| { | |
| "epoch": 0.9996020692399522, | |
| "eval_logits/chosen": -1.4212305545806885, | |
| "eval_logits/rejected": -1.432730793952942, | |
| "eval_logps/chosen": -228.8310546875, | |
| "eval_logps/rejected": -246.39952087402344, | |
| "eval_loss": 0.6470152735710144, | |
| "eval_rewards/accuracies": 0.6128731369972229, | |
| "eval_rewards/chosen": -0.3647947907447815, | |
| "eval_rewards/margins": 0.11783836036920547, | |
| "eval_rewards/rejected": -0.48263317346572876, | |
| "eval_runtime": 326.0, | |
| "eval_samples": 8552, | |
| "eval_samples_per_second": 26.233, | |
| "eval_steps_per_second": 0.411, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6662861807331159, | |
| "train_runtime": 15158.4407, | |
| "train_samples": 160800, | |
| "train_samples_per_second": 10.608, | |
| "train_steps_per_second": 0.041 | |
| } |