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: 150

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	3	8.0793	0.0	8.0793	2.8424
No log	2.0	6	6.7128	0.0	6.7128	2.5909
No log	3.0	9	5.4780	0.0115	5.4780	2.3405
No log	4.0	12	4.2239	0.0039	4.2239	2.0552
No log	5.0	15	2.9978	0.0	2.9978	1.7314
No log	6.0	18	1.9978	0.0575	1.9978	1.4134
No log	7.0	21	1.4549	0.0316	1.4549	1.2062
No log	8.0	24	1.0867	0.0316	1.0867	1.0424
No log	9.0	27	0.9535	0.0382	0.9535	0.9765
No log	10.0	30	1.1253	0.0909	1.1253	1.0608
No log	11.0	33	1.1128	0.0469	1.1128	1.0549
No log	12.0	36	0.8760	0.3539	0.8760	0.9360
No log	13.0	39	1.9916	0.1814	1.9916	1.4112
No log	14.0	42	0.7502	0.4355	0.7502	0.8662
No log	15.0	45	0.7460	0.3335	0.7460	0.8637
No log	16.0	48	0.7719	0.4046	0.7719	0.8786
No log	17.0	51	1.2176	0.1786	1.2176	1.1034
No log	18.0	54	0.6927	0.4536	0.6927	0.8323
No log	19.0	57	0.8228	0.2267	0.8228	0.9071
No log	20.0	60	0.6722	0.3984	0.6722	0.8199
No log	21.0	63	0.7377	0.4101	0.7377	0.8589
No log	22.0	66	0.6738	0.4147	0.6738	0.8209
No log	23.0	69	0.7149	0.3873	0.7149	0.8455
No log	24.0	72	0.7999	0.3358	0.7999	0.8944
No log	25.0	75	0.7108	0.4474	0.7108	0.8431
No log	26.0	78	1.2299	0.1321	1.2299	1.1090
No log	27.0	81	0.8435	0.2911	0.8435	0.9184
No log	28.0	84	0.8560	0.3328	0.8560	0.9252
No log	29.0	87	0.8967	0.3153	0.8967	0.9470
No log	30.0	90	0.9533	0.2414	0.9533	0.9763
No log	31.0	93	0.8706	0.2948	0.8706	0.9331
No log	32.0	96	1.1283	0.1698	1.1283	1.0622
No log	33.0	99	0.8788	0.2729	0.8788	0.9374

genki10/Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold0

Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold0