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	7.8091	0.0	7.8091	2.7945
No log	2.0	8	6.0230	0.0120	6.0230	2.4542
No log	3.0	12	4.3549	0.0039	4.3549	2.0868
No log	4.0	16	2.8512	0.0	2.8512	1.6885
No log	5.0	20	1.6590	0.0316	1.6590	1.2880
No log	6.0	24	1.1273	0.0316	1.1273	1.0617
No log	7.0	28	0.8484	0.3143	0.8484	0.9211
No log	8.0	32	1.5271	0.1172	1.5271	1.2358
No log	9.0	36	0.6306	0.4221	0.6306	0.7941
No log	10.0	40	1.5117	0.1255	1.5117	1.2295
No log	11.0	44	0.6201	0.4774	0.6201	0.7875
No log	12.0	48	1.0680	0.2551	1.0680	1.0335
No log	13.0	52	0.6420	0.3532	0.6420	0.8013
No log	14.0	56	0.8089	0.3359	0.8089	0.8994
No log	15.0	60	0.6309	0.3853	0.6309	0.7943
No log	16.0	64	0.7447	0.4060	0.7447	0.8630
No log	17.0	68	0.6941	0.4198	0.6941	0.8331
No log	18.0	72	0.9106	0.3810	0.9106	0.9543
No log	19.0	76	0.7007	0.4314	0.7007	0.8371
No log	20.0	80	0.7576	0.4493	0.7576	0.8704
No log	21.0	84	0.8637	0.3955	0.8637	0.9294
No log	22.0	88	0.9138	0.3958	0.9138	0.9559
No log	23.0	92	0.6366	0.4683	0.6366	0.7979
No log	24.0	96	1.3913	0.2368	1.3913	1.1795
No log	25.0	100	0.7003	0.4635	0.7003	0.8368
No log	26.0	104	1.1371	0.2969	1.1371	1.0663
No log	27.0	108	0.7364	0.4291	0.7364	0.8581
No log	28.0	112	0.8221	0.3506	0.8221	0.9067
No log	29.0	116	0.9009	0.3618	0.9009	0.9492
No log	30.0	120	0.8307	0.3999	0.8307	0.9114
No log	31.0	124	1.0178	0.2703	1.0178	1.0088
No log	32.0	128	0.8401	0.3575	0.8401	0.9166
No log	33.0	132	0.8488	0.3357	0.8488	0.9213
No log	34.0	136	0.7870	0.3665	0.7870	0.8871
No log	35.0	140	0.7992	0.3487	0.7992	0.8940
No log	36.0	144	0.8077	0.3753	0.8077	0.8987
No log	37.0	148	0.7938	0.4081	0.7938	0.8909
No log	38.0	152	0.7610	0.3973	0.7610	0.8724
No log	39.0	156	0.8621	0.3480	0.8621	0.9285
No log	40.0	160	0.7485	0.4049	0.7485	0.8652
No log	41.0	164	0.7117	0.4227	0.7117	0.8436

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_lo00_k5_k5_fold0

BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo00_k5_k5_fold0