{ "epoch": 0.9981298423724285, "eval_logits/chosen": 1.675267219543457, "eval_logits/rejected": 1.6861435174942017, "eval_logps/chosen": -403.47772216796875, "eval_logps/rejected": -434.26507568359375, "eval_loss": 0.6095927357673645, "eval_rewards/accuracies": 0.6975806355476379, "eval_rewards/chosen": -1.0852103233337402, "eval_rewards/margins": 0.3981803059577942, "eval_rewards/rejected": -1.4833906888961792, "eval_runtime": 88.8294, "eval_samples": 1961, "eval_samples_per_second": 22.076, "eval_steps_per_second": 0.698, "total_flos": 0.0, "train_loss": 0.6216196353991996, "train_runtime": 6954.5059, "train_samples": 59875, "train_samples_per_second": 8.61, "train_steps_per_second": 0.067 }