| { | |
| "epoch": 2.0, | |
| "eval_logits/chosen": -2.3691599369049072, | |
| "eval_logits/rejected": -2.1749157905578613, | |
| "eval_logps/chosen": -298.8498229980469, | |
| "eval_logps/rejected": -272.58660888671875, | |
| "eval_loss": 0.006900906562805176, | |
| "eval_rewards/accuracies": 0.4595000147819519, | |
| "eval_rewards/chosen": 0.002455136040225625, | |
| "eval_rewards/margins": -0.005604185629636049, | |
| "eval_rewards/rejected": 0.008059320971369743, | |
| "eval_runtime": 1421.1253, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 1.407, | |
| "eval_steps_per_second": 0.704, | |
| "train_loss": 0.005910432943725027, | |
| "train_runtime": 19053.6119, | |
| "train_samples": 61135, | |
| "train_samples_per_second": 0.105, | |
| "train_steps_per_second": 0.052 | |
| } |