{ "epoch": 1.0, "eval_logits/chosen": -2.5860071182250977, "eval_logits/rejected": -2.390984535217285, "eval_logps/chosen": -803.2769775390625, "eval_logps/rejected": -1662.8184814453125, "eval_loss": 0.07558085024356842, "eval_rewards/accuracies": 0.953125, "eval_rewards/chosen": -3.7114715576171875, "eval_rewards/margins": 7.48745059967041, "eval_rewards/rejected": -11.198921203613281, "eval_runtime": 32.9329, "eval_samples": 252, "eval_samples_per_second": 7.652, "eval_steps_per_second": 0.243, "train_loss": 0.007740737387427577, "train_runtime": 396.513, "train_samples": 20740, "train_samples_per_second": 52.306, "train_steps_per_second": 0.817 }