567	0.1784	1.2567	1.1210
No log	0.3285	136	0.9381	0.2307	0.9381	0.9685
No log	0.3333	138	0.7142	0.2795	0.7142	0.8451
No log	0.3382	140	0.6960	0.2368	0.6960	0.8343
No log	0.3430	142	0.7194	0.1643	0.7194	0.8482
No log	0.3478	144	0.7069	0.2029	0.7069	0.8408
No log	0.3527	146	0.8457	0.2275	0.8457	0.9196
No log	0.3575	148	0.7414	0.1941	0.7414	0.8610
No log	0.3623	150	0.7162	0.2938	0.7162	0.8463
No log	0.3671	152	0.7151	0.2805	0.7151	0.8457
No log	0.3720	154	0.7294	0.1767	0.7294	0.8541
No log	0.3768	156	1.0364	0.2084	1.0364	1.0181
No log	0.3816	158	1.1460	0.1853	1.1460	1.0705
No log	0.3865	160	1.0650	0.1970	1.0650	1.0320
No log	0.3913	162	0.9547	0.2146	0.9547	0.9771
No log	0.3961	164	0.7515	0.1664	0.7515	0.8669
No log	0.4010	166	0.7146	0.2398	0.7146	0.8453
No log	0.4058	168	0.7202	0.2807	0.7202	0.8486
No log	0.4106	170	0.9297	0.3111	0.9297	0.9642
No log	0.4155	172	1.1130	0.2237	1.1130	1.0550
No log	0.4203	174	0.8935	0.3526	0.8935	0.9452
No log	0.4251	176	0.7485	0.3612	0.7485	0.8652
No log	0.4300	178	0.7487	0.3652	0.7487	0.8653
No log	0.4348	180	0.7959	0.3743	0.7959	0.8921
No log	0.4396	182	0.8790	0.3561	0.8790	0.9375
No log	0.4444	184	0.8131	0.3858	0.8131	0.9017
No log	0.4493	186	0.6981	0.3787	0.6981	0.8355
No log	0.4541	188	0.6664	0.3902	0.6664	0.8164
No log	0.4589	190	0.6466	0.3808	0.6466	0.8041
No log	0.4638	192	0.6441	0.3945	0.6441	0.8026
No log	0.4686	194	0.7083	0.3771	0.7083	0.8416
No log	0.4734	196	0.8337	0.3348	0.8337	0.9131
No log	0.4783	198	0.7679	0.3700	0.7679	0.8763
No log	0.4831	200	0.6496	0.4087	0.6496	0.8060
No log	0.4879	202	0.6448	0.3172	0.6448	0.8030
No log	0.4928	204	0.6885	0.2440	0.6885	0.8298
No log	0.4976	206	0.8107	0.3165	0.8107	0.9004
No log	0.5024	208	1.0132	0.2603	1.0132	1.0066
No log	0.5072	210	1.0492	0.2428	1.0492	1.0243
No log	0.5121	212	0.8933	0.2702	0.8933	0.9451
No log	0.5169	214	0.6569	0.3295	0.6569	0.8105
No log	0.5217	216	0.6409	0.3527	0.6409	0.8005
No log	0.5266	218	0.6300	0.3866	0.6300	0.7937
No log	0.5314	220	0.8547	0.3163	0.8547	0.9245
No log	0.5362	222	0.9754	0.2782	0.9754	0.9876
No log	0.5411	224	0.8529	0.3246	0.8529	0.9235
No log	0.5459	226	0.6840	0.2933	0.6840	0.8270
No log	0.5507	228	0.6217	0.3660	0.6217	0.7885
No log	0.5556	230	0.6445	0.3616	0.6445	0.8028
No log	0.5604	232	0.6875	0.3841	0.6875	0.8291
No log	0.5652	234	0.6002	0.4674	0.6002	0.7747
No log	0.5700	236	0.6340	0.4779	0.6340	0.7962
No log	0.5749	238	0.6832	0.4418	0.6832	0.8266
No log	0.5797	240	0.5909	0.5007	0.5909	0.7687
No log	0.5845	242	0.5939	0.4093	0.5939	0.7706
No log	0.5894	244	0.5803	0.4322	0.5803	0.7618
No log	0.5942	246	0.6677	0.4329	0.6677	0.8172
No log	0.5990	248	0.9902	0.3306	0.9902	0.9951
No log	0.6039	250	0.9869	0.3203	0.9869	0.9934
No log	0.6087	252	0.7199	0.3776	0.7199	0.8484
No log	0.6135	254	0.6199	0.4368	0.6199	0.7874
No log	0.6184	256	0.6016	0.4359	0.6016	0.7756
No log	0.6232	258	0.6023	0.4257	0.6023	0.7761
No log	0.6280	260	0.6339	0.4306	0.6339	0.7962
No log	0.6329	262	0.7260	0.4105	0.7260	0.8520
No log	0.6377	264	0.7948	0.3844	0.7948	0.8915
No log	0.6425	266	0.6656	0.4497	0.6656	0.8158
No log	0.6473	268	0.5675	0.4684	0.5675	0.7533
No log	0.6522	270	0.5618	0.4300	0.5618	0.7495
No log	0.6570	272	0.5491	0.4477	0.5491	0.7410
No log	0.6618	274	0.5510	0.4729	0.5510	0.7423
No log	0.6667	276	0.5425	0.4794	0.5425	0.7366
No log	0.6715	278	0.6099	0.4791	0.6099	0.7810
No log	0.6763	280	0.6061	0.4839	0.6061	0.7786
No log	0.6812	282	0.5278	0.4896	0.5278	0.7265
No log	0.6860	284	0.5469	0.4460	0.5469	0.7395
No log	0.6908	286	0.5380	0.4797	0.5380	0.7335
No log	0.6957	288	0.5378	0.5305	0.5378	0.7334
No log	0.7005	290	0.6036	0.5275	0.6036	0.7769
No log	0.7053	292	0.6518	0.5202	0.6518	0.8073
No log	0.7101	294	0.5815	0.5521	0.5815	0.7626
No log	0.7150	296	0.6317	0.5175	0.6317	0.7948
No log	0.7198	298	0.5793	0.5322	0.5793	0.7611
No log	0.7246	300	0.7073	0.4870	0.7073	0.8410
No log	0.7295	302	0.6423	0.4907	0.6423	0.8014
No log	0.7343	304	0.5469	0.4514	0.5469	0.7396
No log	0.7391	306	0.6290	0.4562	0.6290	0.7931
No log	0.7440	308	0.5726	0.4594	0.5726	0.7567
No log	0.7488	310	0.5502	0.4640	0.5502	0.7418
No log	0.7536	312	0.5479	0.4382	0.5479	0.7402
No log	0.7585	314	0.5798	0.4434	0.5798	0.7615
No log	0.7633	316	0.5601	0.4432	0.5601	0.7484
No log	0.7681	318	0.5422	0.4379	0.5422	0.7364
No log	0.7729	320	0.5739	0.4597	0.5739	0.7575
No log	0.7778	322	0.5998	0.4597	0.5998	0.7744
No log	0.7826	324	0.5428	0.4874	0.5428	0.7367
No log	0.7874	326	0.5459	0.4665	0.5459	0.7388
No log	0.7923	328	0.6149	0.4466	0.6149	0.7841
No log	0.7971	330	0.6008	0.4300	0.6008	0.7751
No log	0.8019	332	0.5639	0.4420	0.5639	0.7509
No log	0.8068	334	0.5663	0.4335	0.5663	0.7525
No log	0.8116	336	0.6073	0.4322	0.6073	0.7793
No log	0.8164	338	0.7503	0.4317	0.7503	0.8662
No log	0.8213	340	0.7104	0.4243	0.7104	0.8428
No log	0.8261	342	0.5794	0.4798	0.5794	0.7612
No log	0.8309	344	0.7353	0.4168	0.7353	0.8575
No log	0.8357	346	0.6988	0.4094	0.6988	0.8359
No log	0.8406	348	0.5819	0.4614	0.5819	0.7628
No log	0.8454	350	0.6966	0.4274	0.6966	0.8346
No log	0.8502	352	0.6598	0.4491	0.6598	0.8123
No log	0.8551	354	0.5731	0.4695	0.5731	0.7570
No log	0.8599	356	0.6861	0.4152	0.6861	0.8283
No log	0.8647	358	0.6613	0.4218	0.6613	0.8132
No log	0.8696	360	0.5721	0.4670	0.5721	0.7564
No log	0.8744	362	0.7264	0.4363	0.7264	0.8523
No log	0.8792	364	0.8739	0.3913	0.8739	0.9349
No log	0.8841	366	0.7313	0.4293	0.7313	0.8552
No log	0.8889	368	0.5945	0.5008	0.5945	0.7710
No log	0.8937	370	0.6306	0.4690	0.6306	0.7941
No log	0.8986	372	0.6189	0.4811	0.6189	0.7867
No log	0.9034	374	0.6407	0.5069	0.6407	0.8005
No log	0.9082	376	0.8693	0.4153	0.8693	0.9324
No log	0.9130	378	0.9686	0.3969	0.9686	0.9842
No log	0.9179	380	0.7622	0.4090	0.7622	0.8730
No log	0.9227	382	0.5952	0.4832	0.5952	0.7715
No log	0.9275	384	0.5749	0.4479	0.5749	0.7582
No log	0.9324	386	0.5869	0.4698	0.5869	0.7661
No log	0.9372	388	0.6879	0.4415	0.6879	0.8294
No log	0.9420	390	0.6862	0.4525	0.6862	0.8283
No log	0.9469	392	0.6271	0.4711	0.6271	0.7919
No log	0.9517	394	0.6621	0.4657	0.6621	0.8137
No log	0.9565	396	0.7243	0.4701	0.7243	0.8511
No log	0.9614	398	0.6952	0.4560	0.6952	0.8338
No log	0.9662	400	0.5920	0.4401	0.5920	0.7694
No log	0.9710	402	0.5406	0.4735	0.5406	0.7352
No log	0.9758	404	0.5606	0.4797	0.5606	0.7488
No log	0.9807	406	0.5542	0.4880	0.5542	0.7445
No log	0.9855	408	0.5656	0.4641	0.5656	0.7521
No log	0.9903	410	0.5598	0.4875	0.5598	0.7482
No log	0.9952	412	0.5654	0.4879	0.5654	0.7519
No log	1.0	414	0.5967	0.5004	0.5967	0.7724
No log	1.0048	416	0.6055	0.5170	0.6055	0.7781
No log	1.0097	418	0.5804	0.5221	0.5804	0.7618
No log	1.0145	420	0.5666	0.5118	0.5666	0.7527
No log	1.0193	422	0.5895	0.5255	0.5895	0.7678
No log	1.0242	424	0.5697	0.5319	0.5697	0.7548
No log	1.0290	426	0.6259	0.5038	0.6259	0.7912
No log	1.0338	428	0.6697	0.4944	0.6697	0.8183
No log	1.0386	430	0.5692	0.5551	0.5692	0.7544
No log	1.0435	432	0.6608	0.4884	0.6608	0.8129
No log	1.0483	434	0.6204	0.5025	0.6204	0.7876
No log	1.0531	436	0.5643	0.5175	0.5643	0.7512
No log	1.0580	438	0.6181	0.4652	0.6181	0.7862
No log	1.0628	440	0.5918	0.4781	0.5918	0.7693
No log	1.0676	442	0.5837	0.4610	0.5837	0.7640
No log	1.0725	444	0.6268	0.4404	0.6268	0.7917
No log	1.0773	446	0.7865	0.4318	0.7865	0.8869
No log	1.0821	448	0.8325	0.4030	0.8325	0.9124
No log	1.0870	450	0.7097	0.4009	0.7097	0.8424
No log	1.0918	452	0.6230	0.4214	0.6230	0.7893
No log	1.0966	454	0.6219	0.4450	0.6219	0.7886
No log	1.1014	456	0.6602	0.4060	0.6602	0.8125
No log	1.1063	458	0.8361	0.4141	0.8361	0.9144
No log	1.1111	460	0.7944	0.4204	0.7944	0.8913
No log	1.1159	462	0.6283	0.4107	0.6283	0.7926
No log	1.1208	464	0.6113	0.4390	0.6113	0.7819
No log	1.1256	466	0.6580	0.4379	0.6580	0.8111
No log	1.1304	468	0.6096	0.4402	0.6096	0.7807
No log	1.1353	470	0.5697	0.4985	0.5697	0.7548
No log	1.1401	472	0.5775	0.5157	0.5775	0.7599
No log	1.1449	474	0.5896	0.5394	0.5896	0.7678
No log	1.1498	476	0.6675	0.5300	0.6675	0.8170
No log	1.1546	478	0.7546	0.4850	0.7546	0.8687
No log	1.1594	480	0.6185	0.5061	0.6185	0.7865
No log	1.1643	482	0.5779	0.5398	0.5779	0.7602
No log	1.1691	484	0.6439	0.5168	0.6439	0.8024
No log	1.1739	486	0.5688	0.5326	0.5688	0.7542
No log	1.1787	488	0.5815	0.4819	0.5815	0.7626
No log	1.1836	490	0.6205	0.4913	0.6205	0.7877
No log	1.1884	492	0.5510	0.4939	0.5510	0.7423
No log	1.1932	494	0.5598	0.5283	0.5598	0.7482
No log	1.1981	496	0.5677	0.5509	0.5677	0.7535
No log	1.2029	498	0.5941	0.5419	0.5941	0.7708
1.006	1.2077	500	0.6758	0.5151	0.6758	0.8220
1.006	1.2126	502	0.6052	0.5619	0.6052	0.7780
1.006	1.2174	504	0.6164	0.5571	0.6164	0.7851
1.006	1.2222	506	0.7070	0.4966	0.7070	0.8409
1.006	1.2271	508	0.6159	0.5705	0.6159	0.7848
1.006	1.2319	510	0.6100	0.5811	0.6100	0.7810
1.006	1.2367	512	0.5981	0.5895	0.5981	0.7734
1.006	1.2415	514	0.5755	0.5539	0.5755	0.7586
1.006	1.2464	516	0.6028	0.5150	0.6028	0.7764
1.006	1.2512	518	0.5452	0.5514	0.5452	0.7384
1.006	1.2560	520	0.5842	0.5165	0.5842	0.7643
1.006	1.2609	522	0.6252	0.4805	0.6252	0.7907
1.006	1.2657	524	0.5512	0.4616	0.5512	0.7424
1.006	1.2705	526	0.5600	0.5282	0.5600	0.7483
1.006	1.2754	528	0.5831	0.4820	0.5831	0.7636
1.006	1.2802	530	0.5445	0.4965	0.5445	0.7379
1.006	1.2850	532	0.6660	0.4704	0.6660	0.8161
1.006	1.2899	534	0.7488	0.4750	0.7488	0.8654
1.006	1.2947	536	0.6338	0.4989	0.6338	0.7961

Framework versions

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