{ "epoch": 1.0, "eval_logits/chosen": -2.810283660888672, "eval_logits/rejected": -2.8077523708343506, "eval_logps/chosen": -31.230178833007812, "eval_logps/rejected": -34.68911361694336, "eval_loss": 0.49349722266197205, "eval_rewards/accuracies": 0.560215950012207, "eval_rewards/chosen": 0.04181605204939842, "eval_rewards/margins": 0.03458160161972046, "eval_rewards/rejected": 0.007234453689306974, "eval_runtime": 112.8053, "eval_samples": 343, "eval_samples_per_second": 3.041, "eval_steps_per_second": 0.381, "train_loss": 1.1209261448352368, "train_runtime": 2723.1709, "train_samples": 3079, "train_samples_per_second": 1.131, "train_steps_per_second": 0.141 }