learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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	5	8.0795	0.0	8.0782	2.8422
No log	2.0	10	4.1543	0.0076	4.1532	2.0379
No log	3.0	15	2.1086	0.0574	2.1078	1.4518
No log	4.0	20	1.2144	0.0102	1.2138	1.1017
No log	5.0	25	1.3068	0.0	1.3062	1.1429
No log	6.0	30	1.1612	0.0102	1.1606	1.0773
No log	7.0	35	0.8530	0.3163	0.8527	0.9234
No log	8.0	40	1.0081	0.1478	1.0077	1.0038
No log	9.0	45	0.6437	0.4067	0.6439	0.8024
No log	10.0	50	0.5887	0.4448	0.5889	0.7674
No log	11.0	55	0.6298	0.4067	0.6299	0.7936
No log	12.0	60	0.6854	0.4970	0.6855	0.8280
No log	13.0	65	1.1055	0.3809	1.1055	1.0514
No log	14.0	70	0.7802	0.5089	0.7805	0.8834
No log	15.0	75	0.6660	0.5796	0.6664	0.8163
No log	16.0	80	1.7856	0.2276	1.7853	1.3361
No log	17.0	85	0.6413	0.4711	0.6416	0.8010
No log	18.0	90	0.8178	0.3834	0.8178	0.9043
No log	19.0	95	1.0264	0.3944	1.0264	1.0131
No log	20.0	100	1.1700	0.3231	1.1698	1.0816
No log	21.0	105	0.9892	0.3469	0.9890	0.9945
No log	22.0	110	0.8260	0.4051	0.8261	0.9089
No log	23.0	115	0.8117	0.3780	0.8118	0.9010
No log	24.0	120	0.9869	0.3817	0.9869	0.9934
No log	25.0	125	1.0555	0.3651	1.0555	1.0274
No log	26.0	130	0.9419	0.3446	0.9418	0.9705
No log	27.0	135	1.1895	0.3249	1.1895	1.0906
No log	28.0	140	1.1982	0.3048	1.1981	1.0946
No log	29.0	145	1.1740	0.2876	1.1739	1.0835
No log	30.0	150	1.1426	0.3277	1.1426	1.0689
No log	31.0	155	1.2270	0.2932	1.2269	1.1076
No log	32.0	160	0.9806	0.3469	0.9805	0.9902
No log	33.0	165	0.8256	0.3807	0.8256	0.9087
No log	34.0	170	0.9664	0.3639	0.9663	0.9830
No log	35.0	175	1.0637	0.3337	1.0636	1.0313
No log	36.0	180	1.0261	0.3570	1.0260	1.0129
No log	37.0	185	1.0846	0.3320	1.0844	1.0413
No log	38.0	190	1.0067	0.3615	1.0066	1.0033
No log	39.0	195	0.9065	0.3772	0.9064	0.9521
No log	40.0	200	1.0410	0.3581	1.0409	1.0202
No log	41.0	205	0.8100	0.3892	0.8099	0.9000
No log	42.0	210	1.0946	0.3417	1.0944	1.0461
No log	43.0	215	1.0115	0.3459	1.0114	1.0057
No log	44.0	220	1.0301	0.3669	1.0301	1.0149
No log	45.0	225	1.1039	0.3286	1.1037	1.0506

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold3

BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold3