{ "epoch": 0.9221902017291066, "eval_logits/chosen": -0.04217853024601936, "eval_logits/rejected": 0.11716891080141068, "eval_logps/chosen": -125.96058654785156, "eval_logps/ref_chosen": -126.4654541015625, "eval_logps/ref_rejected": -162.98605346679688, "eval_logps/rejected": -162.4300994873047, "eval_loss": 0.4705093801021576, "eval_rewards/accuracies": 0.46759259700775146, "eval_rewards/chosen": 0.005048647057265043, "eval_rewards/margins": -0.000510881538502872, "eval_rewards/rejected": 0.005559529177844524, "eval_runtime": 144.9876, "eval_samples": 1080, "eval_samples_per_second": 7.449, "eval_sft_loss": 0.4259297549724579, "eval_steps_per_second": 1.862, "total_flos": 0.0, "train_loss": 0.48907283544540403, "train_runtime": 630.6427, "train_samples": 1387, "train_samples_per_second": 2.199, "train_steps_per_second": 0.016 }