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	4	6.3024	0.0037	6.3024	2.5105
No log	2.0	8	3.5620	0.0079	3.5620	1.8873
No log	3.0	12	2.0508	0.1536	2.0508	1.4320
No log	4.0	16	1.2979	0.0317	1.2979	1.1392
No log	5.0	20	0.8546	0.2823	0.8546	0.9245
No log	6.0	24	0.7859	0.1224	0.7859	0.8865
No log	7.0	28	0.6477	0.3395	0.6477	0.8048
No log	8.0	32	0.5362	0.4758	0.5362	0.7322
No log	9.0	36	0.5344	0.5427	0.5344	0.7310
No log	10.0	40	0.4808	0.5877	0.4808	0.6934
No log	11.0	44	0.4917	0.5712	0.4917	0.7012
No log	12.0	48	0.5406	0.6122	0.5406	0.7352
No log	13.0	52	0.6466	0.5955	0.6466	0.8041
No log	14.0	56	0.6076	0.5972	0.6076	0.7795
No log	15.0	60	0.6484	0.6052	0.6484	0.8052
No log	16.0	64	0.5917	0.6408	0.5917	0.7692
No log	17.0	68	0.5731	0.6411	0.5731	0.7570
No log	18.0	72	0.6566	0.6003	0.6566	0.8103
No log	19.0	76	0.5428	0.6477	0.5428	0.7367
No log	20.0	80	0.5367	0.6486	0.5367	0.7326
No log	21.0	84	0.5180	0.6540	0.5180	0.7197
No log	22.0	88	0.4922	0.6553	0.4922	0.7015
No log	23.0	92	0.4964	0.6330	0.4964	0.7046
No log	24.0	96	0.5144	0.6048	0.5144	0.7173
No log	25.0	100	0.5329	0.6151	0.5329	0.7300
No log	26.0	104	0.5620	0.6236	0.5620	0.7497
No log	27.0	108	0.4955	0.6196	0.4955	0.7039
No log	28.0	112	0.4951	0.6371	0.4951	0.7036
No log	29.0	116	0.5443	0.6551	0.5443	0.7378
No log	30.0	120	0.4922	0.6344	0.4922	0.7016
No log	31.0	124	0.4872	0.6168	0.4872	0.6980
No log	32.0	128	0.4882	0.6394	0.4882	0.6987
No log	33.0	132	0.5221	0.6447	0.5221	0.7225
No log	34.0	136	0.4922	0.6058	0.4922	0.7016
No log	35.0	140	0.4986	0.6170	0.4986	0.7061
No log	36.0	144	0.5215	0.6429	0.5215	0.7221
No log	37.0	148	0.4821	0.6290	0.4821	0.6943
No log	38.0	152	0.4755	0.6192	0.4755	0.6896
No log	39.0	156	0.5016	0.6280	0.5016	0.7082
No log	40.0	160	0.4880	0.6408	0.4880	0.6986
No log	41.0	164	0.4870	0.6117	0.4870	0.6978
No log	42.0	168	0.4937	0.6103	0.4937	0.7026
No log	43.0	172	0.4899	0.6032	0.4899	0.6999
No log	44.0	176	0.4932	0.5832	0.4932	0.7023
No log	45.0	180	0.5079	0.5963	0.5079	0.7127
No log	46.0	184	0.5088	0.6159	0.5088	0.7133
No log	47.0	188	0.4873	0.6133	0.4873	0.6981
No log	48.0	192	0.4780	0.6120	0.4780	0.6914
No log	49.0	196	0.4867	0.6296	0.4867	0.6976
No log	50.0	200	0.4790	0.6341	0.4790	0.6921
No log	51.0	204	0.4755	0.6296	0.4755	0.6896
No log	52.0	208	0.5010	0.6175	0.5010	0.7078

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold4

BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex200_lo50_k10_k10_fold4