learning_rate: 0.0005
train_batch_size: 8
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Pearson R	Spearman R
0.6835	1.0	719	0.6543	0.5224	0.5221
0.6489	2.0	1438	0.6053	0.7743	0.7848
0.6408	3.0	2157	0.6005	0.7826	0.7938
0.6288	4.0	2876	0.5970	0.7778	0.7792
0.6138	5.0	3595	0.6643	0.7622	0.7814
0.6044	6.0	4314	0.6048	0.8059	0.8135
0.597	7.0	5033	0.5865	0.8243	0.8307
0.5946	8.0	5752	0.5702	0.8170	0.8236
0.5915	9.0	6471	0.5738	0.8211	0.8242
0.5891	10.0	7190	0.5698	0.8241	0.8276

Rjp97/microsoft-deberta-v3-large

microsoft-deberta-v3-large