{ "epoch": 3.0, "eval_logits/chosen": -2.1679632663726807, "eval_logits/rejected": -2.144676923751831, "eval_logps/chosen": -250.57945251464844, "eval_logps/rejected": -237.97642517089844, "eval_loss": 0.5249601006507874, "eval_rewards/accuracies": 0.8307291865348816, "eval_rewards/chosen": 0.5658118724822998, "eval_rewards/margins": 2.835527181625366, "eval_rewards/rejected": -2.2697153091430664, "eval_runtime": 201.1633, "eval_samples_per_second": 15.112, "eval_steps_per_second": 0.239, "total_flos": 3785055088410624.0, "train_loss": 0.33236435687059185, "train_runtime": 12185.597, "train_samples_per_second": 6.734, "train_steps_per_second": 0.026 }