| { | |
| "epoch": 3.0, | |
| "eval_log_odds_chosen": 0.4396049678325653, | |
| "eval_log_odds_ratio": -0.6420542597770691, | |
| "eval_logits/chosen": 301.1214599609375, | |
| "eval_logits/rejected": 240.39068603515625, | |
| "eval_logps/chosen": -1.19857656955719, | |
| "eval_logps/rejected": -1.5204962491989136, | |
| "eval_loss": 1.8577181100845337, | |
| "eval_nll_loss": 1.5532194375991821, | |
| "eval_rewards/accuracies": 0.6142857074737549, | |
| "eval_rewards/chosen": -0.599288284778595, | |
| "eval_rewards/margins": 0.16095994412899017, | |
| "eval_rewards/rejected": -0.7602481245994568, | |
| "eval_runtime": 201.8893, | |
| "eval_samples": 553, | |
| "eval_samples_per_second": 2.739, | |
| "eval_steps_per_second": 0.347, | |
| "total_flos": 0.0, | |
| "train_loss": 2.2429193542117165, | |
| "train_runtime": 13126.4564, | |
| "train_samples": 5364, | |
| "train_samples_per_second": 1.226, | |
| "train_steps_per_second": 0.019 | |
| } |