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	7.5492	0.0	7.5492	2.7476
No log	2.0	8	5.7209	0.0116	5.7209	2.3918
No log	3.0	12	3.9898	0.0039	3.9898	1.9974
No log	4.0	16	2.3708	0.1041	2.3708	1.5397
No log	5.0	20	1.5207	0.0316	1.5207	1.2331
No log	6.0	24	1.8901	0.1037	1.8901	1.3748
No log	7.0	28	1.2575	0.0382	1.2575	1.1214
No log	8.0	32	1.6808	0.1349	1.6808	1.2965
No log	9.0	36	1.6782	0.1622	1.6782	1.2954
No log	10.0	40	1.9659	0.1422	1.9659	1.4021
No log	11.0	44	0.9746	0.1873	0.9746	0.9872
No log	12.0	48	1.9466	0.1208	1.9466	1.3952
No log	13.0	52	1.0084	0.2989	1.0084	1.0042
No log	14.0	56	1.4229	0.2165	1.4229	1.1928
No log	15.0	60	2.0514	0.1370	2.0514	1.4323
No log	16.0	64	1.0082	0.2933	1.0082	1.0041
No log	17.0	68	2.2135	0.1272	2.2135	1.4878
No log	18.0	72	1.7081	0.2018	1.7081	1.3069
No log	19.0	76	1.2454	0.2707	1.2454	1.1160
No log	20.0	80	1.5646	0.2141	1.5646	1.2508
No log	21.0	84	2.3750	0.1044	2.3750	1.5411
No log	22.0	88	1.4546	0.2226	1.4546	1.2060
No log	23.0	92	2.1163	0.1027	2.1163	1.4548
No log	24.0	96	2.0200	0.1422	2.0200	1.4213
No log	25.0	100	1.4733	0.2000	1.4733	1.2138
No log	26.0	104	2.0526	0.1187	2.0526	1.4327
No log	27.0	108	1.0852	0.2571	1.0852	1.0417
No log	28.0	112	2.3199	0.0899	2.3199	1.5231

genki10/Trial3BERT_AugV8_k5_task1_organization_sp020_lw070_fold0

Trial3BERT_AugV8_k5_task1_organization_sp020_lw070_fold0