{ "epoch": 2.99, "eval_logits/chosen": -3.0396389961242676, "eval_logits/rejected": -3.0144476890563965, "eval_logps/chosen": -298.3731384277344, "eval_logps/rejected": -242.99319458007812, "eval_loss": 0.6432122588157654, "eval_rewards/accuracies": 0.6984127163887024, "eval_rewards/chosen": 0.06627513468265533, "eval_rewards/margins": 0.1006779745221138, "eval_rewards/rejected": -0.034402843564748764, "eval_runtime": 143.4479, "eval_samples": 2000, "eval_samples_per_second": 13.942, "eval_steps_per_second": 0.439, "train_loss": 0.6612398778398831, "train_runtime": 18623.8854, "train_samples": 61619, "train_samples_per_second": 9.926, "train_steps_per_second": 0.019 }