{ "epoch": 0.9999620277197646, "eval_log_odds_chosen": 1.0117181539535522, "eval_log_odds_ratio": -0.49931100010871887, "eval_logits/chosen": -1.1310417652130127, "eval_logits/rejected": -0.9617669582366943, "eval_logps/chosen": -0.7886484265327454, "eval_logps/rejected": -1.522111415863037, "eval_loss": 1.171636939048767, "eval_nll_loss": 1.1251970529556274, "eval_rewards/accuracies": 0.7246080636978149, "eval_rewards/chosen": -0.07886141538619995, "eval_rewards/margins": 0.07333838939666748, "eval_rewards/rejected": -0.1522044539451599, "eval_runtime": 1586.8642, "eval_samples": 94173, "eval_samples_per_second": 59.141, "eval_steps_per_second": 0.924, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 20.5184, "train_samples": 1685425, "train_samples_per_second": 82142.017, "train_steps_per_second": 641.716 }