|
{ |
|
"epoch": 0.9981298423724285, |
|
"eval_logits/chosen": 2.009596824645996, |
|
"eval_logits/rejected": 2.014779806137085, |
|
"eval_logps/chosen": -0.897185742855072, |
|
"eval_logps/rejected": -1.061065435409546, |
|
"eval_loss": 1.6225711107254028, |
|
"eval_rewards/accuracies": 0.625, |
|
"eval_rewards/chosen": -2.242964267730713, |
|
"eval_rewards/margins": 0.40969952940940857, |
|
"eval_rewards/rejected": -2.6526639461517334, |
|
"eval_runtime": 44.5569, |
|
"eval_samples": 1961, |
|
"eval_samples_per_second": 44.011, |
|
"eval_steps_per_second": 1.391 |
|
} |