learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 10
total_train_batch_size: 20
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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	Mse	Mae	R2	Spearman Correlation
7.0444	1.0	97	0.2106	0.2106	0.3080	-0.0916	nan
2.0581	2.0	194	0.1701	0.1701	0.2693	0.1181	0.2833
1.6404	3.0	291	0.1800	0.1800	0.3289	0.0670	0.3333
1.1040	4.0	388	0.2168	0.2168	0.3728	-0.1240	0.2631
0.5726	5.0	485	0.1988	0.1988	0.3510	-0.0306	0.2295
0.3258	6.0	582	0.1803	0.1803	0.3161	0.0651	0.1804
0.1733	7.0	679	0.1891	0.1891	0.3286	0.0195	0.1746
0.1145	8.0	776	0.1812	0.1812	0.3248	0.0608	0.2181
0.0574	9.0	873	0.1823	0.1823	0.3247	0.0547	0.2339
0.0217	10.0	970	0.1814	0.1814	0.3183	0.0594	0.2032

athirorg/USS-reward-model-baseline

USS-reward-model-baseline