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	9.2662	0.0	9.2663	3.0441
No log	2.0	12	6.4528	0.0	6.4530	2.5403
No log	3.0	18	3.4822	0.0	3.4826	1.8662
No log	4.0	24	1.8345	0.0411	1.8350	1.3546
No log	5.0	30	0.9674	0.0	0.9678	0.9838
No log	6.0	36	1.4029	0.0411	1.4033	1.1846
No log	7.0	42	0.7616	0.3931	0.7620	0.8729
No log	8.0	48	0.8519	0.2702	0.8520	0.9231
No log	9.0	54	1.3689	0.2021	1.3684	1.1698
No log	10.0	60	1.0954	0.2958	1.0950	1.0464
No log	11.0	66	0.8170	0.3516	0.8166	0.9037
No log	12.0	72	1.0523	0.3077	1.0521	1.0257
No log	13.0	78	1.2537	0.2589	1.2534	1.1196
No log	14.0	84	1.5138	0.2071	1.5138	1.2304
No log	15.0	90	1.5331	0.2189	1.5332	1.2382
No log	16.0	96	1.5172	0.1534	1.5175	1.2319
No log	17.0	102	1.5461	0.1614	1.5465	1.2436
No log	18.0	108	1.3989	0.2211	1.3990	1.1828
No log	19.0	114	1.4045	0.2181	1.4046	1.1852
No log	20.0	120	1.4860	0.1966	1.4863	1.2191
No log	21.0	126	1.2498	0.2558	1.2500	1.1180
No log	22.0	132	1.2122	0.2783	1.2124	1.1011
No log	23.0	138	1.1347	0.2971	1.1349	1.0653
No log	24.0	144	1.3906	0.2271	1.3909	1.1794
No log	25.0	150	1.3753	0.1992	1.3755	1.1728
No log	26.0	156	1.6000	0.1777	1.6002	1.2650
No log	27.0	162	1.3534	0.2078	1.3537	1.1635
No log	28.0	168	1.2686	0.2321	1.2688	1.1264
No log	29.0	174	1.7333	0.1560	1.7335	1.3166
No log	30.0	180	1.4641	0.1967	1.4644	1.2101
No log	31.0	186	1.4322	0.1999	1.4325	1.1969
No log	32.0	192	1.4286	0.2053	1.4290	1.1954
No log	33.0	198	1.2438	0.2221	1.2441	1.1154
No log	34.0	204	1.5286	0.1912	1.5288	1.2365
No log	35.0	210	1.5340	0.1691	1.5343	1.2387
No log	36.0	216	1.4810	0.1910	1.4812	1.2170
No log	37.0	222	1.6453	0.1628	1.6454	1.2827

genki10/BERT_V8_sp20_lw10_ex40_lo00_k10_k10_fold2

BERT_V8_sp20_lw10_ex40_lo00_k10_k10_fold2