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	8.1921	0.0018	8.1921	2.8622
No log	2.0	12	3.4279	0.0079	3.4279	1.8514
No log	3.0	18	1.2493	0.0213	1.2493	1.1177
No log	4.0	24	0.9018	0.1336	0.9018	0.9496
No log	5.0	30	1.0926	0.0584	1.0926	1.0453
No log	6.0	36	0.6773	0.4311	0.6773	0.8230
No log	7.0	42	0.6544	0.4566	0.6544	0.8090
No log	8.0	48	0.5969	0.4834	0.5969	0.7726
No log	9.0	54	0.6179	0.4677	0.6179	0.7860
No log	10.0	60	0.7693	0.4247	0.7693	0.8771
No log	11.0	66	0.6403	0.4897	0.6403	0.8002
No log	12.0	72	0.8233	0.4108	0.8233	0.9074
No log	13.0	78	1.0626	0.2972	1.0626	1.0308
No log	14.0	84	0.7579	0.4488	0.7579	0.8706
No log	15.0	90	1.1398	0.3050	1.1398	1.0676
No log	16.0	96	1.2616	0.2801	1.2616	1.1232
No log	17.0	102	1.1871	0.2695	1.1871	1.0895
No log	18.0	108	1.2002	0.2743	1.2002	1.0955
No log	19.0	114	1.2169	0.2885	1.2169	1.1031
No log	20.0	120	1.3211	0.2426	1.3211	1.1494
No log	21.0	126	1.1248	0.3163	1.1248	1.0606
No log	22.0	132	0.8746	0.3846	0.8746	0.9352
No log	23.0	138	0.8958	0.3562	0.8958	0.9465
No log	24.0	144	1.0325	0.3197	1.0325	1.0161
No log	25.0	150	1.2205	0.2835	1.2205	1.1047
No log	26.0	156	1.1325	0.3192	1.1325	1.0642
No log	27.0	162	1.5293	0.2601	1.5293	1.2366
No log	28.0	168	0.9647	0.3493	0.9647	0.9822
No log	29.0	174	1.3043	0.2933	1.3043	1.1421
No log	30.0	180	1.1657	0.3165	1.1657	1.0797
No log	31.0	186	1.1882	0.3068	1.1882	1.0900
No log	32.0	192	1.1761	0.3122	1.1761	1.0845
No log	33.0	198	1.2577	0.2877	1.2577	1.1215
No log	34.0	204	0.7544	0.4231	0.7544	0.8686
No log	35.0	210	0.8278	0.4020	0.8278	0.9098
No log	36.0	216	1.4054	0.2485	1.4054	1.1855
No log	37.0	222	1.1273	0.3060	1.1273	1.0617
No log	38.0	228	1.2427	0.2770	1.2427	1.1148
No log	39.0	234	1.1121	0.2954	1.1121	1.0546
No log	40.0	240	1.3846	0.2610	1.3846	1.1767
No log	41.0	246	1.0286	0.3252	1.0286	1.0142

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_fold4

BERT_V8_sp20_lw10_ex30_lo00_k10_k10_fold4

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_fold4