{ "epoch": 1.0, "eval_logits/chosen": -0.8803853392601013, "eval_logits/rejected": -0.776340126991272, "eval_logps/chosen": -564.5243530273438, "eval_logps/rejected": -893.765869140625, "eval_loss": 0.6910878419876099, "eval_rewards/accuracies": 0.656593382358551, "eval_rewards/chosen": 0.0010129850124940276, "eval_rewards/margins": 0.0048895603977143764, "eval_rewards/rejected": -0.003876575967296958, "eval_runtime": 293.2513, "eval_samples": 2886, "eval_samples_per_second": 9.841, "eval_steps_per_second": 0.31, "train_loss": 0.6850088967217339, "train_runtime": 241.6299, "train_samples": 1144, "train_samples_per_second": 4.735, "train_steps_per_second": 0.074 }