{ "epoch": 0.9999360981532366, "eval_logits/chosen": -1.28125, "eval_logits/rejected": -0.87109375, "eval_logps/chosen": -384.0, "eval_logps/rejected": -426.0, "eval_loss": 0.22941964864730835, "eval_rewards/accuracies": 0.9068260192871094, "eval_rewards/chosen": -17.375, "eval_rewards/margins": 6.09375, "eval_rewards/rejected": -23.5, "eval_runtime": 1564.413, "eval_samples": 55582, "eval_samples_per_second": 35.48, "eval_steps_per_second": 0.555, "total_flos": 0.0, "train_loss": 0.15513539346266378, "train_runtime": 70698.5942, "train_samples": 1001516, "train_samples_per_second": 14.166, "train_steps_per_second": 0.111 }