| { | |
| "epoch": 9.955555555555556, | |
| "eval_logits/chosen": -5270992.0, | |
| "eval_logits/rejected": -6459799.04, | |
| "eval_logps/chosen": -22.9960888671875, | |
| "eval_logps/rejected": -75.276025390625, | |
| "eval_loss": 0.2732886075973511, | |
| "eval_rewards/chosen": -0.7733412170410157, | |
| "eval_rewards/margins": 4.80520004272461, | |
| "eval_rewards/rejected": -5.578541259765625, | |
| "eval_runtime": 20.4365, | |
| "eval_samples_per_second": 4.893, | |
| "eval_steps_per_second": 2.447, | |
| "kl": 0.0 | |
| } |