{ "epoch": 1.0, "eval_error": 0.24423876404762268, "eval_logits/chosen": -3.2264957427978516, "eval_logits/rejected": -3.202725648880005, "eval_logps/chosen": -483.4472961425781, "eval_logps/rejected": -489.55389404296875, "eval_loss": 0.7516975998878479, "eval_preference/chosen": 0.5395633578300476, "eval_preference/rejected": 0.4604366421699524, "eval_rewards/accuracies": 0.527999997138977, "eval_rewards/chosen": -3.127939462661743, "eval_rewards/margins": 0.46949708461761475, "eval_rewards/rejected": -3.5974361896514893, "eval_runtime": 42.1122, "eval_samples_per_second": 23.746, "eval_steps_per_second": 2.968 }