{ "epoch": 2.0, "eval_logits/chosen": -2.6189608573913574, "eval_logits/rejected": -2.6026179790496826, "eval_logps/chosen": -73.61612701416016, "eval_logps/rejected": -82.66606140136719, "eval_loss": 1.2207262516021729, "eval_rewards/accuracies": 0.329365074634552, "eval_rewards/chosen": 0.7525964975357056, "eval_rewards/margins": 2.075026512145996, "eval_rewards/rejected": -1.32243013381958, "eval_runtime": 113.5924, "eval_samples": 2000, "eval_samples_per_second": 17.607, "eval_steps_per_second": 0.555, "total_flos": 0.0, "train_loss": 0.6794358088995106, "train_runtime": 6413.3344, "train_samples": 18340, "train_samples_per_second": 5.719, "train_steps_per_second": 0.09 }