ASAP_FineTuningBERT_Aug_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: 0.5510
• Qwk: 0.7451
• Mse: 0.5510
• Rmse: 0.7423

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	0.0408	2	10.5587	0.0	10.5587	3.2494
No log	0.0816	4	9.0593	0.0	9.0593	3.0099
No log	0.1224	6	7.5739	0.0178	7.5739	2.7521
No log	0.1633	8	6.1203	0.0	6.1203	2.4739
No log	0.2041	10	4.7077	0.0	4.7077	2.1697
No log	0.2449	12	3.4919	0.0305	3.4919	1.8687
No log	0.2857	14	2.5958	0.0079	2.5958	1.6112
No log	0.3265	16	1.8301	-0.0009	1.8301	1.3528
No log	0.3673	18	1.2264	0.1749	1.2264	1.1074
No log	0.4082	20	0.9608	0.0545	0.9608	0.9802
No log	0.4490	22	0.9270	0.0106	0.9270	0.9628
No log	0.4898	24	0.8503	0.0106	0.8503	0.9221
No log	0.5306	26	0.8170	0.0328	0.8170	0.9039
No log	0.5714	28	0.7560	0.1141	0.7560	0.8695
No log	0.6122	30	0.7017	0.1962	0.7017	0.8377
No log	0.6531	32	0.6826	0.4973	0.6826	0.8262
No log	0.6939	34	0.5935	0.2674	0.5935	0.7704
No log	0.7347	36	0.5725	0.3369	0.5725	0.7567
No log	0.7755	38	0.6427	0.5342	0.6427	0.8017
No log	0.8163	40	0.7484	0.4420	0.7484	0.8651
No log	0.8571	42	0.5661	0.4574	0.5661	0.7524
No log	0.8980	44	0.5202	0.4951	0.5202	0.7212
No log	0.9388	46	0.5084	0.5526	0.5084	0.7130
No log	0.9796	48	0.5350	0.5525	0.5350	0.7314
No log	1.0204	50	0.6157	0.2191	0.6157	0.7847
No log	1.0612	52	0.5117	0.5732	0.5117	0.7153
No log	1.1020	54	0.5308	0.6134	0.5308	0.7286
No log	1.1429	56	0.3970	0.5786	0.3970	0.6301
No log	1.1837	58	0.4031	0.5762	0.4031	0.6349
No log	1.2245	60	0.5979	0.5716	0.5979	0.7733
No log	1.2653	62	0.6716	0.5380	0.6716	0.8195
No log	1.3061	64	0.4858	0.5916	0.4858	0.6970
No log	1.3469	66	0.4578	0.4897	0.4578	0.6766
No log	1.3878	68	0.4560	0.5400	0.4560	0.6753
No log	1.4286	70	0.6134	0.5783	0.6134	0.7832
No log	1.4694	72	0.6832	0.5501	0.6832	0.8266
No log	1.5102	74	0.4224	0.6225	0.4224	0.6499
No log	1.5510	76	0.3807	0.5905	0.3807	0.6170
No log	1.5918	78	0.4121	0.6239	0.4121	0.6419
No log	1.6327	80	0.5139	0.6237	0.5139	0.7168
No log	1.6735	82	0.4955	0.6328	0.4955	0.7039
No log	1.7143	84	0.4137	0.6350	0.4137	0.6432
No log	1.7551	86	0.4091	0.6296	0.4091	0.6396
No log	1.7959	88	0.4248	0.6284	0.4248	0.6518
No log	1.8367	90	0.4493	0.6247	0.4493	0.6703
No log	1.8776	92	0.3964	0.5850	0.3964	0.6296
No log	1.9184	94	0.3968	0.5934	0.3968	0.6299
No log	1.9592	96	0.3996	0.6173	0.3996	0.6321
No log	2.0	98	0.4761	0.6063	0.4761	0.6900
No log	2.0408	100	0.4694	0.6123	0.4694	0.6851
No log	2.0816	102	0.4437	0.6151	0.4437	0.6661
No log	2.1224	104	0.4114	0.6248	0.4114	0.6414
No log	2.1633	106	0.4530	0.6263	0.4530	0.6731
No log	2.2041	108	0.5939	0.6113	0.5939	0.7706
No log	2.2449	110	0.8281	0.5304	0.8281	0.9100
No log	2.2857	112	0.5706	0.6226	0.5706	0.7554
No log	2.3265	114	0.3872	0.5757	0.3872	0.6223
No log	2.3673	116	0.3914	0.6089	0.3914	0.6257
No log	2.4082	118	0.6013	0.6209	0.6013	0.7754
No log	2.4490	120	0.5788	0.6444	0.5788	0.7608
No log	2.4898	122	0.4439	0.6446	0.4439	0.6663
No log	2.5306	124	0.4542	0.6485	0.4542	0.6739
No log	2.5714	126	0.4944	0.6570	0.4944	0.7032
No log	2.6122	128	0.5513	0.6839	0.5513	0.7425
No log	2.6531	130	0.4827	0.6659	0.4827	0.6947
No log	2.6939	132	0.3743	0.6005	0.3743	0.6118
No log	2.7347	134	0.3760	0.5962	0.3760	0.6132
No log	2.7755	136	0.5045	0.6870	0.5045	0.7103
No log	2.8163	138	0.5714	0.6702	0.5714	0.7559
No log	2.8571	140	0.4137	0.6159	0.4137	0.6432
No log	2.8980	142	0.3982	0.6056	0.3982	0.6311
No log	2.9388	144	0.4518	0.6306	0.4518	0.6721
No log	2.9796	146	0.4130	0.6074	0.4130	0.6427
No log	3.0204	148	0.3934	0.5977	0.3934	0.6272
No log	3.0612	150	0.4210	0.6198	0.4210	0.6488
No log	3.1020	152	0.5143	0.6329	0.5143	0.7171
No log	3.1429	154	0.4965	0.6277	0.4965	0.7046
No log	3.1837	156	0.4289	0.6203	0.4289	0.6549
No log	3.2245	158	0.3841	0.5789	0.3841	0.6197
No log	3.2653	160	0.4312	0.6363	0.4312	0.6567
No log	3.3061	162	0.4729	0.6679	0.4729	0.6877
No log	3.3469	164	0.3820	0.6302	0.3820	0.6180
No log	3.3878	166	0.3809	0.6393	0.3809	0.6171
No log	3.4286	168	0.5422	0.6973	0.5422	0.7363
No log	3.4694	170	0.6365	0.7199	0.6365	0.7978
No log	3.5102	172	0.4644	0.6863	0.4644	0.6815
No log	3.5510	174	0.4332	0.6931	0.4332	0.6582
No log	3.5918	176	0.5641	0.7100	0.5641	0.7511
No log	3.6327	178	0.6157	0.7202	0.6157	0.7847
No log	3.6735	180	0.4306	0.6845	0.4306	0.6562
No log	3.7143	182	0.3715	0.6469	0.3715	0.6095
No log	3.7551	184	0.3824	0.6664	0.3824	0.6183
No log	3.7959	186	0.5160	0.7158	0.5160	0.7184
No log	3.8367	188	0.4540	0.7203	0.4540	0.6738
No log	3.8776	190	0.3750	0.6436	0.3750	0.6124
No log	3.9184	192	0.3758	0.6433	0.3758	0.6130
No log	3.9592	194	0.4047	0.6908	0.4047	0.6361
No log	4.0	196	0.5673	0.7492	0.5673	0.7532
No log	4.0408	198	0.6172	0.7276	0.6172	0.7856
No log	4.0816	200	0.4254	0.6888	0.4254	0.6523
No log	4.1224	202	0.3846	0.6491	0.3846	0.6201
No log	4.1633	204	0.4845	0.7243	0.4845	0.6960
No log	4.2041	206	0.5566	0.7408	0.5566	0.7461
No log	4.2449	208	0.4267	0.6943	0.4267	0.6533
No log	4.2857	210	0.4272	0.6998	0.4272	0.6536
No log	4.3265	212	0.5318	0.7335	0.5318	0.7293
No log	4.3673	214	0.4779	0.7171	0.4779	0.6913
No log	4.4082	216	0.4608	0.7229	0.4608	0.6789
No log	4.4490	218	0.4025	0.6711	0.4025	0.6344
No log	4.4898	220	0.4468	0.7238	0.4468	0.6684
No log	4.5306	222	0.4140	0.6968	0.4140	0.6435
No log	4.5714	224	0.4050	0.6920	0.4050	0.6364
No log	4.6122	226	0.3989	0.6881	0.3989	0.6316
No log	4.6531	228	0.3959	0.6759	0.3959	0.6292
No log	4.6939	230	0.3848	0.6667	0.3848	0.6204
No log	4.7347	232	0.5152	0.7145	0.5152	0.7178
No log	4.7755	234	0.5334	0.7234	0.5334	0.7303
No log	4.8163	236	0.4302	0.6896	0.4302	0.6559
No log	4.8571	238	0.5161	0.7226	0.5161	0.7184
No log	4.8980	240	0.5682	0.7320	0.5682	0.7538
No log	4.9388	242	0.5183	0.7215	0.5183	0.7199
No log	4.9796	244	0.3877	0.6986	0.3877	0.6226
No log	5.0204	246	0.4036	0.6986	0.4036	0.6353
No log	5.0612	248	0.6315	0.7435	0.6315	0.7946
No log	5.1020	250	0.7402	0.7126	0.7402	0.8604
No log	5.1429	252	0.5175	0.7361	0.5175	0.7194
No log	5.1837	254	0.3760	0.6533	0.3760	0.6132
No log	5.2245	256	0.3832	0.6651	0.3832	0.6190
No log	5.2653	258	0.5435	0.7401	0.5435	0.7372
No log	5.3061	260	0.5996	0.7364	0.5996	0.7744
No log	5.3469	262	0.4389	0.7057	0.4389	0.6625
No log	5.3878	264	0.3730	0.5895	0.3730	0.6108
No log	5.4286	266	0.3813	0.5712	0.3813	0.6175
No log	5.4694	268	0.3832	0.6661	0.3832	0.6190
No log	5.5102	270	0.5630	0.7391	0.5630	0.7504
No log	5.5510	272	0.5997	0.7234	0.5997	0.7744
No log	5.5918	274	0.4750	0.7075	0.4750	0.6892
No log	5.6327	276	0.3800	0.6655	0.3800	0.6164
No log	5.6735	278	0.3968	0.6837	0.3968	0.6299
No log	5.7143	280	0.4484	0.7106	0.4484	0.6696
No log	5.7551	282	0.5921	0.7345	0.5921	0.7695
No log	5.7959	284	0.5035	0.7427	0.5035	0.7095
No log	5.8367	286	0.4175	0.6837	0.4175	0.6461
No log	5.8776	288	0.4724	0.7114	0.4724	0.6873
No log	5.9184	290	0.5301	0.7457	0.5301	0.7281
No log	5.9592	292	0.5814	0.7472	0.5814	0.7625
No log	6.0	294	0.7621	0.7204	0.7621	0.8730
No log	6.0408	296	0.6878	0.7338	0.6878	0.8293
No log	6.0816	298	0.4336	0.6827	0.4336	0.6584
No log	6.1224	300	0.3867	0.6342	0.3867	0.6218
No log	6.1633	302	0.4161	0.6829	0.4161	0.6451
No log	6.2041	304	0.5554	0.7557	0.5554	0.7453
No log	6.2449	306	0.5184	0.7392	0.5184	0.7200
No log	6.2857	308	0.4182	0.6804	0.4182	0.6467
No log	6.3265	310	0.3925	0.6421	0.3925	0.6265
No log	6.3673	312	0.4481	0.6963	0.4481	0.6694
No log	6.4082	314	0.5612	0.7397	0.5612	0.7492
No log	6.4490	316	0.5348	0.7192	0.5348	0.7313
No log	6.4898	318	0.4545	0.6875	0.4545	0.6742
No log	6.5306	320	0.4484	0.6819	0.4484	0.6697
No log	6.5714	322	0.5056	0.7203	0.5056	0.7110
No log	6.6122	324	0.4861	0.6935	0.4861	0.6972
No log	6.6531	326	0.6174	0.7369	0.6174	0.7858
No log	6.6939	328	0.6481	0.7402	0.6481	0.8051
No log	6.7347	330	0.4938	0.6979	0.4938	0.7027
No log	6.7755	332	0.4601	0.6778	0.4601	0.6783
No log	6.8163	334	0.5599	0.7274	0.5599	0.7483
No log	6.8571	336	0.7612	0.7183	0.7612	0.8725
No log	6.8980	338	0.6881	0.7376	0.6881	0.8295
No log	6.9388	340	0.4888	0.6903	0.4888	0.6992
No log	6.9796	342	0.3998	0.6357	0.3998	0.6323
No log	7.0204	344	0.3993	0.6324	0.3993	0.6319
No log	7.0612	346	0.4821	0.6965	0.4821	0.6943
No log	7.1020	348	0.7223	0.7214	0.7223	0.8499
No log	7.1429	350	0.8366	0.7054	0.8366	0.9146
No log	7.1837	352	0.6740	0.7412	0.6740	0.8210
No log	7.2245	354	0.4378	0.6752	0.4378	0.6617
No log	7.2653	356	0.3963	0.6347	0.3963	0.6295
No log	7.3061	358	0.4183	0.6563	0.4183	0.6468
No log	7.3469	360	0.5716	0.7486	0.5716	0.7560
No log	7.3878	362	0.8229	0.6984	0.8229	0.9071
No log	7.4286	364	0.8191	0.6984	0.8191	0.9050
No log	7.4694	366	0.6065	0.7492	0.6065	0.7788
No log	7.5102	368	0.4217	0.6582	0.4217	0.6494
No log	7.5510	370	0.3964	0.6368	0.3964	0.6296
No log	7.5918	372	0.4198	0.6600	0.4198	0.6480
No log	7.6327	374	0.5385	0.7564	0.5385	0.7338
No log	7.6735	376	0.5988	0.7440	0.5988	0.7739
No log	7.7143	378	0.5228	0.7410	0.5228	0.7230
No log	7.7551	380	0.4406	0.6851	0.4406	0.6638
No log	7.7959	382	0.4589	0.7025	0.4589	0.6774
No log	7.8367	384	0.5287	0.7513	0.5287	0.7271
No log	7.8776	386	0.5153	0.7444	0.5153	0.7178
No log	7.9184	388	0.4862	0.728	0.4862	0.6973
No log	7.9592	390	0.4801	0.7244	0.4801	0.6929
No log	8.0	392	0.5149	0.7459	0.5149	0.7176
No log	8.0408	394	0.4643	0.7096	0.4643	0.6814
No log	8.0816	396	0.4553	0.7009	0.4553	0.6748
No log	8.1224	398	0.5337	0.7548	0.5337	0.7306
No log	8.1633	400	0.7244	0.7257	0.7244	0.8511
No log	8.2041	402	0.8182	0.7080	0.8182	0.9045
No log	8.2449	404	0.7316	0.7294	0.7316	0.8553
No log	8.2857	406	0.5459	0.7520	0.5459	0.7388
No log	8.3265	408	0.4213	0.6702	0.4213	0.6491
No log	8.3673	410	0.4054	0.6618	0.4054	0.6367
No log	8.4082	412	0.4370	0.6927	0.4370	0.6611
No log	8.4490	414	0.5127	0.7334	0.5127	0.7160
No log	8.4898	416	0.5631	0.7608	0.5631	0.7504
No log	8.5306	418	0.5482	0.7502	0.5482	0.7404
No log	8.5714	420	0.4857	0.7258	0.4857	0.6969
No log	8.6122	422	0.4757	0.7269	0.4757	0.6897
No log	8.6531	424	0.4981	0.7304	0.4981	0.7058
No log	8.6939	426	0.4921	0.7297	0.4921	0.7015
No log	8.7347	428	0.5064	0.7342	0.5064	0.7116
No log	8.7755	430	0.4788	0.7176	0.4788	0.6919
No log	8.8163	432	0.4734	0.7158	0.4734	0.6880
No log	8.8571	434	0.5186	0.7330	0.5186	0.7202
No log	8.8980	436	0.5618	0.7541	0.5618	0.7496
No log	8.9388	438	0.5526	0.7465	0.5526	0.7433
No log	8.9796	440	0.4982	0.7340	0.4982	0.7058
No log	9.0204	442	0.4574	0.7069	0.4574	0.6763
No log	9.0612	444	0.4349	0.6857	0.4349	0.6595
No log	9.1020	446	0.4416	0.6941	0.4416	0.6645
No log	9.1429	448	0.4531	0.7026	0.4531	0.6731
No log	9.1837	450	0.4727	0.7151	0.4727	0.6875
No log	9.2245	452	0.5098	0.7390	0.5098	0.7140
No log	9.2653	454	0.5445	0.7499	0.5445	0.7379
No log	9.3061	456	0.5649	0.7526	0.5649	0.7516
No log	9.3469	458	0.5518	0.7554	0.5518	0.7429
No log	9.3878	460	0.5493	0.7479	0.5493	0.7411
No log	9.4286	462	0.5317	0.7446	0.5317	0.7292
No log	9.4694	464	0.5014	0.7225	0.5014	0.7081
No log	9.5102	466	0.4820	0.7215	0.4820	0.6943
No log	9.5510	468	0.4826	0.7215	0.4826	0.6947
No log	9.5918	470	0.4886	0.7229	0.4886	0.6990
No log	9.6327	472	0.5002	0.7248	0.5002	0.7072
No log	9.6735	474	0.5240	0.7387	0.5240	0.7239
No log	9.7143	476	0.5446	0.7434	0.5446	0.7380
No log	9.7551	478	0.5674	0.7475	0.5674	0.7533
No log	9.7959	480	0.5796	0.7550	0.5796	0.7613
No log	9.8367	482	0.5774	0.7529	0.5774	0.7599
No log	9.8776	484	0.5708	0.7466	0.5708	0.7555
No log	9.9184	486	0.5618	0.7475	0.5618	0.7495
No log	9.9592	488	0.5542	0.7456	0.5542	0.7445
No log	10.0	490	0.5510	0.7451	0.5510	0.7423

Framework versions

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