|
{ |
|
"epoch": 1.0, |
|
"eval_logits/chosen": -2.5062618255615234, |
|
"eval_logits/rejected": -2.5199859142303467, |
|
"eval_logps/chosen": -272.93438720703125, |
|
"eval_logps/rejected": -250.28643798828125, |
|
"eval_loss": 0.6350826025009155, |
|
"eval_pred_label": 8465.072265625, |
|
"eval_rewards/accuracies": 0.6200000047683716, |
|
"eval_rewards/chosen": 0.029984984546899796, |
|
"eval_rewards/margins": 0.06345725804567337, |
|
"eval_rewards/rejected": -0.033472273498773575, |
|
"eval_runtime": 446.4868, |
|
"eval_samples": 2000, |
|
"eval_samples_per_second": 4.479, |
|
"eval_steps_per_second": 0.28, |
|
"eval_use_label": 7566.92822265625 |
|
} |