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	10.2169	0.0	10.2168	3.1964
No log	2.0	8	7.3752	0.0	7.3754	2.7158
No log	3.0	12	4.7127	0.0039	4.7131	2.1710
No log	4.0	16	3.0328	0.0	3.0333	1.7416
No log	5.0	20	1.7756	0.0318	1.7760	1.3327
No log	6.0	24	1.1578	0.0107	1.1583	1.0763
No log	7.0	28	1.3289	0.0	1.3296	1.1531
No log	8.0	32	1.0483	0.0	1.0488	1.0241
No log	9.0	36	1.0752	0.0268	1.0754	1.0370
No log	10.0	40	0.8705	0.2601	0.8708	0.9332
No log	11.0	44	0.8022	0.3026	0.8023	0.8957
No log	12.0	48	0.8478	0.1381	0.8483	0.9210
No log	13.0	52	0.7948	0.1788	0.7949	0.8916
No log	14.0	56	0.6486	0.3205	0.6484	0.8052
No log	15.0	60	0.6634	0.3190	0.6630	0.8142
No log	16.0	64	0.6333	0.3728	0.6328	0.7955
No log	17.0	68	0.7363	0.3879	0.7359	0.8579
No log	18.0	72	0.6163	0.5067	0.6156	0.7846
No log	19.0	76	0.8214	0.3471	0.8210	0.9061
No log	20.0	80	0.9302	0.2383	0.9300	0.9644
No log	21.0	84	0.6857	0.4326	0.6850	0.8277
No log	22.0	88	0.8727	0.2857	0.8724	0.9340
No log	23.0	92	0.7681	0.3669	0.7677	0.8762
No log	24.0	96	0.8723	0.2887	0.8721	0.9338
No log	25.0	100	0.9011	0.2906	0.9009	0.9491
No log	26.0	104	0.8403	0.3257	0.8400	0.9165
No log	27.0	108	0.8516	0.3171	0.8512	0.9226
No log	28.0	112	0.7580	0.3769	0.7574	0.8703
No log	29.0	116	0.7825	0.3649	0.7821	0.8844
No log	30.0	120	0.8569	0.3271	0.8568	0.9256
No log	31.0	124	0.8339	0.3166	0.8337	0.9131
No log	32.0	128	0.9288	0.2433	0.9289	0.9638
No log	33.0	132	0.7777	0.4400	0.7771	0.8815

genki10/Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold2

Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold2