{ "epoch": 1.9986987638256344, "eval_logits/chosen": 452.641357421875, "eval_logits/rejected": 436.01385498046875, "eval_logps/chosen": -295.9647216796875, "eval_logps/rejected": -334.555419921875, "eval_loss": 0.6477869153022766, "eval_rewards/accuracies": 0.6168639063835144, "eval_rewards/chosen": -0.34524381160736084, "eval_rewards/margins": 0.23360556364059448, "eval_rewards/rejected": -0.5788493752479553, "eval_runtime": 243.7753, "eval_samples": 5406, "eval_samples_per_second": 22.176, "eval_steps_per_second": 0.693, "total_flos": 0.0, "train_loss": 0.6547494133313497, "train_runtime": 8032.2795, "train_samples": 49171, "train_samples_per_second": 12.243, "train_steps_per_second": 0.096 }