| { | |
| "epoch": 9.777777777777779, | |
| "eval_logits/chosen": -5352758.4, | |
| "eval_logits/rejected": -8100233.066666666, | |
| "eval_logps/chosen": -18.011005859375, | |
| "eval_logps/rejected": -31.702437337239584, | |
| "eval_loss": 0.4178004264831543, | |
| "eval_rewards/chosen": 0.04088887691497803, | |
| "eval_rewards/margins": 0.9511072429021199, | |
| "eval_rewards/rejected": -0.9102183659871419, | |
| "eval_runtime": 7.7876, | |
| "eval_samples_per_second": 5.136, | |
| "eval_steps_per_second": 2.568, | |
| "kl": 0.9340324401855469 | |
| } |