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	12.4165	-0.0006	12.4143	3.5234
No log	2.0	8	8.0229	0.0	8.0213	2.8322
No log	3.0	12	5.3111	0.0175	5.3097	2.3043
No log	4.0	16	3.3558	0.0	3.3547	1.8316
No log	5.0	20	1.8174	0.0514	1.8168	1.3479
No log	6.0	24	1.3808	0.0102	1.3803	1.1748
No log	7.0	28	1.6506	0.0266	1.6500	1.2845
No log	8.0	32	1.7302	0.1088	1.7297	1.3152
No log	9.0	36	1.3929	0.0730	1.3927	1.1801
No log	10.0	40	2.2243	0.1197	2.2244	1.4914
No log	11.0	44	1.6846	0.0754	1.6851	1.2981
No log	12.0	48	1.6343	0.0879	1.6351	1.2787
No log	13.0	52	1.2519	0.2049	1.2528	1.1193
No log	14.0	56	1.8538	0.1003	1.8545	1.3618
No log	15.0	60	1.5222	0.1412	1.5230	1.2341
No log	16.0	64	1.9149	0.1100	1.9158	1.3841
No log	17.0	68	2.0196	0.1152	2.0205	1.4214
No log	18.0	72	2.6068	0.0784	2.6078	1.6149
No log	19.0	76	2.9196	0.0572	2.9207	1.7090
No log	20.0	80	2.0767	0.1119	2.0778	1.4415
No log	21.0	84	1.8601	0.1115	1.8612	1.3643
No log	22.0	88	1.9171	0.1413	1.9183	1.3850
No log	23.0	92	1.6209	0.1652	1.6223	1.2737
No log	24.0	96	3.1992	0.0728	3.2004	1.7890
No log	25.0	100	2.1660	0.1281	2.1673	1.4722
No log	26.0	104	2.0406	0.1170	2.0420	1.4290
No log	27.0	108	2.5657	0.0819	2.5669	1.6021
No log	28.0	112	2.1916	0.0692	2.1927	1.4808

genki10/BERT_AugV8_k5_task1_organization_sp010_lw070_fold3

BERT_AugV8_k5_task1_organization_sp010_lw070_fold3