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	6	6.5736	0.0	6.5736	2.5639
No log	2.0	12	3.9041	0.0039	3.9041	1.9759
No log	3.0	18	1.7330	0.0316	1.7330	1.3164
No log	4.0	24	0.9136	0.0316	0.9136	0.9558
No log	5.0	30	0.7790	0.2771	0.7790	0.8826
No log	6.0	36	0.8344	0.2904	0.8344	0.9134
No log	7.0	42	0.6693	0.3340	0.6693	0.8181
No log	8.0	48	0.6759	0.2887	0.6759	0.8221
No log	9.0	54	0.6126	0.3542	0.6126	0.7827
No log	10.0	60	0.6793	0.3193	0.6793	0.8242
No log	11.0	66	0.7651	0.3253	0.7651	0.8747
No log	12.0	72	0.6896	0.4700	0.6896	0.8304
No log	13.0	78	0.7273	0.4175	0.7273	0.8528
No log	14.0	84	0.6511	0.4605	0.6511	0.8069
No log	15.0	90	0.7819	0.3593	0.7819	0.8843
No log	16.0	96	0.8854	0.3024	0.8854	0.9410
No log	17.0	102	0.8160	0.3395	0.8160	0.9033
No log	18.0	108	0.7487	0.3713	0.7487	0.8652
No log	19.0	114	0.8344	0.3355	0.8344	0.9135
No log	20.0	120	0.8314	0.2771	0.8314	0.9118
No log	21.0	126	0.7480	0.3727	0.7480	0.8649
No log	22.0	132	0.9940	0.2074	0.9940	0.9970
No log	23.0	138	0.7924	0.3604	0.7924	0.8902
No log	24.0	144	0.9166	0.2703	0.9166	0.9574
No log	25.0	150	0.7149	0.3915	0.7149	0.8455
No log	26.0	156	0.9768	0.2164	0.9768	0.9884
No log	27.0	162	0.7593	0.3932	0.7593	0.8714
No log	28.0	168	0.9222	0.2397	0.9222	0.9603
No log	29.0	174	0.9315	0.2310	0.9315	0.9652
No log	30.0	180	0.8535	0.2989	0.8535	0.9238
No log	31.0	186	0.7939	0.3224	0.7939	0.8910
No log	32.0	192	0.9193	0.2771	0.9193	0.9588
No log	33.0	198	0.7183	0.3959	0.7183	0.8476
No log	34.0	204	0.8705	0.2184	0.8705	0.9330
No log	35.0	210	0.9986	0.1259	0.9986	0.9993
No log	36.0	216	0.7959	0.2699	0.7959	0.8921
No log	37.0	222	0.6716	0.4293	0.6716	0.8195
No log	38.0	228	0.7933	0.3024	0.7933	0.8906
No log	39.0	234	0.8228	0.2582	0.8228	0.9071
No log	40.0	240	0.8497	0.2589	0.8497	0.9218
No log	41.0	246	0.7943	0.3045	0.7943	0.8912
No log	42.0	252	0.8576	0.2720	0.8576	0.9261

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_lo100_k10_k10_fold0

BERT_V8_sp10_lw40_ex100_lo100_k10_k10_fold0

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo100_k10_k10_fold0