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	6.8081	0.0	6.8084	2.6093
No log	2.0	8	4.0019	0.0078	4.0021	2.0005
No log	3.0	12	2.2719	0.1592	2.2724	1.5074
No log	4.0	16	1.3855	0.0213	1.3860	1.1773
No log	5.0	20	0.9511	0.0107	0.9516	0.9755
No log	6.0	24	0.7528	0.1646	0.7532	0.8679
No log	7.0	28	0.6645	0.2247	0.6647	0.8153
No log	8.0	32	0.5956	0.4652	0.5958	0.7719
No log	9.0	36	0.4893	0.5714	0.4894	0.6995
No log	10.0	40	0.5534	0.5663	0.5533	0.7438
No log	11.0	44	0.5757	0.5584	0.5757	0.7588
No log	12.0	48	0.5182	0.6041	0.5183	0.7200
No log	13.0	52	0.5284	0.5570	0.5285	0.7270
No log	14.0	56	0.6075	0.5551	0.6075	0.7794
No log	15.0	60	0.4919	0.6158	0.4919	0.7013
No log	16.0	64	0.6514	0.5142	0.6514	0.8071
No log	17.0	68	0.6447	0.5323	0.6446	0.8029
No log	18.0	72	0.5594	0.4855	0.5594	0.7479
No log	19.0	76	0.5366	0.5597	0.5366	0.7325
No log	20.0	80	0.5347	0.5430	0.5347	0.7312
No log	21.0	84	0.4938	0.5838	0.4937	0.7026
No log	22.0	88	0.4997	0.5830	0.4997	0.7069
No log	23.0	92	0.5346	0.5714	0.5347	0.7312
No log	24.0	96	0.5546	0.5518	0.5547	0.7448
No log	25.0	100	0.4823	0.5577	0.4823	0.6945
No log	26.0	104	0.4866	0.5616	0.4866	0.6975
No log	27.0	108	0.5122	0.5607	0.5121	0.7156
No log	28.0	112	0.5072	0.5429	0.5072	0.7122
No log	29.0	116	0.4983	0.5567	0.4983	0.7059
No log	30.0	120	0.5179	0.5546	0.5179	0.7196
No log	31.0	124	0.5396	0.5146	0.5397	0.7346
No log	32.0	128	0.5586	0.5036	0.5586	0.7474
No log	33.0	132	0.5460	0.4922	0.5460	0.7389
No log	34.0	136	0.4988	0.5767	0.4988	0.7062
No log	35.0	140	0.6006	0.4979	0.6006	0.7750
No log	36.0	144	0.4829	0.5729	0.4828	0.6949
No log	37.0	148	0.5222	0.5398	0.5222	0.7226
No log	38.0	152	0.5017	0.5524	0.5017	0.7083
No log	39.0	156	0.5885	0.5042	0.5885	0.7671
No log	40.0	160	0.4880	0.5458	0.4879	0.6985
No log	41.0	164	0.6013	0.5005	0.6013	0.7754
No log	42.0	168	0.5036	0.5548	0.5035	0.7096
No log	43.0	172	0.5070	0.5362	0.5070	0.7120
No log	44.0	176	0.5445	0.4888	0.5445	0.7379
No log	45.0	180	0.5067	0.5428	0.5067	0.7118

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

genki10/BERT_V8_sp10_lw20_ex100_lo50_k10_k10_fold2

BERT_V8_sp10_lw20_ex100_lo50_k10_k10_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_k10_k10_fold2