{ "epoch": 1.971563981042654, "eval_eta": 0.004999999888241291, "eval_logits/chosen": 163.31393432617188, "eval_logits/rejected": 161.63084411621094, "eval_logps/chosen": -408.5458679199219, "eval_logps/rejected": -463.5101013183594, "eval_loss": 0.5857101082801819, "eval_rewards/accuracies": 0.7021276354789734, "eval_rewards/chosen": -0.733529269695282, "eval_rewards/margins": 1.3885893821716309, "eval_rewards/rejected": -2.1221187114715576, "eval_runtime": 443.0016, "eval_samples": 750, "eval_samples_per_second": 1.693, "eval_steps_per_second": 0.212, "total_flos": 0.0, "train_loss": 0.48392796287169826, "train_runtime": 15946.9173, "train_samples": 6750, "train_samples_per_second": 0.847, "train_steps_per_second": 0.007 }