|
{ |
|
"epoch": 1.0, |
|
"eval_logits/chosen": 1.828277349472046, |
|
"eval_logits/rejected": 1.9234589338302612, |
|
"eval_logps/chosen": -131.74139404296875, |
|
"eval_logps/rejected": -192.50405883789062, |
|
"eval_loss": 0.5775244235992432, |
|
"eval_pred_label": 1039.875, |
|
"eval_rewards/accuracies": 0.3671875, |
|
"eval_rewards/chosen": -0.678291380405426, |
|
"eval_rewards/margins": 0.47481971979141235, |
|
"eval_rewards/rejected": -1.153111219406128, |
|
"eval_runtime": 125.2019, |
|
"eval_samples": 2000, |
|
"eval_samples_per_second": 15.974, |
|
"eval_steps_per_second": 0.256, |
|
"eval_use_label": 7748.125 |
|
} |