| { | |
| "epoch": 0.9997382884061764, | |
| "eval_logits/chosen": -0.8689022064208984, | |
| "eval_logits/rejected": -0.2690173089504242, | |
| "eval_logps/chosen": -397.43707275390625, | |
| "eval_logps/rejected": -497.619384765625, | |
| "eval_loss": 0.49802955985069275, | |
| "eval_rewards/accuracies": 0.7379999756813049, | |
| "eval_rewards/chosen": -2.1241602897644043, | |
| "eval_rewards/margins": 0.9601246118545532, | |
| "eval_rewards/rejected": -3.084285020828247, | |
| "eval_runtime": 316.8163, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 6.313, | |
| "eval_steps_per_second": 0.789, | |
| "total_flos": 0.0, | |
| "train_loss": 0.5374546366836388, | |
| "train_runtime": 38043.1849, | |
| "train_samples": 61134, | |
| "train_samples_per_second": 1.607, | |
| "train_steps_per_second": 0.05 | |
| } |