{ "epoch": 1.0, "eval_logits/chosen": -2.5063796043395996, "eval_logits/rejected": -2.5199685096740723, "eval_logps/chosen": -272.9034729003906, "eval_logps/rejected": -250.30796813964844, "eval_loss": 0.6366299986839294, "eval_pred_label": 6857.14404296875, "eval_rewards/accuracies": 0.6320000290870667, "eval_rewards/chosen": 0.03307868540287018, "eval_rewards/margins": 0.06870328634977341, "eval_rewards/rejected": -0.03562460467219353, "eval_runtime": 441.6525, "eval_samples": 2000, "eval_samples_per_second": 4.528, "eval_steps_per_second": 0.283, "eval_use_label": 9174.8564453125, "train_loss": 0.6567496789063458, "train_runtime": 24439.922, "train_samples": 61135, "train_samples_per_second": 2.501, "train_steps_per_second": 0.039 }