{ "epoch": 2.9447852760736195, "eval_logits/chosen": -2.3613531589508057, "eval_logits/rejected": -2.339138984680176, "eval_logps/chosen": -307.6524353027344, "eval_logps/rejected": -228.04098510742188, "eval_loss": 0.5027558207511902, "eval_rewards/accuracies": 0.875, "eval_rewards/chosen": 3.6010191440582275, "eval_rewards/margins": 3.400972843170166, "eval_rewards/rejected": 0.2000463604927063, "eval_runtime": 78.6331, "eval_samples_per_second": 14.663, "eval_steps_per_second": 0.242, "total_flos": 1414680891359232.0, "train_loss": 0.23404777497053147, "train_runtime": 4394.1396, "train_samples_per_second": 7.082, "train_steps_per_second": 0.027 }