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	4	9.8257	0.0018	9.8240	3.1343
No log	2.0	8	5.9230	0.0432	5.9217	2.4334
No log	3.0	12	3.5939	0.0038	3.5929	1.8955
No log	4.0	16	1.8570	0.0528	1.8562	1.3624
No log	5.0	20	1.1050	0.0102	1.1045	1.0509
No log	6.0	24	0.8647	0.1192	0.8644	0.9297
No log	7.0	28	0.8063	0.1489	0.8059	0.8977
No log	8.0	32	0.9996	0.1921	0.9995	0.9997
No log	9.0	36	0.7886	0.3961	0.7887	0.8881
No log	10.0	40	1.2674	0.3456	1.2678	1.1259
No log	11.0	44	1.2061	0.3403	1.2066	1.0984
No log	12.0	48	0.7582	0.4512	0.7588	0.8711
No log	13.0	52	0.8385	0.4216	0.8391	0.9160
No log	14.0	56	0.7615	0.4588	0.7618	0.8728
No log	15.0	60	0.7612	0.4532	0.7615	0.8727
No log	16.0	64	0.9011	0.4228	0.9016	0.9495
No log	17.0	68	0.9822	0.3690	0.9828	0.9913
No log	18.0	72	1.1433	0.3141	1.1439	1.0695
No log	19.0	76	1.3613	0.2542	1.3618	1.1670
No log	20.0	80	0.9052	0.3826	0.9056	0.9516
No log	21.0	84	1.4135	0.2432	1.4139	1.1891
No log	22.0	88	1.0541	0.3264	1.0545	1.0269
No log	23.0	92	1.0845	0.3232	1.0850	1.0416
No log	24.0	96	0.9120	0.4106	0.9125	0.9552
No log	25.0	100	1.2307	0.2766	1.2311	1.1096
No log	26.0	104	1.2194	0.2664	1.2200	1.1045
No log	27.0	108	1.2270	0.2441	1.2275	1.1079
No log	28.0	112	1.0726	0.3140	1.0731	1.0359
No log	29.0	116	1.1589	0.2819	1.1594	1.0767
No log	30.0	120	0.9678	0.3024	0.9682	0.9840
No log	31.0	124	1.1879	0.2328	1.1883	1.0901
No log	32.0	128	0.9852	0.3352	0.9857	0.9928
No log	33.0	132	0.9971	0.3444	0.9976	0.9988
No log	34.0	136	1.2483	0.2408	1.2487	1.1175
No log	35.0	140	0.8800	0.3717	0.8804	0.9383
No log	36.0	144	1.4634	0.2153	1.4638	1.2099
No log	37.0	148	0.8824	0.3696	0.8827	0.9395
No log	38.0	152	1.1537	0.2608	1.1540	1.0743
No log	39.0	156	1.1222	0.2823	1.1227	1.0596
No log	40.0	160	0.9534	0.3604	0.9539	0.9767
No log	41.0	164	1.0497	0.2957	1.0501	1.0247
No log	42.0	168	1.0688	0.2901	1.0691	1.0340
No log	43.0	172	1.0982	0.2784	1.0986	1.0481
No log	44.0	176	1.0593	0.3015	1.0597	1.0294

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_k7_k7_fold3

BERT_V8_sp10_lw40_ex100_lo50_k7_k7_fold3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex100_lo50_k7_k7_fold3