| { | |
| "epoch": 0.9990762978015888, | |
| "eval_logits/chosen": -1.0541683435440063, | |
| "eval_logits/rejected": -0.8055270910263062, | |
| "eval_logps/chosen": -522.3192749023438, | |
| "eval_logps/rejected": -728.829833984375, | |
| "eval_loss": 0.7119433283805847, | |
| "eval_rewards/accuracies": 0.7080000042915344, | |
| "eval_rewards/chosen": -4.293468475341797, | |
| "eval_rewards/margins": 1.8028156757354736, | |
| "eval_rewards/rejected": -6.096283435821533, | |
| "eval_runtime": 191.3844, | |
| "eval_samples": 1999, | |
| "eval_samples_per_second": 10.445, | |
| "eval_steps_per_second": 1.306, | |
| "total_flos": 0.0, | |
| "train_loss": 0.3691282767280789, | |
| "train_runtime": 28319.5283, | |
| "train_samples": 64953, | |
| "train_samples_per_second": 2.294, | |
| "train_steps_per_second": 0.018 | |
| } |