{ "epoch": 1.9998721963064732, "eval_logits/chosen": 0.208984375, "eval_logits/rejected": 0.8125, "eval_logps/chosen": -416.0, "eval_logps/rejected": -438.0, "eval_loss": 0.2576223611831665, "eval_rewards/accuracies": 0.8927131295204163, "eval_rewards/chosen": -15.0, "eval_rewards/margins": 5.84375, "eval_rewards/rejected": -20.875, "eval_runtime": 1478.528, "eval_samples": 55582, "eval_samples_per_second": 37.541, "eval_steps_per_second": 0.587, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 23.3629, "train_samples": 1001516, "train_samples_per_second": 42867.703, "train_steps_per_second": 334.889 }