| { |
| "epoch": 1.0, |
| "eval_logits/chosen": -2.2980051040649414, |
| "eval_logits/rejected": -2.2472665309906006, |
| "eval_logps/chosen": -273.0010070800781, |
| "eval_logps/rejected": -300.89141845703125, |
| "eval_loss": 0.5999026298522949, |
| "eval_rewards/accuracies": 0.7265625, |
| "eval_rewards/chosen": -0.10589609295129776, |
| "eval_rewards/margins": 0.2828805148601532, |
| "eval_rewards/rejected": -0.38877660036087036, |
| "eval_runtime": 135.2273, |
| "eval_samples": 2000, |
| "eval_samples_per_second": 14.79, |
| "eval_steps_per_second": 0.237 |
| } |