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	7.7974	0.0	7.7955	2.7920
No log	2.0	8	4.5758	0.0038	4.5746	2.1388
No log	3.0	12	3.0489	0.0	3.0480	1.7459
No log	4.0	16	1.8396	0.0427	1.8389	1.3561
No log	5.0	20	1.1717	0.0	1.1712	1.0822
No log	6.0	24	0.8397	0.2856	0.8394	0.9162
No log	7.0	28	0.8513	0.2785	0.8510	0.9225
No log	8.0	32	0.6803	0.3878	0.6801	0.8247
No log	9.0	36	0.6071	0.4358	0.6069	0.7791
No log	10.0	40	0.6048	0.3789	0.6049	0.7777
No log	11.0	44	0.5504	0.5545	0.5506	0.7420
No log	12.0	48	0.5272	0.6000	0.5273	0.7262
No log	13.0	52	0.5587	0.5626	0.5587	0.7475
No log	14.0	56	0.7921	0.4330	0.7923	0.8901
No log	15.0	60	0.6017	0.5731	0.6017	0.7757
No log	16.0	64	1.0999	0.3449	1.1001	1.0489
No log	17.0	68	0.9318	0.3686	0.9320	0.9654
No log	18.0	72	0.5990	0.5928	0.5990	0.7739
No log	19.0	76	1.0535	0.3471	1.0537	1.0265
No log	20.0	80	0.5768	0.5860	0.5767	0.7594
No log	21.0	84	0.6482	0.5432	0.6483	0.8052
No log	22.0	88	0.6528	0.4941	0.6529	0.8080
No log	23.0	92	0.5918	0.5621	0.5918	0.7693
No log	24.0	96	0.9818	0.3700	0.9819	0.9909
No log	25.0	100	0.5727	0.5855	0.5727	0.7568
No log	26.0	104	0.7964	0.4513	0.7965	0.8925
No log	27.0	108	0.8290	0.4364	0.8291	0.9106
No log	28.0	112	0.5663	0.5867	0.5662	0.7525
No log	29.0	116	0.8902	0.4106	0.8903	0.9436
No log	30.0	120	0.8903	0.4082	0.8904	0.9436
No log	31.0	124	0.5659	0.5720	0.5658	0.7522
No log	32.0	128	0.6465	0.4917	0.6466	0.8041
No log	33.0	132	0.5900	0.5376	0.5900	0.7681
No log	34.0	136	0.7099	0.4429	0.7099	0.8425
No log	35.0	140	0.5662	0.5924	0.5661	0.7524
No log	36.0	144	0.7743	0.4482	0.7743	0.8799
No log	37.0	148	0.6808	0.4771	0.6808	0.8251
No log	38.0	152	0.7428	0.4430	0.7428	0.8619
No log	39.0	156	0.6918	0.4524	0.6918	0.8318
No log	40.0	160	0.6328	0.5183	0.6328	0.7955
No log	41.0	164	0.6694	0.4962	0.6694	0.8182
No log	42.0	168	0.6794	0.5025	0.6795	0.8243

Framework versions

Transformers 4.47.0
Pytorch 2.5.1+cu121
Datasets 3.3.1
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo100_k7_k7_fold3

BERT_V8_sp10_lw20_ex100_lo100_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo100_k7_k7_fold3