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	4	9.8673	0.0010	9.8673	3.1412
No log	2.0	8	7.3517	0.0	7.3519	2.7114
No log	3.0	12	5.4033	0.0267	5.4037	2.3246
No log	4.0	16	3.7976	0.0	3.7980	1.9488
No log	5.0	20	2.6519	0.0	2.6524	1.6286
No log	6.0	24	1.8458	0.0280	1.8462	1.3587
No log	7.0	28	1.1914	0.0	1.1918	1.0917
No log	8.0	32	0.9078	0.0481	0.9081	0.9529
No log	9.0	36	0.9622	0.0615	0.9625	0.9811
No log	10.0	40	0.8871	0.3027	0.8873	0.9419
No log	11.0	44	1.1023	0.2199	1.1026	1.0500
No log	12.0	48	0.6189	0.5066	0.6192	0.7869
No log	13.0	52	1.1188	0.3092	1.1189	1.0578
No log	14.0	56	0.5778	0.4169	0.5781	0.7603
No log	15.0	60	0.5706	0.4243	0.5708	0.7555
No log	16.0	64	0.7402	0.4179	0.7407	0.8606
No log	17.0	68	0.5639	0.5311	0.5642	0.7511
No log	18.0	72	1.0154	0.3362	1.0159	1.0079
No log	19.0	76	0.5844	0.5543	0.5845	0.7646
No log	20.0	80	0.8892	0.4104	0.8894	0.9431
No log	21.0	84	0.7328	0.4178	0.7334	0.8564
No log	22.0	88	0.6888	0.4745	0.6890	0.8301
No log	23.0	92	0.6719	0.4437	0.6723	0.8200
No log	24.0	96	0.6602	0.4712	0.6606	0.8128
No log	25.0	100	0.6684	0.4476	0.6687	0.8177
No log	26.0	104	0.7783	0.3905	0.7786	0.8824
No log	27.0	108	0.6718	0.5037	0.6720	0.8198
No log	28.0	112	0.9150	0.3192	0.9153	0.9567
No log	29.0	116	0.6273	0.4397	0.6276	0.7922
No log	30.0	120	0.5568	0.4887	0.5570	0.7463
No log	31.0	124	0.7969	0.4079	0.7971	0.8928
No log	32.0	128	0.6947	0.4176	0.6952	0.8338
No log	33.0	132	0.6337	0.5141	0.6341	0.7963
No log	34.0	136	0.9068	0.3753	0.9070	0.9524

genki10/BERT_AugV8_k5_task1_organization_sp020_lw010_fold2

BERT_AugV8_k5_task1_organization_sp020_lw010_fold2