{ "epoch": 2.997999555456768, "eval_logits/chosen": -2.8460819721221924, "eval_logits/rejected": -2.8720545768737793, "eval_logps/chosen": -0.8352006673812866, "eval_logps/rejected": -1.0736578702926636, "eval_loss": 0.8975116014480591, "eval_odds_ratio_loss": 0.6231085658073425, "eval_rewards/accuracies": 0.5899999737739563, "eval_rewards/chosen": -0.0835200697183609, "eval_rewards/margins": 0.023845719173550606, "eval_rewards/rejected": -0.10736579447984695, "eval_runtime": 189.1831, "eval_samples_per_second": 5.286, "eval_sft_loss": 0.8352006673812866, "eval_steps_per_second": 2.643, "total_flos": 1.985199772705751e+18, "train_loss": 0.9645641791862949, "train_runtime": 17170.3123, "train_samples_per_second": 1.572, "train_steps_per_second": 0.098 }