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	4.0876	0.0079	4.0857	2.0213
No log	2.0	12	1.9713	0.0379	1.9696	1.4034
No log	3.0	18	1.0622	0.0	1.0608	1.0300
No log	4.0	24	0.8941	0.1496	0.8928	0.9449
No log	5.0	30	1.2786	0.0816	1.2772	1.1301
No log	6.0	36	0.8487	0.2439	0.8473	0.9205
No log	7.0	42	0.9698	0.1597	0.9684	0.9841
No log	8.0	48	0.9718	0.1925	0.9706	0.9852
No log	9.0	54	0.8566	0.2976	0.8554	0.9249
No log	10.0	60	0.8733	0.3532	0.8720	0.9338
No log	11.0	66	1.0493	0.3527	1.0482	1.0238
No log	12.0	72	1.0377	0.3371	1.0371	1.0184
No log	13.0	78	0.8361	0.3719	0.8351	0.9138
No log	14.0	84	1.0638	0.3465	1.0625	1.0308
No log	15.0	90	0.7725	0.4284	0.7715	0.8783
No log	16.0	96	0.7782	0.3854	0.7770	0.8815
No log	17.0	102	0.7359	0.4495	0.7350	0.8573
No log	18.0	108	0.7242	0.4473	0.7232	0.8504
No log	19.0	114	0.8177	0.4213	0.8168	0.9038
No log	20.0	120	0.8398	0.3884	0.8386	0.9158
No log	21.0	126	0.9788	0.3712	0.9772	0.9885
No log	22.0	132	0.9649	0.3600	0.9635	0.9816
No log	23.0	138	0.8337	0.4278	0.8327	0.9125
No log	24.0	144	0.8146	0.3923	0.8134	0.9019
No log	25.0	150	0.8143	0.3902	0.8132	0.9018
No log	26.0	156	0.9089	0.3584	0.9076	0.9527
No log	27.0	162	0.8781	0.3887	0.8767	0.9363
No log	28.0	168	0.8372	0.4043	0.8358	0.9142
No log	29.0	174	0.9641	0.3539	0.9628	0.9812
No log	30.0	180	0.8950	0.3440	0.8938	0.9454
No log	31.0	186	0.8761	0.3581	0.8748	0.9353
No log	32.0	192	0.9157	0.3640	0.9142	0.9562
No log	33.0	198	0.8860	0.3906	0.8846	0.9405
No log	34.0	204	0.9127	0.3365	0.9112	0.9546
No log	35.0	210	0.8505	0.3750	0.8490	0.9214
No log	36.0	216	0.9328	0.3760	0.9314	0.9651
No log	37.0	222	0.8405	0.4281	0.8392	0.9161
No log	38.0	228	0.8035	0.3927	0.8022	0.8957
No log	39.0	234	0.8349	0.3847	0.8335	0.9130
No log	40.0	240	0.9140	0.3585	0.9125	0.9552
No log	41.0	246	0.8685	0.3844	0.8671	0.9312
No log	42.0	252	0.8449	0.3672	0.8435	0.9184
No log	43.0	258	0.8958	0.3471	0.8943	0.9457
No log	44.0	264	0.7920	0.3966	0.7907	0.8892
No log	45.0	270	0.9027	0.3430	0.9014	0.9494
No log	46.0	276	0.8389	0.3804	0.8376	0.9152
No log	47.0	282	0.8877	0.3699	0.8862	0.9414

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp20_lw10_ex30_lo00_k10_k10_fold1

BERT_V8_sp20_lw10_ex30_lo00_k10_k10_fold1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp20_lw10_ex30_lo00_k10_k10_fold1