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
22.9021	1.0	97	1.5700	0.1938	0.2856	-0.0045	nan
17.8187	2.0	194	2.1893	0.2106	0.3009	-0.0917	0.1105
290.6176	3.0	291	47.6834	0.5032	0.5697	-1.6088	0.1146
518.1736	4.0	388	54.6556	0.2628	0.3755	-0.3622	0.1508
567.3146	5.0	485	57.8539	0.3017	0.4718	-0.5641	0.1994
574.1879	6.0	582	56.7874	0.2290	0.4001	-0.1873	0.1062
559.3920	7.0	679	55.2139	0.2447	0.3755	-0.2685	0.1472
544.8656	8.0	776	54.0387	0.2628	0.3924	-0.3626	0.1332
535.0054	9.0	873	53.2574	0.2067	0.2983	-0.0716	0.1215
529.6823	10.0	970	52.9809	0.1859	0.2835	0.0363	0.1418

athirorg/USS-reward-model-grl-source

USS-reward-model-grl-source