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	7.8555	0.0	7.8559	2.8028
No log	2.0	8	4.7991	0.0078	4.7996	2.1908
No log	3.0	12	2.6940	0.0	2.6944	1.6415
No log	4.0	16	1.7389	0.0345	1.7393	1.3188
No log	5.0	20	1.0869	0.0029	1.0873	1.0427
No log	6.0	24	0.8309	0.3136	0.8312	0.9117
No log	7.0	28	0.7467	0.3814	0.7470	0.8643
No log	8.0	32	1.0731	0.2022	1.0732	1.0359
No log	9.0	36	0.6776	0.3813	0.6779	0.8234
No log	10.0	40	0.7722	0.3083	0.7723	0.8788
No log	11.0	44	0.5534	0.4507	0.5535	0.7440
No log	12.0	48	0.5905	0.3619	0.5907	0.7686
No log	13.0	52	0.4999	0.4944	0.5000	0.7071
No log	14.0	56	0.7988	0.3311	0.7992	0.8940
No log	15.0	60	0.5767	0.5627	0.5769	0.7595
No log	16.0	64	0.9382	0.3831	0.9382	0.9686
No log	17.0	68	0.6329	0.5100	0.6332	0.7957
No log	18.0	72	1.0502	0.2100	1.0502	1.0248
No log	19.0	76	0.7351	0.3844	0.7351	0.8574
No log	20.0	80	0.4790	0.5959	0.4790	0.6921
No log	21.0	84	0.8299	0.4103	0.8296	0.9108
No log	22.0	88	0.8470	0.4468	0.8472	0.9204
No log	23.0	92	0.6479	0.4014	0.6480	0.8050
No log	24.0	96	0.7628	0.3632	0.7627	0.8733
No log	25.0	100	0.7156	0.4709	0.7159	0.8461
No log	26.0	104	0.7886	0.3332	0.7886	0.8880
No log	27.0	108	0.5443	0.4972	0.5444	0.7378
No log	28.0	112	0.5942	0.4649	0.5942	0.7708
No log	29.0	116	0.7716	0.4502	0.7719	0.8786
No log	30.0	120	0.7039	0.3769	0.7041	0.8391
No log	31.0	124	0.5994	0.4984	0.5994	0.7742
No log	32.0	128	0.6987	0.4796	0.6988	0.8359
No log	33.0	132	0.6254	0.4839	0.6255	0.7909
No log	34.0	136	0.6618	0.4027	0.6619	0.8136
No log	35.0	140	0.6675	0.4421	0.6677	0.8171

genki10/BERT_AugV8_k5_task1_organization_sp010_lw040_fold2

BERT_AugV8_k5_task1_organization_sp010_lw040_fold2