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	2	9.8585	0.0018	9.8586	3.1398
No log	2.0	4	8.4117	0.0	8.4119	2.9003
No log	3.0	6	6.6849	0.0	6.6852	2.5856
No log	4.0	8	5.5352	0.0356	5.5356	2.3528
No log	5.0	10	4.1738	0.0039	4.1743	2.0431
No log	6.0	12	3.3873	0.0	3.3879	1.8406
No log	7.0	14	2.7102	0.0	2.7107	1.6464
No log	8.0	16	2.1644	0.1202	2.1649	1.4714
No log	9.0	18	1.6858	0.0268	1.6863	1.2986
No log	10.0	20	1.3099	0.0107	1.3104	1.1447
No log	11.0	22	1.0419	0.0	1.0424	1.0210
No log	12.0	24	0.8704	0.2452	0.8709	0.9332
No log	13.0	26	0.7725	0.1884	0.7730	0.8792
No log	14.0	28	0.6886	0.1839	0.6888	0.8300
No log	15.0	30	0.6229	0.4162	0.6229	0.7893
No log	16.0	32	0.5715	0.3577	0.5712	0.7558
No log	17.0	34	1.0522	0.3265	1.0525	1.0259
No log	18.0	36	0.9232	0.3791	0.9235	0.9610
No log	19.0	38	0.4859	0.5786	0.4856	0.6968
No log	20.0	40	0.4769	0.5305	0.4770	0.6906
No log	21.0	42	0.6261	0.4548	0.6264	0.7915
No log	22.0	44	0.4992	0.4984	0.4994	0.7067
No log	23.0	46	0.6242	0.5029	0.6242	0.7901
No log	24.0	48	0.4974	0.5014	0.4976	0.7054
No log	25.0	50	0.5870	0.4831	0.5873	0.7664
No log	26.0	52	0.5131	0.5188	0.5133	0.7164
No log	27.0	54	0.5510	0.5537	0.5509	0.7422
No log	28.0	56	0.4880	0.5865	0.4881	0.6987
No log	29.0	58	0.5347	0.5546	0.5349	0.7314
No log	30.0	60	0.4829	0.5667	0.4830	0.6949
No log	31.0	62	0.4963	0.5590	0.4964	0.7046
No log	32.0	64	0.6428	0.4765	0.6432	0.8020
No log	33.0	66	0.6425	0.4737	0.6429	0.8018
No log	34.0	68	0.6503	0.5538	0.6501	0.8063
No log	35.0	70	0.8260	0.4784	0.8257	0.9087
No log	36.0	72	0.5256	0.5330	0.5257	0.7250
No log	37.0	74	1.0742	0.2745	1.0746	1.0366
No log	38.0	76	0.9463	0.3081	0.9467	0.9730
No log	39.0	78	0.5241	0.5320	0.5241	0.7239
No log	40.0	80	0.5550	0.5636	0.5549	0.7449
No log	41.0	82	0.5498	0.5017	0.5499	0.7415
No log	42.0	84	0.5711	0.4899	0.5712	0.7558
No log	43.0	86	0.5030	0.5526	0.5030	0.7092
No log	44.0	88	0.5293	0.5643	0.5294	0.7276
No log	45.0	90	0.5889	0.5177	0.5891	0.7675
No log	46.0	92	0.4991	0.5641	0.4991	0.7065
No log	47.0	94	0.5045	0.5407	0.5045	0.7103
No log	48.0	96	0.5624	0.4909	0.5625	0.7500
No log	49.0	98	0.5159	0.5248	0.5160	0.7183
No log	50.0	100	0.4973	0.5506	0.4973	0.7052
No log	51.0	102	0.5520	0.5389	0.5521	0.7430
No log	52.0	104	0.6834	0.4572	0.6836	0.8268
No log	53.0	106	0.5651	0.5267	0.5653	0.7518
No log	54.0	108	0.5068	0.5498	0.5068	0.7119
No log	55.0	110	0.5132	0.5295	0.5133	0.7165
No log	56.0	112	0.6798	0.4537	0.6800	0.8246
No log	57.0	114	0.7507	0.4459	0.7509	0.8666
No log	58.0	116	0.6014	0.4860	0.6016	0.7756

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_lo50_k3_k3_fold2

BERT_V8_sp10_lw20_ex100_lo50_k3_k3_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw20_ex100_lo50_k3_k3_fold2