{ "epoch": 0.48, "eval_logits/chosen": -2.1746628284454346, "eval_logits/rejected": -1.971569538116455, "eval_logps/chosen": -430.4875183105469, "eval_logps/rejected": -496.7296142578125, "eval_loss": 0.6893993616104126, "eval_rewards/accuracies": 0.6679999828338623, "eval_rewards/chosen": -0.1984768956899643, "eval_rewards/margins": 0.08663950115442276, "eval_rewards/rejected": -0.28511643409729004, "eval_runtime": 1049.0946, "eval_samples": 2000, "eval_samples_per_second": 1.906, "eval_steps_per_second": 1.906, "train_loss": 4.683178136915897e-05, "train_runtime": 5.5433, "train_samples": 61135, "train_samples_per_second": 11.029, "train_steps_per_second": 5.592 }