| { | |
| "epoch": 9.99018645731109, | |
| "eval_logits/chosen": -1.40625, | |
| "eval_logits/rejected": -1.4296875, | |
| "eval_logps/chosen": -580.0, | |
| "eval_logps/chosen_bottom_tokens": -13.9375, | |
| "eval_logps/chosen_top_tokens": -0.000881195068359375, | |
| "eval_logps/rejected": -604.0, | |
| "eval_logps/rejected_bottom_tokens": -13.8125, | |
| "eval_logps/rejected_top_tokens": -0.000858306884765625, | |
| "eval_loss": 0.5990539789199829, | |
| "eval_rewards/accuracies": 0.7164179086685181, | |
| "eval_rewards/chosen": -1.875, | |
| "eval_rewards/margins": 0.7734375, | |
| "eval_rewards/rejected": -2.640625, | |
| "eval_runtime": 107.9788, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 18.522, | |
| "eval_steps_per_second": 0.62, | |
| "total_flos": 0.0, | |
| "train_loss": 0.40154263242522953, | |
| "train_runtime": 75277.8699, | |
| "train_samples": 61134, | |
| "train_samples_per_second": 8.121, | |
| "train_steps_per_second": 0.068 | |
| } |