{ "epoch": 0.9993060374739764, "eval_logits/chosen": -0.12094812095165253, "eval_logits/rejected": 0.3205632269382477, "eval_logps/chosen": -505.86859130859375, "eval_logps/rejected": -652.3658447265625, "eval_loss": 0.3974800109863281, "eval_rewards/accuracies": 0.8129699230194092, "eval_rewards/chosen": -1.2128452062606812, "eval_rewards/margins": 1.2095903158187866, "eval_rewards/rejected": -2.4224352836608887, "eval_runtime": 388.0524, "eval_samples": 8491, "eval_samples_per_second": 21.881, "eval_steps_per_second": 0.343, "total_flos": 0.0, "train_loss": 0.5189602105981774, "train_runtime": 20904.8753, "train_samples": 184443, "train_samples_per_second": 8.823, "train_steps_per_second": 0.034 }