{ "epoch": 1.0, "eval_logits/chosen": -2.232933521270752, "eval_logits/rejected": -2.2280824184417725, "eval_logps/chosen": -34.02503967285156, "eval_logps/rejected": -37.51841735839844, "eval_loss": 1.0816813707351685, "eval_rewards/accuracies": 0.5103820562362671, "eval_rewards/chosen": 0.004756772890686989, "eval_rewards/margins": 0.005652438849210739, "eval_rewards/rejected": -0.0008956658421084285, "eval_runtime": 145.5936, "eval_samples": 343, "eval_samples_per_second": 2.356, "eval_steps_per_second": 0.295, "train_loss": 0.8446982934877469, "train_runtime": 3252.3399, "train_samples": 3079, "train_samples_per_second": 0.947, "train_steps_per_second": 0.118 }