| { | |
| "epoch": 2.9865871833084947, | |
| "eval_log_odds_chosen": 0.33574143052101135, | |
| "eval_log_odds_ratio": -0.6769095063209534, | |
| "eval_logits/chosen": 292.74676513671875, | |
| "eval_logits/rejected": 259.2041320800781, | |
| "eval_logps/chosen": -1.2910676002502441, | |
| "eval_logps/rejected": -1.5239651203155518, | |
| "eval_loss": 2.003471851348877, | |
| "eval_nll_loss": 1.6439613103866577, | |
| "eval_rewards/accuracies": 0.6115108132362366, | |
| "eval_rewards/chosen": -0.6455338001251221, | |
| "eval_rewards/margins": 0.1164487823843956, | |
| "eval_rewards/rejected": -0.7619825601577759, | |
| "eval_runtime": 378.1416, | |
| "eval_samples": 553, | |
| "eval_samples_per_second": 1.462, | |
| "eval_steps_per_second": 0.368 | |
| } |