{ "epoch": 0.9965156794425087, "eval_logits/chosen": -2.3508927822113037, "eval_logits/rejected": -2.3035717010498047, "eval_logps/chosen": -294.2789306640625, "eval_logps/rejected": -318.7192687988281, "eval_loss": 0.624984860420227, "eval_rewards/accuracies": 0.6953125, "eval_rewards/chosen": -0.316490113735199, "eval_rewards/margins": 0.24408146739006042, "eval_rewards/rejected": -0.5605716109275818, "eval_runtime": 105.1694, "eval_samples": 2000, "eval_samples_per_second": 19.017, "eval_steps_per_second": 0.304, "total_flos": 0.0, "train_loss": 0.6505647914392965, "train_runtime": 3852.398, "train_samples": 18340, "train_samples_per_second": 4.761, "train_steps_per_second": 0.037 }