{ "epoch": 16.0, "eval_logits/chosen": -3.3399085998535156, "eval_logits/rejected": -3.46624755859375, "eval_logps/chosen": -47.42058563232422, "eval_logps/rejected": -75.21272277832031, "eval_loss": 2.4941890239715576, "eval_rewards/accuracies": 0.125, "eval_rewards/chosen": -1.73505437374115, "eval_rewards/margins": -1.73505437374115, "eval_rewards/rejected": 0.0, "eval_runtime": 33.5322, "eval_samples": 310, "eval_samples_per_second": 9.245, "eval_steps_per_second": 0.298, "total_flos": 0.0, "train_loss": 0.0022047922514670387, "train_runtime": 763.2324, "train_samples": 5700, "train_samples_per_second": 119.492, "train_steps_per_second": 3.752 }