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	6.7072	0.0	6.7060	2.5896
No log	2.0	8	3.9260	0.0	3.9248	1.9811
No log	3.0	12	2.3906	0.1019	2.3898	1.5459
No log	4.0	16	1.4956	0.0202	1.4950	1.2227
No log	5.0	20	0.9975	0.0202	0.9970	0.9985
No log	6.0	24	1.4872	0.0202	1.4864	1.2192
No log	7.0	28	0.8617	0.3503	0.8612	0.9280
No log	8.0	32	1.2550	0.0667	1.2546	1.1201
No log	9.0	36	0.8200	0.3246	0.8199	0.9055
No log	10.0	40	1.7661	0.1618	1.7658	1.3288
No log	11.0	44	0.6914	0.4504	0.6917	0.8317
No log	12.0	48	2.2211	0.1326	2.2209	1.4903
No log	13.0	52	1.1609	0.2115	1.1613	1.0776
No log	14.0	56	1.0254	0.2492	1.0259	1.0129
No log	15.0	60	2.3529	0.0798	2.3527	1.5339
No log	16.0	64	1.3979	0.1817	1.3980	1.1824
No log	17.0	68	1.0652	0.2360	1.0652	1.0321
No log	18.0	72	2.0761	0.0896	2.0756	1.4407
No log	19.0	76	1.0300	0.2448	1.0301	1.0149
No log	20.0	80	1.0630	0.2453	1.0630	1.0310
No log	21.0	84	2.0979	0.0938	2.0973	1.4482
No log	22.0	88	1.2701	0.2239	1.2699	1.1269
No log	23.0	92	1.1227	0.2366	1.1227	1.0596
No log	24.0	96	1.7710	0.1185	1.7706	1.3307
No log	25.0	100	1.1824	0.2515	1.1826	1.0875
No log	26.0	104	1.2211	0.2398	1.2214	1.1052

genki10/Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold3

Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold3