{ "epoch": 1.0, "eval_logits/chosen": -2.8279476165771484, "eval_logits/rejected": -2.8258962631225586, "eval_logps/chosen": -31.732280731201172, "eval_logps/rejected": -35.50532150268555, "eval_loss": 0.9294446110725403, "eval_rewards/accuracies": 0.6009136438369751, "eval_rewards/chosen": -0.08996524661779404, "eval_rewards/margins": 0.07146809250116348, "eval_rewards/rejected": -0.16143333911895752, "eval_runtime": 112.8197, "eval_samples": 343, "eval_samples_per_second": 3.04, "eval_steps_per_second": 0.381, "train_loss": 0.8011291454364727, "train_runtime": 2726.0249, "train_samples": 3079, "train_samples_per_second": 1.129, "train_steps_per_second": 0.141 }