{ "epoch": 1.0, "eval_logits/chosen": 98.98882293701172, "eval_logits/rejected": 98.9751968383789, "eval_logps/chosen": -32.437740325927734, "eval_logps/rejected": -35.96149826049805, "eval_loss": 8.017751693725586, "eval_rewards/accuracies": 0.5220099687576294, "eval_rewards/chosen": 0.0010875342413783073, "eval_rewards/margins": 8.220935706049204e-05, "eval_rewards/rejected": 0.0010053252335637808, "eval_runtime": 103.7392, "eval_samples": 343, "eval_samples_per_second": 3.306, "eval_steps_per_second": 0.415, "train_loss": 5.985443219271573, "train_runtime": 2557.1257, "train_samples": 3079, "train_samples_per_second": 1.204, "train_steps_per_second": 0.151 }