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	3	8.6984	0.0018	8.6984	2.9493
No log	2.0	6	5.6922	0.0104	5.6922	2.3858
No log	3.0	9	3.8351	0.0118	3.8351	1.9583
No log	4.0	12	2.5953	0.0040	2.5953	1.6110
No log	5.0	15	1.7944	0.0617	1.7944	1.3395
No log	6.0	18	1.2511	0.0420	1.2511	1.1185
No log	7.0	21	0.9150	0.0420	0.9150	0.9566
No log	8.0	24	0.7553	0.4050	0.7553	0.8691
No log	9.0	27	0.6263	0.4333	0.6263	0.7914
No log	10.0	30	0.5943	0.4579	0.5943	0.7709
No log	11.0	33	0.5692	0.5291	0.5692	0.7545
No log	12.0	36	0.5383	0.5414	0.5383	0.7337
No log	13.0	39	0.5319	0.5146	0.5319	0.7293
No log	14.0	42	0.5244	0.5487	0.5244	0.7241
No log	15.0	45	0.5357	0.6136	0.5357	0.7319
No log	16.0	48	0.5320	0.6583	0.5320	0.7294
No log	17.0	51	0.5133	0.6790	0.5133	0.7164
No log	18.0	54	0.5361	0.6572	0.5361	0.7322
No log	19.0	57	0.5594	0.6511	0.5594	0.7479
No log	20.0	60	0.6633	0.5284	0.6633	0.8145
No log	21.0	63	0.5968	0.5886	0.5968	0.7726
No log	22.0	66	0.5408	0.6104	0.5408	0.7354
No log	23.0	69	0.5244	0.6373	0.5244	0.7242
No log	24.0	72	0.5886	0.5719	0.5886	0.7672
No log	25.0	75	0.5102	0.6283	0.5102	0.7143
No log	26.0	78	0.5610	0.5781	0.5610	0.7490
No log	27.0	81	0.5320	0.6206	0.5320	0.7294
No log	28.0	84	0.5657	0.5989	0.5657	0.7521
No log	29.0	87	0.5526	0.6192	0.5526	0.7434
No log	30.0	90	0.5308	0.6462	0.5308	0.7286
No log	31.0	93	0.5480	0.5937	0.5480	0.7403
No log	32.0	96	0.5132	0.6305	0.5132	0.7164
No log	33.0	99	0.6011	0.5493	0.6011	0.7753
No log	34.0	102	0.5118	0.6210	0.5118	0.7154
No log	35.0	105	0.5118	0.6402	0.5118	0.7154
No log	36.0	108	0.5773	0.5881	0.5773	0.7598
No log	37.0	111	0.5254	0.6540	0.5254	0.7249
No log	38.0	114	0.6434	0.5513	0.6434	0.8021
No log	39.0	117	0.5848	0.5564	0.5848	0.7647
No log	40.0	120	0.5974	0.5980	0.5974	0.7729
No log	41.0	123	0.5570	0.5871	0.5570	0.7463
No log	42.0	126	0.5741	0.5441	0.5741	0.7577
No log	43.0	129	0.5178	0.6114	0.5178	0.7196
No log	44.0	132	0.5235	0.6074	0.5235	0.7236
No log	45.0	135	0.5146	0.6372	0.5146	0.7173
No log	46.0	138	0.5625	0.6121	0.5625	0.7500
No log	47.0	141	0.5443	0.6107	0.5443	0.7378

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold4

BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k5_k5_fold4