{ "epoch": 1.0, "eval_logits/chosen": -2.4597132205963135, "eval_logits/rejected": -2.398695468902588, "eval_logps/chosen": -278.69171142578125, "eval_logps/rejected": -230.4560089111328, "eval_loss": 0.6642152070999146, "eval_rewards/accuracies": 0.6480000019073486, "eval_rewards/chosen": 0.10415761172771454, "eval_rewards/margins": 0.06405296921730042, "eval_rewards/rejected": 0.04010463133454323, "eval_runtime": 444.8959, "eval_samples": 2000, "eval_samples_per_second": 4.495, "eval_steps_per_second": 0.281, "train_loss": 0.6728762634529555, "train_runtime": 27528.1814, "train_samples": 61966, "train_samples_per_second": 2.251, "train_steps_per_second": 0.035 }