learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
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: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
0.3124	1.0	719	0.6001	0.8669	0.8705
0.2672	2.0	1438	0.5349	0.8732	0.8747
0.3019	3.0	2157	0.5183	0.8774	0.8800
0.214	4.0	2876	0.5480	0.8796	0.8818
0.1671	5.0	3595	0.5136	0.8809	0.8831
0.2153	6.0	4314	0.5384	0.8804	0.8827
0.2223	7.0	5033	0.5181	0.8791	0.8806
0.1442	8.0	5752	0.5166	0.8785	0.8799
0.1452	9.0	6471	0.5177	0.8784	0.8799
0.1215	10.0	7190	0.5183	0.8791	0.8802

jhj1769/stsb-lora

stsb-lora