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	9.4253	0.0037	9.4228	3.0697
No log	2.0	6	6.7742	0.0	6.7723	2.6024
No log	3.0	9	4.3289	0.0167	4.3268	2.0801
No log	4.0	12	3.1557	0.0	3.1539	1.7759
No log	5.0	15	2.0207	0.1774	2.0191	1.4209
No log	6.0	18	1.5313	0.0379	1.5297	1.2368
No log	7.0	21	1.2119	0.0	1.2103	1.1001
No log	8.0	24	1.1090	0.0	1.1075	1.0524
No log	9.0	27	1.0426	0.0185	1.0412	1.0204
No log	10.0	30	1.2136	0.0418	1.2120	1.1009
No log	11.0	33	0.9845	0.1823	0.9830	0.9915
No log	12.0	36	0.9667	0.1993	0.9651	0.9824
No log	13.0	39	0.9798	0.2130	0.9784	0.9891
No log	14.0	42	0.6815	0.3822	0.6801	0.8247
No log	15.0	45	1.1947	0.2316	1.1933	1.0924
No log	16.0	48	0.8624	0.3266	0.8610	0.9279
No log	17.0	51	0.7316	0.4062	0.7304	0.8547
No log	18.0	54	0.7970	0.4491	0.7959	0.8921
No log	19.0	57	0.7149	0.5020	0.7140	0.8450
No log	20.0	60	1.3948	0.2139	1.3933	1.1804
No log	21.0	63	0.8116	0.3733	0.8106	0.9003
No log	22.0	66	1.0203	0.2865	1.0187	1.0093
No log	23.0	69	0.8537	0.3637	0.8523	0.9232
No log	24.0	72	0.8952	0.3764	0.8937	0.9454
No log	25.0	75	1.4133	0.2396	1.4114	1.1880
No log	26.0	78	0.8919	0.3721	0.8905	0.9437
No log	27.0	81	0.9862	0.3206	0.9845	0.9922
No log	28.0	84	1.0782	0.3212	1.0764	1.0375
No log	29.0	87	0.8469	0.3463	0.8456	0.9196
No log	30.0	90	1.0618	0.2594	1.0602	1.0296
No log	31.0	93	1.0478	0.2762	1.0461	1.0228
No log	32.0	96	1.0879	0.3105	1.0860	1.0421
No log	33.0	99	0.9136	0.3191	0.9119	0.9549
No log	34.0	102	1.0959	0.2770	1.0939	1.0459

genki10/Trial3BERT_AugV8_k3_task1_organization_sp060_lw010_fold1

Trial3BERT_AugV8_k3_task1_organization_sp060_lw010_fold1