{ "epoch": 4.0, "eval_logits/chosen": -2.223867654800415, "eval_logits/rejected": -2.219041109085083, "eval_logps/chosen": -34.07316970825195, "eval_logps/rejected": -37.6160888671875, "eval_loss": 0.947879433631897, "eval_rewards/accuracies": 0.5419435501098633, "eval_rewards/chosen": -0.0347554087638855, "eval_rewards/margins": 0.05476636067032814, "eval_rewards/rejected": -0.08952176570892334, "eval_runtime": 145.6786, "eval_samples": 343, "eval_samples_per_second": 2.354, "eval_steps_per_second": 0.295, "train_loss": 0.15107146371881683, "train_runtime": 10740.8737, "train_samples": 3079, "train_samples_per_second": 1.147, "train_steps_per_second": 0.143 }