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	3	9.5163	0.0	9.5139	3.0845
No log	2.0	6	8.4213	0.0	8.4191	2.9016
No log	3.0	9	6.2838	0.0	6.2815	2.5063
No log	4.0	12	4.2698	0.0	4.2678	2.0659
No log	5.0	15	3.0357	0.0	3.0338	1.7418
No log	6.0	18	2.3399	-0.0231	2.3381	1.5291
No log	7.0	21	1.5678	0.0315	1.5663	1.2515
No log	8.0	24	1.2303	0.0211	1.2288	1.1085
No log	9.0	27	1.1547	0.0315	1.1531	1.0738
No log	10.0	30	0.9384	0.0615	0.9369	0.9679
No log	11.0	33	1.1290	0.0734	1.1271	1.0617
No log	12.0	36	0.8003	0.3252	0.7988	0.8938
No log	13.0	39	0.8097	0.3034	0.8081	0.8989
No log	14.0	42	0.8223	0.2601	0.8210	0.9061
No log	15.0	45	0.6469	0.3928	0.6459	0.8037
No log	16.0	48	0.6379	0.4696	0.6368	0.7980
No log	17.0	51	0.6753	0.4632	0.6744	0.8212
No log	18.0	54	0.8539	0.4138	0.8522	0.9232
No log	19.0	57	0.7288	0.4839	0.7279	0.8532
No log	20.0	60	0.7100	0.5085	0.7088	0.8419
No log	21.0	63	0.5390	0.6269	0.5383	0.7337
No log	22.0	66	0.7272	0.5129	0.7261	0.8521
No log	23.0	69	0.6818	0.5615	0.6813	0.8254
No log	24.0	72	0.7044	0.5661	0.7034	0.8387
No log	25.0	75	0.7271	0.5109	0.7259	0.8520
No log	26.0	78	0.6235	0.5639	0.6229	0.7892
No log	27.0	81	0.8350	0.4415	0.8339	0.9132
No log	28.0	84	0.6136	0.5524	0.6130	0.7830
No log	29.0	87	0.6692	0.5163	0.6685	0.8176
No log	30.0	90	0.6316	0.5389	0.6311	0.7944
No log	31.0	93	0.6753	0.5160	0.6748	0.8215
No log	32.0	96	1.1228	0.3352	1.1218	1.0592
No log	33.0	99	0.6572	0.5331	0.6566	0.8103
No log	34.0	102	0.6440	0.5153	0.6434	0.8021
No log	35.0	105	0.7518	0.4647	0.7510	0.8666
No log	36.0	108	0.6578	0.4865	0.6572	0.8107

genki10/BERT_AugV8_k3_task1_organization_sp010_lw070_fold1

BERT_AugV8_k3_task1_organization_sp010_lw070_fold1