{ "epoch": 0.9965156794425087, "eval_logits/chosen": -2.281348943710327, "eval_logits/rejected": -2.2318127155303955, "eval_logps/chosen": -292.6180114746094, "eval_logps/rejected": -316.9007568359375, "eval_loss": 0.6281932592391968, "eval_rewards/accuracies": 0.703125, "eval_rewards/chosen": -0.2998806834220886, "eval_rewards/margins": 0.2425060272216797, "eval_rewards/rejected": -0.5423867106437683, "eval_runtime": 104.9019, "eval_samples": 2000, "eval_samples_per_second": 19.065, "eval_steps_per_second": 0.305, "total_flos": 0.0, "train_loss": 0.6505647914392965, "train_runtime": 3852.398, "train_samples": 18340, "train_samples_per_second": 4.761, "train_steps_per_second": 0.037 }