{ "epoch": 0.9989528795811519, "eval_logits/chosen": -0.34589293599128723, "eval_logits/rejected": -0.3294574022293091, "eval_logps/chosen": -2883.560791015625, "eval_logps/ref_chosen": -288.6414794921875, "eval_logps/ref_rejected": -265.96160888671875, "eval_logps/rejected": -2528.9130859375, "eval_loss": 0.6624810695648193, "eval_r_dpo/chosen_len": 286.97601318359375, "eval_r_dpo/length_delta": 40.88800048828125, "eval_r_dpo/regularization_term": 4.088800430297852, "eval_r_dpo/rejected_len": 246.08799743652344, "eval_runtime": 196.5258, "eval_samples": 2000, "eval_samples_per_second": 10.177, "eval_steps_per_second": 1.272 }