| { |
| "epoch": 0.9981298423724285, |
| "eval_abs_diff": 0.306640625, |
| "eval_all_logps_1": -811.0883178710938, |
| "eval_all_logps_1_values": -811.0883178710938, |
| "eval_all_logps_2": 447.4254150390625, |
| "eval_all_logps_2_values": 447.4254150390625, |
| "eval_logits/chosen": 5.71875, |
| "eval_logits/rejected": 5.6875, |
| "eval_logps/chosen": -2.1875, |
| "eval_logps/rejected": -2.1875, |
| "eval_loss": 1.6943204402923584, |
| "eval_original_losses": 1.75, |
| "eval_rewards/accuracies": 0.46370968222618103, |
| "eval_rewards/chosen": -5.4375, |
| "eval_rewards/margins": 0.0089111328125, |
| "eval_rewards/rejected": -5.46875, |
| "eval_runtime": 13.179, |
| "eval_samples": 1961, |
| "eval_samples_per_second": 148.797, |
| "eval_steps_per_second": 4.704, |
| "eval_weight": 1.0 |
| } |