{ "epoch": 1.0, "eval_logits/chosen": 97.70832824707031, "eval_logits/rejected": 97.6825942993164, "eval_logps/chosen": -33.185726165771484, "eval_logps/rejected": -37.16183853149414, "eval_loss": 0.9545474052429199, "eval_rewards/accuracies": 0.5888704061508179, "eval_rewards/chosen": -0.07425507158041, "eval_rewards/margins": 0.045276571065187454, "eval_rewards/rejected": -0.11953166127204895, "eval_runtime": 103.7845, "eval_samples": 343, "eval_samples_per_second": 3.305, "eval_steps_per_second": 0.414, "train_loss": 0.88636748450143, "train_runtime": 2554.6221, "train_samples": 3079, "train_samples_per_second": 1.205, "train_steps_per_second": 0.151 }