{ "epoch": 2.986666666666667, "eval_logits/chosen": -2.677677869796753, "eval_logits/rejected": -2.6818528175354004, "eval_logps/chosen": -1.0619781017303467, "eval_logps/rejected": -1.1974726915359497, "eval_loss": 1.1249287128448486, "eval_odds_ratio_loss": 0.62950599193573, "eval_rewards/accuracies": 0.4399999976158142, "eval_rewards/chosen": -0.10619781166315079, "eval_rewards/margins": 0.013549459166824818, "eval_rewards/rejected": -0.11974727362394333, "eval_runtime": 57.437, "eval_samples_per_second": 1.741, "eval_sft_loss": 1.0619781017303467, "eval_steps_per_second": 0.435, "total_flos": 2.303993975490478e+17, "train_loss": 1.1586682626179285, "train_runtime": 5352.1206, "train_samples_per_second": 0.504, "train_steps_per_second": 0.031 }