[
  {
    "seed": 0,
    "method": "rl_answer_only",
    "epoch": 0,
    "reward": 0.69765625,
    "kl": 0.09151929542422295,
    "entropy": 2.1317424297332765,
    "effective_group_rate": 0.5171875
  },
  {
    "seed": 0,
    "method": "rl_answer_only",
    "epoch": 1,
    "reward": 0.70859375,
    "kl": 0.060246463492512704,
    "entropy": 2.203758418560028,
    "effective_group_rate": 0.5484375
  },
  {
    "seed": 0,
    "method": "rl_answer_only",
    "epoch": 2,
    "reward": 0.721484375,
    "kl": 0.06607583463191986,
    "entropy": 2.2701305150985718,
    "effective_group_rate": 0.53125
  },
  {
    "seed": 0,
    "method": "rl_answer_only",
    "epoch": 3,
    "reward": 0.733203125,
    "kl": 0.07197542190551758,
    "entropy": 2.250333857536316,
    "effective_group_rate": 0.4953125
  },
  {
    "seed": 0,
    "method": "rl_answer_only",
    "epoch": 4,
    "reward": 0.733984375,
    "kl": 0.07924420684576035,
    "entropy": 2.1893630743026735,
    "effective_group_rate": 0.4953125
  },
  {
    "seed": 0,
    "method": "rl_grounding",
    "epoch": 0,
    "reward": 0.6345117092132568,
    "kl": 0.10152660049498081,
    "entropy": 2.102505850791931,
    "effective_group_rate": 0.746875
  },
  {
    "seed": 0,
    "method": "rl_grounding",
    "epoch": 1,
    "reward": 0.6546484112739563,
    "kl": 0.10132558755576611,
    "entropy": 2.048615348339081,
    "effective_group_rate": 0.7546875
  },
  {
    "seed": 0,
    "method": "rl_grounding",
    "epoch": 2,
    "reward": 0.6693164110183716,
    "kl": 0.13069079592823982,
    "entropy": 1.9451080918312074,
    "effective_group_rate": 0.7171875
  },
  {
    "seed": 0,
    "method": "rl_grounding",
    "epoch": 3,
    "reward": 0.6697070121765136,
    "kl": 0.13405263423919678,
    "entropy": 1.8889973998069762,
    "effective_group_rate": 0.6953125
  },
  {
    "seed": 0,
    "method": "rl_grounding",
    "epoch": 4,
    "reward": 0.6717187404632569,
    "kl": 0.14765012711286546,
    "entropy": 1.8661739349365234,
    "effective_group_rate": 0.73125
  },
  {
    "seed": 0,
    "method": "rl_weak",
    "epoch": 0,
    "reward": 0.54892578125,
    "kl": 0.07007534969598055,
    "entropy": 2.1410422325134277,
    "effective_group_rate": 0.590625
  },
  {
    "seed": 0,
    "method": "rl_weak",
    "epoch": 1,
    "reward": 0.57158203125,
    "kl": 0.07839753441512584,
    "entropy": 2.19478098154068,
    "effective_group_rate": 0.609375
  },
  {
    "seed": 0,
    "method": "rl_weak",
    "epoch": 2,
    "reward": 0.59658203125,
    "kl": 0.2190353289246559,
    "entropy": 2.1868765592575072,
    "effective_group_rate": 0.628125
  },
  {
    "seed": 0,
    "method": "rl_weak",
    "epoch": 3,
    "reward": 0.633203125,
    "kl": 0.6091389715671539,
    "entropy": 2.0356229901313783,
    "effective_group_rate": 0.646875
  },
  {
    "seed": 0,
    "method": "rl_weak",
    "epoch": 4,
    "reward": 0.67060546875,
    "kl": 1.140233474969864,
    "entropy": 1.7287241339683532,
    "effective_group_rate": 0.690625
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 0,
    "loss": 2.8564857006073
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 1,
    "loss": 2.759970498085022
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 2,
    "loss": 2.6549918174743654
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 3,
    "loss": 2.5108174085617065
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 4,
    "loss": 2.3069069147109986
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 5,
    "loss": 2.059319317340851
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 6,
    "loss": 1.7980661869049073
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 7,
    "loss": 1.546747100353241
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 8,
    "loss": 1.3386505365371704
  },
  {
    "seed": 0,
    "method": "sft",
    "epoch": 9,
    "loss": 1.1224345803260802
  },
  {
    "seed": 1,
    "method": "rl_answer_only",
    "epoch": 0,
    "reward": 0.728515625,
    "kl": 0.08828504318371415,
    "entropy": 1.9384552717208863,
    "effective_group_rate": 0.528125
  },
  {
    "seed": 1,
    "method": "rl_answer_only",
    "epoch": 1,
    "reward": 0.726953125,
    "kl": 0.04449792206287384,
    "entropy": 1.9057790637016296,
    "effective_group_rate": 0.496875
  },
  {
    "seed": 1,
    "method": "rl_answer_only",
    "epoch": 2,
    "reward": 0.73046875,
    "kl": 0.062079131975769995,
    "entropy": 1.8780338287353515,
    "effective_group_rate": 0.475
  },
  {
    "seed": 1,
    "method": "rl_answer_only",
    "epoch": 3,
    "reward": 0.761328125,
    "kl": 0.06315752379596233,
    "entropy": 1.8744932413101196,
    "effective_group_rate": 0.4546875
  },
  {
    "seed": 1,
    "method": "rl_answer_only",
    "epoch": 4,
    "reward": 0.7578125,
    "kl": 0.09103308320045471,
    "entropy": 1.8792544245719909,
    "effective_group_rate": 0.478125
  },
  {
    "seed": 1,
    "method": "rl_grounding",
    "epoch": 0,
    "reward": 0.6781054496765136,
    "kl": 0.0984038295224309,
    "entropy": 1.8482726454734801,
    "effective_group_rate": 0.7515625
  },
  {
    "seed": 1,
    "method": "rl_grounding",
    "epoch": 1,
    "reward": 0.6911718606948852,
    "kl": 0.04724629670381546,
    "entropy": 1.7725580334663391,
    "effective_group_rate": 0.7140625
  },
  {
    "seed": 1,
    "method": "rl_grounding",
    "epoch": 2,
    "reward": 0.6970312297344208,
    "kl": 0.05781697481870651,
    "entropy": 1.705031192302704,
    "effective_group_rate": 0.6765625
  },
  {
    "seed": 1,
    "method": "rl_grounding",
    "epoch": 3,
    "reward": 0.719628918170929,
    "kl": 0.08150238543748856,
    "entropy": 1.6546992063522339,
    "effective_group_rate": 0.665625
  },
  {
    "seed": 1,
    "method": "rl_grounding",
    "epoch": 4,
    "reward": 0.7181250095367432,
    "kl": 0.0961519718170166,
    "entropy": 1.5956939101219176,
    "effective_group_rate": 0.6703125
  },
  {
    "seed": 1,
    "method": "rl_weak",
    "epoch": 0,
    "reward": 0.56513671875,
    "kl": 0.07250000033527612,
    "entropy": 1.951923418045044,
    "effective_group_rate": 0.5953125
  },
  {
    "seed": 1,
    "method": "rl_weak",
    "epoch": 1,
    "reward": 0.573046875,
    "kl": 0.10445916429162025,
    "entropy": 1.9447291135787963,
    "effective_group_rate": 0.6078125
  },
  {
    "seed": 1,
    "method": "rl_weak",
    "epoch": 2,
    "reward": 0.59736328125,
    "kl": 0.231311596930027,
    "entropy": 1.8334349274635315,
    "effective_group_rate": 0.6078125
  },
  {
    "seed": 1,
    "method": "rl_weak",
    "epoch": 3,
    "reward": 0.64580078125,
    "kl": 0.5836134135723114,
    "entropy": 1.7131507754325868,
    "effective_group_rate": 0.6375
  },
  {
    "seed": 1,
    "method": "rl_weak",
    "epoch": 4,
    "reward": 0.70537109375,
    "kl": 1.4495355546474458,
    "entropy": 1.4280468106269837,
    "effective_group_rate": 0.678125
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 0,
    "loss": 2.8586000204086304
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 1,
    "loss": 2.754020404815674
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 2,
    "loss": 2.6328274726867678
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 3,
    "loss": 2.4527918100357056
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 4,
    "loss": 2.2025521755218507
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 5,
    "loss": 1.9204668760299684
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 6,
    "loss": 1.6480712175369263
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 7,
    "loss": 1.4361789345741272
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 8,
    "loss": 1.179182082414627
  },
  {
    "seed": 1,
    "method": "sft",
    "epoch": 9,
    "loss": 0.9645488381385803
  },
  {
    "seed": 2,
    "method": "rl_answer_only",
    "epoch": 0,
    "reward": 0.740625,
    "kl": 0.05296501237899065,
    "entropy": 2.2659966230392454,
    "effective_group_rate": 0.421875
  },
  {
    "seed": 2,
    "method": "rl_answer_only",
    "epoch": 1,
    "reward": 0.753125,
    "kl": 0.031139200553297997,
    "entropy": 2.3089439630508424,
    "effective_group_rate": 0.4484375
  },
  {
    "seed": 2,
    "method": "rl_answer_only",
    "epoch": 2,
    "reward": 0.764453125,
    "kl": 0.036854694969952105,
    "entropy": 2.317354345321655,
    "effective_group_rate": 0.4515625
  },
  {
    "seed": 2,
    "method": "rl_answer_only",
    "epoch": 3,
    "reward": 0.771875,
    "kl": 0.041548822447657584,
    "entropy": 2.3570294857025145,
    "effective_group_rate": 0.421875
  },
  {
    "seed": 2,
    "method": "rl_answer_only",
    "epoch": 4,
    "reward": 0.781640625,
    "kl": 0.06505760103464127,
    "entropy": 2.4012911558151244,
    "effective_group_rate": 0.43125
  },
  {
    "seed": 2,
    "method": "rl_grounding",
    "epoch": 0,
    "reward": 0.6380468726158142,
    "kl": 0.06408509891480207,
    "entropy": 2.1965668559074403,
    "effective_group_rate": 0.725
  },
  {
    "seed": 2,
    "method": "rl_grounding",
    "epoch": 1,
    "reward": 0.6523828029632568,
    "kl": 0.029238646291196345,
    "entropy": 2.1483010768890383,
    "effective_group_rate": 0.73125
  },
  {
    "seed": 2,
    "method": "rl_grounding",
    "epoch": 2,
    "reward": 0.6621679484844207,
    "kl": 0.07972618974745274,
    "entropy": 2.0759276747703552,
    "effective_group_rate": 0.7203125
  },
  {
    "seed": 2,
    "method": "rl_grounding",
    "epoch": 3,
    "reward": 0.6703320264816284,
    "kl": 0.03247001115232706,
    "entropy": 2.0873629450798035,
    "effective_group_rate": 0.7125
  },
  {
    "seed": 2,
    "method": "rl_grounding",
    "epoch": 4,
    "reward": 0.6710351586341858,
    "kl": 0.06326359435915947,
    "entropy": 2.0296805262565614,
    "effective_group_rate": 0.6828125
  },
  {
    "seed": 2,
    "method": "rl_weak",
    "epoch": 0,
    "reward": 0.57763671875,
    "kl": 0.0634000612422824,
    "entropy": 2.2625670433044434,
    "effective_group_rate": 0.5328125
  },
  {
    "seed": 2,
    "method": "rl_weak",
    "epoch": 1,
    "reward": 0.60078125,
    "kl": 0.07900752425193787,
    "entropy": 2.2955939769744873,
    "effective_group_rate": 0.596875
  },
  {
    "seed": 2,
    "method": "rl_weak",
    "epoch": 2,
    "reward": 0.626171875,
    "kl": 0.23670133352279663,
    "entropy": 2.263717031478882,
    "effective_group_rate": 0.65
  },
  {
    "seed": 2,
    "method": "rl_weak",
    "epoch": 3,
    "reward": 0.65302734375,
    "kl": 0.3703400373458862,
    "entropy": 2.20552419424057,
    "effective_group_rate": 0.646875
  },
  {
    "seed": 2,
    "method": "rl_weak",
    "epoch": 4,
    "reward": 0.7013671875,
    "kl": 1.0599908649921417,
    "entropy": 1.9244227051734923,
    "effective_group_rate": 0.6953125
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 0,
    "loss": 2.8506731271743773
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 1,
    "loss": 2.7294000387191772
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 2,
    "loss": 2.5811492919921877
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 3,
    "loss": 2.397210454940796
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 4,
    "loss": 2.1410638093948364
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 5,
    "loss": 1.8556795835494995
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 6,
    "loss": 1.6953421115875245
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 7,
    "loss": 1.4981114745140076
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 8,
    "loss": 1.3217952489852904
  },
  {
    "seed": 2,
    "method": "sft",
    "epoch": 9,
    "loss": 1.1568683981895447
  }
]
