|
{ |
|
"epoch": 0.9981298423724285, |
|
"eval_logits/chosen": -1.1332677602767944, |
|
"eval_logits/rejected": -1.1544803380966187, |
|
"eval_logps/chosen": -715.691650390625, |
|
"eval_logps/rejected": -871.3291625976562, |
|
"eval_loss": 0.38531965017318726, |
|
"eval_rewards/accuracies": 0.875, |
|
"eval_rewards/chosen": -4.425616264343262, |
|
"eval_rewards/margins": 1.6173373460769653, |
|
"eval_rewards/rejected": -6.0429534912109375, |
|
"eval_runtime": 126.4968, |
|
"eval_samples": 1961, |
|
"eval_samples_per_second": 15.502, |
|
"eval_steps_per_second": 0.49 |
|
} |