{ "epoch": 1.0, "eval_logits/chosen": -2.658360004425049, "eval_logits/rejected": -2.620964527130127, "eval_logps/chosen": -289.316650390625, "eval_logps/rejected": -318.2507019042969, "eval_loss": 55196.58984375, "eval_rewards/accuracies": 0.5619999766349792, "eval_rewards/chosen": -289.316650390625, "eval_rewards/margins": 28.934038162231445, "eval_rewards/rejected": -318.2507019042969, "eval_runtime": 1123.3053, "eval_samples": 2000, "eval_samples_per_second": 1.78, "eval_steps_per_second": 0.111, "total_flos": 0.0, "train_loss": 57346.567718553764, "train_runtime": 71624.9556, "train_samples": 61135, "train_samples_per_second": 0.854, "train_steps_per_second": 0.018 }