{ "epoch": 1.971563981042654, "eval_logits/chosen": 91.48676300048828, "eval_logits/rejected": 85.7594223022461, "eval_logps/chosen": -445.9359436035156, "eval_logps/rejected": -479.6258239746094, "eval_loss": 0.465834379196167, "eval_rewards/accuracies": 0.7291666865348816, "eval_rewards/chosen": -4.113387584686279, "eval_rewards/margins": 1.7643555402755737, "eval_rewards/rejected": -5.877742767333984, "eval_runtime": 131.0653, "eval_samples": 750, "eval_samples_per_second": 5.722, "eval_steps_per_second": 0.183, "total_flos": 0.0, "train_loss": 0.38906457561713, "train_runtime": 3484.4936, "train_samples": 6750, "train_samples_per_second": 3.874, "train_steps_per_second": 0.03 }