learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	1	12.3019	-0.0020	12.3000	3.5071
No log	2.0	2	10.9116	0.0089	10.9096	3.3030
No log	3.0	3	9.9812	0.0	9.9792	3.1590
No log	4.0	4	8.9151	0.0	8.9133	2.9855
No log	5.0	5	7.9658	0.0	7.9641	2.8221
No log	6.0	6	7.2662	0.0	7.2646	2.6953
No log	7.0	7	6.6524	0.0	6.6509	2.5789
No log	8.0	8	5.9786	0.0074	5.9773	2.4448
No log	9.0	9	5.3502	0.0175	5.3488	2.3127
No log	10.0	10	4.8500	0.0038	4.8487	2.2020
No log	11.0	11	4.4072	0.0038	4.4059	2.0990
No log	12.0	12	3.9620	0.0038	3.9609	1.9902
No log	13.0	13	3.4977	0.0	3.4966	1.8699
No log	14.0	14	3.0668	0.0	3.0659	1.7510
No log	15.0	15	2.7716	0.0088	2.7708	1.6646
No log	16.0	16	2.3741	0.1043	2.3732	1.5405
No log	17.0	17	2.1112	0.0653	2.1104	1.4527
No log	18.0	18	2.0057	0.0674	2.0050	1.4160
No log	19.0	19	1.7212	0.0503	1.7205	1.3117
No log	20.0	20	1.5399	0.0401	1.5392	1.2407
No log	21.0	21	1.3918	0.0401	1.3912	1.1795
No log	22.0	22	1.2436	0.0401	1.2431	1.1150
No log	23.0	23	1.2559	0.0401	1.2554	1.1204
No log	24.0	24	1.2059	0.0401	1.2055	1.0980
No log	25.0	25	1.0531	0.0401	1.0527	1.0260
No log	26.0	26	0.9098	0.1711	0.9095	0.9537
No log	27.0	27	0.8500	0.3560	0.8497	0.9218
No log	28.0	28	0.8171	0.3532	0.8169	0.9038
No log	29.0	29	0.9297	0.2418	0.9295	0.9641
No log	30.0	30	0.9443	0.2654	0.9441	0.9717
No log	31.0	31	0.8533	0.3541	0.8532	0.9237
No log	32.0	32	0.6970	0.4720	0.6970	0.8349
No log	33.0	33	0.6480	0.4989	0.6480	0.8050
No log	34.0	34	0.7083	0.4641	0.7083	0.8416
No log	35.0	35	0.9638	0.4048	0.9638	0.9817
No log	36.0	36	1.0920	0.3856	1.0920	1.0450
No log	37.0	37	1.0088	0.4161	1.0089	1.0044
No log	38.0	38	0.7970	0.4902	0.7970	0.8928
No log	39.0	39	0.7138	0.4890	0.7139	0.8449
No log	40.0	40	0.7563	0.4872	0.7563	0.8697
No log	41.0	41	0.9296	0.4305	0.9295	0.9641
No log	42.0	42	0.9446	0.4230	0.9445	0.9719
No log	43.0	43	0.8340	0.4742	0.8340	0.9132
No log	44.0	44	0.6967	0.4864	0.6967	0.8347
No log	45.0	45	0.7066	0.4795	0.7067	0.8407
No log	46.0	46	0.8246	0.4477	0.8246	0.9081
No log	47.0	47	1.0732	0.3567	1.0730	1.0359
No log	48.0	48	1.1076	0.3264	1.1073	1.0523
No log	49.0	49	0.9517	0.3995	0.9515	0.9754
No log	50.0	50	0.7501	0.4605	0.7501	0.8661
No log	51.0	51	0.6413	0.4694	0.6414	0.8009
No log	52.0	52	0.6218	0.4825	0.6219	0.7886
No log	53.0	53	0.6378	0.4721	0.6378	0.7986
No log	54.0	54	0.7249	0.4394	0.7247	0.8513
No log	55.0	55	0.8702	0.4127	0.8699	0.9327
No log	56.0	56	0.9393	0.3973	0.9389	0.9690
No log	57.0	57	0.8954	0.4091	0.8951	0.9461
No log	58.0	58	0.7855	0.4477	0.7853	0.8862
No log	59.0	59	0.6767	0.4712	0.6767	0.8226
No log	60.0	60	0.6601	0.4784	0.6601	0.8124
No log	61.0	61	0.6932	0.4812	0.6932	0.8326
No log	62.0	62	0.7901	0.4767	0.7900	0.8888
No log	63.0	63	0.9093	0.4349	0.9092	0.9535

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo100_k1_k1_fold3

BERT_V8_sp10_lw40_ex50_lo100_k1_k1_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo100_k1_k1_fold3