| { | |
| "epoch": 0.9985553308292401, | |
| "eval_logits/chosen": -0.4112316370010376, | |
| "eval_logits/rejected": -0.38529691100120544, | |
| "eval_logps/chosen": -154.36468505859375, | |
| "eval_logps/rejected": -161.3667755126953, | |
| "eval_loss": 1.598533034324646, | |
| "eval_nll_loss": 0.42096075415611267, | |
| "eval_rewards/accuracies": 0.623913049697876, | |
| "eval_rewards/chosen": -15.436468124389648, | |
| "eval_rewards/margins": 0.7002089619636536, | |
| "eval_rewards/rejected": -16.13667869567871, | |
| "eval_runtime": 73.3622, | |
| "eval_samples": 1826, | |
| "eval_samples_per_second": 24.89, | |
| "eval_steps_per_second": 1.568, | |
| "total_flos": 0.0, | |
| "train_loss": 1.77929983039697, | |
| "train_runtime": 9807.604, | |
| "train_samples": 55376, | |
| "train_samples_per_second": 5.646, | |
| "train_steps_per_second": 0.044 | |
| } |