{ "epoch": 0.9997810698387214, "eval_logits/chosen": -2.3908660411834717, "eval_logits/rejected": -2.3908660411834717, "eval_logps/chosen": -310.7823181152344, "eval_logps/rejected": -310.7823181152344, "eval_loss": 0.6931472420692444, "eval_rewards/accuracies": 0.0, "eval_rewards/chosen": -0.043037299066782, "eval_rewards/margins": 0.0, "eval_rewards/rejected": -0.043037299066782, "eval_runtime": 2686.5205, "eval_samples": 6090, "eval_samples_per_second": 2.267, "eval_steps_per_second": 0.284, "total_flos": 0.0, "train_loss": 0.18720042388804636, "train_runtime": 41876.0871, "train_samples": 54810, "train_samples_per_second": 1.309, "train_steps_per_second": 0.082 }