{ "epoch": 0.9998751404669747, "eval_logits/chosen": -2.571059465408325, "eval_logits/rejected": -2.6589972972869873, "eval_logps/chosen": -0.11967950314283371, "eval_logps/rejected": -652.1184692382812, "eval_loss": 0.22132086753845215, "eval_rewards/accuracies": 1.0, "eval_rewards/chosen": 0.2579382359981537, "eval_rewards/margins": 6.330402374267578, "eval_rewards/rejected": -6.072464466094971, "eval_runtime": 0.6743, "eval_samples": 5, "eval_samples_per_second": 7.415, "eval_steps_per_second": 4.449, "total_flos": 0.0, "train_loss": 0.2426841035559699, "train_runtime": 8271.4989, "train_samples": 16017, "train_samples_per_second": 1.936, "train_steps_per_second": 0.484 }