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	9.4678	0.0018	9.4680	3.0770
No log	2.0	8	5.6498	0.0125	5.6504	2.3771
No log	3.0	12	3.2526	0.0078	3.2532	1.8037
No log	4.0	16	1.7447	0.0475	1.7452	1.3210
No log	5.0	20	1.0805	0.0213	1.0809	1.0397
No log	6.0	24	0.7882	0.3093	0.7886	0.8880
No log	7.0	28	0.8520	0.0851	0.8524	0.9233
No log	8.0	32	0.6906	0.4648	0.6909	0.8312
No log	9.0	36	0.6094	0.3077	0.6094	0.7806
No log	10.0	40	0.6223	0.4521	0.6225	0.7890
No log	11.0	44	0.5708	0.5298	0.5709	0.7556
No log	12.0	48	0.7110	0.5292	0.7111	0.8433
No log	13.0	52	0.5535	0.3477	0.5535	0.7440
No log	14.0	56	0.6141	0.5041	0.6143	0.7838
No log	15.0	60	0.5143	0.5387	0.5145	0.7173
No log	16.0	64	0.6078	0.5371	0.6082	0.7799
No log	17.0	68	0.6969	0.3852	0.6974	0.8351
No log	18.0	72	0.6101	0.4599	0.6105	0.7813
No log	19.0	76	0.5598	0.5179	0.5599	0.7483
No log	20.0	80	0.6098	0.4876	0.6099	0.7810
No log	21.0	84	0.6362	0.4621	0.6363	0.7977
No log	22.0	88	0.8321	0.3611	0.8322	0.9123
No log	23.0	92	0.6278	0.4595	0.6279	0.7924
No log	24.0	96	0.6298	0.4990	0.6298	0.7936
No log	25.0	100	0.8940	0.3267	0.8943	0.9457
No log	26.0	104	0.7005	0.4875	0.7005	0.8369
No log	27.0	108	1.0902	0.2586	1.0903	1.0442
No log	28.0	112	0.5957	0.4388	0.5958	0.7719
No log	29.0	116	0.6727	0.4529	0.6728	0.8203
No log	30.0	120	0.6313	0.4587	0.6313	0.7946
No log	31.0	124	0.6512	0.4367	0.6513	0.8070
No log	32.0	128	0.6760	0.4341	0.6761	0.8223
No log	33.0	132	0.6208	0.4486	0.6209	0.7880
No log	34.0	136	0.6420	0.4517	0.6422	0.8014
No log	35.0	140	0.6458	0.4303	0.6459	0.8037
No log	36.0	144	0.6184	0.4480	0.6183	0.7863
No log	37.0	148	0.7081	0.3748	0.7080	0.8414
No log	38.0	152	0.6478	0.4258	0.6477	0.8048
No log	39.0	156	0.7801	0.3871	0.7801	0.8832
No log	40.0	160	0.5784	0.4460	0.5784	0.7605
No log	41.0	164	0.6059	0.5240	0.6059	0.7784
No log	42.0	168	0.6172	0.5090	0.6172	0.7856
No log	43.0	172	0.6226	0.4719	0.6227	0.7891
No log	44.0	176	0.6481	0.4294	0.6481	0.8051
No log	45.0	180	0.7245	0.4066	0.7244	0.8511

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold2

BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

genki10/
BERT_V8_sp10_lw40_ex50_lo50_k7_k7_fold2