{ "epoch": 1.0, "eval_logits/chosen": -1.0520579814910889, "eval_logits/rejected": -1.0065128803253174, "eval_logps/chosen": -406.3271789550781, "eval_logps/rejected": -408.65692138671875, "eval_loss": 0.042073994874954224, "eval_rewards/accuracies": 0.6014999747276306, "eval_rewards/chosen": -0.010021946392953396, "eval_rewards/margins": 0.031399574130773544, "eval_rewards/rejected": -0.041421521455049515, "eval_runtime": 546.029, "eval_samples": 2000, "eval_samples_per_second": 3.663, "eval_steps_per_second": 0.916, "train_loss": 0.07849642387894454, "train_runtime": 13138.6455, "train_samples": 61135, "train_samples_per_second": 1.142, "train_steps_per_second": 0.071 }