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: 100

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	4	7.6303	0.0	7.6303	2.7623
No log	2.0	8	5.9804	0.0222	5.9804	2.4455
No log	3.0	12	4.3509	0.0039	4.3509	2.0859
No log	4.0	16	2.8283	0.0	2.8283	1.6818
No log	5.0	20	1.6669	0.0316	1.6669	1.2911
No log	6.0	24	1.0831	0.0316	1.0831	1.0407
No log	7.0	28	0.7940	0.3369	0.7940	0.8911
No log	8.0	32	0.6650	0.4664	0.6650	0.8155
No log	9.0	36	1.1243	0.2852	1.1243	1.0603
No log	10.0	40	0.6593	0.5164	0.6593	0.8119
No log	11.0	44	0.7973	0.4689	0.7973	0.8929
No log	12.0	48	0.7193	0.4787	0.7193	0.8481
No log	13.0	52	0.6115	0.4943	0.6115	0.7820
No log	14.0	56	0.6015	0.5182	0.6015	0.7756
No log	15.0	60	0.8141	0.4382	0.8141	0.9023
No log	16.0	64	0.7557	0.4222	0.7557	0.8693
No log	17.0	68	0.7358	0.4916	0.7358	0.8578
No log	18.0	72	0.9763	0.4418	0.9763	0.9881
No log	19.0	76	0.8405	0.4784	0.8405	0.9168
No log	20.0	80	0.8930	0.4650	0.8930	0.9450
No log	21.0	84	0.9562	0.4252	0.9562	0.9778
No log	22.0	88	0.9078	0.4618	0.9078	0.9528
No log	23.0	92	0.8865	0.4621	0.8865	0.9416
No log	24.0	96	0.8880	0.4380	0.8880	0.9424
No log	25.0	100	1.0764	0.4624	1.0764	1.0375
No log	26.0	104	0.9767	0.4311	0.9767	0.9883
No log	27.0	108	0.9745	0.4540	0.9745	0.9872
No log	28.0	112	0.9742	0.4243	0.9742	0.9870
No log	29.0	116	0.9860	0.4596	0.9860	0.9930
No log	30.0	120	0.9965	0.4193	0.9965	0.9983
No log	31.0	124	0.9928	0.4700	0.9928	0.9964
No log	32.0	128	0.9348	0.4649	0.9348	0.9668
No log	33.0	132	0.9463	0.4661	0.9463	0.9728
No log	34.0	136	0.9713	0.4346	0.9713	0.9856

genki10/Version3_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold0

Version3_ASAP_FineTuningBERT_AugV12_k3_task1_organization_k3_k3_fold0