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	7	6.5018	0.0018	6.5018	2.5499
No log	2.0	14	2.2725	0.1911	2.2725	1.5075
No log	3.0	21	1.1469	0.0316	1.1469	1.0709
No log	4.0	28	1.0851	0.0445	1.0851	1.0417
No log	5.0	35	1.2609	0.0855	1.2609	1.1229
No log	6.0	42	0.7981	0.3325	0.7981	0.8934
No log	7.0	49	0.7306	0.3773	0.7306	0.8547
No log	8.0	56	0.7094	0.3716	0.7094	0.8423
No log	9.0	63	0.8864	0.3936	0.8864	0.9415
No log	10.0	70	0.9928	0.3922	0.9928	0.9964
No log	11.0	77	0.8963	0.4374	0.8963	0.9467
No log	12.0	84	0.9029	0.4354	0.9029	0.9502
No log	13.0	91	1.0790	0.3739	1.0790	1.0387
No log	14.0	98	1.2047	0.3388	1.2047	1.0976
No log	15.0	105	0.9592	0.3365	0.9592	0.9794
No log	16.0	112	0.8266	0.4430	0.8266	0.9092
No log	17.0	119	0.8550	0.4444	0.8550	0.9246
No log	18.0	126	0.8631	0.4556	0.8631	0.9290
No log	19.0	133	0.9530	0.4115	0.9530	0.9762
No log	20.0	140	1.1274	0.3026	1.1274	1.0618
No log	21.0	147	1.0088	0.3529	1.0088	1.0044
No log	22.0	154	0.9639	0.3848	0.9639	0.9818
No log	23.0	161	1.1877	0.3280	1.1877	1.0898
No log	24.0	168	1.4136	0.2816	1.4136	1.1890
No log	25.0	175	1.2064	0.3409	1.2064	1.0984
No log	26.0	182	0.7517	0.4492	0.7517	0.8670
No log	27.0	189	0.7946	0.4503	0.7946	0.8914
No log	28.0	196	0.9668	0.3989	0.9668	0.9833
No log	29.0	203	1.0861	0.3438	1.0861	1.0421
No log	30.0	210	1.1921	0.3192	1.1921	1.0919
No log	31.0	217	1.1317	0.3278	1.1317	1.0638
No log	32.0	224	1.0921	0.3143	1.0921	1.0450
No log	33.0	231	0.9712	0.3636	0.9712	0.9855

genki10/BERT_AugV8_k10_task1_organization_sp060_lw010_fold4

BERT_AugV8_k10_task1_organization_sp060_lw010_fold4