{ "epoch": 1.0, "eval_logits/chosen": -1.3947696685791016, "eval_logits/rejected": -1.4550445079803467, "eval_logps/chosen": -347.72125244140625, "eval_logps/rejected": -439.48944091796875, "eval_loss": 0.5181241035461426, "eval_rewards/accuracies": 0.78515625, "eval_rewards/chosen": -0.8810909390449524, "eval_rewards/margins": 0.8462980389595032, "eval_rewards/rejected": -1.7273890972137451, "eval_runtime": 95.1997, "eval_samples": 2000, "eval_samples_per_second": 21.008, "eval_steps_per_second": 0.336, "total_flos": 0.0, "train_loss": 0.5605571830478531, "train_runtime": 8972.3869, "train_samples": 61134, "train_samples_per_second": 6.814, "train_steps_per_second": 0.213 }