{ "epoch": 2.9906542056074765, "eval_logits/chosen": -2.243978500366211, "eval_logits/rejected": -2.222538471221924, "eval_logps/chosen": -235.60606384277344, "eval_logps/rejected": -220.67372131347656, "eval_loss": 0.5969974994659424, "eval_rewards/accuracies": 0.7881944179534912, "eval_rewards/chosen": 1.1264705657958984, "eval_rewards/margins": 2.10550856590271, "eval_rewards/rejected": -0.9790381193161011, "eval_runtime": 150.6075, "eval_samples_per_second": 15.139, "eval_steps_per_second": 0.239, "total_flos": 2829829665718272.0, "train_loss": 0.33513165613015494, "train_runtime": 8778.1887, "train_samples_per_second": 7.011, "train_steps_per_second": 0.027 }