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 Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	6	7.3087	0.0	7.3090	2.7035
No log	2.0	12	3.7671	0.0039	3.7676	1.9410
No log	3.0	18	1.5718	0.0475	1.5723	1.2539
No log	4.0	24	0.9419	0.0612	0.9422	0.9707
No log	5.0	30	0.9047	0.0268	0.9051	0.9514
No log	6.0	36	0.9220	0.0683	0.9222	0.9603
No log	7.0	42	0.7418	0.4144	0.7419	0.8613
No log	8.0	48	1.0721	-0.0005	1.0723	1.0355
No log	9.0	54	1.2486	0.3404	1.2486	1.1174
No log	10.0	60	0.9860	0.0068	0.9862	0.9931
No log	11.0	66	0.7966	0.3951	0.7966	0.8925
No log	12.0	72	0.7400	0.2987	0.7399	0.8602
No log	13.0	78	0.6812	0.4018	0.6810	0.8252
No log	14.0	84	0.8977	0.2371	0.8973	0.9472
No log	15.0	90	0.9236	0.2477	0.9235	0.9610
No log	16.0	96	1.4848	0.1434	1.4852	1.2187
No log	17.0	102	0.8469	0.2980	0.8468	0.9202
No log	18.0	108	0.8884	0.3172	0.8882	0.9425
No log	19.0	114	1.1677	0.1708	1.1679	1.0807
No log	20.0	120	1.0523	0.1405	1.0522	1.0258
No log	21.0	126	1.1521	0.1611	1.1523	1.0735
No log	22.0	132	1.2604	0.0641	1.2606	1.1228
No log	23.0	138	1.2733	0.1561	1.2736	1.1286
No log	24.0	144	1.0796	0.1395	1.0796	1.0390
No log	25.0	150	1.0176	0.1812	1.0173	1.0086
No log	26.0	156	1.2886	0.1253	1.2886	1.1352
No log	27.0	162	1.5425	0.0871	1.5427	1.2421
No log	28.0	168	1.3259	0.1014	1.3262	1.1516
No log	29.0	174	1.2219	0.0098	1.2221	1.1055
No log	30.0	180	1.3464	0.0796	1.3467	1.1605
No log	31.0	186	1.4010	0.1354	1.4012	1.1837
No log	32.0	192	1.1678	0.2012	1.1680	1.0807
No log	33.0	198	0.9712	0.1695	0.9712	0.9855
No log	34.0	204	1.1300	0.2006	1.1302	1.0631
No log	35.0	210	1.2442	0.0987	1.2443	1.1155
No log	36.0	216	1.4998	0.1333	1.5002	1.2248
No log	37.0	222	1.0294	0.0949	1.0293	1.0146

genki10/BERT_V8_sp10_lw40_ex10_lo00_k10_k10_fold2

BERT_V8_sp10_lw40_ex10_lo00_k10_k10_fold2