| { | |
| "epoch": 2.0, | |
| "eval_logits/chosen": -2.5716235637664795, | |
| "eval_logits/rejected": -2.555190324783325, | |
| "eval_logps/chosen": -73.5245361328125, | |
| "eval_logps/rejected": -81.39889526367188, | |
| "eval_loss": 0.6463928818702698, | |
| "eval_rewards/accuracies": 0.3710317313671112, | |
| "eval_rewards/chosen": 0.48334550857543945, | |
| "eval_rewards/margins": 0.6186185479164124, | |
| "eval_rewards/rejected": -0.13527308404445648, | |
| "eval_runtime": 113.7854, | |
| "eval_samples": 2000, | |
| "eval_samples_per_second": 17.577, | |
| "eval_steps_per_second": 0.554, | |
| "total_flos": 0.0, | |
| "train_loss": 0.5264799162901237, | |
| "train_runtime": 6499.6728, | |
| "train_samples": 18340, | |
| "train_samples_per_second": 5.643, | |
| "train_steps_per_second": 0.088 | |
| } |