learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use 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	5	6.5055	0.0107	6.5056	2.5506
No log	2.0	10	3.4209	0.0	3.4212	1.8496
No log	3.0	15	1.8030	0.0551	1.8034	1.3429
No log	4.0	20	1.0677	0.0107	1.0682	1.0335
No log	5.0	25	0.8662	0.1192	0.8665	0.9309
No log	6.0	30	0.7529	0.3863	0.7531	0.8678
No log	7.0	35	1.2292	0.1906	1.2293	1.1087
No log	8.0	40	0.5762	0.4901	0.5760	0.7589
No log	9.0	45	0.6416	0.4656	0.6411	0.8007
No log	10.0	50	0.8365	0.3648	0.8357	0.9142
No log	11.0	55	0.6277	0.4454	0.6268	0.7917
No log	12.0	60	0.8422	0.3773	0.8415	0.9174
No log	13.0	65	1.7173	0.1680	1.7169	1.3103
No log	14.0	70	0.6944	0.4734	0.6933	0.8327
No log	15.0	75	1.3719	0.1940	1.3714	1.1711
No log	16.0	80	0.8437	0.3862	0.8428	0.9181
No log	17.0	85	0.8697	0.3938	0.8687	0.9320
No log	18.0	90	1.2818	0.2230	1.2812	1.1319
No log	19.0	95	1.0335	0.2848	1.0328	1.0163
No log	20.0	100	0.8214	0.3458	0.8206	0.9059
No log	21.0	105	1.0635	0.2570	1.0627	1.0309
No log	22.0	110	1.0050	0.3041	1.0042	1.0021
No log	23.0	115	0.8789	0.3435	0.8780	0.9370
No log	24.0	120	0.8644	0.3598	0.8635	0.9293
No log	25.0	125	1.2001	0.2235	1.1995	1.0952
No log	26.0	130	1.0217	0.2454	1.0210	1.0104
No log	27.0	135	0.9550	0.2711	0.9542	0.9768
No log	28.0	140	1.2965	0.2222	1.2959	1.1384
No log	29.0	145	0.7689	0.4475	0.7681	0.8764
No log	30.0	150	1.3905	0.2486	1.3900	1.1790
No log	31.0	155	0.8820	0.3399	0.8813	0.9388
No log	32.0	160	0.8712	0.2966	0.8704	0.9330
No log	33.0	165	1.0478	0.2599	1.0473	1.0234
No log	34.0	170	1.0520	0.2868	1.0514	1.0254
No log	35.0	175	1.0198	0.2640	1.0193	1.0096
No log	36.0	180	1.0310	0.2773	1.0304	1.0151
No log	37.0	185	1.1293	0.2332	1.1287	1.0624
No log	38.0	190	1.0372	0.2378	1.0366	1.0182

genki10/BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold2

BERT_V8_sp20_lw10_ex40_lo00_k7_k7_fold2