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	2	12.2869	-0.0027	12.2869	3.5053
No log	2.0	4	7.5577	0.0054	7.5577	2.7491
No log	3.0	6	6.7752	0.0054	6.7752	2.6029
No log	4.0	8	5.9555	0.0180	5.9555	2.4404
No log	5.0	10	5.1251	0.0115	5.1251	2.2639
No log	6.0	12	4.4230	0.0115	4.4230	2.1031
No log	7.0	14	3.7911	0.0115	3.7911	1.9471
No log	8.0	16	3.4785	0.0115	3.4785	1.8651
No log	9.0	18	3.4839	0.0077	3.4839	1.8665
No log	10.0	20	3.1118	0.0077	3.1118	1.7640
No log	11.0	22	2.6168	-0.0187	2.6168	1.6177
No log	12.0	24	2.2278	0.0370	2.2278	1.4926
No log	13.0	26	1.9504	0.0520	1.9504	1.3966
No log	14.0	28	1.7885	0.0644	1.7885	1.3374
No log	15.0	30	1.5474	0.0520	1.5474	1.2439
No log	16.0	32	1.5242	0.0419	1.5242	1.2346
No log	17.0	34	1.3806	0.0419	1.3806	1.1750
No log	18.0	36	1.1813	0.0520	1.1813	1.0869
No log	19.0	38	1.0047	0.0715	1.0047	1.0024
No log	20.0	40	0.9528	0.0810	0.9528	0.9761
No log	21.0	42	0.9973	0.0955	0.9973	0.9987
No log	22.0	44	1.1116	0.1212	1.1116	1.0543
No log	23.0	46	0.9125	0.1326	0.9125	0.9553
No log	24.0	48	0.7502	0.4506	0.7502	0.8661
No log	25.0	50	0.7303	0.4542	0.7303	0.8546
No log	26.0	52	0.7485	0.3733	0.7485	0.8651
No log	27.0	54	0.7343	0.3781	0.7343	0.8569
No log	28.0	56	0.6959	0.4967	0.6959	0.8342
No log	29.0	58	0.9120	0.4242	0.9120	0.9550
No log	30.0	60	1.0410	0.3725	1.0410	1.0203
No log	31.0	62	0.6171	0.5656	0.6171	0.7855
No log	32.0	64	0.5599	0.4028	0.5599	0.7483
No log	33.0	66	0.6160	0.3665	0.6160	0.7849
No log	34.0	68	0.5938	0.3881	0.5938	0.7706
No log	35.0	70	0.5340	0.4052	0.5340	0.7308
No log	36.0	72	0.5144	0.5586	0.5144	0.7172
No log	37.0	74	0.9795	0.3882	0.9795	0.9897
No log	38.0	76	1.6837	0.2816	1.6837	1.2976
No log	39.0	78	1.6893	0.2796	1.6893	1.2997
No log	40.0	80	0.9011	0.4312	0.9011	0.9493
No log	41.0	82	0.5552	0.4265	0.5552	0.7451
No log	42.0	84	0.6641	0.3460	0.6641	0.8149
No log	43.0	86	0.6112	0.3645	0.6112	0.7818
No log	44.0	88	0.6717	0.4437	0.6717	0.8196
No log	45.0	90	0.7899	0.3516	0.7899	0.8888
No log	46.0	92	0.7230	0.3906	0.7230	0.8503
No log	47.0	94	0.6662	0.4211	0.6662	0.8162
No log	48.0	96	0.6335	0.4159	0.6335	0.7959
No log	49.0	98	0.6219	0.4115	0.6219	0.7886
No log	50.0	100	0.6206	0.4330	0.6206	0.7878
No log	51.0	102	0.6306	0.4231	0.6306	0.7941
No log	52.0	104	0.6502	0.4179	0.6502	0.8064
No log	53.0	106	0.6609	0.4112	0.6609	0.8130
No log	54.0	108	0.6997	0.3906	0.6997	0.8365
No log	55.0	110	0.6714	0.4215	0.6714	0.8194
No log	56.0	112	0.6789	0.4180	0.6789	0.8240
No log	57.0	114	0.7168	0.3880	0.7168	0.8467
No log	58.0	116	0.7388	0.4060	0.7388	0.8595
No log	59.0	118	0.6757	0.4377	0.6757	0.8220
No log	60.0	120	0.6579	0.4229	0.6579	0.8111
No log	61.0	122	0.6355	0.4478	0.6355	0.7972

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold0

BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k1_k1_fold0