{ "epoch": 0.9982631930527722, "eval_logits/chosen": -1.4208170175552368, "eval_logits/rejected": -1.4303871393203735, "eval_logps/chosen": -1.6523464918136597, "eval_logps/rejected": -2.212089776992798, "eval_loss": 1.294402003288269, "eval_rewards/accuracies": 0.8353658318519592, "eval_rewards/chosen": -16.52346420288086, "eval_rewards/margins": 5.597432613372803, "eval_rewards/rejected": -22.120895385742188, "eval_runtime": 112.7838, "eval_samples": 1961, "eval_samples_per_second": 17.387, "eval_steps_per_second": 1.091, "total_flos": 0.0, "train_loss": 1.7982526555561662, "train_runtime": 17001.7268, "train_samples": 59876, "train_samples_per_second": 3.522, "train_steps_per_second": 0.027 }