{ "epoch": 1.0, "eval_logits/chosen": -2.9083194732666016, "eval_logits/rejected": -2.835282325744629, "eval_logps/chosen": -817.455078125, "eval_logps/rejected": -1091.8406982421875, "eval_loss": 0.6746304631233215, "eval_rewards/accuracies": 0.6612318754196167, "eval_rewards/chosen": -0.020445356145501137, "eval_rewards/margins": 0.039513371884822845, "eval_rewards/rejected": -0.059958722442388535, "eval_runtime": 2163.8157, "eval_samples": 19864, "eval_samples_per_second": 9.18, "eval_steps_per_second": 0.287, "train_loss": 0.5004948377609253, "train_runtime": 257.4676, "train_samples": 1128, "train_samples_per_second": 4.381, "train_steps_per_second": 0.07 }