{ | |
"epoch": 2.994871794871795, | |
"eval_logits/chosen": -2.405457019805908, | |
"eval_logits/rejected": -2.3732309341430664, | |
"eval_logps/chosen": -190.46534729003906, | |
"eval_logps/rejected": -218.4866485595703, | |
"eval_loss": 0.4467383623123169, | |
"eval_rewards/accuracies": 0.8163461685180664, | |
"eval_rewards/chosen": -3.198800802230835, | |
"eval_rewards/margins": 2.761833906173706, | |
"eval_rewards/rejected": -5.960635185241699, | |
"eval_runtime": 521.0004, | |
"eval_samples_per_second": 15.958, | |
"eval_steps_per_second": 0.25 | |
} |