ASAP_FineTuningBERT_Aug_k1_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: 0.5628
• Qwk: 0.6860
• Mse: 0.5628
• Rmse: 0.7502

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	0.0417	2	12.2581	0.0	12.2581	3.5012
No log	0.0833	4	10.7305	0.0	10.7305	3.2757
No log	0.125	6	9.3780	0.0	9.3780	3.0624
No log	0.1667	8	7.8940	0.0151	7.8940	2.8096
No log	0.2083	10	6.3407	0.0054	6.3407	2.5181
No log	0.25	12	4.9823	0.0	4.9823	2.2321
No log	0.2917	14	3.7871	0.0301	3.7871	1.9461
No log	0.3333	16	2.7847	0.0153	2.7847	1.6687
No log	0.375	18	2.1250	0.0115	2.1250	1.4577
No log	0.4167	20	1.6283	0.0115	1.6283	1.2761
No log	0.4583	22	1.2686	0.1303	1.2686	1.1263
No log	0.5	24	0.9786	0.0520	0.9786	0.9893
No log	0.5417	26	0.8287	0.0316	0.8287	0.9104
No log	0.5833	28	0.7935	0.0316	0.7935	0.8908
No log	0.625	30	0.7533	0.0316	0.7533	0.8679
No log	0.6667	32	0.6665	0.0753	0.6665	0.8164
No log	0.7083	34	0.6449	0.3184	0.6449	0.8031
No log	0.75	36	0.6085	0.1907	0.6085	0.7800
No log	0.7917	38	0.5721	0.4768	0.5721	0.7564
No log	0.8333	40	0.5803	0.2019	0.5803	0.7617
No log	0.875	42	0.5634	0.2306	0.5634	0.7506
No log	0.9167	44	0.5410	0.5480	0.5410	0.7356
No log	0.9583	46	0.6210	0.4826	0.6210	0.7880
No log	1.0	48	0.5538	0.5020	0.5538	0.7442
No log	1.0417	50	0.5771	0.1895	0.5771	0.7597
No log	1.0833	52	0.5687	0.2029	0.5687	0.7541
No log	1.125	54	0.5276	0.5275	0.5276	0.7264
No log	1.1667	56	0.5453	0.5648	0.5453	0.7384
No log	1.2083	58	0.5077	0.5160	0.5077	0.7126
No log	1.25	60	0.5021	0.3805	0.5021	0.7086
No log	1.2917	62	0.5300	0.4025	0.5300	0.7280
No log	1.3333	64	0.4410	0.5028	0.4410	0.6641
No log	1.375	66	0.4923	0.5735	0.4923	0.7016
No log	1.4167	68	0.5228	0.4128	0.5228	0.7230
No log	1.4583	70	0.5592	0.2526	0.5592	0.7478
No log	1.5	72	0.4490	0.5548	0.4490	0.6700
No log	1.5417	74	0.4208	0.5768	0.4208	0.6487
No log	1.5833	76	0.4057	0.5977	0.4057	0.6370
No log	1.625	78	0.3985	0.5970	0.3985	0.6312
No log	1.6667	80	0.4250	0.6164	0.4250	0.6519
No log	1.7083	82	0.3931	0.6120	0.3931	0.6270
No log	1.75	84	0.3950	0.6040	0.3950	0.6285
No log	1.7917	86	0.4534	0.5853	0.4534	0.6733
No log	1.8333	88	0.4305	0.6085	0.4305	0.6561
No log	1.875	90	0.4210	0.6151	0.4210	0.6488
No log	1.9167	92	0.3865	0.5706	0.3865	0.6217
No log	1.9583	94	0.3874	0.5898	0.3874	0.6224
No log	2.0	96	0.3856	0.5708	0.3856	0.6210
No log	2.0417	98	0.3949	0.5304	0.3949	0.6284
No log	2.0833	100	0.3864	0.5834	0.3864	0.6216
No log	2.125	102	0.4122	0.6112	0.4122	0.6421
No log	2.1667	104	0.3922	0.5980	0.3922	0.6263
No log	2.2083	106	0.3827	0.5633	0.3827	0.6187
No log	2.25	108	0.4362	0.5978	0.4362	0.6604
No log	2.2917	110	0.4792	0.6069	0.4792	0.6922
No log	2.3333	112	0.5797	0.5806	0.5797	0.7614
No log	2.375	114	0.4223	0.5988	0.4223	0.6499
No log	2.4167	116	0.4240	0.5275	0.4240	0.6512
No log	2.4583	118	0.3983	0.5674	0.3983	0.6311
No log	2.5	120	0.5535	0.5916	0.5535	0.7440
No log	2.5417	122	0.4987	0.5933	0.4987	0.7062
No log	2.5833	124	0.3885	0.5930	0.3885	0.6233
No log	2.625	126	0.3974	0.6135	0.3974	0.6304
No log	2.6667	128	0.3875	0.5881	0.3875	0.6225
No log	2.7083	130	0.4514	0.6044	0.4514	0.6718
No log	2.75	132	0.5186	0.5907	0.5186	0.7202
No log	2.7917	134	0.4316	0.6159	0.4316	0.6570
No log	2.8333	136	0.3962	0.5359	0.3962	0.6294
No log	2.875	138	0.4328	0.5041	0.4328	0.6579
No log	2.9167	140	0.3864	0.5561	0.3864	0.6216
No log	2.9583	142	0.4972	0.6064	0.4972	0.7051
No log	3.0	144	0.6056	0.5604	0.6056	0.7782
No log	3.0417	146	0.4761	0.5995	0.4761	0.6900
No log	3.0833	148	0.3775	0.5663	0.3775	0.6144
No log	3.125	150	0.3730	0.5665	0.3730	0.6107
No log	3.1667	152	0.4008	0.6126	0.4008	0.6331
No log	3.2083	154	0.4142	0.6154	0.4142	0.6436
No log	3.25	156	0.3880	0.5830	0.3880	0.6229
No log	3.2917	158	0.4069	0.5207	0.4069	0.6379
No log	3.3333	160	0.3738	0.5850	0.3738	0.6114
No log	3.375	162	0.4507	0.6037	0.4507	0.6714
No log	3.4167	164	0.5241	0.6019	0.5241	0.7240
No log	3.4583	166	0.4212	0.5970	0.4212	0.6490
No log	3.5	168	0.3993	0.6004	0.3993	0.6319
No log	3.5417	170	0.4117	0.6118	0.4117	0.6416
No log	3.5833	172	0.4920	0.6171	0.4920	0.7014
No log	3.625	174	0.4386	0.6154	0.4386	0.6622
No log	3.6667	176	0.3971	0.5804	0.3971	0.6302
No log	3.7083	178	0.4044	0.6160	0.4044	0.6359
No log	3.75	180	0.4749	0.6503	0.4749	0.6892
No log	3.7917	182	0.4711	0.6558	0.4711	0.6864
No log	3.8333	184	0.4122	0.6236	0.4122	0.6421
No log	3.875	186	0.4383	0.6486	0.4383	0.6620
No log	3.9167	188	0.5540	0.6602	0.5540	0.7443
No log	3.9583	190	0.5229	0.6323	0.5229	0.7231
No log	4.0	192	0.4143	0.6229	0.4143	0.6437
No log	4.0417	194	0.4092	0.6111	0.4092	0.6397
No log	4.0833	196	0.4004	0.5858	0.4004	0.6328
No log	4.125	198	0.4240	0.6261	0.4240	0.6511
No log	4.1667	200	0.4509	0.6569	0.4509	0.6715
No log	4.2083	202	0.4430	0.6487	0.4430	0.6656
No log	4.25	204	0.4532	0.6583	0.4532	0.6732
No log	4.2917	206	0.4805	0.6885	0.4805	0.6931
No log	4.3333	208	0.4514	0.6544	0.4514	0.6719
No log	4.375	210	0.4293	0.6459	0.4293	0.6552
No log	4.4167	212	0.4752	0.6891	0.4752	0.6893
No log	4.4583	214	0.4589	0.6740	0.4589	0.6775
No log	4.5	216	0.4621	0.6708	0.4621	0.6798
No log	4.5417	218	0.4957	0.7025	0.4957	0.7041
No log	4.5833	220	0.4422	0.6703	0.4422	0.6650
No log	4.625	222	0.4888	0.6952	0.4888	0.6991
No log	4.6667	224	0.5012	0.7037	0.5012	0.7080
No log	4.7083	226	0.4190	0.6442	0.4190	0.6473
No log	4.75	228	0.4185	0.6441	0.4185	0.6469
No log	4.7917	230	0.4844	0.7022	0.4844	0.6960
No log	4.8333	232	0.5227	0.7161	0.5227	0.7230
No log	4.875	234	0.4612	0.6805	0.4612	0.6791
No log	4.9167	236	0.4814	0.6974	0.4814	0.6938
No log	4.9583	238	0.5769	0.7178	0.5769	0.7596
No log	5.0	240	0.4859	0.7007	0.4859	0.6971
No log	5.0417	242	0.4442	0.6773	0.4442	0.6665
No log	5.0833	244	0.4165	0.6516	0.4165	0.6454
No log	5.125	246	0.4202	0.6602	0.4202	0.6482
No log	5.1667	248	0.5381	0.7025	0.5381	0.7335
No log	5.2083	250	0.5786	0.6944	0.5786	0.7606
No log	5.25	252	0.4437	0.6777	0.4437	0.6661
No log	5.2917	254	0.4171	0.6386	0.4171	0.6458
No log	5.3333	256	0.4688	0.6921	0.4689	0.6847
No log	5.375	258	0.6081	0.7018	0.6081	0.7798
No log	5.4167	260	0.5369	0.6948	0.5369	0.7327
No log	5.4583	262	0.4274	0.5976	0.4274	0.6538
No log	5.5	264	0.4447	0.5303	0.4447	0.6668
No log	5.5417	266	0.4336	0.6118	0.4336	0.6585
No log	5.5833	268	0.5903	0.6987	0.5903	0.7683
No log	5.625	270	0.7164	0.6834	0.7164	0.8464
No log	5.6667	272	0.6050	0.7011	0.6050	0.7778
No log	5.7083	274	0.4476	0.6450	0.4476	0.6690
No log	5.75	276	0.4332	0.5720	0.4332	0.6582
No log	5.7917	278	0.4307	0.6173	0.4307	0.6563
No log	5.8333	280	0.5598	0.6834	0.5598	0.7482
No log	5.875	282	0.6906	0.6884	0.6906	0.8310
No log	5.9167	284	0.5984	0.6804	0.5984	0.7735
No log	5.9583	286	0.4716	0.6710	0.4716	0.6867
No log	6.0	288	0.4506	0.6608	0.4506	0.6713
No log	6.0417	290	0.5083	0.6793	0.5083	0.7129
No log	6.0833	292	0.5147	0.6824	0.5147	0.7174
No log	6.125	294	0.5067	0.6828	0.5067	0.7119
No log	6.1667	296	0.4556	0.6576	0.4556	0.6750
No log	6.2083	298	0.4707	0.6685	0.4707	0.6861
No log	6.25	300	0.6061	0.6875	0.6061	0.7785
No log	6.2917	302	0.6728	0.6809	0.6728	0.8203
No log	6.3333	304	0.5539	0.6913	0.5539	0.7443
No log	6.375	306	0.4382	0.6209	0.4382	0.6619
No log	6.4167	308	0.4331	0.5703	0.4331	0.6581
No log	6.4583	310	0.4449	0.6556	0.4449	0.6670
No log	6.5	312	0.5719	0.6966	0.5719	0.7563
No log	6.5417	314	0.6454	0.7033	0.6454	0.8034
No log	6.5833	316	0.5645	0.6968	0.5645	0.7513
No log	6.625	318	0.4620	0.6619	0.4620	0.6797
No log	6.6667	320	0.4495	0.6195	0.4495	0.6705
No log	6.7083	322	0.4732	0.6789	0.4732	0.6879
No log	6.75	324	0.5300	0.6948	0.5300	0.7280
No log	6.7917	326	0.5037	0.6855	0.5037	0.7097
No log	6.8333	328	0.4607	0.6759	0.4607	0.6787
No log	6.875	330	0.5010	0.6861	0.5010	0.7078
No log	6.9167	332	0.5533	0.6893	0.5533	0.7439
No log	6.9583	334	0.5596	0.6945	0.5596	0.7481
No log	7.0	336	0.5392	0.6886	0.5392	0.7343
No log	7.0417	338	0.4774	0.6620	0.4774	0.6909
No log	7.0833	340	0.4694	0.6394	0.4694	0.6852
No log	7.125	342	0.5115	0.6768	0.5115	0.7152
No log	7.1667	344	0.6132	0.7095	0.6132	0.7831
No log	7.2083	346	0.5996	0.7072	0.5996	0.7743
No log	7.25	348	0.5277	0.6910	0.5277	0.7264
No log	7.2917	350	0.4747	0.6340	0.4747	0.6890
No log	7.3333	352	0.4738	0.6486	0.4738	0.6883
No log	7.375	354	0.5077	0.6793	0.5077	0.7126
No log	7.4167	356	0.5837	0.7007	0.5837	0.7640
No log	7.4583	358	0.5623	0.6994	0.5623	0.7498
No log	7.5	360	0.4817	0.6795	0.4817	0.6941
No log	7.5417	362	0.4693	0.6629	0.4693	0.6851
No log	7.5833	364	0.5108	0.6813	0.5108	0.7147
No log	7.625	366	0.5911	0.7010	0.5911	0.7688
No log	7.6667	368	0.5656	0.7047	0.5656	0.7520
No log	7.7083	370	0.5176	0.6799	0.5176	0.7194
No log	7.75	372	0.5084	0.6783	0.5084	0.7131
No log	7.7917	374	0.5234	0.6770	0.5234	0.7235
No log	7.8333	376	0.5778	0.6995	0.5778	0.7601
No log	7.875	378	0.5784	0.6920	0.5784	0.7605
No log	7.9167	380	0.5380	0.6839	0.5380	0.7335
No log	7.9583	382	0.5480	0.6838	0.5480	0.7403
No log	8.0	384	0.5856	0.6847	0.5856	0.7653
No log	8.0417	386	0.6271	0.6930	0.6271	0.7919
No log	8.0833	388	0.5795	0.6822	0.5795	0.7613
No log	8.125	390	0.5065	0.6551	0.5065	0.7117
No log	8.1667	392	0.4912	0.6515	0.4912	0.7009
No log	8.2083	394	0.5290	0.6635	0.5290	0.7273
No log	8.25	396	0.5962	0.6864	0.5962	0.7722
No log	8.2917	398	0.6260	0.6898	0.6260	0.7912
No log	8.3333	400	0.5698	0.6918	0.5698	0.7549
No log	8.375	402	0.4957	0.6631	0.4957	0.7040
No log	8.4167	404	0.4712	0.6402	0.4712	0.6864
No log	8.4583	406	0.4821	0.6604	0.4821	0.6943
No log	8.5	408	0.5369	0.6874	0.5369	0.7328
No log	8.5417	410	0.5864	0.6789	0.5864	0.7658
No log	8.5833	412	0.5693	0.6734	0.5693	0.7545
No log	8.625	414	0.5160	0.6800	0.5160	0.7184
No log	8.6667	416	0.4742	0.6562	0.4742	0.6886
No log	8.7083	418	0.4792	0.6613	0.4792	0.6922
No log	8.75	420	0.5247	0.6751	0.5247	0.7244
No log	8.7917	422	0.5716	0.6781	0.5716	0.7561
No log	8.8333	424	0.5928	0.6819	0.5928	0.7699
No log	8.875	426	0.5721	0.6802	0.5721	0.7563
No log	8.9167	428	0.5185	0.6805	0.5185	0.7201
No log	8.9583	430	0.4814	0.6604	0.4814	0.6938
No log	9.0	432	0.4823	0.6578	0.4823	0.6945
No log	9.0417	434	0.5074	0.6720	0.5074	0.7123
No log	9.0833	436	0.5592	0.6892	0.5592	0.7478
No log	9.125	438	0.6047	0.6928	0.6047	0.7776
No log	9.1667	440	0.6198	0.6935	0.6198	0.7873
No log	9.2083	442	0.5909	0.6912	0.5909	0.7687
No log	9.25	444	0.5490	0.6911	0.5490	0.7409
No log	9.2917	446	0.5281	0.6831	0.5281	0.7267
No log	9.3333	448	0.5187	0.6817	0.5187	0.7202
No log	9.375	450	0.5260	0.6816	0.5260	0.7253
No log	9.4167	452	0.5262	0.6816	0.5262	0.7254
No log	9.4583	454	0.5384	0.6894	0.5384	0.7338
No log	9.5	456	0.5464	0.6813	0.5464	0.7392
No log	9.5417	458	0.5426	0.6813	0.5426	0.7366
No log	9.5833	460	0.5340	0.6781	0.5340	0.7308
No log	9.625	462	0.5341	0.6781	0.5341	0.7308
No log	9.6667	464	0.5366	0.6763	0.5366	0.7326
No log	9.7083	466	0.5371	0.6745	0.5371	0.7328
No log	9.75	468	0.5408	0.6757	0.5408	0.7354
No log	9.7917	470	0.5518	0.6774	0.5518	0.7429
No log	9.8333	472	0.5634	0.6883	0.5634	0.7506
No log	9.875	474	0.5658	0.6883	0.5658	0.7522
No log	9.9167	476	0.5639	0.6860	0.5639	0.7509
No log	9.9583	478	0.5630	0.6860	0.5630	0.7503
No log	10.0	480	0.5628	0.6860	0.5628	0.7502

Framework versions

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