ASAP_FineTuningBERT_Aug_k1_task1_organization_fold2

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: 0.6043
• Qwk: 0.6954
• Mse: 0.6043
• Rmse: 0.7774

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	10.7657	0.0	10.7657	3.2811
No log	0.0833	4	8.2253	0.0183	8.2253	2.8680
No log	0.125	6	6.5378	0.0041	6.5378	2.5569
No log	0.1667	8	5.2750	0.0018	5.2750	2.2967
No log	0.2083	10	3.4516	0.0404	3.4516	1.8579
No log	0.25	12	2.6091	0.0137	2.6091	1.6153
No log	0.2917	14	1.9316	0.0078	1.9316	1.3898
No log	0.3333	16	1.4906	0.0037	1.4906	1.2209
No log	0.375	18	1.1079	0.0860	1.1079	1.0526
No log	0.4167	20	0.9248	0.0334	0.9248	0.9617
No log	0.4583	22	0.8210	0.0241	0.8210	0.9061
No log	0.5	24	0.7948	0.0107	0.7948	0.8915
No log	0.5417	26	0.8327	0.2923	0.8327	0.9125
No log	0.5833	28	0.7003	0.2360	0.7003	0.8368
No log	0.625	30	0.6243	0.1686	0.6243	0.7902
No log	0.6667	32	0.6385	0.4514	0.6385	0.7991
No log	0.7083	34	0.5220	0.4335	0.5220	0.7225
No log	0.75	36	0.7136	0.2509	0.7136	0.8447
No log	0.7917	38	0.5256	0.3999	0.5256	0.7250
No log	0.8333	40	0.5568	0.5058	0.5568	0.7462
No log	0.875	42	0.5081	0.5435	0.5081	0.7128
No log	0.9167	44	0.4580	0.4864	0.4580	0.6768
No log	0.9583	46	0.4694	0.5194	0.4694	0.6851
No log	1.0	48	0.6405	0.4764	0.6405	0.8003
No log	1.0417	50	0.6573	0.4495	0.6573	0.8108
No log	1.0833	52	0.4553	0.5499	0.4553	0.6748
No log	1.125	54	0.4816	0.4867	0.4816	0.6940
No log	1.1667	56	0.4365	0.5584	0.4365	0.6607
No log	1.2083	58	0.5495	0.5828	0.5495	0.7413
No log	1.25	60	0.4410	0.5941	0.4410	0.6641
No log	1.2917	62	0.4411	0.5933	0.4411	0.6641
No log	1.3333	64	0.4733	0.5958	0.4733	0.6880
No log	1.375	66	0.3988	0.5604	0.3988	0.6315
No log	1.4167	68	0.4185	0.6009	0.4185	0.6469
No log	1.4583	70	0.5885	0.5849	0.5885	0.7672
No log	1.5	72	0.4821	0.6061	0.4821	0.6943
No log	1.5417	74	0.4191	0.5966	0.4191	0.6474
No log	1.5833	76	0.3935	0.5474	0.3935	0.6273
No log	1.625	78	0.5128	0.5898	0.5128	0.7161
No log	1.6667	80	0.9075	0.4586	0.9075	0.9526
No log	1.7083	82	0.8435	0.4645	0.8435	0.9184
No log	1.75	84	0.5071	0.5828	0.5071	0.7121
No log	1.7917	86	0.4188	0.5815	0.4188	0.6472
No log	1.8333	88	0.4762	0.5850	0.4762	0.6901
No log	1.875	90	0.5308	0.5879	0.5308	0.7286
No log	1.9167	92	0.4211	0.5919	0.4211	0.6489
No log	1.9583	94	0.3857	0.5509	0.3857	0.6211
No log	2.0	96	0.4026	0.6002	0.4026	0.6345
No log	2.0417	98	0.5385	0.6043	0.5385	0.7338
No log	2.0833	100	0.4661	0.6168	0.4661	0.6827
No log	2.125	102	0.4228	0.6228	0.4228	0.6502
No log	2.1667	104	0.3912	0.5845	0.3912	0.6254
No log	2.2083	106	0.5121	0.6151	0.5121	0.7156
No log	2.25	108	0.6569	0.5691	0.6569	0.8105
No log	2.2917	110	0.6346	0.5780	0.6346	0.7966
No log	2.3333	112	0.3990	0.6045	0.3990	0.6317
No log	2.375	114	0.3813	0.5694	0.3813	0.6175
No log	2.4167	116	0.4148	0.6142	0.4148	0.6440
No log	2.4583	118	0.6545	0.5707	0.6545	0.8090
No log	2.5	120	0.6300	0.5924	0.6300	0.7937
No log	2.5417	122	0.4086	0.5913	0.4086	0.6392
No log	2.5833	124	0.3951	0.5829	0.3951	0.6286
No log	2.625	126	0.5591	0.6010	0.5591	0.7477
No log	2.6667	128	0.6101	0.6029	0.6101	0.7811
No log	2.7083	130	0.4895	0.5991	0.4895	0.6997
No log	2.75	132	0.4068	0.5928	0.4068	0.6378
No log	2.7917	134	0.4556	0.5814	0.4556	0.6750
No log	2.8333	136	0.5489	0.6170	0.5489	0.7409
No log	2.875	138	0.5014	0.6340	0.5014	0.7081
No log	2.9167	140	0.4151	0.6306	0.4151	0.6443
No log	2.9583	142	0.4103	0.6134	0.4103	0.6405
No log	3.0	144	0.5142	0.6563	0.5142	0.7171
No log	3.0417	146	0.5363	0.6662	0.5363	0.7323
No log	3.0833	148	0.5616	0.6778	0.5616	0.7494
No log	3.125	150	0.4689	0.6814	0.4689	0.6847
No log	3.1667	152	0.4135	0.6465	0.4135	0.6430
No log	3.2083	154	0.4662	0.6662	0.4662	0.6828
No log	3.25	156	0.8330	0.5723	0.8330	0.9127
No log	3.2917	158	0.9640	0.5480	0.9640	0.9819
No log	3.3333	160	0.6666	0.5727	0.6666	0.8165
No log	3.375	162	0.4117	0.5973	0.4117	0.6417
No log	3.4167	164	0.4293	0.6170	0.4293	0.6552
No log	3.4583	166	0.6960	0.6004	0.6960	0.8343
No log	3.5	168	0.7161	0.6118	0.7161	0.8463
No log	3.5417	170	0.4412	0.6809	0.4412	0.6643
No log	3.5833	172	0.3832	0.6456	0.3832	0.6190
No log	3.625	174	0.4678	0.7017	0.4678	0.6840
No log	3.6667	176	0.7057	0.6904	0.7057	0.8401
No log	3.7083	178	0.5916	0.6907	0.5916	0.7692
No log	3.75	180	0.4017	0.6291	0.4017	0.6338
No log	3.7917	182	0.4045	0.6393	0.4045	0.6360
No log	3.8333	184	0.4320	0.6974	0.4320	0.6573
No log	3.875	186	0.5215	0.7016	0.5215	0.7221
No log	3.9167	188	0.5924	0.7071	0.5924	0.7696
No log	3.9583	190	0.4533	0.6953	0.4533	0.6733
No log	4.0	192	0.4720	0.6931	0.4720	0.6870
No log	4.0417	194	0.6832	0.6945	0.6832	0.8265
No log	4.0833	196	0.6646	0.7116	0.6646	0.8152
No log	4.125	198	0.4405	0.6850	0.4405	0.6637
No log	4.1667	200	0.3757	0.5815	0.3757	0.6129
No log	4.2083	202	0.3955	0.6029	0.3955	0.6289
No log	4.25	204	0.5973	0.7051	0.5973	0.7728
No log	4.2917	206	0.7222	0.6888	0.7222	0.8498
No log	4.3333	208	0.5359	0.7020	0.5359	0.7321
No log	4.375	210	0.4703	0.6855	0.4703	0.6858
No log	4.4167	212	0.4739	0.6944	0.4739	0.6884
No log	4.4583	214	0.6845	0.6734	0.6845	0.8274
No log	4.5	216	0.7362	0.6653	0.7362	0.8580
No log	4.5417	218	0.5030	0.6474	0.5030	0.7093
No log	4.5833	220	0.3952	0.5584	0.3952	0.6287
No log	4.625	222	0.3953	0.5853	0.3953	0.6287
No log	4.6667	224	0.5264	0.6530	0.5264	0.7255
No log	4.7083	226	0.7965	0.6560	0.7965	0.8925
No log	4.75	228	0.7343	0.6601	0.7343	0.8569
No log	4.7917	230	0.4832	0.6334	0.4832	0.6951
No log	4.8333	232	0.3936	0.5900	0.3936	0.6274
No log	4.875	234	0.4282	0.6461	0.4282	0.6544
No log	4.9167	236	0.6184	0.6872	0.6184	0.7864
No log	4.9583	238	0.6767	0.6869	0.6767	0.8226
No log	5.0	240	0.5716	0.7012	0.5716	0.7561
No log	5.0417	242	0.4097	0.6760	0.4097	0.6401
No log	5.0833	244	0.3916	0.6583	0.3916	0.6258
No log	5.125	246	0.4861	0.7076	0.4861	0.6972
No log	5.1667	248	0.5545	0.7013	0.5545	0.7446
No log	5.2083	250	0.5001	0.7110	0.5001	0.7072
No log	5.25	252	0.5789	0.6996	0.5789	0.7608
No log	5.2917	254	0.5651	0.7012	0.5651	0.7517
No log	5.3333	256	0.4139	0.6762	0.4139	0.6434
No log	5.375	258	0.3925	0.5355	0.3925	0.6265
No log	5.4167	260	0.3857	0.5556	0.3857	0.6211
No log	5.4583	262	0.4237	0.6623	0.4237	0.6509
No log	5.5	264	0.6273	0.6957	0.6273	0.7920
No log	5.5417	266	0.7270	0.6923	0.7270	0.8526
No log	5.5833	268	0.6028	0.6976	0.6028	0.7764
No log	5.625	270	0.4743	0.6633	0.4743	0.6887
No log	5.6667	272	0.4617	0.6621	0.4617	0.6795
No log	5.7083	274	0.5382	0.6847	0.5382	0.7336
No log	5.75	276	0.7118	0.6860	0.7118	0.8437
No log	5.7917	278	0.8327	0.6753	0.8327	0.9125
No log	5.8333	280	0.7823	0.6949	0.7823	0.8845
No log	5.875	282	0.6016	0.7136	0.6016	0.7756
No log	5.9167	284	0.3981	0.6556	0.3981	0.6309
No log	5.9583	286	0.3857	0.5847	0.3857	0.6211
No log	6.0	288	0.3808	0.6048	0.3808	0.6171
No log	6.0417	290	0.4824	0.6944	0.4824	0.6946
No log	6.0833	292	0.7217	0.7020	0.7217	0.8495
No log	6.125	294	0.7880	0.6823	0.7880	0.8877
No log	6.1667	296	0.6048	0.6923	0.6048	0.7777
No log	6.2083	298	0.4116	0.6263	0.4116	0.6416
No log	6.25	300	0.3896	0.5833	0.3896	0.6242
No log	6.2917	302	0.4164	0.6621	0.4164	0.6453
No log	6.3333	304	0.5897	0.7020	0.5897	0.7679
No log	6.375	306	0.8162	0.6843	0.8162	0.9034
No log	6.4167	308	0.7777	0.6946	0.7777	0.8819
No log	6.4583	310	0.5658	0.7083	0.5658	0.7522
No log	6.5	312	0.3994	0.6243	0.3994	0.6320
No log	6.5417	314	0.3873	0.5620	0.3873	0.6223
No log	6.5833	316	0.3947	0.6068	0.3947	0.6283
No log	6.625	318	0.5119	0.6942	0.5119	0.7155
No log	6.6667	320	0.6877	0.7083	0.6877	0.8293
No log	6.7083	322	0.6772	0.7068	0.6772	0.8229
No log	6.75	324	0.5486	0.6935	0.5486	0.7407
No log	6.7917	326	0.4506	0.6687	0.4506	0.6713
No log	6.8333	328	0.4711	0.6731	0.4711	0.6864
No log	6.875	330	0.5570	0.6915	0.5570	0.7464
No log	6.9167	332	0.7005	0.6907	0.7005	0.8369
No log	6.9583	334	0.6728	0.6906	0.6728	0.8203
No log	7.0	336	0.5453	0.6971	0.5453	0.7385
No log	7.0417	338	0.5274	0.7105	0.5274	0.7262
No log	7.0833	340	0.6117	0.7126	0.6117	0.7821
No log	7.125	342	0.7077	0.6988	0.7077	0.8413
No log	7.1667	344	0.6474	0.7108	0.6474	0.8046
No log	7.2083	346	0.5001	0.6831	0.5001	0.7072
No log	7.25	348	0.4499	0.6560	0.4499	0.6707
No log	7.2917	350	0.4495	0.6559	0.4495	0.6705
No log	7.3333	352	0.4939	0.6673	0.4939	0.7028
No log	7.375	354	0.6531	0.7050	0.6531	0.8082
No log	7.4167	356	0.8291	0.6565	0.8291	0.9105
No log	7.4583	358	0.8070	0.6620	0.8070	0.8983
No log	7.5	360	0.6436	0.6892	0.6436	0.8022
No log	7.5417	362	0.5314	0.6770	0.5314	0.7289
No log	7.5833	364	0.4958	0.6746	0.4958	0.7042
No log	7.625	366	0.5176	0.6801	0.5176	0.7194
No log	7.6667	368	0.5773	0.6953	0.5773	0.7598
No log	7.7083	370	0.6013	0.7075	0.6013	0.7754
No log	7.75	372	0.5657	0.7083	0.5657	0.7521
No log	7.7917	374	0.4732	0.7004	0.4732	0.6879
No log	7.8333	376	0.4706	0.6983	0.4706	0.6860
No log	7.875	378	0.5283	0.7006	0.5283	0.7268
No log	7.9167	380	0.6123	0.7025	0.6123	0.7825
No log	7.9583	382	0.6428	0.6936	0.6428	0.8018
No log	8.0	384	0.5758	0.6948	0.5758	0.7588
No log	8.0417	386	0.4962	0.7115	0.4962	0.7044
No log	8.0833	388	0.5020	0.7072	0.5020	0.7085
No log	8.125	390	0.5627	0.6965	0.5627	0.7501
No log	8.1667	392	0.6506	0.7019	0.6506	0.8066
No log	8.2083	394	0.7079	0.7049	0.7079	0.8414
No log	8.25	396	0.6469	0.6982	0.6469	0.8043
No log	8.2917	398	0.5411	0.7013	0.5411	0.7356
No log	8.3333	400	0.5018	0.7143	0.5018	0.7084
No log	8.375	402	0.5157	0.7055	0.5157	0.7182
No log	8.4167	404	0.5275	0.6994	0.5275	0.7263
No log	8.4583	406	0.5201	0.7055	0.5201	0.7212
No log	8.5	408	0.5216	0.6990	0.5216	0.7222
No log	8.5417	410	0.5621	0.6942	0.5621	0.7497
No log	8.5833	412	0.6347	0.7010	0.6347	0.7967
No log	8.625	414	0.7340	0.6877	0.7340	0.8567
No log	8.6667	416	0.7498	0.6842	0.7498	0.8659
No log	8.7083	418	0.6884	0.6975	0.6884	0.8297
No log	8.75	420	0.6261	0.6935	0.6261	0.7912
No log	8.7917	422	0.6042	0.6896	0.6042	0.7773
No log	8.8333	424	0.5943	0.6910	0.5943	0.7709
No log	8.875	426	0.5923	0.6882	0.5923	0.7696
No log	8.9167	428	0.5774	0.6967	0.5774	0.7599
No log	8.9583	430	0.5922	0.6954	0.5922	0.7695
No log	9.0	432	0.6230	0.6946	0.6230	0.7893
No log	9.0417	434	0.6648	0.7012	0.6648	0.8153
No log	9.0833	436	0.6526	0.7048	0.6526	0.8078
No log	9.125	438	0.6050	0.6911	0.6050	0.7778
No log	9.1667	440	0.5683	0.6876	0.5683	0.7538
No log	9.2083	442	0.5459	0.6753	0.5459	0.7388
No log	9.25	444	0.5326	0.6796	0.5326	0.7298
No log	9.2917	446	0.5409	0.6755	0.5409	0.7354
No log	9.3333	448	0.5647	0.6927	0.5647	0.7515
No log	9.375	450	0.5759	0.6875	0.5759	0.7589
No log	9.4167	452	0.5919	0.6900	0.5919	0.7694
No log	9.4583	454	0.6127	0.6867	0.6127	0.7827
No log	9.5	456	0.6028	0.6877	0.6028	0.7764
No log	9.5417	458	0.6010	0.6877	0.6010	0.7753
No log	9.5833	460	0.6012	0.6916	0.6012	0.7754
No log	9.625	462	0.5903	0.6969	0.5903	0.7683
No log	9.6667	464	0.5997	0.6930	0.5997	0.7744
No log	9.7083	466	0.6021	0.6930	0.6021	0.7759
No log	9.75	468	0.6001	0.6930	0.6001	0.7747
No log	9.7917	470	0.6003	0.6916	0.6003	0.7748
No log	9.8333	472	0.5992	0.6916	0.5992	0.7741
No log	9.875	474	0.5982	0.6925	0.5982	0.7735
No log	9.9167	476	0.5994	0.6916	0.5994	0.7742
No log	9.9583	478	0.6028	0.6954	0.6028	0.7764
No log	10.0	480	0.6043	0.6954	0.6043	0.7774

Framework versions

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