{ | |
"epoch": 0.9989701338825953, | |
"eval_logits/chosen": -2.019674301147461, | |
"eval_logits/rejected": -1.920204997062683, | |
"eval_logps/chosen": -340.5888671875, | |
"eval_logps/rejected": -434.97796630859375, | |
"eval_loss": 0.49337291717529297, | |
"eval_rewards/accuracies": 0.75, | |
"eval_rewards/chosen": -1.182220697402954, | |
"eval_rewards/margins": 0.8897156119346619, | |
"eval_rewards/rejected": -2.0719363689422607, | |
"eval_runtime": 62.0498, | |
"eval_samples_per_second": 16.116, | |
"eval_steps_per_second": 0.258 | |
} |