ASAP_FineTuningBERT_Aug_k5_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: 0.4453
• Qwk: 0.6414
• Mse: 0.4453
• Rmse: 0.6673

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	0.0190	2	11.1206	0.0	11.1206	3.3348
No log	0.0381	4	10.2553	0.0	10.2553	3.2024
No log	0.0571	6	9.6595	0.0	9.6595	3.1080
No log	0.0762	8	8.8553	0.0018	8.8553	2.9758
No log	0.0952	10	7.8522	0.0054	7.8522	2.8022
No log	0.1143	12	6.8986	0.0	6.8986	2.6265
No log	0.1333	14	6.0416	0.0	6.0416	2.4580
No log	0.1524	16	5.1749	0.0	5.1749	2.2748
No log	0.1714	18	4.2891	0.0	4.2891	2.0710
No log	0.1905	20	3.4786	0.0201	3.4786	1.8651
No log	0.2095	22	2.7967	0.0115	2.7967	1.6723
No log	0.2286	24	2.1915	0.0077	2.1915	1.4804
No log	0.2476	26	1.7164	0.0039	1.7164	1.3101
No log	0.2667	28	1.3003	0.0627	1.3003	1.1403
No log	0.2857	30	1.0726	0.0419	1.0726	1.0356
No log	0.3048	32	0.8719	0.0316	0.8719	0.9338
No log	0.3238	34	0.7986	0.0316	0.7986	0.8936
No log	0.3429	36	0.7812	0.0316	0.7812	0.8839
No log	0.3619	38	0.7859	0.0212	0.7859	0.8865
No log	0.3810	40	0.7649	0.0316	0.7649	0.8746
No log	0.4	42	0.7328	0.0316	0.7328	0.8560
No log	0.4190	44	0.7204	0.2351	0.7204	0.8488
No log	0.4381	46	0.6876	0.0753	0.6876	0.8292
No log	0.4571	48	0.6432	0.1239	0.6432	0.8020
No log	0.4762	50	0.6456	0.3648	0.6456	0.8035
No log	0.4952	52	0.6401	0.3865	0.6401	0.8001
No log	0.5143	54	0.5915	0.2671	0.5915	0.7691
No log	0.5333	56	0.5791	0.2005	0.5791	0.7610
No log	0.5524	58	0.5879	0.1180	0.5879	0.7668
No log	0.5714	60	0.5859	0.1419	0.5859	0.7654
No log	0.5905	62	0.6425	0.2705	0.6425	0.8015
No log	0.6095	64	0.6766	0.1366	0.6766	0.8226
No log	0.6286	66	0.5825	0.1212	0.5825	0.7632
No log	0.6476	68	0.5883	0.1603	0.5883	0.7670
No log	0.6667	70	0.5436	0.1739	0.5436	0.7373
No log	0.6857	72	0.5074	0.3969	0.5074	0.7123
No log	0.7048	74	0.5023	0.4673	0.5023	0.7087
No log	0.7238	76	0.5314	0.4702	0.5314	0.7290
No log	0.7429	78	0.4935	0.4233	0.4935	0.7025
No log	0.7619	80	0.5039	0.5622	0.5039	0.7099
No log	0.7810	82	0.6403	0.4908	0.6403	0.8002
No log	0.8	84	0.5530	0.5379	0.5530	0.7437
No log	0.8190	86	0.4792	0.5234	0.4792	0.6922
No log	0.8381	88	0.4842	0.5194	0.4842	0.6959
No log	0.8571	90	0.5891	0.5140	0.5891	0.7675
No log	0.8762	92	0.5434	0.5593	0.5434	0.7372
No log	0.8952	94	1.0094	0.2648	1.0094	1.0047
No log	0.9143	96	1.0891	0.2672	1.0891	1.0436
No log	0.9333	98	0.5320	0.4983	0.5320	0.7294
No log	0.9524	100	0.7963	0.1291	0.7963	0.8924
No log	0.9714	102	0.6422	0.4790	0.6422	0.8014
No log	0.9905	104	0.4869	0.5482	0.4869	0.6978
No log	1.0095	106	0.4740	0.4875	0.4740	0.6885
No log	1.0286	108	0.5145	0.4083	0.5145	0.7173
No log	1.0476	110	0.4976	0.4145	0.4976	0.7054
No log	1.0667	112	0.4679	0.5187	0.4679	0.6841
No log	1.0857	114	0.4842	0.5624	0.4842	0.6959
No log	1.1048	116	0.5116	0.5557	0.5116	0.7153
No log	1.1238	118	0.5343	0.5496	0.5343	0.7310
No log	1.1429	120	0.4964	0.5463	0.4964	0.7046
No log	1.1619	122	0.4484	0.5716	0.4484	0.6696
No log	1.1810	124	0.4473	0.5886	0.4473	0.6688
No log	1.2	126	0.5878	0.5364	0.5878	0.7667
No log	1.2190	128	0.4909	0.5908	0.4909	0.7007
No log	1.2381	130	0.4371	0.5126	0.4371	0.6611
No log	1.2571	132	0.4337	0.5799	0.4337	0.6585
No log	1.2762	134	0.4227	0.5607	0.4227	0.6501
No log	1.2952	136	0.4206	0.5344	0.4206	0.6485
No log	1.3143	138	0.4596	0.5921	0.4596	0.6780
No log	1.3333	140	0.5366	0.5546	0.5366	0.7325
No log	1.3524	142	0.5373	0.5582	0.5373	0.7330
No log	1.3714	144	0.4832	0.5888	0.4832	0.6951
No log	1.3905	146	0.4141	0.5566	0.4141	0.6435
No log	1.4095	148	0.4305	0.5735	0.4305	0.6561
No log	1.4286	150	0.6221	0.5515	0.6221	0.7888
No log	1.4476	152	0.5467	0.5613	0.5467	0.7394
No log	1.4667	154	0.4189	0.5495	0.4189	0.6472
No log	1.4857	156	0.4953	0.4668	0.4953	0.7038
No log	1.5048	158	0.4221	0.5374	0.4221	0.6497
No log	1.5238	160	0.4556	0.5755	0.4556	0.6750
No log	1.5429	162	0.5248	0.5669	0.5248	0.7244
No log	1.5619	164	0.4491	0.5666	0.4491	0.6702
No log	1.5810	166	0.4230	0.5493	0.4230	0.6504
No log	1.6	168	0.4223	0.5402	0.4223	0.6499
No log	1.6190	170	0.4243	0.5483	0.4243	0.6514
No log	1.6381	172	0.4440	0.5819	0.4440	0.6663
No log	1.6571	174	0.6050	0.5685	0.6050	0.7778
No log	1.6762	176	0.5420	0.5926	0.5420	0.7362
No log	1.6952	178	0.4787	0.5870	0.4787	0.6918
No log	1.7143	180	0.4648	0.5749	0.4648	0.6818
No log	1.7333	182	0.4709	0.5861	0.4709	0.6862
No log	1.7524	184	0.5404	0.6030	0.5404	0.7351
No log	1.7714	186	0.4414	0.5832	0.4414	0.6644
No log	1.7905	188	0.4486	0.5471	0.4486	0.6697
No log	1.8095	190	0.4359	0.5897	0.4359	0.6603
No log	1.8286	192	0.4412	0.5796	0.4412	0.6643
No log	1.8476	194	0.5179	0.4785	0.5179	0.7196
No log	1.8667	196	0.5498	0.4726	0.5498	0.7415
No log	1.8857	198	0.4693	0.4916	0.4693	0.6850
No log	1.9048	200	0.4618	0.5536	0.4618	0.6796
No log	1.9238	202	0.5056	0.5932	0.5056	0.7111
No log	1.9429	204	0.4296	0.5561	0.4296	0.6554
No log	1.9619	206	0.4364	0.4758	0.4364	0.6606
No log	1.9810	208	0.4834	0.4247	0.4834	0.6952
No log	2.0	210	0.4376	0.4747	0.4376	0.6615
No log	2.0190	212	0.4145	0.5372	0.4145	0.6438
No log	2.0381	214	0.4242	0.5619	0.4242	0.6513
No log	2.0571	216	0.4107	0.5395	0.4107	0.6409
No log	2.0762	218	0.4286	0.4779	0.4286	0.6547
No log	2.0952	220	0.5129	0.4311	0.5129	0.7162
No log	2.1143	222	0.4326	0.4833	0.4326	0.6577
No log	2.1333	224	0.4444	0.5679	0.4444	0.6666
No log	2.1524	226	0.5377	0.5965	0.5377	0.7333
No log	2.1714	228	0.5827	0.5784	0.5827	0.7634
No log	2.1905	230	0.4403	0.5850	0.4403	0.6636
No log	2.2095	232	0.4138	0.5620	0.4138	0.6433
No log	2.2286	234	0.4189	0.5599	0.4189	0.6472
No log	2.2476	236	0.4279	0.5590	0.4279	0.6541
No log	2.2667	238	0.4163	0.5639	0.4163	0.6452
No log	2.2857	240	0.4317	0.5926	0.4317	0.6571
No log	2.3048	242	0.6422	0.5810	0.6422	0.8014
No log	2.3238	244	0.6168	0.5564	0.6168	0.7853
No log	2.3429	246	0.4087	0.5400	0.4087	0.6393
No log	2.3619	248	0.4189	0.4907	0.4189	0.6472
No log	2.3810	250	0.3995	0.5523	0.3995	0.6320
No log	2.4	252	0.4711	0.5615	0.4711	0.6863
No log	2.4190	254	0.6255	0.5518	0.6255	0.7909
No log	2.4381	256	0.5543	0.5752	0.5543	0.7445
No log	2.4571	258	0.4195	0.5762	0.4195	0.6477
No log	2.4762	260	0.3962	0.5747	0.3962	0.6294
No log	2.4952	262	0.4271	0.5708	0.4271	0.6535
No log	2.5143	264	0.4498	0.5735	0.4498	0.6706
No log	2.5333	266	0.4666	0.5824	0.4666	0.6830
No log	2.5524	268	0.3877	0.5870	0.3877	0.6226
No log	2.5714	270	0.4015	0.5286	0.4015	0.6337
No log	2.5905	272	0.4063	0.5187	0.4063	0.6375
No log	2.6095	274	0.3977	0.5922	0.3977	0.6306
No log	2.6286	276	0.4153	0.6054	0.4153	0.6444
No log	2.6476	278	0.4079	0.6111	0.4079	0.6386
No log	2.6667	280	0.4058	0.5952	0.4058	0.6370
No log	2.6857	282	0.4283	0.6375	0.4283	0.6544
No log	2.7048	284	0.4771	0.6332	0.4771	0.6907
No log	2.7238	286	0.5357	0.6570	0.5357	0.7319
No log	2.7429	288	0.4925	0.6640	0.4925	0.7018
No log	2.7619	290	0.4089	0.6174	0.4089	0.6394
No log	2.7810	292	0.4098	0.5554	0.4098	0.6401
No log	2.8	294	0.3987	0.5702	0.3987	0.6314
No log	2.8190	296	0.4093	0.6462	0.4093	0.6398
No log	2.8381	298	0.4064	0.6361	0.4064	0.6375
No log	2.8571	300	0.3966	0.5467	0.3966	0.6297
No log	2.8762	302	0.4010	0.5229	0.4010	0.6333
No log	2.8952	304	0.4068	0.6216	0.4068	0.6378
No log	2.9143	306	0.5340	0.6729	0.5340	0.7308
No log	2.9333	308	0.5382	0.6698	0.5382	0.7336
No log	2.9524	310	0.4062	0.6122	0.4062	0.6374
No log	2.9714	312	0.3981	0.5361	0.3981	0.6310
No log	2.9905	314	0.3952	0.5609	0.3952	0.6286
No log	3.0095	316	0.4195	0.5823	0.4195	0.6477
No log	3.0286	318	0.4010	0.5672	0.4010	0.6332
No log	3.0476	320	0.4009	0.5291	0.4009	0.6331
No log	3.0667	322	0.4071	0.5090	0.4071	0.6381
No log	3.0857	324	0.4098	0.5954	0.4098	0.6401
No log	3.1048	326	0.4635	0.6175	0.4635	0.6808
No log	3.1238	328	0.4452	0.6272	0.4452	0.6672
No log	3.1429	330	0.4138	0.6186	0.4138	0.6433
No log	3.1619	332	0.4355	0.6453	0.4355	0.6599
No log	3.1810	334	0.5553	0.6709	0.5553	0.7452
No log	3.2	336	0.5088	0.6576	0.5088	0.7133
No log	3.2190	338	0.4079	0.5856	0.4079	0.6387
No log	3.2381	340	0.4001	0.5627	0.4001	0.6325
No log	3.2571	342	0.4231	0.5911	0.4231	0.6504
No log	3.2762	344	0.4679	0.6203	0.4679	0.6840
No log	3.2952	346	0.5581	0.6757	0.5581	0.7471
No log	3.3143	348	0.4882	0.6603	0.4882	0.6987
No log	3.3333	350	0.4364	0.5718	0.4364	0.6606
No log	3.3524	352	0.4382	0.5588	0.4382	0.6620
No log	3.3714	354	0.4424	0.6272	0.4424	0.6652
No log	3.3905	356	0.4554	0.6310	0.4554	0.6748
No log	3.4095	358	0.4198	0.5801	0.4198	0.6479
No log	3.4286	360	0.4422	0.6116	0.4422	0.6650
No log	3.4476	362	0.5392	0.6473	0.5392	0.7343
No log	3.4667	364	0.4916	0.6315	0.4916	0.7012
No log	3.4857	366	0.4655	0.6346	0.4655	0.6822
No log	3.5048	368	0.4448	0.6038	0.4448	0.6669
No log	3.5238	370	0.4591	0.5619	0.4591	0.6776
No log	3.5429	372	0.4551	0.6485	0.4551	0.6746
No log	3.5619	374	0.5635	0.6870	0.5635	0.7507
No log	3.5810	376	0.4752	0.6702	0.4752	0.6893
No log	3.6	378	0.4810	0.5052	0.4810	0.6936
No log	3.6190	380	0.6412	0.3916	0.6412	0.8008
No log	3.6381	382	0.5161	0.4640	0.5161	0.7184
No log	3.6571	384	0.4253	0.6018	0.4253	0.6522
No log	3.6762	386	0.4565	0.6444	0.4565	0.6757
No log	3.6952	388	0.4247	0.6032	0.4247	0.6517
No log	3.7143	390	0.4165	0.6032	0.4165	0.6454
No log	3.7333	392	0.4372	0.6250	0.4372	0.6612
No log	3.7524	394	0.4511	0.6543	0.4511	0.6716
No log	3.7714	396	0.4491	0.6564	0.4491	0.6702
No log	3.7905	398	0.5513	0.6839	0.5513	0.7425
No log	3.8095	400	0.5520	0.6935	0.5520	0.7430
No log	3.8286	402	0.4454	0.6605	0.4454	0.6674
No log	3.8476	404	0.4361	0.5574	0.4361	0.6604
No log	3.8667	406	0.4361	0.5324	0.4361	0.6604
No log	3.8857	408	0.4141	0.6480	0.4141	0.6435
No log	3.9048	410	0.5777	0.6738	0.5777	0.7600
No log	3.9238	412	0.6799	0.6786	0.6799	0.8246
No log	3.9429	414	0.5265	0.6707	0.5265	0.7256
No log	3.9619	416	0.3997	0.5839	0.3997	0.6322
No log	3.9810	418	0.4016	0.5514	0.4016	0.6337
No log	4.0	420	0.4085	0.6087	0.4085	0.6392
No log	4.0190	422	0.5168	0.6253	0.5168	0.7189
No log	4.0381	424	0.4926	0.6081	0.4926	0.7018
No log	4.0571	426	0.4001	0.5844	0.4001	0.6326
No log	4.0762	428	0.3982	0.5403	0.3982	0.6311
No log	4.0952	430	0.3950	0.5819	0.3950	0.6285
No log	4.1143	432	0.4017	0.5958	0.4017	0.6338
No log	4.1333	434	0.4164	0.6260	0.4164	0.6453
No log	4.1524	436	0.4830	0.6756	0.4830	0.6950
No log	4.1714	438	0.4446	0.6526	0.4446	0.6668
No log	4.1905	440	0.4269	0.6247	0.4269	0.6534
No log	4.2095	442	0.4933	0.6771	0.4933	0.7023
No log	4.2286	444	0.4826	0.6740	0.4826	0.6947
No log	4.2476	446	0.4342	0.6218	0.4342	0.6589
No log	4.2667	448	0.4422	0.6325	0.4422	0.6650
No log	4.2857	450	0.4993	0.6682	0.4993	0.7066
No log	4.3048	452	0.5245	0.6834	0.5245	0.7242
No log	4.3238	454	0.5213	0.6915	0.5213	0.7220
No log	4.3429	456	0.4277	0.6220	0.4277	0.6540
No log	4.3619	458	0.4191	0.5763	0.4191	0.6474
No log	4.3810	460	0.4164	0.6171	0.4164	0.6453
No log	4.4	462	0.4962	0.6707	0.4962	0.7044
No log	4.4190	464	0.5005	0.6680	0.5005	0.7075
No log	4.4381	466	0.4223	0.6310	0.4223	0.6498
No log	4.4571	468	0.4147	0.5355	0.4147	0.6439
No log	4.4762	470	0.4049	0.5597	0.4049	0.6363
No log	4.4952	472	0.4614	0.6342	0.4614	0.6793
No log	4.5143	474	0.6720	0.6579	0.6720	0.8198
No log	4.5333	476	0.6784	0.6526	0.6784	0.8236
No log	4.5524	478	0.5061	0.6733	0.5061	0.7114
No log	4.5714	480	0.4349	0.6257	0.4349	0.6595
No log	4.5905	482	0.4378	0.6276	0.4378	0.6617
No log	4.6095	484	0.4602	0.6601	0.4602	0.6784
No log	4.6286	486	0.5115	0.6803	0.5115	0.7152
No log	4.6476	488	0.5112	0.6784	0.5112	0.7150
No log	4.6667	490	0.4478	0.6495	0.4478	0.6691
No log	4.6857	492	0.4405	0.5812	0.4405	0.6637
No log	4.7048	494	0.4306	0.6203	0.4306	0.6562
No log	4.7238	496	0.4425	0.6426	0.4425	0.6652
No log	4.7429	498	0.4725	0.6646	0.4725	0.6874
0.6523	4.7619	500	0.4580	0.6490	0.4580	0.6767
0.6523	4.7810	502	0.4411	0.6319	0.4411	0.6641
0.6523	4.8	504	0.5040	0.6574	0.5040	0.7099
0.6523	4.8190	506	0.6127	0.6776	0.6127	0.7827
0.6523	4.8381	508	0.5360	0.6836	0.5360	0.7321
0.6523	4.8571	510	0.4434	0.6257	0.4434	0.6659
0.6523	4.8762	512	0.4351	0.6230	0.4351	0.6596
0.6523	4.8952	514	0.4647	0.6564	0.4647	0.6817
0.6523	4.9143	516	0.5084	0.6896	0.5084	0.7130
0.6523	4.9333	518	0.5430	0.6810	0.5430	0.7369
0.6523	4.9524	520	0.5030	0.6647	0.5030	0.7092
0.6523	4.9714	522	0.5422	0.6663	0.5422	0.7364
0.6523	4.9905	524	0.4926	0.6495	0.4926	0.7018
0.6523	5.0095	526	0.4804	0.6504	0.4804	0.6931
0.6523	5.0286	528	0.4623	0.6346	0.4623	0.6799
0.6523	5.0476	530	0.5017	0.6604	0.5017	0.7083
0.6523	5.0667	532	0.5205	0.6633	0.5205	0.7215
0.6523	5.0857	534	0.4720	0.6503	0.4720	0.6870
0.6523	5.1048	536	0.4273	0.6117	0.4273	0.6537
0.6523	5.1238	538	0.4254	0.5844	0.4254	0.6522
0.6523	5.1429	540	0.4279	0.5933	0.4279	0.6541
0.6523	5.1619	542	0.4412	0.6147	0.4412	0.6642
0.6523	5.1810	544	0.4453	0.6414	0.4453	0.6673

Framework versions

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