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	9.2889	0.0018	9.2863	3.0473
No log	2.0	6	7.3564	0.0	7.3540	2.7118
No log	3.0	9	6.0659	0.0	6.0636	2.4624
No log	4.0	12	4.2560	0.0040	4.2538	2.0625
No log	5.0	15	2.8941	0.0	2.8924	1.7007
No log	6.0	18	2.2313	0.1119	2.2295	1.4932
No log	7.0	21	1.4484	0.0106	1.4468	1.2028
No log	8.0	24	1.1335	0.0172	1.1322	1.0640
No log	9.0	27	0.9956	0.0106	0.9942	0.9971
No log	10.0	30	1.0433	0.0482	1.0419	1.0207
No log	11.0	33	0.7927	0.3209	0.7914	0.8896
No log	12.0	36	0.9873	0.1824	0.9859	0.9929
No log	13.0	39	0.8198	0.3523	0.8185	0.9047
No log	14.0	42	0.6458	0.4618	0.6446	0.8029
No log	15.0	45	1.1801	0.2553	1.1782	1.0855
No log	16.0	48	0.8187	0.3986	0.8170	0.9039
No log	17.0	51	0.6558	0.4320	0.6544	0.8090
No log	18.0	54	0.8083	0.4009	0.8064	0.8980
No log	19.0	57	0.8560	0.3391	0.8553	0.9248
No log	20.0	60	0.7249	0.4169	0.7239	0.8508
No log	21.0	63	0.8236	0.4454	0.8216	0.9064
No log	22.0	66	0.5635	0.5685	0.5620	0.7497
No log	23.0	69	0.7509	0.4552	0.7489	0.8654
No log	24.0	72	0.6226	0.5048	0.6209	0.7880
No log	25.0	75	0.6613	0.4794	0.6595	0.8121
No log	26.0	78	1.0857	0.3195	1.0834	1.0409
No log	27.0	81	0.7134	0.4467	0.7117	0.8436
No log	28.0	84	0.8327	0.3747	0.8307	0.9114
No log	29.0	87	0.8022	0.4152	0.8001	0.8945
No log	30.0	90	0.9159	0.3633	0.9135	0.9558
No log	31.0	93	0.8062	0.4187	0.8039	0.8966
No log	32.0	96	0.9858	0.3166	0.9832	0.9916
No log	33.0	99	0.9514	0.3344	0.9490	0.9741
No log	34.0	102	0.9650	0.3430	0.9626	0.9811
No log	35.0	105	0.7703	0.4064	0.7683	0.8765
No log	36.0	108	0.9903	0.3416	0.9880	0.9940
No log	37.0	111	0.7201	0.4946	0.7181	0.8474

genki10/BERT_AugV8_k3_task1_organization_sp020_lw010_fold1

BERT_AugV8_k3_task1_organization_sp020_lw010_fold1