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	8.8582	0.0	8.8556	2.9758
No log	2.0	8	5.0843	0.0438	5.0822	2.2544
No log	3.0	12	3.0370	0.0	3.0352	1.7422
No log	4.0	16	1.6071	0.0211	1.6055	1.2671
No log	5.0	20	1.1983	0.0106	1.1969	1.0940
No log	6.0	24	1.2041	0.0106	1.2027	1.0967
No log	7.0	28	1.2316	0.0491	1.2300	1.1091
No log	8.0	32	0.9090	0.1834	0.9075	0.9527
No log	9.0	36	0.9548	0.2554	0.9530	0.9762
No log	10.0	40	0.7921	0.2657	0.7908	0.8893
No log	11.0	44	0.6229	0.4779	0.6217	0.7885
No log	12.0	48	0.6415	0.3934	0.6406	0.8004
No log	13.0	52	0.7317	0.3738	0.7308	0.8549
No log	14.0	56	0.7796	0.3922	0.7786	0.8824
No log	15.0	60	0.5789	0.5138	0.5782	0.7604
No log	16.0	64	1.1058	0.3421	1.1048	1.0511
No log	17.0	68	0.7588	0.3796	0.7580	0.8706
No log	18.0	72	0.8384	0.3687	0.8375	0.9151
No log	19.0	76	0.8425	0.3846	0.8416	0.9174
No log	20.0	80	0.7782	0.4170	0.7774	0.8817
No log	21.0	84	0.7823	0.4058	0.7816	0.8841
No log	22.0	88	0.9430	0.3296	0.9421	0.9706
No log	23.0	92	1.1426	0.2827	1.1415	1.0684
No log	24.0	96	0.7989	0.3842	0.7982	0.8934
No log	25.0	100	0.8593	0.3630	0.8585	0.9265
No log	26.0	104	0.9861	0.3118	0.9852	0.9926
No log	27.0	108	0.8398	0.3790	0.8391	0.9160
No log	28.0	112	0.7766	0.4270	0.7760	0.8809
No log	29.0	116	0.8967	0.3376	0.8958	0.9465
No log	30.0	120	0.7895	0.3511	0.7887	0.8881

genki10/Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold1

Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold1