{ "epoch": 1.0, "eval_logits/chosen": 98.53792572021484, "eval_logits/rejected": 98.51567077636719, "eval_logps/chosen": -32.65095138549805, "eval_logps/rejected": -36.31239318847656, "eval_loss": 0.7163410782814026, "eval_rewards/accuracies": 0.5573089718818665, "eval_rewards/chosen": -0.10388783365488052, "eval_rewards/margins": 0.06904496997594833, "eval_rewards/rejected": -0.17293280363082886, "eval_runtime": 103.6495, "eval_samples": 343, "eval_samples_per_second": 3.309, "eval_steps_per_second": 0.415 }