| { | |
| "epoch": 0.9965977492802931, | |
| "eval_logits/chosen": -14.663813591003418, | |
| "eval_logits/rejected": -14.17200756072998, | |
| "eval_logps/chosen": -1043.5623779296875, | |
| "eval_logps/rejected": -1566.9300537109375, | |
| "eval_loss": 0.5627544522285461, | |
| "eval_rewards/accuracies": 0.6959999799728394, | |
| "eval_rewards/chosen": -0.7292414307594299, | |
| "eval_rewards/margins": 0.5532797574996948, | |
| "eval_rewards/rejected": -1.2825212478637695, | |
| "eval_runtime": 148.9641, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 13.426, | |
| "eval_steps_per_second": 0.839, | |
| "total_flos": 0.0, | |
| "train_loss": 0.6157421479706003, | |
| "train_runtime": 11733.4361, | |
| "train_samples": 61134, | |
| "train_samples_per_second": 5.21, | |
| "train_steps_per_second": 0.02 | |
| } |