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	4	9.9995	0.0018	9.9979	3.1619
No log	2.0	8	6.1966	0.0274	6.1953	2.4890
No log	3.0	12	3.6070	0.0038	3.6061	1.8990
No log	4.0	16	1.9759	0.0542	1.9753	1.4054
No log	5.0	20	1.2207	0.0102	1.2201	1.1046
No log	6.0	24	0.9989	0.0855	0.9985	0.9992
No log	7.0	28	1.4739	0.0796	1.4736	1.2139
No log	8.0	32	1.2039	0.1649	1.2039	1.0972
No log	9.0	36	1.6348	0.1666	1.6349	1.2786
No log	10.0	40	1.6103	0.1749	1.6106	1.2691
No log	11.0	44	1.2022	0.2839	1.2027	1.0967
No log	12.0	48	2.2001	0.1145	2.2003	1.4833
No log	13.0	52	2.0799	0.1086	2.0800	1.4422
No log	14.0	56	1.0766	0.2484	1.0768	1.0377
No log	15.0	60	1.7081	0.1447	1.7083	1.3070
No log	16.0	64	1.1370	0.2267	1.1375	1.0665
No log	17.0	68	1.9803	0.1015	1.9806	1.4073
No log	18.0	72	1.3995	0.1782	1.4000	1.1832
No log	19.0	76	1.5201	0.1341	1.5205	1.2331
No log	20.0	80	2.0226	0.0799	2.0227	1.4222
No log	21.0	84	1.7743	0.0692	1.7744	1.3321
No log	22.0	88	1.6926	0.1030	1.6928	1.3011
No log	23.0	92	1.5781	0.1200	1.5782	1.2563
No log	24.0	96	1.4590	0.1000	1.4590	1.2079
No log	25.0	100	1.8950	0.0269	1.8948	1.3765
No log	26.0	104	1.3415	0.1406	1.3415	1.1583
No log	27.0	108	1.3980	0.1585	1.3982	1.1825
No log	28.0	112	1.9254	0.1271	1.9256	1.3877
No log	29.0	116	1.3255	0.2072	1.3259	1.1515
No log	30.0	120	1.6156	0.1533	1.6159	1.2712
No log	31.0	124	1.3590	0.1924	1.3592	1.1659
No log	32.0	128	1.6767	0.1223	1.6768	1.2949
No log	33.0	132	1.6145	0.1315	1.6146	1.2707
No log	34.0	136	1.3716	0.1793	1.3717	1.1712
No log	35.0	140	2.0151	0.0929	2.0149	1.4195
No log	36.0	144	1.1872	0.1725	1.1871	1.0896
No log	37.0	148	1.8245	0.0911	1.8243	1.3507
No log	38.0	152	1.1849	0.1865	1.1850	1.0886
No log	39.0	156	2.2430	0.0769	2.2429	1.4976
No log	40.0	160	1.9577	0.0819	1.9577	1.3992
No log	41.0	164	0.9640	0.2376	0.9642	0.9819

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_k5_k5_fold3

BERT_V8_sp20_lw10_ex40_lo00_k5_k5_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_k5_k5_fold3