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	Accuracy	Mae	Mse	Spearman
1.9625	1.0	97	0.1664	0.7895	0.2136	0.2198	nan
1.7734	2.0	194	0.1560	0.7864	0.2167	0.2229	-0.0219
1.6929	3.0	291	0.1500	0.7895	0.2136	0.2198	0.1267
1.6534	4.0	388	0.1466	0.7957	0.2074	0.2136	0.1565
1.5126	5.0	485	0.1476	0.7771	0.2260	0.2322	0.0783
1.2003	6.0	582	0.1716	0.7647	0.2353	0.2353	0.2609
0.5857	7.0	679	0.2275	0.6997	0.3003	0.3003	0.2808
0.1346	8.0	776	0.2655	0.7492	0.2508	0.2508	0.2835
0.0169	9.0	873	0.3173	0.7616	0.2384	0.2384	0.2765
0.0017	10.0	970	0.3322	0.7709	0.2291	0.2291	0.2520

athirorg/USS-reward-model-ordinal

USS-reward-model-ordinal