| { |
| "epoch": 0.9995071463775259, |
| "eval_logits/chosen": -2.784608840942383, |
| "eval_logits/rejected": -2.676510810852051, |
| "eval_logps/chosen": -528.9862670898438, |
| "eval_logps/rejected": -625.0216064453125, |
| "eval_loss": 0.5057918429374695, |
| "eval_rewards/accuracies": 0.7822580933570862, |
| "eval_rewards/chosen": -2.6609416007995605, |
| "eval_rewards/margins": 0.8503015041351318, |
| "eval_rewards/rejected": -3.5112433433532715, |
| "eval_runtime": 328.3509, |
| "eval_samples": 1976, |
| "eval_samples_per_second": 6.018, |
| "eval_steps_per_second": 0.378, |
| "total_flos": 0.0, |
| "train_loss": 0.30356378627011527, |
| "train_runtime": 18867.8748, |
| "train_samples": 64923, |
| "train_samples_per_second": 3.441, |
| "train_steps_per_second": 0.027 |
| } |