{ "epoch": 0.9985553308292401, "eval_logits/chosen": -0.37041226029396057, "eval_logits/rejected": -0.3487028181552887, "eval_logps/chosen": -160.84490966796875, "eval_logps/rejected": -168.74127197265625, "eval_loss": 1.4404404163360596, "eval_nll_loss": 0.278992623090744, "eval_rewards/accuracies": 0.6326087117195129, "eval_rewards/chosen": -16.084491729736328, "eval_rewards/margins": 0.7896348834037781, "eval_rewards/rejected": -16.874126434326172, "eval_runtime": 76.7035, "eval_samples": 1826, "eval_samples_per_second": 23.806, "eval_steps_per_second": 1.499, "total_flos": 0.0, "train_loss": 1.6635627029118714, "train_runtime": 10783.4889, "train_samples": 55376, "train_samples_per_second": 5.135, "train_steps_per_second": 0.04 }